WO2019062710A1 - 通信方法及其通信设备 - Google Patents

通信方法及其通信设备 Download PDF

Info

Publication number
WO2019062710A1
WO2019062710A1 PCT/CN2018/107337 CN2018107337W WO2019062710A1 WO 2019062710 A1 WO2019062710 A1 WO 2019062710A1 CN 2018107337 W CN2018107337 W CN 2018107337W WO 2019062710 A1 WO2019062710 A1 WO 2019062710A1
Authority
WO
WIPO (PCT)
Prior art keywords
network element
information
session
feature index
service
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2018/107337
Other languages
English (en)
French (fr)
Inventor
李岩
吴晓波
朱方园
辛阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Priority to EP18863523.9A priority Critical patent/EP3683714B1/en
Publication of WO2019062710A1 publication Critical patent/WO2019062710A1/zh
Priority to US16/824,859 priority patent/US11451286B2/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/02—Standardisation; Integration
    • H04L41/024—Standardisation; Integration using relational databases for representation of network management data, e.g. managing via structured query language [SQL]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/22—Indexing; Data structures therefor; Storage structures
    • G06F16/2228—Indexing structures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/25—Integrating or interfacing systems involving database management systems
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/0413—MIMO systems
    • H04B7/0426—Power distribution
    • H04B7/043—Power distribution using best eigenmode, e.g. beam forming or beam steering
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
    • H04B7/0613—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
    • H04B7/0684—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission using different training sequences per antenna
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1095—Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/14—Session management
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/10—Scheduling measurement reports ; Arrangements for measurement reports
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W48/00—Access restriction; Network selection; Access point selection
    • H04W48/18—Selecting a network or a communication service
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W76/00—Connection management
    • H04W76/10—Connection setup
    • H04W76/11—Allocation or use of connection identifiers
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W80/00—Wireless network protocols or protocol adaptations to wireless operation
    • H04W80/08—Upper layer protocols
    • H04W80/10—Upper layer protocols adapted for application session management, e.g. SIP [Session Initiation Protocol]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/5041—Network service management, e.g. ensuring proper service fulfilment according to agreements characterised by the time relationship between creation and deployment of a service

Definitions

  • the present application relates to the field of communications, and more specifically, to a communication method, a database network element, a data analysis network element, a control plane network element, and a user plane network element.
  • the present application provides a communication method, a database network element, a data analysis network element, a control plane network element, and a user plane network element, and can apply a big data analysis technology to identify a service type in a communication network supporting big data.
  • the present application provides a method of communication.
  • the communication method includes: the database network element acquires training data, the training data includes service transmission data and network data; the database network element sends training data to the data analysis network element; the database network element receives the first information, the first information from the data analysis network element.
  • the training data is obtained by the database network element and sent to the data analysis network element, so that the data analysis network element can perform the subsequent steps of the service type identification according to the training data.
  • the database network element can be deployed in a distributed manner and is close to the service server, the data synchronization technology of the database network element can be used to reduce the delay in acquiring the training data.
  • the distributed database network element can also be close to the control plane network element in the deployment implementation. Therefore, receiving the first information from the data analysis network element by the database network element helps to reduce the subsequent transmission of the database network element to the control plane network element. The delay of the feature index list set.
  • the database network element collects service transmission data by implementing the following methods:
  • the database network element can collect service transmission data from the operator platform, the third-party service server, and the vertical industry control center.
  • the service transmission data collected by the database network element may include: an IP quintuple, a packet size and time, a service type, a service experience, and an extension field.
  • the IP quintuple may include the IP address and port of the terminal, the IP address and port of the service server, and the transmission protocol.
  • the database network element can collect the network data by acquiring the network data from the terminal, the access network device, the core network element, and the like.
  • the core network element that obtains the network data may include an Access and Mobility Management Function (AMF) network element, a Session Management Function (SMF) network element, User Plane Function (UPF) network element, Unified Data Management (UDM) network element, Application Function (AF) network element, Packet and Flow Description Function (PFDF) At least one of the network elements.
  • AMF Access and Mobility Management Function
  • SMF Session Management Function
  • UPF User Plane Function
  • UDM Unified Data Management
  • AF Application Function
  • PFDF Packet and Flow Description Function
  • the network data may include at least one of a terminal's IP address and port number, terminal type, terminal location information, time, DNN, and network congestion status.
  • the training data includes network data and service transmission data, which helps the data analysis network element to obtain more accurate first information according to the training data, thereby helping to improve the accuracy of service type identification.
  • the database network element can associate the service data with the network data to obtain the training data.
  • a possible implementation manner for the database network element to obtain the training data includes: after the database network element collects the service data and the network data, the database network element determines that the same IP quintuple is included according to the IP quintuple and time information in the service data.
  • the network data of the time information, thereby associating the service data with the network data, and the associated business data and network data can be stored in the database network element as complete training data.
  • the database network element after the database network element receives the first information, stores the first information by: the database network element can use the service identifier as the data index information, and store the corresponding information of each service identifier. A list of feature indexes and a DNN corresponding to each service identifier.
  • the database network element after the database network element receives the first information, stores the first information by: the database network element can use the DNN as the data index information, and store the service corresponding to each DNN.
  • the communications method further includes: the database network element transmitting the first information to the control plane network element.
  • the control plane network element can perform subsequent steps in the service type identification according to the first information.
  • the first information further includes at least one of the following information corresponding to each feature index list in the first feature index list set: network slice type, session And Session Continuity (SSC) mode, Packet Data Unit (PDU) session type.
  • SSC session And Session Continuity
  • PDU Packet Data Unit
  • the first information may include at least one of a service identifier corresponding to each feature index list, a DNN of a service type corresponding to each feature index list, and a network slice type, an SSC mode, and a PDU session type.
  • the at least one of the network segment type, the SSC mode, and the PDU session type helps the database network element to send the first information to the control plane network element, and the control plane network element can be based on the first information and the user plane network element.
  • the supported network slice type, the SSC mode, and the PDU session type determine a more accurate second feature index list set for the user plane network element, thereby helping to improve the accuracy of subsequent service type identification.
  • the communication method further includes: the database network element receives the DNN of the first session from the control plane network element; and the database network element receives the first information according to the DNN of the first session.
  • the second information includes a second feature index list set corresponding to the DNN of the first session and a service identifier corresponding to each feature index list in the second feature index list set; the database network element is directed to the control plane The network element sends the second information.
  • the database network element obtains the second information from the first information according to the request of the control plane network element, and sends the second information to the control plane network element, so that the control plane network element can perform the subsequent steps in the service type identification.
  • the first information further includes at least one of the following information corresponding to each feature index list in the first feature index list set: network slice type, SSC Mode, PDU session type.
  • the communications method further includes: the database network element receiving, by the control plane network element, at least one of the following information of the first session: a network slice type, and an SSC mode , PDU session type.
  • the database network element obtains the second information from the first information according to the DNN of the first session, including: the database network element according to the DNN of the first session and the at least one information of the first session, from the first The second information is obtained by querying in a message.
  • the database network element searches for the second information from the first information according to the at least one information of the first session according to the DNN of the first session, which helps improve the accuracy of the second information, and further helps improve the service.
  • the efficiency of identification is the reason for the second information.
  • the communication method further includes: the database network element is from the user plane
  • the network element receives the third information, where the third information includes the first service identifier set, and the database network element queries the first information according to each service identifier in the first service identifier set to obtain each service according to the first service identifier set. Identifying a corresponding feature index list; the database network element queries, according to the feature index list corresponding to each service identifier in the first service identifier set, the network data feature value list corresponding to each service identifier in the first service identifier set.
  • the database network element sends a list of network data feature values corresponding to each service identifier in the first service identifier set to the user plane network element.
  • the database network element can be deployed in a distributed manner and is close to the user plane network element.
  • the database network element provides the network data value for identifying the service type for the user plane network element according to the request of the user plane network element. It helps to reduce the delay of network data value transmission.
  • the communications method further includes: the database network element receives the third information from the user plane network element, where the third information includes the network data feature. An index list; the database network element obtains a network data value corresponding to the feature index in the network data feature index list, and obtains a network data feature value list; the database network element sends the network data feature value list to the user plane network element.
  • the database network element can be deployed in a distributed manner and close to the user plane network element. Therefore, when the database network element sends the network data feature value to the user plane network element according to the request of the user plane network element, the network can be reduced. The delay in the transmission of data values.
  • the network data feature index list includes a feature index without repetition.
  • the third information further includes at least one of the following information: a time when the user plane network element receives the service transmission data of the first session, The session identifier of a session, the identifier of the terminal corresponding to the first session, the IP address of the terminal corresponding to the first session, the port of the terminal corresponding to the first session, the IP address of the service server corresponding to the first session, and the service server A service transfer protocol corresponding to the port and the service data corresponding to the first session.
  • the network data value sent by the database network element to the user plane network element is determined by the database network element according to the at least one type of information, so that the accuracy of the network data value can be improved, thereby helping to improve the accuracy of the service type identification. rate.
  • the present application provides a communication method.
  • the communication method includes: the data analysis network element receives the training data sent by the database network element, the training data includes service transmission data and network data; and the data analysis network element determines the first information according to the training data, where the first information includes the first feature index list set. And the service identifier corresponding to each feature index list in the first feature index list set and the DNN corresponding to the service identifier; the data analysis network element sends the first information to the database network element.
  • the data analysis network element obtains a feature index list for identifying the service type according to the training data, so that the service type can be identified according to the feature index list in the subsequent step.
  • the training data that the data analysis network element obtains the feature index list is received from the database network element, and the database network element can be distributedly deployed in the deployment implementation, and is close to the source of the training data, and the second aspect of the communication method It helps to reduce the delay of database network elements to obtain training data.
  • the data analysis In addition to transmitting data according to the service, the data analysis also determines the first information according to the network data, which helps to improve the accuracy of service identification.
  • the first information further includes at least one of the following information corresponding to each feature index list in the first feature index list set: network slice type, SSC mode, PDU session Types of.
  • the first information further includes the foregoing at least one type of information, so that the database network element or the control plane network element can determine the feature index list supported by the user plane network element according to the information, and help improve the feature index column determined for the user plane network element. Accuracy, which in turn helps improve the accuracy of business type identification.
  • the present application provides a communication method.
  • the communication method includes: the control plane network element receives the first information from the database network element, where the first information includes the first feature index list set and the service identifier and the service identifier corresponding to each feature index list in the first feature index list set.
  • the DNN the control plane network element queries the first information to obtain the second information according to the DNN of the first session, where the second information includes the second feature index list set and the service corresponding to each feature index list in the second feature index list.
  • the control plane network element sends the second information to the user plane network element.
  • control plane network element receives the first information from the database network element, and determines a feature index list corresponding to the user plane network element, so that the user plane network element can continue to perform related steps in the service type identification.
  • the distributed database network element can be close to the control plane network element in the deployment implementation. Therefore, the control plane network element receives the first information from the database network element, which helps reduce the delay of the first information transmission.
  • control plane network element that receives the first information from the data network element may be an SMF network element or a Policy Control Function (PCF) network element.
  • PCF Policy Control Function
  • the first information further includes at least one of the following information corresponding to each feature index list in the first feature index list set: network slice type, SSC mode, PDU session Types of.
  • the control plane network element obtains the second information from the first information according to the DNN of the first session, including: the control plane network element according to the DNN of the first session, the network slice type of the first session, the SSC mode, and the PDU session. At least one type of information in the type, the second information is queried from the first information.
  • the control plane network element determines the second information according to the at least one information of the first session according to the DNN of the first session, which helps improve the accuracy of the second information, thereby helping to improve the accuracy of the service type identification. .
  • the present application provides a communication method.
  • the communication method includes: the control plane network element sends the DNN of the first session to the database network element; the control plane network element receives the second information from the database network element, where the second information includes the second feature index list set and the second feature index list set.
  • Each of the feature index lists corresponds to the service identifier, and each feature index list in the second feature index list set corresponds to the DNN of the first session; the control plane network element sends the second information to the user plane network element.
  • control plane network element requests the second information from the database network element, and sends the second information to the user plane network element, so that the user plane network element can perform the subsequent step in the service type identification according to the second information.
  • the distributed database network element can be close to the control plane network element in the deployment implementation. Therefore, the control plane network element receives the first information from the database network element, which helps reduce the delay of the first information transmission.
  • control plane network element that receives the first information from the data network element may be an SMF network element or a PCF network element.
  • the communications method before the control plane network element receives the second information from the database network element, the communications method further includes: the control plane network element sends the following at least the first session to the database network element One type of information: network slice type, SSC mode, PDU session type.
  • control plane network element In addition to sending the DNN of the first session to the database network element, the control plane network element also sends the at least one type of information of the first session, which helps the database network element to determine a more accurate second information, thereby helping to improve the service.
  • the type of recognition accuracy is a measure of recognition accuracy.
  • the present application provides a communication method.
  • the communication method includes: the user plane network element receives the second information from the control plane network element, where the second information includes the second feature index list set and the service identifier corresponding to each feature index list in the second feature index list set;
  • the network element receives the service transmission data of the first session;
  • the user plane network element determines a service identifier corresponding to the feature index list of the second feature index list set that cannot obtain the feature value according to the service transmission data, and obtains the first service identifier set;
  • the user plane sends the third information to the database network element, where the third information includes the first service identifier set.
  • the user plane network element receives the network data feature value list corresponding to each service identifier in the first service identifier set from the database network element.
  • the user plane network element requests the network data value corresponding to the feature index in the feature index list from the database data, so that the user plane network element can perform subsequent steps to implement the identification of the service type.
  • the user plane network element requests the network data value from the database network element, which helps reduce the delay.
  • the third information includes at least one of the following information: a time when the user plane processes the service transmission data of the first session, a session identifier of the first session, and a first session correspondence
  • the identifier of the terminal, the IP address of the terminal corresponding to the first session, the port of the terminal corresponding to the first session, the IP address of the service server corresponding to the first session, the port corresponding to the first session in the service server, and the first session The service transmission protocol of the corresponding business data.
  • the user plane network element sends the first service identifier set to the database network element, and sends the at least one type of information, which helps the database network element to determine the network data value according to the at least one type of information, thereby helping to improve the determined
  • the accuracy of network data values which in turn helps to improve the accuracy of business type identification.
  • the present application provides a communication method.
  • the communication method includes: the user plane network element receives the second information from the control plane network element, where the second information includes the second feature index list set and the service identifier corresponding to each feature index list in the second feature index list set;
  • the network element receives the service transmission data of the first session; the user plane network element determines a feature index of the second feature index list set that cannot obtain the feature value according to the service transmission data, and obtains a network data feature index list; the user plane network element to the database
  • the network element sends a network data feature index list; the user plane network element receives the network data feature value list corresponding to the network data feature index list from the database network element.
  • the user plane network element sends the feature index list to the database network element, and receives the network data feature value list corresponding to the feature index list obtained by the database network element, so that the user plane network element can continue to perform the service type identification follow-up step.
  • the duplicate feature index may be removed to obtain a network data feature index list.
  • the third information includes at least one of the following information: a time when the user plane processes the service transmission data that receives the first session, a session identifier of the first session, and a first session correspondence
  • the user plane network element sends the first service identifier set to the database network element, and sends the at least one type of information, which helps the database network element to determine the network data value according to the at least one type of information, thereby helping to improve the determined
  • the accuracy of network data values which in turn helps to improve the accuracy of business type identification.
  • the training data is obtained by the database network element
  • the data analysis network element obtains the feature index list corresponding to the service type according to the training data
  • the database network element records the feature index list and provides the control index to the control plane.
  • the network element sends the feature index list
  • the control plane network element sends the feature index list supported by the user plane network element to the user plane network element
  • the user plane processing acquires the feature value of the service transmission data according to the feature index list, and sends the feature value to the data.
  • the network element is analyzed, and the data analysis network element determines the service type according to the feature value and informs the user of the network element.
  • the above communication method implements a communication method for applying a service type identification based on a big data analysis technology in a communication system.
  • the database network element can be deployed closer to the service server, the control plane network element, and the user plane network element, the database data element acquires the training data and sends the feature index to the control plane network element, which helps reduce the delay. .
  • the user plane network element may also request network data values from the database network element, and may also reduce the delay.
  • the application provides a database network element.
  • the database network element includes means for performing the communication method of the first aspect or any of the possible implementations of the first aspect.
  • the modules included in the database network element can be implemented by software and/or hardware.
  • the application provides a data analysis network element.
  • the data analysis network element includes means for performing the communication method of any of the possible implementations of the second aspect or the second aspect.
  • the modules included in the data analysis network element can be implemented by software and/or hardware.
  • control plane network element includes means for performing the communication method of any of the possible implementations of the third aspect or the third aspect.
  • the modules included in the control plane network element can be implemented by software and/or hardware.
  • the application provides a control plane network element.
  • the control plane network element includes means for performing the communication method of any of the possible implementations of the fourth aspect or the fourth aspect.
  • the modules included in the control plane network element can be implemented by software and/or hardware.
  • the application provides a user plane network element.
  • the user plane network element includes means for performing the communication method of any of the possible implementations of the fifth aspect or the fifth aspect.
  • the modules included in the user plane network element can be implemented by software and/or hardware.
  • the application provides a user plane network element.
  • the user plane network element includes means for performing the communication method of any of the possible implementations of the sixth aspect or the sixth aspect.
  • the modules included in the user plane network element can be implemented by software and/or hardware.
  • the application provides a database network element.
  • the database network element includes a processor, a transmitter, and a receiver.
  • the processor is used to execute the program.
  • the processor, the transmitter, and the receiver implement the communication method of any of the possible implementations of the first aspect or the first aspect when the processor executes the code.
  • the database network element may further comprise a memory for storing code executed by the processor.
  • the application provides a data analysis network element.
  • the data analysis network element includes a processor, a transmitter, and a receiver.
  • the processor is used to execute the program.
  • the processor, the transmitter, and the receiver implement the communication method in any one of the possible implementations of the second aspect or the second aspect when the processor executes the code.
  • the data analysis network element may further comprise a memory for storing code executed by the processor.
  • the application provides a control plane network element.
  • the control plane network element includes a processor, a transmitter, and a receiver.
  • the processor is used to execute the program.
  • the processor, the transmitter, and the receiver implement the communication method in any one of the possible implementations of the third aspect or the third aspect when the processor executes the code.
  • control plane network element may further comprise a memory for storing code executed by the processor.
  • the application provides a control plane network element.
  • the control plane network element includes a processor, a transmitter, and a receiver.
  • the processor is used to execute the program.
  • the processor, the transmitter, and the receiver implement the communication method in any one of the possible implementations of the fourth aspect or the fourth aspect when the processor executes the code.
  • control plane network element may further comprise a memory for storing code executed by the processor.
  • the application provides a user plane network element.
  • the user plane network element includes a processor, a transmitter, and a receiver.
  • the processor is used to execute the program.
  • the processor, the transmitter, and the receiver implement the communication method in any one of the possible implementations of the fifth aspect or the fifth aspect when the processor executes the code.
  • the user plane network element may further include a memory for storing code executed by the processor.
  • the application provides a user plane network element.
  • the user plane network element includes a processor, a transmitter, and a receiver.
  • the processor is used to execute the program.
  • the processor, the transmitter, and the receiver implement the communication method in any one of the possible implementations of the sixth aspect or the sixth aspect when the processor executes the code.
  • the user plane network element may further include a memory for storing code executed by the processor.
  • the present application provides a computer readable storage medium.
  • Program code for database network element execution is stored in the computer readable storage medium.
  • the program code includes instructions for performing the communication method of the first aspect or any of the possible implementations of the first aspect.
  • the application provides a computer readable storage medium.
  • Program code for data analysis network element execution is stored in the computer readable storage medium.
  • the program code includes instructions for performing the communication method of any of the possible implementations of the second aspect or the second aspect.
  • the present application provides a computer readable storage medium.
  • Program code for controlling execution of the surface network element is stored in the computer readable storage medium.
  • the program code includes instructions for performing the communication method of any of the possible implementations of the third aspect or the third aspect.
  • the present application provides a computer readable storage medium.
  • the computer readable storage medium stores program code for controlling execution of the surface network element.
  • the program code includes instructions for performing the communication method of any of the possible implementations of the fourth aspect or the fourth aspect.
  • the application provides a computer readable storage medium.
  • Program code for user plane network element execution is stored in the computer readable storage medium.
  • the program code includes instructions for performing the communication method of any of the possible implementations of the fifth aspect or the fifth aspect.
  • the application provides a computer readable storage medium.
  • Program code for user plane network element execution is stored in the computer readable storage medium.
  • the program code includes instructions for performing the communication method of any of the possible implementations of the sixth aspect or the sixth aspect.
  • the application provides a computer program product comprising instructions.
  • the database network element is caused to perform the communication method of the first aspect or any of the possible implementations of the first aspect.
  • the application provides a computer program product comprising instructions.
  • the data analysis network element is caused to perform the communication method in any one of the possible implementations of the second aspect or the second aspect.
  • the application provides a computer program product comprising instructions.
  • the control plane network element is caused to perform the communication method in any one of the possible implementations of the third aspect or the third aspect.
  • the application provides a computer program product comprising instructions.
  • the control plane network element is caused to perform the communication method in any one of the possible implementations of the fourth aspect or the fourth aspect.
  • the present application provides a computer program product comprising instructions.
  • the computer program product runs on the user plane network element, the user plane network element is caused to perform the communication method in any one of the possible implementations of the fifth aspect or the fifth aspect.
  • the application provides a computer program product comprising instructions.
  • the computer program product is run on the user plane network element, the user plane network element is caused to perform the communication method in any one of the possible implementations of the fourth aspect or the fourth aspect.
  • the present application provides a chip system, the chip system including a processor, configured to support a database network element, a data analysis network element, a control plane network element, or a user plane network element to implement the foregoing corresponding aspects.
  • the functions involved for example, generate or process information involved in the above communication methods.
  • the chip system further includes a memory for storing necessary program instructions and data of the database network element, the data analysis network element, the control plane network element or the user plane network element.
  • the chip system can be composed of chips, and can also include chips and other discrete devices.
  • FIG. 1 is a system architecture diagram of an application scenario in which a communication method of an embodiment of the present application is applicable;
  • FIG. 2 is a schematic interaction flowchart of a communication method according to an embodiment of the present application.
  • FIG. 3 is a schematic interaction flowchart of a communication method according to another embodiment of the present application.
  • FIG. 4 is a schematic interaction flowchart of a communication method according to another embodiment of the present application.
  • FIG. 5 is a schematic interaction flowchart of a communication method according to another embodiment of the present application.
  • FIG. 6 is a schematic interaction flowchart of a communication method according to another embodiment of the present application.
  • FIG. 7 is a schematic interaction flowchart of a communication method according to another embodiment of the present application.
  • FIG. 8 is a schematic flowchart of a communication method according to an embodiment of the present application.
  • FIG. 9 is a schematic flowchart of a communication method according to another embodiment of the present application.
  • FIG. 10 is a schematic flowchart of a communication method according to another embodiment of the present application.
  • FIG. 11 is a schematic flowchart of a communication method according to another embodiment of the present application.
  • FIG. 12 is a schematic flowchart of a communication method according to another embodiment of the present application.
  • FIG. 13 is a schematic flowchart of a communication method according to another embodiment of the present application.
  • FIG. 14 is a schematic structural diagram of a database network element according to an embodiment of the present application.
  • 15 is a schematic structural diagram of a data analysis network element according to an embodiment of the present application.
  • 16 is a schematic structural diagram of a control plane network element according to an embodiment of the present application.
  • 17 is a schematic structural diagram of a control plane network element according to another embodiment of the present application.
  • FIG. 18 is a schematic structural diagram of a user plane network element according to an embodiment of the present application.
  • FIG. 19 is a schematic structural diagram of a user plane network element according to another embodiment of the present application.
  • FIG. 20 is a schematic structural diagram of a database network element according to another embodiment of the present application.
  • 21 is a schematic structural diagram of a data analysis network element according to another embodiment of the present application.
  • 22 is a schematic structural diagram of a control plane network element according to another embodiment of the present application.
  • FIG. 23 is a schematic structural diagram of a control plane network element according to another embodiment of the present application.
  • FIG. 24 is a schematic structural diagram of a user plane network element according to another embodiment of the present application.
  • 25 is a schematic structural diagram of a user plane network element according to another embodiment of the present application.
  • Figure 26 is a schematic block diagram of a chip system of one embodiment of the present application.
  • the communication system to which the communication method of the embodiment of the present application is applicable may include a terminal 110, an access network (AN) device 120, a UPF network element 130, an AMF network element 140, and an SMF network element 150.
  • NWDA Network Data Analytics
  • SDSF Structured Data Storage Function
  • the embodiment of the present application is not limited to the system architecture shown in FIG. 1.
  • the device in FIG. 1 may be hardware, functionally divided software, or a combination of the two.
  • the terminal 110 may be a User Equipment (UE).
  • Terminal 110 can communicate with one or more core networks (CNs) via AN device 120.
  • a terminal may be referred to as an access terminal, a terminal device, a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a wireless network device, a user agent, or a user device.
  • the terminal can be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA), and a wireless communication function.
  • the AN device 120 may specifically be a Radio Access Network (RAN) device.
  • RAN Radio Access Network
  • An example of an AN device 120 is a base station (BS).
  • a base station also referred to as a base station device, is a device that accesses a terminal to a wireless network, including but not limited to: Transmission Reception Point (TRP), 5G Node B (gNB), and evolved Node B ( Evolved Node B, eNB), Radio Network Controller (RNC), Node B (Node B, NB), Base Station Controller (BSC), Base Transceiver Station (BTS), A home base station (for example, Home evolved node B, or Home Node B, HNB), a Base Band Unit (BBU), or a Wifi Access Point (AP), or a small base station device (pico).
  • TRP Transmission Reception Point
  • gNB 5G Node B
  • eNB evolved Node B
  • RNC Radio Network Controller
  • Node B Node B
  • BSC Base Station Controller
  • BTS Base Transceiver Station
  • a home base station for example, Home evolved node B, or
  • base station is not limited in the embodiment of the present application.
  • the names of devices with base station functions may vary.
  • base stations the foregoing devices for providing wireless communication functions to terminals are collectively referred to as base stations.
  • the UPF network element 130 has functions of packet forwarding, encapsulation, and statistics of the terminal.
  • the AMF network element 140 network element is responsible for terminal access and mobility management.
  • access and mobility management includes mobility state management, temporary identity identification of the assigned terminal, authentication and authorization terminals, and the like.
  • the SMF network element 150 is responsible for selecting, reselecting, and assigning IP addresses of the UPF network element, and is also responsible for establishing, modifying, and releasing sessions, and QoS control.
  • the PCF network element 160 may include policy control decisions and functions based on flow charging control, terminal subscription data management, or QoS control.
  • the NWDA network element 170 can analyze the network level data and notify the data analysis result to other network elements through the SDSF network element 180.
  • the network level data includes data generated, stored and managed by the core network.
  • the SDSF network element 180 can store structured data.
  • the structured data includes at least one of application policy data, network topology data, and big data analysis data in the network.
  • the SDSF network element 180 can be used to implement capability opening inside or outside the network.
  • FIG. 2 is a schematic interaction flowchart of a communication method according to an embodiment of the present application. It should be understood that FIG. 2 illustrates the steps or operations of the communication method, but these steps or operations are merely examples, and other embodiments of the present application may also perform other operations or variations of the operations in FIG. 2. Moreover, the various steps in FIG. 2 may be performed in a different order than that presented in FIG. 2, and it is possible that not all operations in FIG. 2 are to be performed.
  • the database network element collects network data.
  • the database network element may collect historical network data, that is, network data that has been generated before, from one or more of the terminal, the access network, the control plane network element, and the user plane network element.
  • Database network elements include, but are not limited to, SDSF network elements, such as SDSF 180 in FIG.
  • Control plane network elements include, but are not limited to, Control Plane Function (CPF) network elements.
  • the CPF network element may include the AMF network element 140, the SMF network element 150, or the PCF network element 160 shown in FIG.
  • the user plane network element may include a User Plane Function (UPF) network element.
  • UPF User Plane Function
  • the UPF network element can be the UPF network element 130 shown in FIG.
  • the network data may include a DNN of a service type to which the service transmission data associated with the network data belongs.
  • the step S201 may include: the database network element subscribes to the network data of the control plane network element, and then receives the network data that is reported by the control plane network element in real time or periodically reported.
  • the network data includes, but is not limited to, at least one of a terminal's IP address, a terminal type (Terminal Type), a cell ID (Cell ID), a network congestion status, and a network data collection start time.
  • the database network element collects service transmission data.
  • Service transmission data is specific business data, and can also be called application data.
  • a database network element can collect service transmission data of different service types.
  • service types For example, voice services, WeChat services, and car navigation map services are different types of services. It should be understood that the voice service, the WeChat service, and the in-vehicle navigation map service are only examples, and should not constitute a limitation of the service type of the embodiment of the present application.
  • the service transmission data may include at least one of the following information: an IP quintuple, a data packet, a size of the data packet, a start time of the service transmission data, a service type, a service experience, and an extension field.
  • the service transmission data collected by the database network element may include uplink service transmission data and/or downlink service transmission data.
  • the database network element can collect service transmission data from an application platform (Application Platform, AP).
  • the application platform may include an OTT (Over The Top) service center, a vertical control center, a carrier platform, or a third-party service server.
  • the service transmission data collected by the database network element is historical service transmission data, that is, the service transmission data transmitted before in the network.
  • S202 may be located before S201, or S201 may be located before S202, or S201 and S202 may be performed at the same time or concurrently.
  • the database network element associates the service transmission data collected by S201 with the network data collected by S202 to obtain training data.
  • the database network element associates the service transmission data with the network data by using information such as IP quintuple or time to obtain training data.
  • the service transmission data collected by the database network element includes information such as the IP address and time of the terminal, and the time may be the start time of the service transmission data.
  • the service in the network data collected by the database network element includes information such as the IP address and time of the terminal, and the time may be the start time of network data generation.
  • the database network element can associate the service transmission data including the same terminal IP or time and the network data with the network data to obtain training data.
  • the database network element sends the training data to the data analysis network element.
  • the training data includes associated service transmission data and network data. Accordingly, the data analysis network element receives the training data.
  • the data analysis network element includes, but is not limited to, an NWDA network element, for example, the NWDA network element 170 in FIG.
  • the database network element may send the training data to the data analysis network element, or the data analysis network element may send the request message for requesting the training data to the database network element, where the database network element receives the data analysis network element and sends the data. After the request message, the training data is sent to the data analysis network element.
  • the database network element may send the training data to the data analysis network element in batches. For example, in the process of sending the training data to the data analysis network element by the database network element, if the network is congested, the database network element can continue to send the training data to the data analysis network element when the network is idle.
  • the data analysis network element generates first information according to the training data.
  • the first information includes a first feature index list set, a service identifier corresponding to each feature index list in the first feature index list set, and a DNN corresponding to the service identifier.
  • a data analysis network element deployed with Feature Engineering generates a big data model based on the training data, wherein the feature engineering converts the original data into features to better represent the actual problem of the prediction model processing by the features, thereby Improve the accuracy of unknown data.
  • Feature engineering is the process of generating, extracting, deleting, or combining changes with specific domain knowledge or automated methods in which the target problem is located.
  • the process of converting the training data into features by the data analysis network element includes the following steps: integrating the data, that is, integrating the data into one data set; preprocessing the data, that is, cleaning, formatting, and sampling the data; converting the data, and transforming the data by the feature engineering It is key information; data modeling, that is, building a model, evaluating a model, and adjusting a model.
  • This model can also be called a big data model for identifying business types.
  • the data analysis network element can separate the key information in the training data.
  • the key information includes a list of service characteristics corresponding to different service types.
  • the business feature list may be simply referred to as a feature list.
  • a list of service characteristics corresponds to a unique type of service, so that a unique type of service can be identified based on a list of service characteristics.
  • Each service type can have a unique service identifier. Therefore, after the data analysis network element obtains the feature list corresponding to the service type according to the training data, the data relationship may be based on the correspondence between the service type and the service identifier and the correspondence between the service type and the feature list. The correspondence between the feature list and the service identifier is obtained. Each feature list corresponds to a service identifier.
  • the training data includes service transmission data of the video service and the payment service, and network data.
  • the data analysis network element performs big data analysis on the training data to obtain an exemplary feature list of the video service and the payment service.
  • the exemplary feature list of the video service may include the following features: the size of the first packet in the video service flow, the average of all packet sizes in the video service flow, the entropy of all packet sizes in the video service flow, and the use of video services. Time, terminal location and cell identification.
  • the size of the first packet in the video service stream, the average value of all packet sizes in the video service stream, the entropy of all packet sizes in the video service stream, and the usage time of the video service may be data transmission data of the data analysis network element according to the video service.
  • the obtained terminal location and the cell identifier may be obtained by the data analysis network element according to the network data associated with the service transmission data of the video service.
  • the exemplary feature list of the payment service may include the following features: the average of the time interval of all the packets in the payment service flow, the entropy of the time interval of all the packets in the payment service flow, the usage time of the payment service, and the terminal type.
  • the average value of the time interval of all the packets in the payment service flow, the entropy of the time interval of all the packets in the payment service flow, and the usage time of the payment service may be obtained by the data analysis network element according to the service transmission data of the payment service.
  • the terminal type may be obtained by the data analysis network element according to the network data associated with the service transmission data of the payment service.
  • the feature lists may be mixed, or the newly obtained feature list may be integrated into the existing feature list set, and the union is obtained to obtain a total feature list without repeated features.
  • the total list of features that can be obtained by mixing the features in the feature list of the video service and the payment service described above is as shown in Table 1.
  • feature usage time The size of the first packet in the stream The mean of all packet sizes in the stream Entropy of all packet sizes in the stream The mean of the time interval between all the packets in the stream Entropy of the time interval of all packets in the stream terminal type
  • the data analysis network element can assign an index to each feature.
  • Table 2 shows the correspondence between features and indexes in the total feature list shown in Table 1.
  • feature index usage time 1 The size of the first packet in the stream 2
  • the mean of all packet sizes in the stream 3 Entropy of all packet sizes in the stream 4
  • the mean of the time interval between all the packets in the stream 5 Entropy of the time interval of all packets in the stream 6 terminal type 7 Terminal location 8 Cell logo 9
  • the feature index list corresponding to the different service types can be obtained according to the feature list corresponding to the different service types.
  • the feature index list of the obtained payment service and the feature index list of the video service are as shown in Table 3.
  • the feature index list can be extended to a binary space. Assuming that the number of features in the total feature list is n, then each feature index list can be represented as an n-dimensional binary string.
  • the feature index list can be represented by a binary string of length 9.
  • the binary feature index list of the payment service may be represented as 100011100
  • the binary feature index list of the video service may be represented as 111100011.
  • the plurality of feature index lists obtained by the data analysis network element may form a feature index list set, and the feature index list set may be referred to as a first feature index list set.
  • the same business type can correspond to multiple feature lists. Accordingly, the same service type can correspond to multiple feature index lists.
  • the congestion of the network may be different, which may cause different times for the user to use the payment service, and the number of feature lists corresponding to the payment service generated by the data analysis network element according to the training data may be multiple.
  • the number of user groups using the payment service in the city A is about 100,000 users, and the data analysis network element performs big data analysis on the training data of the city.
  • the list of feature indexes corresponding to the payment service is shown in Table 4.
  • Table 4 Feature list of payment services (City A, 7:00 am to 17:00 pm)
  • the data analysis network element analyzes the city's training data after big data analysis.
  • the list of feature indexes corresponding to the service is shown in Table 5.
  • the user group using the payment service in the city A is greatly reduced to 20,000 users.
  • the payment service corresponds to the payment service.
  • the feature index list is shown in Table 6.
  • the feature index list corresponding to the feature list of the payment service in FIG. 4 to FIG. 6 is as shown in Table 7.
  • each service type may have a unique service identifier.
  • a feature index list corresponds to a service identifier. If multiple feature lists correspond to one service type, the feature index list is represented by: multiple feature index lists corresponding to one service identifier.
  • Table 8 shows the correspondence between the three feature index lists of the payment service and the service identifiers in Table 7. That is, the service identifier of the payment service corresponds to the feature index list-1, the feature index list-2, and the feature index list-3. Or it can be said that the feature index list-1, the feature index list-2, and the feature index list-3 all correspond to the service identifier of the payment service.
  • Table 8 is only an example in which multiple feature index lists correspond to the same service identifier, and the representation form or storage form of the correspondence relationship between the feature index list and the service identifier should not be restricted.
  • the correspondence between the service identifier of the payment service and the multiple feature index lists may be as shown in Table 9.
  • Business identifier Feature index list Business identifier of the payment service Feature Index List-1 Business identifier of the payment service Feature Index List-2 Business identifier of the payment service Feature Index List-3
  • the network data may include the DNN corresponding to the service type.
  • the data analysis network element may also obtain the service type corresponding to the service type. The correspondence between the DNN and the service identifier of the service type.
  • DNN Business identifier Feature index list DNN-1 Business logo 1 ⁇ 1,5,6,7 ⁇ DNN-1 Business logo 2 ⁇ 1,2,3,4,8,9 ⁇
  • DNN-2 Business logo 3 ⁇ 1,4,7,...,19 ⁇ DNN-2 Business logo 3 ⁇ 1,2,3,...,1000 ⁇ DNN-3 Business logo 4 ⁇ 1,2,3,...,200 ⁇
  • Table 5 or Table 11 includes five feature index lists, each of which has a unique corresponding service identifier.
  • the four service types corresponding to the five feature index lists belong to three different DNNs.
  • the data analysis network element sends the first information to the database network element.
  • the database network element receives the first information.
  • the correspondence between the feature and the index may also be included in the first information.
  • the correspondence information as shown in Table 2 may be included in the first information.
  • the database network element can know which feature corresponds to the feature index in each feature index list in the first feature index set.
  • the database network element may store the first information.
  • the database network element after the database network element receives the first information, stores the first information by: the database network element can use the service identifier as the data index information, and store the corresponding information of each service identifier. A list of feature indexes and a DNN corresponding to each service identifier.
  • the database network element after the database network element receives the first information, stores the first information by: the database network element can use the DNN as the data index information, and store the service corresponding to each DNN.
  • the database network element sends the first information to the control plane network element.
  • the control plane network element receives the first information.
  • the first information sent by the data analysis network element to the database network element may also include the correspondence between the feature and the index.
  • the control plane network element may be an AMF network element, an SMF network element or a PCF network element, or other control plane function network element.
  • the control network element may be the AMF network element 140, the SMF network element 150, or the PCF network element 160 shown in FIG.
  • control plane network element may save the first information.
  • the database network element can directly send the first information to the SMF network element or the PCF network element, or can also pass the Network Exposure Function (NEF).
  • the network element sends the first information to the SMF network element or the PCF network element.
  • the terminal initiates a modification process of an existing session or initiates a new session establishment process.
  • the session is referred to as a first session.
  • the first session may be a Service Data Flow.
  • the first session can be identified by an IP quintuple.
  • the UE When the UE initiates the first session, it carries the DNN associated with the first session.
  • the DNN associated with the first session may be referred to as a first DNN.
  • the control plane network element queries, according to the first DNN, the second information from the first information, where the second information includes a second feature index list set corresponding to the first DNN and each feature index in the second feature index list set.
  • the service ID corresponding to the list is a second feature index list set corresponding to the first DNN and each feature index in the second feature index list set.
  • control plane network element may filter the locally saved first information according to the first DNN, and match the feature index list and the service identifier corresponding to the first DNN.
  • the feature index list corresponding to the first DNN filtered from the first information constitutes a second feature index list set.
  • the control plane network element generates the second information according to the second feature index list set and the filtered service identifier, where the second information includes the second feature index list set and the filtered service identifier.
  • the control plane network element may generate the second information according to Table 11, second.
  • the information may include the contents shown in Table 12.
  • Table 12 List of service identifiers and feature indexes included in the second information
  • Business identifier Feature index list Business logo 1 ⁇ 1,5,6,7 ⁇ Business logo 2 ⁇ 1,2,3,4,8,9 ⁇
  • the second information sent by the control plane network element to the user plane network element may also include the corresponding relationship.
  • the user plane network element can locally store the corresponding relationship between the feature and the index.
  • the subsequent control plane network element sends the second information corresponding to the service type to the user plane network element again, the second information may include only the feature index corresponding to the service type.
  • the user plane network element may obtain the feature list corresponding to the feature index list according to the corresponding relationship between the saved feature and the index.
  • the control plane network element sends the second information to the user plane network element.
  • the user plane network element receives the second information.
  • User plane network elements include, but are not limited to, UPF network elements.
  • the user plane network element can be the UPF network element 130 shown in FIG.
  • control plane network element that sends the second information to the user plane network element may be an SMF network element.
  • the SMF network element determines the second information according to the first information, and sends the second information to the user plane network element.
  • the SMF network element obtains, from the PCF network element, the second information determined by the PCF network element according to the first information, the SMF network element and the second The information is sent to the UPF network element.
  • control plane network element sends the second information to the user plane network element is only an example, and should not be limited in the embodiment of the present application.
  • the user plane network element receives the service transmission data of the terminal.
  • the service transmission data may be uplink service transmission data or downlink service transmission data.
  • S211 may also be located before S209 or S210.
  • the user plane network element obtains the feature value in the service transmission data according to the second information.
  • the user plane network element obtains, from the service transmission data, a list of feature values corresponding to each feature index list in the second feature index list set.
  • the user plane network element can obtain the feature index 1 and 2 from the service transmission data.
  • 3, 4, 5, and 6 corresponding features "use time”, “size of the first packet in the stream”, “average of all packet sizes in the stream”, “entropy of all packet sizes in the stream”, “all packets in the stream”
  • the eigenvalue corresponding to the mean of the time interval of the uplink and the downlink and the entropy of the time interval of all the packets in the stream.
  • the user plane network element can transmit the feature values as shown in Table 13 from the service.
  • Table 13 Eigenvalues obtained from traffic transmission data
  • the terminal type, the terminal location, and the cell identifier belong to the network data, so the user plane network element cannot obtain the terminal type, the terminal location, and the cell identifier corresponding to the feature indexes 7, 8, and 9 respectively according to the service transmission data.
  • the feature value, next, the user plane network element performs S213.
  • the user plane network element sends third information to the database network element, where the third information carries the first service identifier set.
  • the database network element receives the third information sent by the user plane network element.
  • a feature index list composed of feature indexes that cannot obtain feature values according to service transmission data is referred to as a first network data feature index list.
  • the training data includes network data
  • the feature index list is generated according to the training data
  • the feature value corresponding to the feature index corresponding to the network data cannot be obtained from the service transmission data.
  • the user plane network element may filter out the feature index that cannot obtain the feature value from the service transmission data, and obtain the first network data feature index list.
  • the user plane network element does not obtain the feature values corresponding to the features "terminal type”, “terminal location”, and “cell identity” corresponding to the feature indexes 7, 8, and 9 in Table 12 from the service transmission data. That is, the feature indexes 7, 8, and 9 constitute a first network data feature index list as shown in Table 14.
  • the user plane network element obtains the first network data feature index list, and may remove the duplicate feature index in the first network data index list to obtain a first network data feature index list that does not include the duplicate feature index.
  • the service identifier corresponding to the feature index list to which each feature index belongs in the first network data feature index list may be determined.
  • the service identifier corresponding to all feature indexes in the first network data feature index list constitutes a first service identifier set.
  • the service identifier corresponding to the feature index 7 that cannot obtain the feature value according to the service transmission data in Table 12 is the service identifier 1
  • the service identifier corresponding to the indexes 8 and 9 that cannot obtain the feature value according to the service transmission data in Table 12 is the service identifier 2 Therefore, the correspondence between the first network data feature index list and the service identifier as shown in FIG. 15 can be obtained.
  • the user plane network element can obtain the first service identifier set including the service identifier 1 and the service identifier 2 according to the table 15, as shown in Table 16.
  • the database network element collects network data of the first session.
  • the network data of the first session may include a type of a terminal that initiates the first session, a time when the terminal initiates the first session, a cell identifier to which the terminal belongs, and the like.
  • S214 may be located anywhere between S208 and S213.
  • the database network element sends a network data feature value list to the user plane network element.
  • the user plane network element receives the network data feature value list.
  • the database network element collects the network data of the first session, and after receiving the third message sent by the user plane network element, may determine that the feature index list corresponding to each service identifier in the first service identifier set corresponds to the network data.
  • Feature index The feature list composed of the feature indexes corresponding to the network data in the feature index list corresponding to all the service identifiers in the first service identifier set may be referred to as a second network data feature index list.
  • the feature values of the feature corresponding to each feature index in the second network data feature index list are obtained from the collected network data of the first session.
  • the list of feature values composed of the feature values corresponding to each feature index in the second network data feature index list obtained from the network data of the first session may be referred to as a network data feature value list.
  • the database network element may acquire the features of the terminal type, the terminal location, and the cell identifier from the network data of the first session. Network data feature value.
  • An example of the network data feature value list obtained by the database network element is: the database network element obtains the first service identity set according to the first service identifier set of the table 16 and includes the service identifier 1 and the service identifier 2; further, the database The network element searches for the feature index 7 "terminal type" corresponding to the service identifier 1 and belongs to the network data according to the first information acquired by the S206. The database network element determines the feature value corresponding to the "terminal type" according to the network data acquired in S214.
  • the database network element determines the feature values corresponding to the “terminal location” and the “cell identity” according to the network data acquired by S214 according to the feature index 8 “terminal location” corresponding to the service identifier 2 and the feature index 9 “cell identity”.
  • the database network element may send a list of network data feature values as shown in Table 17 to the user plane network element.
  • the user plane network element sends, to the data analysis network element, a second feature index list set and a feature value list corresponding to each feature index list in the second feature index list set.
  • the second feature index list set and the feature value list corresponding to each feature index list in the second feature index list set correspond to the first session.
  • the feature value sent by the user plane network element to the data analysis network element includes not only the feature value of the service transmission data but also the network data feature value.
  • the data analysis network element receives the feature value from the user plane network element.
  • the user plane network element may send a list of feature values as shown in Table 18 to the data analysis network element according to Table 13 and Table 17, the list of feature values corresponding to the first session.
  • Table 18 list of feature values corresponding to the first session
  • the data analysis network element determines, according to the second feature index list set received from the user plane network element and the feature value list corresponding to each feature index list in the second feature index list set, the data packet in the first session is determined. business type.
  • the data analysis network element may send the second feature index list set of the user plane network element and the feature value list corresponding to each feature index list in the second feature index list set as the big data generated in S205.
  • the input parameter of the model, the output result of the big data model is the service type corresponding to the data packet in the first session.
  • the data is
  • the service type determined by the analysis network element can only be one of the two, that is, the feature index list set sent by the user plane network element and the feature value list corresponding to each feature index list correspond to the unique service type.
  • the data analysis network element sends the service type determined in S217 to the user plane network element.
  • the user plane network element receives the service type.
  • the division of labor between the network elements cooperates to complete the identification of the service type.
  • the database network element can be deployed in a distributed manner and is deployed close to the application server and the core network element, it helps to reduce the delay in acquiring the training data and delivering the first information.
  • the data analysis network element may determine the service type of the terminal according to the network data of the terminal and the service transmission data, thereby improving the recognition accuracy.
  • the first information may further include at least one of the following information corresponding to each feature index list in the first feature index list set: a network slice type, an SSC mode, and a PDU session type.
  • the control plane network element queries the first information to obtain the second information, the control plane network element can be based not only on The DNN of the first session may also filter the second information according to at least one of the network slice type, the SSC mode, and the PDU session type of the first session.
  • the second information is filtered from the first information, and each of the feature index lists in the second feature index list set in the second information corresponds to the DNN of the first session, and corresponds to the first session.
  • the first service identifier set determined by the database network element is empty, in the embodiment of the present application, there may be no S213 and S215, or even no S214.
  • the third information may further carry at least one of the following information: a time when the user plane network element receives the service transmission data of the first session, a session identifier of the first session, and the first The identifier of the terminal corresponding to the session, the IP address of the terminal corresponding to the first session, the port of the terminal corresponding to the first session, the IP address of the service server corresponding to the first session, the port corresponding to the first session in the service server, and the first The service transmission protocol of the session's service transmission data.
  • the database network element may further acquire the feature value of the network data that satisfies the at least one type of information according to the at least one information carried in the third information.
  • the third information sent by the user plane network element to the database network element may carry the IP address of the terminal, the IP address of the terminal is used to identify the terminal, and the database network element determines the network data of the terminal according to the IP address of the terminal.
  • the network element of the first session when the network element of the first session collects network data of the first session, the network element may also collect one or more pieces of information according to the DNN corresponding to the first session, the IP address of the terminal, the ID of the terminal, and the PDU session ID. Network data for a session.
  • the user plane network element may directly communicate with the database network element, or may communicate with the database network element through the SMF network element.
  • FIG. 3 is a schematic interaction flowchart of a communication method according to an embodiment of the present application. It should be understood that FIG. 3 illustrates steps or operations of the communication method, but these steps or operations are merely examples, and other embodiments of the present application may also perform other operations or variations of the operations in FIG. Moreover, the various steps in FIG. 3 may be performed in a different order than that presented in FIG. 3, and it is possible that not all operations in FIG. 3 are to be performed.
  • the user plane network element sends third information to the database network element, where the third information carries a network data feature index list.
  • the database network element receives the third information sent by the user plane network element.
  • the user plane network element obtains the feature value from the service transmission data, it is determined that all feature indexes of the second feature index list set that cannot obtain the feature value according to the service transmission data are determined.
  • the feature index of the second feature index list set that cannot obtain the feature value according to the service transmission data constitutes a network data feature index list.
  • the training data since the training data includes network data, when the feature index list is generated according to the training data, there may be a feature index corresponding to the network data in the feature index list.
  • the feature value corresponding to the feature index corresponding to the network data is not available from the service transmission data.
  • the user plane network element may filter out the feature index that cannot obtain the feature value from the service transmission data, and obtain a network data feature index list.
  • the user plane network element does not obtain the feature values corresponding to the features "terminal type”, “terminal location”, and “cell identity” corresponding to the feature indexes 7, 8, and 9 in Table 12 from the service transmission data. That is, the feature indexes 7, 8, and 9 constitute a network data feature index list.
  • the user plane network element may remove the duplicate feature index in the network data feature index list to obtain a network data feature index list that does not include the duplicate feature index.
  • S314 can refer to S214 in FIG. 2, and details are not described herein again.
  • the database network element sends a network data feature value list to the user plane network element.
  • the user plane network element receives the network data feature value list from the database network element.
  • the database network element obtains the feature value of the feature corresponding to each feature index in the network data feature index list from the collected network data of the first session.
  • the list of feature values composed of the feature values corresponding to each feature index in the network data feature index list obtained from the network data of the first session may be referred to as a network data feature value list.
  • the database network element may obtain network data corresponding to the features "terminal type”, “terminal location”, and "cell identity” from the network data of the first session. Eigenvalues.
  • FIG. 4 is a schematic interaction flowchart of a communication method according to an embodiment of the present application. It should be understood that FIG. 4 illustrates steps or operations of the communication method, but these steps or operations are merely examples, and other embodiments of the present application may also perform other operations or variations of the operations in FIG. Moreover, the various steps in FIG. 4 may be performed in a different order than that presented in FIG. 4, and it is possible that not all operations in FIG. 4 are to be performed.
  • the user plane network element sends third information to the database network element, where the third information is used to request network data corresponding to the first session.
  • the database network element receives the third information sent by the user plane network element.
  • the second feature index list set has a feature index that cannot obtain the feature value according to the service transmission data.
  • the user plane network element sends the third information to the database network element to request the network data of the first session, which is convenient for subsequent description.
  • the index list composed of the feature indexes in the feature index list set that cannot obtain the feature values according to the service transmission data is referred to as a network data feature index list.
  • the training data includes network data
  • the feature index list is generated according to the training data
  • the user plane network element does not obtain the feature values corresponding to the features "terminal type”, “terminal location”, and “cell identity” corresponding to the feature indexes 7, 8, and 9 in Table 12 from the service transmission data. Then, the user plane network element sends the third information to the database network element to request the network data of the first session.
  • the third information may include a time when the user plane network element receives the service transmission data of the first session, a session identifier of the first session, an identifier of the terminal corresponding to the first session, an IP address of the terminal corresponding to the first session, and the first The port of the terminal corresponding to the session, the IP address of the service server corresponding to the first session, the port corresponding to the first session in the service server, the service transmission protocol of the service transmission data of the first session, and the like.
  • the database network element may collect network data of the first session according to the third information.
  • the database network element may collect network data that meets at least one of the following conditions: a time when the user plane network element receives the service transmission data of the first session, a session identifier of the first session, an identifier of the terminal corresponding to the first session, and a first session.
  • the database network element sends network data to the user plane network element. Accordingly, the user plane network element receives network data from the database network element.
  • the user plane network element After receiving the network data of the first session from the database network element, the user plane network element obtains the feature value of the feature corresponding to the feature index in the network data feature index list from the network data of the first session.
  • a list of feature values of features corresponding to the feature index in the network data feature index list is referred to as a network data feature value list.
  • FIG. 5 is a schematic interaction flowchart of a communication method according to an embodiment of the present application. It should be understood that FIG. 5 illustrates steps or operations of the communication method, but these steps or operations are merely examples, and other embodiments of the present application may also perform other operations or variations of the operations in FIG. 5. Moreover, the various steps in FIG. 5 may be performed in a different order than that presented in FIG. 5, and it is possible that not all operations in FIG. 5 are to be performed.
  • S507 can refer to S208, and for brevity, no further details are provided herein.
  • the control plane network element sends the DNN of the first session to the database network element.
  • the database network element receives the DNN of the first session sent by the control plane network element.
  • S509 The database network element queries, according to the DNN of the first session, the second information, where the second information includes the second feature index list set and the service type corresponding to each feature index list in the second feature list set. Business identity.
  • the database network element obtains the second information from the first information according to the first DNN associated with the first session, where the second information includes the second feature index list set and the second feature index list set corresponding to the first DNN.
  • the service ID corresponding to the feature index list is not limited to the feature index list.
  • the database network element may filter the locally saved first information according to the first DNN, and match the feature index list and the service identifier corresponding to the first DNN.
  • the feature index list corresponding to the first DNN filtered from the first information constitutes a second feature index list set.
  • the database network element generates the second information according to the second feature index list set and the filtered service identifier, where the second information includes the second feature index list set and the filtered service identifier.
  • the database network element may generate the second information according to Table 11, the second information.
  • the contents shown in Table 12 can be included.
  • the second information sent by the database network element to the control plane network element may also include the corresponding relationship.
  • the control plane network element can locally save the total feature list.
  • the second information may include only the feature index list corresponding to the service type.
  • the control plane network element may send the corresponding relationship between the feature and the index to the user plane network element, so that the user plane network element can obtain the feature list corresponding to the feature index list in the second information according to the corresponding relationship.
  • the database network element sends the second information to the control plane network element.
  • the control plane network element receives the second information sent by the database network element.
  • S511 to S519 can refer to the corresponding steps in S210 to S218. For the sake of brevity, it will not be repeated here.
  • control plane network element may further send the following at least one type of information of the first session to the database network element: a network slice type, an SSC mode, and a PDU session type.
  • the database network element further receives the at least one type of information of the first session from the CPF network element.
  • the second information when the database network element queries the second information from the first information, the second information may be obtained according to the at least one information of the first session, in addition to the DNN of the first session. In this way, it helps to obtain more accurate second information, which helps to improve the accuracy of business type identification.
  • the second information may further include at least one of the following information corresponding to each feature index list in the second feature index list set: DNN, network slice type, service and SSC mode, PDU session Types of.
  • the control plane network element may be configured according to the And determining, by the at least one type of information corresponding to each feature index list in the second feature index list set, whether the feature index list corresponding to the second session is included in the second feature index list set.
  • control plane network element determines that the second feature index list set includes the feature index list corresponding to the second session according to the at least one information corresponding to each feature index list in the second feature index list set, the control plane network The element can no longer request the second information from the database network element, thereby helping to improve the efficiency of the service type identification.
  • FIG. 6 is a schematic interaction flowchart of a communication method according to an embodiment of the present application. It should be understood that FIG. 6 illustrates steps or operations of the communication method, but these steps or operations are merely examples, and other embodiments of the present application may also perform other operations or variations of the operations in FIG. 6. Moreover, the various steps in FIG. 6 may be performed in a different order than that presented in FIG. 6, and it is possible that not all operations in FIG. 6 are to be performed.
  • FIG. 7 is a schematic interaction flowchart of a communication method according to an embodiment of the present application. It should be understood that FIG. 7 illustrates steps or operations of the communication method, but these steps or operations are merely examples, and other embodiments of the present application may also perform other operations or variations of the operations in FIG. Moreover, the various steps in FIG. 7 may be performed in a different order than that presented in FIG. 7, and it is possible that not all operations in FIG. 7 are to be performed.
  • S717 to S719 reference may be made to S517 to S519 in FIG. 5, and details are not described herein for brevity.
  • the database network element may re-execute S201 to S207.
  • the database network element may re-execute S301 to S307.
  • the database network element may re-execute S401 to S407.
  • the database network element may re-execute S501 to S506.
  • the database network element may re-execute S601 to S606.
  • the database network element may re-execute S701 to S706.
  • FIG. 8 A schematic interaction flowchart of the communication method of the embodiment of the present application is described above with reference to FIG. 2 to FIG. 7.
  • the single-side communication method of the embodiment of the present application is described below with reference to FIG. 8 to FIG.
  • FIG. 8 is a schematic flowchart of a communication method according to an embodiment of the present application. It should be understood that FIG. 8 illustrates steps or operations of the communication method, but these steps or operations are merely examples, and other embodiments of the present application may also perform other operations or variations of the operations of FIG. Moreover, the various steps in FIG. 8 may be performed in a different order than that presented in FIG. 8, and it is possible that not all operations in FIG. 8 are to be performed.
  • the database network element acquires training data, where the training data includes service transmission data and network data.
  • S201 to S203 in Fig. 2 S301 to S303 in Fig. 3, S401 to S403 in Fig. 4, S501 to S503 in Fig. 5, S601 to S603 in Fig. 6, and S701 to S703 in Fig. 7.
  • the database network element sends the training data to the data analysis network element.
  • the database network element receives the first information from the data analysis network element, where the first information includes the first feature index list set, the service identifier corresponding to each feature index list in the first feature index list set, and the DNN corresponding to the service identifier.
  • S206 in FIG. 2 S306 in FIG. 3, S406 in FIG. 4, S506 in FIG. 5, S606 in FIG. 6, and S706 in FIG.
  • the communication method shown in FIG. 8 may further include: the database network element sending the first information to the control plane network element.
  • S207 in Fig. 2 S307 in Fig. 3, and S407 in Fig. 4.
  • the communication method shown in FIG. 8 may further include: the database network element receives the DNN of the first session from the control plane network element; and the database network element queries the first information according to the DNN of the first session.
  • the second information includes a second feature index list set corresponding to the DNN of the first session and a service identifier corresponding to each feature index list in the second feature index list set; the database network element sends the first to the control plane network element Two information.
  • the communication method shown in FIG. 8 may further include: the database network element receives the third information from the user plane network element, where the third information includes the first service identifier set; and the database network element obtains the first information from the first information. a list of feature indexes corresponding to each service identifier in a service identifier set; the database network element queries the network service data for each of the first service identifier sets according to the feature index list corresponding to each service identifier in the first service identifier set A list of network data feature values corresponding to the service identifiers; the database network element sends a list of network data feature values corresponding to each service identifier in the first service identifier set to the user plane network element.
  • FIG. 9 is a schematic flowchart of a communication method according to an embodiment of the present application. It should be understood that FIG. 9 illustrates steps or operations of the communication method, but these steps or operations are merely examples, and other embodiments of the present application may also perform other operations or variations of the operations in FIG. Moreover, the various steps in FIG. 9 may be performed in a different order than that presented in FIG. 9, and it is possible that not all operations in FIG. 9 are to be performed.
  • the data analysis network element receives training data from a database network element, where the training data includes service transmission data and network data.
  • the data analysis network element determines the first information according to the training data, where the first information includes the first feature index list set and the service identifier corresponding to each feature index list in the first feature index list set and the DNN corresponding to the service identifier.
  • S205 in Fig. 2 S305 in Fig. 3, S405 in Fig. 4, S505 in Fig. 5, S605 in Fig. 6, and S705 in Fig. 7.
  • the data analysis network element sends the first information to the database network element.
  • S206 in FIG. 2 S306 in FIG. 3, S406 in FIG. 4, S506 in FIG. 5, S606 in FIG. 6, and S706 in FIG.
  • FIG. 10 is a schematic flowchart of a communication method according to an embodiment of the present application. It should be understood that FIG. 10 illustrates steps or operations of the communication method, but these steps or operations are merely examples, and other embodiments of the present application may also perform other operations or variations of the operations in FIG. Moreover, the various steps in FIG. 10 may be performed in a different order than that presented in FIG. 10, and it is possible that not all operations in FIG. 10 are to be performed.
  • the control plane network element receives the first information from the database network element, where the first information includes the first feature index list set and the service identifier corresponding to each feature index list in the first feature index list set and the DNN corresponding to the service identifier.
  • S207 in Fig. 2 S307 in Fig. 3, and S407 in Fig. 4.
  • the control plane network element queries, according to the DNN of the first session, the second information, where the second information includes a second feature index list set corresponding to the DNN of the first session, and a second feature index list.
  • the service identifier corresponding to each feature index list.
  • S209 in Fig. 2 S309 in Fig. 3, and S409 in Fig. 4.
  • the control plane network element sends the second information to the user plane network element.
  • S210 in Fig. 2 S310 in Fig. 3, and S410 in Fig. 4.
  • FIG. 11 is a schematic flowchart of a communication method according to an embodiment of the present application. It should be understood that FIG. 11 illustrates steps or operations of the communication method, but these steps or operations are merely examples, and other embodiments of the present application may also perform other operations or variations of the operations in FIG. Moreover, the various steps in FIG. 11 may be performed in a different order than that presented in FIG. 11, and it is possible that not all operations in FIG. 11 are to be performed.
  • control plane network element sends the DNN of the first session to the database network element.
  • the control plane network element receives the second information from the database network element, where the second information includes a second feature index list set and a service identifier corresponding to each feature index list in the second feature index list set, where the service identifier corresponds to the DNN.
  • S510 in FIG. 5 S610 in FIG. 6, and S710 in FIG.
  • control plane network element sends the second information to the user plane network element.
  • the communication method may further include: the control plane network element sends the following at least one type of information of the first session to the database network element: network slice type, SSC mode , PDU session type.
  • FIG. 12 is a schematic flowchart of a communication method according to an embodiment of the present application. It should be understood that FIG. 12 illustrates steps or operations of the communication method, but these steps or operations are merely examples, and other embodiments of the present application may also perform other operations or variations of the operations in FIG. Moreover, the various steps in FIG. 12 may be performed in a different order than that presented in FIG. 12, and it is possible that not all operations in FIG. 12 are to be performed.
  • the user plane network element receives the second information from the control plane network element, where the second information includes the second feature index list set and the service identifier corresponding to each feature index list in the second feature index list set.
  • the user plane network element receives the service transmission data of the first session.
  • the user plane network element determines, in the second feature index list set, the service identifier corresponding to the feature index list that cannot obtain the feature value according to the service transmission data, obtains the first service identifier set, and sends the third information to the database network element, and the third The information includes a first set of service identifiers.
  • the user plane network element receives, from the database network element, a list of network data feature values corresponding to each service identifier in the first service identifier set.
  • S215 in Fig. 2 S516 in Fig. 5.
  • FIG. 13 is a schematic flowchart of a communication method according to an embodiment of the present application. It should be understood that FIG. 13 illustrates steps or operations of the communication method, but these steps or operations are merely examples, and other embodiments of the present application may also perform other operations or variations of the operations in FIG. Moreover, the various steps in FIG. 13 may be performed in a different order than that presented in FIG. 13, and it is possible that not all operations in FIG. 13 are to be performed.
  • the user plane network element receives the second information from the control plane network element, where the second information includes the second feature index list set and the service identifier corresponding to each feature index list in the second feature index list set.
  • the user plane network element receives the service transmission data of the first session.
  • the user plane network element determines a feature index of the second feature index list set that cannot obtain the feature value according to the service transmission data, obtains a network data feature index list, and sends the network data feature index list to the database network element.
  • the user plane network element receives, from the database network element, a list of network data feature values corresponding to the network data feature index list.
  • FIG. 14 A schematic structural diagram of a database network element of an embodiment of the present application is shown in FIG. It should be understood that the database network element 1400 shown in FIG. 14 is only an example, and the database network element in the embodiment of the present application may further include other modules or units, or include modules similar in function to the respective modules in FIG. 14, or Includes all the modules in Figure 14.
  • the processing module 1401 is configured to acquire training data, where the training data includes service transmission data and network data.
  • the sending module 1402 is configured to send training data to the data analysis network element.
  • the receiving module 1403 is configured to receive the first information from the data analysis network element, where the first information includes the first feature index list set, the service identifier corresponding to each feature index list in the first feature index list set, and the data corresponding to the service identifier.
  • Network name DNN is configured to receive the first information from the data analysis network element, where the first information includes the first feature index list set, the service identifier corresponding to each feature index list in the first feature index list set, and the data corresponding to the service identifier.
  • the first information may further include at least one of the following information corresponding to each feature index list in the first feature index list set: a network slice type, an SSC mode, and a PDU session type.
  • the sending module 1402 is further configured to: send the first information to the control plane network element.
  • the receiving module is further configured to: receive the DNN of the first session from the control plane network element;
  • the processing module 1401 is further configured to: query, according to the DNN of the first session, the second information from the first information, where the second information includes a second feature index list set corresponding to the DNN of the first session, and the second feature The service identifier corresponding to each feature index list in the index list set.
  • the sending module is further configured to: send the second information to the control plane network element.
  • the receiving module 1403 is further configured to: receive, by the control plane network element, at least one of the following information of the first session: a network slice type, an SSC mode, and a PDU session type.
  • the processing module 1401 is specifically configured to: query the second information from the first information according to the DNN of the first session and the at least one information of the first session.
  • the receiving module 1403 is further configured to: receive third information from the user plane network element, where the third information includes the first service identifier set.
  • processing module 1401 is further configured to:
  • the query obtains a feature index list corresponding to each service identifier in the first service identifier set;
  • the network data feature value list corresponding to each service identifier in the first service identifier set is obtained from the network data according to the feature index list corresponding to each service identifier in the first service identifier set.
  • the sending module 1402 is further configured to: send, to the user plane network element, a network data feature value list corresponding to each service identifier in the first service identifier set.
  • the third information may further include at least one of the following: a time when the user plane network element receives the service transmission data of the first session, a session identifier of the first session, and a terminal corresponding to the first session.
  • the identifier of the terminal the Internet Protocol IP address of the terminal corresponding to the first session, the port of the terminal corresponding to the first session, the IP address of the service server corresponding to the first session, and the service server A service corresponding to the port, the service transmission protocol of the service transmission data of the first session.
  • FIG. 15 A schematic structural diagram of a data analysis network element of an embodiment of the present application is shown in FIG. It should be understood that the data analysis network element 1500 shown in FIG. 15 is only an example, and the data analysis network element of the embodiment of the present application may further include other modules or units, or include modules similar in function to the respective modules in FIG. 15 , or It is not necessary to include all the modules in Figure 15.
  • the receiving module 1501 is configured to receive training data from a database network element, where the training data includes service transmission data and network data.
  • the processing module 1502 is configured to determine first information according to the training data, where the first information includes a first feature index list set and a service identifier corresponding to each feature index list in the first feature index list set and a DNN corresponding to the service identifier.
  • the sending module 1503 is configured to send the first information to the database network element.
  • the first information may further include at least one of the following information corresponding to each feature index list in the first feature index list set: a network slice type, an SSC mode, and a PDU session type.
  • each module included in the data analysis network element 1500 in FIG. 15 may be used to implement the corresponding steps performed by the data analysis network element in the communication method shown in any one of FIG. 2 to FIG. No longer.
  • FIG. 16 A schematic structural diagram of a control plane network element of an embodiment of the present application is shown in FIG. 16. It should be understood that the control plane network element 1600 shown in FIG. 16 is only an example, and the control plane network element of the embodiment of the present application may further include other modules or units, or include modules similar in function to the respective modules in FIG. 16, or It is not necessary to include all the modules in Figure 16.
  • the receiving module 1601 is configured to receive the first information from the database network element, where the first information includes the first feature index list set and the service identifier corresponding to each feature index list in the first feature index list set and the DNN corresponding to the service identifier.
  • the processing module 1602 is configured to query, according to the DNN of the first session, the second information, where the second information includes a second feature index list set corresponding to the DNN of the first session and a second feature index list.
  • the sending module 1603 is configured to send the second information to the user plane network element.
  • the first information may further include at least one of the following information corresponding to each feature index list in the first feature index list set: a network slice type, an SSC mode, and a PDU session type.
  • the processing module 1602 is specifically configured to: query the second information from the first information according to at least one of a DNN of the first session and a network slice type, an SSC mode, and a PDU session type of the first session.
  • control plane network element 1600 in FIG. 16 may be used to implement the corresponding steps performed by the control plane network element in the communication method shown in FIG. 2, FIG. 3 or FIG. 4, for the sake of brevity, here. No longer.
  • FIG. 17 A schematic structural diagram of a control plane network element of an embodiment of the present application is shown in FIG. It should be understood that the control plane network element 1700 shown in FIG. 17 is only an example, and the control plane network element of the embodiment of the present application may further include other modules or units, or include modules similar in function to the respective modules in FIG. 17, or It is not necessary to include all the modules in Figure 17.
  • the sending module 1701 is configured to send the DNN of the first session to the database network element.
  • the receiving module 1702 is configured to receive second information from the database network element, where the second information includes a service identifier corresponding to each feature index list in the second feature index list set and the second feature index list set, and the service identifier and the first session The DNN corresponds.
  • the sending module 1701 is further configured to send the second information to the user plane network element.
  • the sending module 1701 is further configured to: send, to the database network element, at least one of the following information of the first session: a network slice type, an SSC mode, and a PDU session type.
  • control plane network element 1700 in FIG. 17 may be used to implement the corresponding steps performed by the control plane network element in the communication method shown in FIG. 5, FIG. 6, or FIG. 7, for the sake of brevity, here. No longer.
  • FIG. 18 A schematic structural diagram of a user plane network element in one embodiment of the present application is shown in FIG. 18. It should be understood that the user plane network element 1800 shown in FIG. 18 is only an example, and the user plane network element in the embodiment of the present application may further include other modules or units, or include modules similar in function to the respective modules in FIG. 18, or It is not necessary to include all the modules in Figure 18.
  • the receiving module 1801 is configured to receive second information from the control plane network element, where the second information includes a second feature index list set and a service identifier corresponding to each feature index list in the second feature index list set.
  • the receiving module 1801 is further configured to receive service transmission data of the first session.
  • the processing module 1802 is configured to determine a service identifier corresponding to the feature index list in the second feature index list set that cannot obtain the feature value according to the service transmission data, to obtain the first service identifier set.
  • the sending module 1803 is configured to send third information to the database network element, where the third information includes the first service identifier set.
  • the receiving module 1801 is further configured to receive, from the database network element, a list of network data feature values corresponding to each service identifier in the first service identifier set.
  • the third information further includes at least one of the following information: a time when the user plane processes the service transmission data of the first session, a session identifier of the first session, an identifier of the terminal corresponding to the first session, and a corresponding The IP address of the terminal, the port of the terminal corresponding to the first session, the IP address of the service server corresponding to the first session, the port corresponding to the first session in the service server, and the service transmission protocol of the service transmission data corresponding to the first session.
  • each module included in the user plane network element 1800 in FIG. 18 may be used to implement the corresponding steps performed by the user plane network element in the communication method shown in FIG. 2 or FIG. 5, and details are not described herein for brevity. .
  • FIG. 19 A schematic structural diagram of a user plane network element in one embodiment of the present application is shown in FIG. It should be understood that the user plane network element 1900 shown in FIG. 19 is only an example, and the user plane network element in the embodiment of the present application may further include other modules or units, or include modules similar in function to the modules in FIG. 19, or It is not necessary to include all the modules in Figure 19.
  • the receiving module 1901 is configured to receive second information from the control plane network element, where the second information includes a second feature index list set and a service identifier corresponding to each feature index list in the second feature index list set.
  • the receiving module 1901 is further configured to receive service transmission data of the first session.
  • the processing module 1902 is configured to determine a feature index of the second feature index list set that cannot obtain the feature value according to the service transmission data, and obtain a network data feature index list.
  • the sending module 1903 is configured to send a network data feature index list to the database network element.
  • the receiving module 1901 is further configured to receive, from the database network element, a network data feature value list corresponding to the network data feature index list.
  • the third information may include at least one of the following: a time when the user plane processes the service transmission data of the first session, a session identifier of the first session, an identifier of the terminal corresponding to the first session, and a corresponding The IP address of the terminal, the port of the terminal corresponding to the first session, the IP address of the service server corresponding to the first session, the port corresponding to the first session in the service server, and the service transmission protocol of the service data corresponding to the first session.
  • modules included in the user plane network element 1900 in FIG. 19 may be used to implement the corresponding steps performed by the user plane network element in the communication method shown in FIG. 3 or FIG. 6. For brevity, details are not described herein again. .
  • FIG. 20 is a schematic structural diagram of a database network element according to an embodiment of the present application. It should be understood that the database network element 2000 shown in FIG. 20 is only an example, and the database network element in the embodiment of the present application may further include other modules or units, or include modules similar in function to the modules in FIG. 20, or not Includes all the modules in Figure 20.
  • the processor 2020 can be used to implement the operations or steps performed by the processing module 1401 in FIG. 14.
  • the transmitter 2040 can be used to implement the operations or steps performed by the sending module 1402 in FIG. 14, and the receiver 2030 can be used to implement the map.
  • Receiver 2030 and transmitter 2040 can be integrated together, referred to as a transceiver.
  • the database network element 2000 can also include a memory 2010 for storing program code executed by the processor 2020.
  • the memory 2020 can be integrated in the processor 2020.
  • FIG. 21 is a schematic structural diagram of a data analysis network element according to an embodiment of the present application. It should be understood that the data analysis network element 2100 shown in FIG. 21 is only an example, and the data analysis network element of the embodiment of the present application may further include other modules or units, or include modules similar in function to the respective modules in FIG. 21, or It is not necessary to include all the modules in Figure 21.
  • the processor 2120 can be used to implement the operations or steps performed by the processing module 1502 in FIG. 15, and the transmitter 2140 can be used to implement the operations or steps performed by the sending module 1503 in FIG. 15, and the receiver 2130 can be used to implement the map.
  • Receiver 2130 and transmitter 2140 can be integrated together, referred to as a transceiver.
  • the data analysis network element 2100 may also include a memory 2110 for storing program code executed by the processor 2120.
  • the memory 2120 can be integrated in the processor 2120.
  • FIG. 22 is a schematic structural diagram of a control plane network element according to an embodiment of the present application. It should be understood that the control plane network element 2200 shown in FIG. 22 is only an example, and the control plane network element of the embodiment of the present application may further include other modules or units, or include modules similar in function to the respective modules in FIG. 22, or It is not necessary to include all the modules in Figure 22.
  • the processor 2220 can be used to implement the operations or steps performed by the processing module 1602 in FIG. 16.
  • the transmitter 2240 can be used to implement the operations or steps performed by the sending module 1603 in FIG. 16, and the receiver 2230 can be used to implement the map. The operation or step performed by the receiving module 1601 in 16.
  • Receiver 2230 and transmitter 2240 can be integrated together, referred to as a transceiver.
  • control plane network element 2200 can also include a memory 2210 for storing program code executed by the processor 2220.
  • the processor 2220 can be integrated with a memory.
  • FIG. 23 is a schematic structural diagram of a control plane network element according to an embodiment of the present application. It should be understood that the control plane network element 2300 shown in FIG. 23 is only an example, and the control plane network element in the embodiment of the present application may further include other modules or units, or include modules similar in function to the respective modules in FIG. 23, or It is not necessary to include all the modules in Figure 23.
  • the transmitter 2340 can be used to implement the operations or steps performed by the sending module 1701 in FIG. 17, and the receiver 2330 can be used to implement the operations or steps performed by the receiving module 1702 in FIG.
  • Receiver 2330 and transmitter 2340 can be integrated together, referred to as a transceiver.
  • control plane network element 2300 may also include a memory 2310 and a processor 2320.
  • the memory 2310 is configured to store program code
  • the processor 2320 is configured to execute the program code stored in the memory 2310.
  • the memory 2310 can be integrated into the processor 2320.
  • FIG. 24 is a schematic structural diagram of a user plane network element according to an embodiment of the present application. It should be understood that the user plane network element 2400 shown in FIG. 24 is only an example, and the user plane network element of the embodiment of the present application may further include other modules or units, or include modules similar in function to the respective modules in FIG. 24, or It is not necessary to include all the modules in Figure 24.
  • the processor 2420 can be used to implement the operations or steps performed by the processing module 1802 in FIG. 18.
  • the transmitter 2440 can be used to implement the operations or steps performed by the sending module 1803 in FIG. 18.
  • the receiver 2430 can be used to implement the map. The operation or step performed by the receiving module 1801 in 18.
  • Receiver 2430 and transmitter 2440 can be integrated together, referred to as a transceiver.
  • the user plane network element 2400 can also include a memory 2410 for storing program code executed by the processor 2420.
  • the memory 2420 can be integrated with a memory.
  • FIG. 25 is a schematic structural diagram of a user plane network element according to an embodiment of the present application. It should be understood that the user plane network element 2500 shown in FIG. 25 is only an example, and the user plane network element in the embodiment of the present application may further include other modules or units, or include modules similar in function to the respective modules in FIG. 25, or It is not necessary to include all the modules in Figure 25.
  • the processor 2520 can be used to implement the operations or steps performed by the processing module 1902 in FIG. 19.
  • the transmitter 2540 can be used to implement the operations or steps performed by the sending module 1903 in FIG. 19, and the receiver 2530 can be used to implement the map.
  • Receiver 2530 and transmitter 2540 can be integrated together, referred to as a transceiver.
  • the user plane network element 2500 can also include a memory 2510 for storing program code executed by the processor 2520.
  • the memory 2520 can be integrated with a memory.
  • Figure 26 is a schematic block diagram of a chip system of one embodiment of the present application. It should be understood that the chip system 2600 illustrated in FIG. 26 is only an example, and the chip system of the embodiment of the present application may further include other modules or units, or include modules similar to those of the respective modules in FIG. 26, or not including the figure. All modules in 26.
  • the chip system 2600 includes a processor 2610, configured to support the foregoing database network element, the data analysis network element, the control plane network element, or the user plane network element to implement functions involved in the corresponding communication method, for example, generating or processing the foregoing communication method.
  • the information involved is not limited to, but not limited to, generating or processing the foregoing communication method.
  • the chip system 2600 may include one or more processors 2600, which are not limited in this application.
  • the chip system 2600 further includes a memory 2620 for storing necessary program instructions and data of a database network element, a data analysis network element, a control plane network element, or a user plane network element.
  • the chip system can be composed of chips, and can also include chips and other discrete devices.
  • the computer program product includes one or more computer instructions.
  • the computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable device.
  • the computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be from a website site, computer, server or data center Transfer to another website site, computer, server, or data center by wire (eg, coaxial cable, fiber optic, digital subscriber line (DSL), or wireless (eg, infrared, wireless, microwave, etc.).
  • the computer readable storage medium can be any available media that can be accessed by a computer or a data storage device such as a server, data center, or the like that includes one or more available media.
  • the usable medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (such as a solid state disk (SSD)).

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Power Engineering (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Computer Security & Cryptography (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Telephonic Communication Services (AREA)

Abstract

本申请提供通信方法、数据库网元、数据分析网元、控制面网元和用户面网元。该通信方法包括：数据库网元获取训练数据，训练数据包括业务传输数据和网络数据；数据库网元向数据分析网元发送训练数据；数据库网元从数据分析网元接收第一信息，第一信息包括第一特征索引列表集合、第一特征索引列表集合中的每个特征索引列表对应的业务标识和业务标识对应的DNN。本申请提供的通信方法、数据库网元、数据分析网元、控制面网元和用户面网元能够在支持大数据的通信网络中，识别业务类型。

Description

通信方法及其通信设备
本申请要求于2017年09月30日提交中国专利局、申请号为201710916010.3、申请名称为“通信方法及其通信设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及通信领域，并且更具体地，涉及通信方法、数据库网元、数据分析网元、控制面网元和用户面网元。
背景技术
在通信网络中，通过识别业务类型，可以实现入侵检测、差异化服务、流量监控、服务质量(Quality Of Service，QoS)保障、计费管理等等。随着多用户、多业务、多业务场景等的爆炸式发展，如何在支持大数据的通信网络，如第五代(the 5 thgeneration，5G)通信网络中实现业务类型识别成为了亟需解决的问题。
发明内容
本申请提供一种通信方法、数据库网元、数据分析网元、控制面网元和用户面网元，能够在支持大数据的通信网络中，应用大数据分析技术，识别业务类型。
第一方面，本申请提供了一种通信方法。该通信方法包括：数据库网元获取训练数据，训练数据包括业务传输数据和网络数据；数据库网元向数据分析网元发送训练数据；数据库网元从数据分析网元接收第一信息，第一信息包括第一特征索引列表集合、第一特征索引列表集合中的每个特征索引列表对应的业务标识和业务标识对应的数据网络名称(Data Network Name，DNN)。
第一方面中，由数据库网元获取训练数据并发送给数据分析网元，使得数据分析网元可以根据训练数据执行业务类型识别的后续步骤。
此外，由于数据库网元在部署实现上可以采用分布式部署方式，并靠近业务服务器，利用数据库网元的数据同步技术，有助于降低获取训练数据的时延。
同样的，分布式数据库网元在部署实现上也可以靠近控制面网元，因此，由数据库网元从数据分析网元接收第一信息，有助于降低数据库网元后续向控制面网元发送特征索引列表集合的时延。
在一种可能的设计中，数据库网元收集业务传输数据可通过如下方式实现：数据库网元可以从运营商平台、第三方业务服务器、垂直行业管控中心收集业务传输数据。
在一种可能的设计中，数据库网元收集的业务传输数据可以包括：IP五元组、数据包的大小和时间、业务类型、业务体验、扩展字段。其中，IP五元组可以包括终端的IP地址和端口、业务服务器的IP地址和端口、传输协议。
在一种可能的设计中，数据库网元收集网络数据可通过如下方式实现：数据库网元可以从终端、接入网设备、核心网网元等设备获取网络数据。
在一种可能的设计中，获取网络数据的核心网网元可以包括接入和移动性管理功能(Access and Mobility Management Function，AMF)网元、会话管理功能(Session Management Function，SMF)网元、用户面功能(User Plane Function，UPF)网元、统一数据管理(Unified Data Management，UDM)网元、应用功能(Application Function，AF)网元、包流描述功能(Packet and Flow Description Function，PFDF)网元中的至少一种。
在一种可能的设计中，网络数据可以包括终端的IP地址和端口号、终端类型、终端位置信息、时间、DNN、网络拥塞状况中的至少一种。
训练数据包括网络数据和业务传输数据，有助于数据分析网元根据训练数据得到更为准确的第一信息，进而有助于提高业务类型识别的准确率。
在一种可能的设计中，数据库网元收集业务数据与网络数据之后，数据库网元可以将业务数据与网络数据进行关联，以获取训练数据。
数据库网元获取训练数据的一种可能的实现方式包括：数据库网元收集业务数据和网络数据之后，数据库网元根据业务数据中的IP五元组、时间信息，确定包含相同的IP五元组、时间信息的网络数据，从而将业务数据和网络数据关联，关联之后的业务数据和网络数据可作为完整的训练数据保存在数据库网元中。
在一种可能的设计中，数据库网元接收第一信息之后，数据库网元存储第一信息可通过如下方式实现：数据库网元可以将业务标识作为数据索引信息，存储每个业务标识所对应的特征索引列表以及每个业务标识所对应的DNN。
在另外一种可能的设计中，数据库网元接收第一信息之后，数据库网元存储第一信息可通过如下方式实现：数据库网元可以将DNN作为数据索引信息，存储每个DNN所对应的业务标识、以及每个业务标识所对应的特征索引列表。
结合第一方面，在第一种可能的实现方式中，该通信方法还包括：数据库网元向控制面网元发送第一信息。这样，控制面网元可以根据第一信息执行业务类型识别中的后续步骤。
结合第一种可能的实现方式，在第二种可能的实现方式中，第一信息还包括第一特征索引列表集合中的每个特征索引列表对应的以下至少一种信息：网络切片类型、会话和业务连续性(Session and Service Continuity，SSC)模式、分组数据单元(Packet Data Unit，PDU)会话类型。
也就是说，第一信息可以包括每个特征索引列表对应的业务标识、每个特征索引列表对应的业务类型的DNN以及网络切片类型、SSC模式、PDU会话类型中的至少一种。
其中，网络切片类型、SSC模式、PDU会话类型中的至少一种信息有助于数据库网元将第一信息发送至控制面网元后，控制面网元可以根据第一信息以及用户面网元所支持的网络切片类型、SSC模式、PDU会话类型，为用户面网元确定更为准确的第二特征索引列表集合，从而有助于提高后续业务类型识别的准确率。
结合第一方面，在第三种可能的实现方式中，该通信方法还包括：数据库网元从控制面网元接收第一会话的DNN；数据库网元根据第一会话的DNN，从第一信息中查询得到 第二信息，第二信息包括与第一会话的DNN对应的第二特征索引列表集合以及第二特征索引列表集合中的每个特征索引列表对应的业务标识；数据库网元向控制面网元发送第二信息。
数据库网元根据控制面网元的请求，从第一信息中获取第二信息，并向控制面网元发送第二信息，以便于控制面网元可以执行业务类型识别中的后续步骤。
结合第三种可能的实现方式，在第四种可能的实现方式中，第一信息还包括第一特征索引列表集合中的每个特征索引列表对应的以下至少一种信息：网络切片类型、SSC模式、PDU会话类型。
结合第四种可能的实现方式，在第五种可能的实现方式中，该通信方法还包括：数据库网元从控制面网元接收第一会话的以下至少一种信息：网络切片类型、SSC模式、PDU会话类型。其中，数据库网元根据第一会话的DNN，从第一信息中查询得到第二信息，包括：数据库网元根据第一会话的DNN和第一会话的所述至少一种信息，从所述第一信息中查询得到所述第二信息。
数据库网元除了根据第一会话的DNN，还根据第一会话的上述至少一种信息，从第一信息中查询第二信息，有助于提高第二信息的准确性，进一步有助于提高业务识别的效率。
结合第一方面或上述任意一种可能的实现方式，在第六种可能的实现方式中，数据库网元向控制面网元发送第一信息之后，该通信方法还包括：数据库网元从用户面网元接收第三信息，第三信息包括第一业务标识集合；数据库网元根据第一业务标识集合中的每个业务标识从第一信息中查询得到根据第一业务标识集合中的每个业务标识对应的特征索引列表；数据库网元根据第一业务标识集合中的每个业务标识对应的特征索引列表从网络数据中查询得到第一业务标识集合中每个业务标识对应的网络数据特征值列表；数据库网元向用户面网元发送第一业务标识集合中每个业务标识对应的网络数据特征值列表。
由于数据库网元在部署实现上可以采用分布式部署方式，并靠近用户面网元，当数据库网元根据用户面网元的请求，为用户面网元提供用于识别业务类型的网络数据值时，有助于降低网络数据值传输的时延。
结合第一方面或上述任意一种可能的实现方式，在第七种可能的实现方式中，该通信方法还包括：数据库网元从用户面网元接收第三信息，第三信息包括网络数据特征索引列表；数据库网元获取网络数据特征索引列表中的特征索引对应的网络数据值，得到网络数据特征值列表；数据库网元向用户面网元发送网络数据特征值列表。
由于数据库网元在部署实现上可以采用分布式部署方式，并靠近用户面网元，因此，当数据库网元根据用户面网元的请求向用户面网元发送网络数据特征值时，可以降低网络数据值传输的时延。
可选地，网络数据特征索引列表中包括的是无重复的特征索引。
结合第六种或第七种可能的实现方式，在第八种可能的实现方式中，第三信息还包括以下至少一种信息：用户面网元接收第一会话的业务传输数据的时间、第一会话的会话标识、第一会话对应的终端的标识、第一会话对应的终端的IP地址、第一会话对应的终端的端口、第一会话对应的业务服务器的IP地址、业务服务器中与第一会话对应的端口、第一会话对应的业务数据的业务传输协议。
其中，数据库网元向用户面网元发送的网络数据值，是数据库网元还根据上述至少一种信息确定的，这样可以提高网络数据值的准确性，从而有助于提高业务类型识别的准确率。
第二方面，本申请提供了一种通信方法。该通信方法包括：数据分析网元接收数据库网元发送的训练数据，训练数据包括业务传输数据和网络数据；数据分析网元根据训练数据确定第一信息，第一信息包括第一特征索引列表集合以及第一特征索引列表集合中的每个特征索引列表对应的业务标识和业务标识对应的DNN；数据分析网元向数据库网元发送第一信息。
第二方面中，由数据分析网元根据训练数据获取用于识别业务类型的特征索引列表，以便于后续步骤中可以根据该特征索引列表识别业务类型。
此外，数据分析网元获取特征索引列表所依据的训练数据是从数据库网元接收的，基于数据库网元可以在部署实现上采用分布式部署，并靠近训练数据的来源，第二方面的通信方法中，有助于降低数据库网元获取训练数据的时延。
数据分析除了根据业务传输数据，还根据网络数据确定第一信息，有助于提高业务识别的准确性。
结合第二方面，在第一种可能的实现方式中，第一信息还包括第一特征索引列表集合中的每个特征索引列表对应的以下至少一种信息：网络切片类型、SSC模式、PDU会话类型。
第一信息还包括上述至少一种信息，使得数据库网元或者控制面网元可以根据这些信息确定用户面网元支持的特征索引列表，有助于提高为用户面网元确定的特征索引列的准确性，进而有助于提高业务类型识别的准确率。
第三方面，本申请提供了一种通信方法。该通信方法包括：控制面网元从数据库网元接收第一信息，第一信息包括第一特征索引列表集合以及第一特征索引列表集合中的每个特征索引列表对应的业务标识和业务标识对应的DNN；控制面网元根据第一会话的DNN，从第一信息中查询得到第二信息，第二信息包括第二特征索引列表集合和第二特征索引列表中每个特征索引列表对应的业务标识；控制面网元向用户面网元发送第二信息。
该通信方法中，由控制面网元从数据库网元接收第一信息，并确定用户面网元对应的特征索引列表，以便于用户面网元能够继续执行业务类型识别中的相关步骤。
此外，分布式数据库网元在部署实现上可以靠近控制面网元，因此，控制面网元从数据库网元接收第一信息，有助于降低第一信息传输的时延。
可选地，从数据网元接收第一信息的控制面网元可以为SMF网元或策略控制功能(Policy Control Function，PCF)网元。
结合第三方面，在第一种可能的实现方式中，第一信息还包括第一特征索引列表集合中的每个特征索引列表对应的以下至少一种信息：网络切片类型、SSC模式、PDU会话类型。其中，控制面网元根据第一会话的DNN，从第一信息中查询得到第二信息，包括：控制面网元根据第一会话的DNN和第一会话的网络切片类型、SSC模式、PDU会话类型中的至少一种信息，从第一信息中查询得到第二信息。
控制面网元除了根据第一会话的DNN，还根据第一会话的上述至少一种信息确定第二信息，有助于提高第二信息的准确率，进而有助于提高业务类型识别的准确率。
第四方面，本申请提供了一种通信方法。该通信方法包括：控制面网元向数据库网元发送第一会话的DNN；控制面网元从数据库网元接收第二信息，第二信息包括第二特征索引列表集合和第二特征索引列表集合中每个特征索引列表对应的业务标识，第二特征索引列表集合中的每个特征索引列表对应第一会话的DNN；控制面网元向用户面网元发送第二信息。
第四方面中，控制面网元向数据库网元请求得到第二信息，并向用户面网元发送第二信息，使得用户面网元可以根据第二信息执行业务类型识别中的后续步骤。
此外，分布式数据库网元在部署实现上可以靠近控制面网元，因此，控制面网元从数据库网元接收第一信息，有助于降低第一信息传输的时延。
可选地，从数据网元接收第一信息的控制面网元可以为SMF网元或PCF网元。
结合第四方面，在第一种可能的实现方式中，控制面网元从数据库网元接收第二信息之前，该通信方法还包括：控制面网元向数据库网元发送第一会话的以下至少一种信息：网络切片类型、SSC模式、PDU会话类型。
控制面网元除了向数据库网元发送第一会话的DNN以外，还发送第一会话的上述至少一种信息，有助于数据库网元确定出更准确的第二信息，从而有助于提高业务类型的识别准确率。
第五方面，本申请提供了一种通信方法。该通信方法包括：用户面网元从控制面网元接收第二信息，第二信息包括第二特征索引列表集合以及第二特征索引列表集合中的每个特征索引列表对应的业务标识；用户面网元接收第一会话的业务传输数据；用户面网元确定第二特征索引列表集合中不能根据业务传输数据得到特征值的特征索引列表所对应的业务标识，得到第一业务标识集合；用户面网元向数据库网元发送第三信息，第三信息包括第一业务标识集合；用户面网元从数据库网元接收第一业务标识集合中每个业务标识对应的网络数据特征值列表。
第五方面中，由用户面网元向数据库数据请求特征索引列表中的特征索引对应的网络数据值，使得用户面网元能够执行后续步骤，以实现业务类型的识别。
此外，由于数据库网元可以部署得离用户面网元较近，因此，用户面网元从数据库网元请求网络数据值，有助于降低时延。
结合第五方面，在第一种可能的实现方式中，第三信息包括以下至少一种信息：用户面处理接收第一会话的业务传输数据的时间、第一会话的会话标识、第一会话对应的终端的标识、第一会话对应的终端的IP地址、第一会话对应的终端的端口、第一会话对应的业务服务器的IP地址、业务服务器中与第一会话对应的的端口、第一会话对应的业务数据的业务传输协议。
用户面网元除了向数据库网元发送第一业务标识集合，还发送上述至少一种信息，有助于数据库网元还可以根据上述至少一种信息确定网络数据值，从而有助于提高确定的网络数据值的准确性，进而有助于提高业务类型识别的准确性。
第六方面，本申请提供一种通信方法。该通信方法包括：用户面网元从控制面网元接收第二信息，第二信息包括第二特征索引列表集合以及第二特征索引列表集合中的每个特征索引列表对应的业务标识；用户面网元接收第一会话的业务传输数据；用户面网元确定所述第二特征索引列表集合中不能根据业务传输数据得到特征值的特征索引，得到网络数 据特征索引列表；用户面网元向数据库网元发送网络数据特征索引列表；用户面网元从数据库网元接收网络数据特征索引列表对应的网络数据特征值列表。
第六方面中，用户面网元向数据库网元发送特征索引列表，并接收数据库网元获取的该特征索引列表对应的网络数据特征值列表，使得用户面网元可以继续执行业务类型识别的后续步骤。
可选地，用户面网元确定所述第二特征索引列表集合中不能根据业务传输数据得到特征值的特征索引后，可以去除重复的特征索引，得到网络数据特征索引列表。
结合第六方面，在第一种可能的实现方式中，第三信息包括以下至少一种信息：用户面处理接收第一会话的业务传输数据的时间、第一会话的会话标识、第一会话对应的终端的标识、第一会话对应的终端的IP地址、第一会话对应的终端的端口、第一会话对应的业务服务器的IP地址、业务服务器中与第一会话对应的端口、第一会话对应的业务数据的业务传输协议。
用户面网元除了向数据库网元发送第一业务标识集合，还发送上述至少一种信息，有助于数据库网元还可以根据上述至少一种信息确定网络数据值，从而有助于提高确定的网络数据值的准确性，进而有助于提高业务类型识别的准确性。
综上所述，本申请提供的上述通信方法，由数据库网元获取训练数据，数据分析网元根据该训练数据获取业务类型对应的特征索引列表，数据库网元记录这些特征索引列表并向控制面网元发送特征索引列表，控制面网元再向用户面网元发送用户面网元支持的特征索引列表，用户面处理根据特征索引列表获取业务传输数据的特征值、并将特征值发送给数据分析网元，由数据分析网元根据特征值确定业务类型并告知用户面网元。
上述通信方法实现了通信系统中应用基于大数据分析的技术进行业务类型识别的通信方法。
此外，由于数据库网元可以部署得离业务服务器、控制面网元和用户面网元较近，因此由数据库网元获取训练数据和向控制面网元下发特征索引，有助于降低时延。
当训练数据包括网络数据时，用户面网元还可以向数据库网元请求网络数据值，也可以降低时延。
第七方面，本申请提供了一种数据库网元。该数据库网元包括用于执行第一方面或第一方面中任意一种可能的实现方式中的通信方法的模块。该数据库网元包括的模块可以通过软件和/或硬件方式实现。
第八方面，本申请提供了一种数据分析网元。该数据分析网元包括用于执行第二方面或第二方面中任意一种可能的实现方式中的通信方法的模块。该数据分析网元包括的模块可以通过软件和/或硬件方式实现。
第九方面，本申请提供了一种控制面网元。该控制面网元包括用于执行第三方面或第三方面中任意一种可能的实现方式中的通信方法的模块。该控制面网元包括的模块可以通过软件和/或硬件方式实现。
第十方面，本申请提供了一种控制面网元。该控制面网元包括用于执行第四方面或第四方面中任意一种可能的实现方式中的通信方法的模块。该控制面网元包括的模块可以通过软件和/或硬件方式实现。
第十一方面，本申请提供了一种用户面网元。该用户面网元包括用于执行第五方面或 第五方面中任意一种可能的实现方式中的通信方法的模块。该用户面网元包括的模块可以通过软件和/或硬件方式实现。
第十二方面，本申请提供了一种用户面网元。该用户面网元包括用于执行第六方面或第六方面中任意一种可能的实现方式中的通信方法的模块。该用户面网元包括的模块可以通过软件和/或硬件方式实现。
第十三方面，本申请提供了一种数据库网元。该数据库网元包括处理器、发送器和接收器。处理器用于执行程序。当处理器执行代码时，处理器、发送器和接收器实现第一方面或第一方面中任意一种可能的实现方式中的通信方法。
可选地，该数据库网元还可以包括存储器，该存储器用于存储处理器执行的代码。
第十四方面，本申请提供了一种数据分析网元。该数据分析网元包括处理器、发送器和接收器。处理器用于执行程序。当处理器执行代码时，处理器、发送器和接收器实现第二方面或第二方面中任意一种可能的实现方式中的通信方法。
可选地，该数据分析网元还可以包括存储器，该存储器用于存储处理器执行的代码。
第十五方面，本申请提供了一种控制面网元。该控制面网元包括处理器、发送器和接收器。处理器用于执行程序。当处理器执行代码时，处理器、发送器和接收器实现第三方面或第三方面中任意一种可能的实现方式中的通信方法。
可选地，该控制面网元还可以包括存储器，该存储器用于存储处理器执行的代码。
第十六方面，本申请提供了一种控制面网元。该控制面网元包括处理器、发送器和接收器。处理器用于执行程序。当处理器执行代码时，处理器、发送器和接收器实现第四方面或第四方面中任意一种可能的实现方式中的通信方法。
可选地，该控制面网元还可以包括存储器，该存储器用于存储处理器执行的代码。
第十七方面，本申请提供了一种用户面网元。该用户面网元包括处理器、发送器和接收器。处理器用于执行程序。当处理器执行代码时，处理器、发送器和接收器实现第五方面或第五方面中任意一种可能的实现方式中的通信方法。
可选地，该用户面网元还可以包括存储器，该存储器用于存储处理器执行的代码。
第十八方面，本申请提供了一种用户面网元。该用户面网元包括处理器、发送器和接收器。处理器用于执行程序。当处理器执行代码时，处理器、发送器和接收器实现第六方面或第六方面中任意一种可能的实现方式中的通信方法。
可选地，该用户面网元还可以包括存储器，该存储器用于存储处理器执行的代码。
第十九方面，本申请提供了一种计算机可读存储介质。该计算机可读存储介质中存储用于数据库网元执行的程序代码。该程序代码包括用于执行第一方面或第一方面中任意一种可能的实现方式中的通信方法的指令。
第二十方面，本申请提供了一种计算机可读存储介质。该计算机可读存储介质中存储用于数据分析网元执行的程序代码。该程序代码包括用于执行第二方面或第二方面中任意一种可能的实现方式中的通信方法的指令。
第二十一方面，本申请提供了一种计算机可读存储介质。该计算机可读存储介质中存储用于控制面网元执行的程序代码。该程序代码包括用于执行第三方面或第三方面中任意一种可能的实现方式中的通信方法的指令。
第二十二方面，本申请提供了一种计算机可读存储介质。该计算机可读存储介质中存 储用于控制面网元执行的程序代码。该程序代码包括用于执行第四方面或第四方面中任意一种可能的实现方式中的通信方法的指令。
第二十三方面，本申请提供了一种计算机可读存储介质。该计算机可读存储介质中存储用于用户面网元执行的程序代码。该程序代码包括用于执行第五方面或第五方面中任意一种可能的实现方式中的通信方法的指令。
第二十四方面，本申请提供了一种计算机可读存储介质。该计算机可读存储介质中存储用于用户面网元执行的程序代码。该程序代码包括用于执行第六方面或第六方面中任意一种可能的实现方式中的通信方法的指令。
第二十五方面，本申请提供了一种包含指令的计算机程序产品。当该计算机程序产品在数据库网元上运行时，使得数据库网元执行第一方面或第一方面中任意一种可能的实现方式中的通信方法。
第二十六方面，本申请提供了一种包含指令的计算机程序产品。当该计算机程序产品在数据分析网元上运行时，使得数据分析网元执行第二方面或第二方面中任意一种可能的实现方式中的通信方法。
第二十七方面，本申请提供了一种包含指令的计算机程序产品。当该计算机程序产品在控制面网元上运行时，使得控制面网元执行第三方面或第三方面中任意一种可能的实现方式中的通信方法。
第二十八方面，本申请提供了一种包含指令的计算机程序产品。当该计算机程序产品在控制面网元上运行时，使得控制面网元执行第四方面或第四方面中任意一种可能的实现方式中的通信方法。
第二十九方面，本申请提供了一种包含指令的计算机程序产品。当该计算机程序产品在用户面网元上运行时，使得用户面网元执行第五方面或第五方面中任意一种可能的实现方式中的通信方法。
第三十方面，本申请提供了一种包含指令的计算机程序产品。当该计算机程序产品在用户面网元上运行时，使得用户面网元执行第四方面或第四方面中任意一种可能的实现方式中的通信方法。
第三十一方面，本申请供了一种芯片系统，该芯片系统包括处理器，用于支持数据库网元、数据分析网元、控制面网元或用户面网元实现上述对应的方面中所涉及的功能，例如，生成或处理上述通信方法中所涉及的信息。
在一种可能的设计中，所述芯片系统还包括存储器，所述存储器，用于保存数据库网元、数据分析网元、控制面网元或用户面网元必要的程序指令和数据。该芯片系统，可以由芯片构成，也可以包含芯片和其他分立器件。
附图说明
图1是可以应用本申请实施例的通信方法的应用场景的系统架构图；
图2是本申请一个实施例的通信方法的示意性交互流程图；
图3是本申请另一个实施例的通信方法的示意性交互流程图；
图4是本申请另一个实施例的通信方法的示意性交互流程图；
图5是本申请另一个实施例的通信方法的示意性交互流程图；
图6是本申请另一个实施例的通信方法的示意性交互流程图；
图7是本申请另一个实施例的通信方法的示意性交互流程图；
图8是本申请一个实施例的通信方法的示意性流程图；
图9是本申请另一个实施例的通信方法的示意性流程图；
图10是本申请另一个实施例的通信方法的示意性流程图；
图11是本申请另一个实施例的通信方法的示意性流程图；
图12是本申请另一个实施例的通信方法的示意性流程图；
图13是本申请另一个实施例的通信方法的示意性流程图；
图14是本申请一个实施例的数据库网元的示意性结构图；
图15是本申请一个实施例的数据分析网元的示意性结构图；
图16是本申请一个实施例的控制面网元的示意性结构图；
图17是本申请另一个实施例的控制面网元的示意性结构图；
图18是本申请一个实施例的用户面网元的示意性结构图；
图19是本申请另一个实施例的用户面网元的示意性结构图；
图20是本申请另一个实施例的数据库网元的示意性结构图；
图21是本申请另一个实施例的数据分析网元的示意性结构图；
图22是本申请另一个实施例的控制面网元的示意性结构图；
图23是本申请另一个实施例的控制面网元的示意性结构图；
图24是本申请另一个实施例的用户面网元的示意性结构图；
图25是本申请另一个实施例的用户面网元的示意性结构图；
图26是本申请一个实施例的芯片系统的示意性结构图。
具体实施方式
下面将结合附图，对本申请中的技术方案进行描述。
如图1所示，可以应用本申请实施例的通信方法的通信系统中可以包括终端110、接入网(Access Network，AN)设备120、UPF网元130、AMF网元140、SMF网元150、PCF网元160、网络数据分析(Network Data Analytics，NWDA)网元170和结构化数据存储功能(Structured Data Storage Function，SDSF)网元180。
应理解，本申请实施例并不限于图1所示的系统架构中，此外，图1中的装置可以是硬件，也可以是从功能上划分的软件或者以上二者的结合。
终端110可以是用户设备(User Equipment，UE)。终端110可以经AN设备120与一个或多个核心网(Core Network，CN)进行通信。终端可称为接入终端、终端设备、用户单元、用户站、移动站、移动台、远方站、远程终端、移动设备、用户终端、无线网络设备、用户代理或用户装置。终端可以是蜂窝电话、无绳电话、会话启动协议(Session Initiation Protocol，SIP)电话、无线本地环路(Wireless Local Loop，WLL)站、个人数字处理(Personal Digital Assistant，PDA)、具有无线通信功能的手持设备、计算设备或连接到无线调制解调器的其它设备、车载设备、可穿戴设备或物联网、车辆网中的终端设备以及未来网络中的任意形态的终端设备等。
AN设备120具体可以是无线接入网(Radio Access Network，RAN)设备。
AN设备120的一种示例是基站(Base Station，BS)。基站，也可称为基站设备，是一种将终端接入到无线网络的设备，包括但不限于：传输接收点(Transmission Reception Point，TRP)、5G节点B(gNB)、演进型节点B(evolved Node B，eNB)、无线网络控制器(Radio Network Controller，RNC)、节点B(Node B，NB)、基站控制器(Base Station Controller，BSC)、基站收发台(Base Transceiver Station,BTS)、家庭基站(例如，Home evolved nodeB，或Home Node B，HNB)、基带单元(Base Band Unit，BBU)，或Wifi接入点(Access Point，AP)，或小基站设备(pico)等。
应理解，本申请实施例对基站的具体类型不作限定。采用不同无线接入技术的系统中，具备基站功能的设备的名称可能会有所不同。为方便描述，本申请所有实施例中，上述为终端提供无线通信功能的装置统称为基站。
UPF网元130具有终端的报文转发、封装和统计等功能。
AMF网元140网元负责终端的接入和移动性管理，例如，接入和移动性管理包括移动性状态管理、分配终端的临时身份标识、认证和授权终端等。
SMF网元150负责UPF网元的选择、重选，IP地址的分配等，还可以负责会话的建立、修改和释放以及QoS控制等。
PCF网元160可包括策略控制决策和基于流计费控制、终端签约数据管理或QoS控制等等功能。
NWDA网元170可以分析网络级数据，并将数据分析结果通过SDSF网元180告知给其他网元。其中，网络级数据包括由核心网产生、存储和管理的数据。
SDSF网元180可以存储结构化数据。例如，结构化数据包括应用策略数据，网络拓扑数据、网络中的大数据分析数据中的至少一项。SDSF网元180可以用于实现网络内部或外部的能力开放。
图2是本申请一个实施例的通信方法的示意性交互流程图。应理解，图2示出了该通信方法的步骤或操作，但这些步骤或操作仅是示例，本申请实施例还可以执行其他操作或者图2中的各个操作的变形。此外，图2中的各个步骤可以按照与图2呈现的不同的顺序来执行，并且有可能并非要执行图2中的全部操作。
S201，数据库网元收集网络数据。可选地，数据库网元可以从终端、接入网、控制面网元和用户面网元中的一个或多个收集历史网络数据，即在此之前已经产生的网络数据。
数据库网元包括但不限于SDSF网元，例如，图1中的SDSF 180。
控制面网元包括但不限于控制面功能(Control Plane Function，CPF)网元。CPF网元可以包括图1中所示的AMF网元140、SMF网元150或PCF网元160。
用户面网元可以包括用户面功能(User Plane Function，UPF)网元。例如，UPF网元可以是图1中所示的UPF网元130。
网络数据中可以包括与网络数据关联的业务传输数据所属的业务类型的DNN。
可选地，步骤S201中可以包括：数据库网元向控制面网元订阅网络数据，然后接收控制面网元实时上报或者周期性上报的网络数据。
网络数据包括但不限于终端的IP地址、终端类型(Terminal Type)、小区标识(Cell ID)、网络拥塞状况，网络数据收集的起始时间中的至少一项。
S202，数据库网元收集业务传输数据。业务传输数据就是具体的业务数据，也可以称 为应用数据。
例如，数据库网元可以收集不同业务类型的业务传输数据。例如，语音业务、微信业务和车载导航地图业务为不同的业务类型。应理解，语音业务、微信业务和车载导航地图业务只是示例，不应构成本申请实施例的业务类型的限制。
业务传输数据可以包括以下至少一种信息：IP五元组，数据包，数据包的大小，业务传输数据的起始时间，业务类型，业务体验，扩展字段。
数据库网元收集的业务传输数据可以包括上行业务传输数据和/或下行业务传输数据。
例如，数据库网元可以从应用平台(Application Platform，AP)收集业务传输数据。应用平台可以包括OTT(Over The Top)服务中心、垂直管控中心、运营商平台或第三方业务服务器等。
数据库网元收集的业务传输数据是历史业务传输数据，即在此之前在网络中传输过的业务传输数据。
应理解，本申请实施例并不限制S201与S202的执行顺序。例如，S202可以位于S201之前，或者S201可以位于S202之前，或者S201与S202可以交叉或同时执行。
S203，数据库网元将S201收集到的业务传输数据与S202收集到的网络数据进行关联，得到训练数据。
例如，数据库网元通过IP五元组或时间等信息，将业务传输数据和网络数据进行关联，得到训练数据。
例如，数据库网元收集的业务传输数据中包括终端的IP和时间等信息，该时间可以是业务传输数据的起始时间。数据库网元收集的网络数据中业务包括终端的IP和时间等信息，该时间可以是网络数据生成的起始时间。这样，数据库网元可以将包括了相同终端IP或时间等信息的业务传输数据和网络数据关联在一起，得到训练数据。
S204，数据库网元向数据分析网元发送训练数据。该训练数据包括关联的业务传输数据和网络数据。相应地，数据分析网元接收该训练数据。
其中，数据分析网元包括但不限于NWDA网元，例如，图1中的NWDA网元170。
可选地，可以是数据库网元主动向数据分析网元发送训练数据；也可以是数据分析网元向数据库网元发送用于请求训练数据的请求消息，数据库网元收到数据分析网元发送的请求消息后，向数据分析网元发送训练数据。
可选地，若训练数据较多，数据库网元可以分批向数据分析网元发送训练数据。例如，数据库网元向数据分析网元发送训练数据的过程中，若网络拥塞，则数据库网元可以在网络空闲情况下继续向数据分析网元发送训练数据。
S205，数据分析网元根据训练数据生成第一信息，第一信息包括第一特征索引列表集合、第一特征索引列表集合中的每个特征索引列表对应的业务标识和业务标识对应的DNN。
例如，部署有特征工程(Feature Engineering)的数据分析网元根据训练数据生成大数据模型，其中，特征工程是将原始数据转化为特征，以通过特征更好地表示预测模型处理的实际问题，从而提升对于未知数据的准确性。特征工程是用目标问题所在的特定领域知识或者自动化的方法来生成、提取、删减或者组合变化得到特征。
数据分析网元将训练数据转换为特征的过程包括如下步骤：整合数据，即将数据整合为一个数据集；预处理数据，即对数据进行清洗、格式化、采样；转换数据，特征工程将数据转换成关键信息；数据建模，即构建模型、评估模型、调整模型，该模型也可以称为大数据模型，用于识别业务类型。
通过特征工程，数据分析网元可以将训练数据中的关键信息分离出来。该关键信息包括不同业务类型对应的业务特征列表。业务特征列表可以简称为特征列表。
一个业务特征列表对应一个唯一的业务类型，这样，根据一个业务特征列表可以识别出唯一的业务类型。
由于每个业务类型可以有唯一的业务标识，因此，数据分析网元根据训练数据分析得到业务类型对应的特征列表后，可以根据业务类型和业务标识的对应关系以及业务类型和特征列表的对应关系，得到特征列表与业务标识的对应关系。其中，每个特征列表对应一个业务标识。
例如，训练数据中包括视频业务和支付业务的业务传输数据以及网络数据。数据分析网元对训练数据进行大数据分析，得到视频业务和支付业务的示例性特征列表。
视频业务的示例性特征列表中可以包括如下特征：视频业务流(flow)中首个包的大小、视频业务流中所有包大小的均值、视频业务流中所有包大小的熵、视频业务的使用时间、终端位置和小区标识。其中，视频业务流中首个包的大小、视频业务流中所有包大小的均值、视频业务流中所有包大小的熵、视频业务的使用时间可以是数据分析网元根据视频业务的业务传输数据得到的；终端位置和小区标识可以是数据分析网元根据视频业务的业务传输数据关联的网络数据得到的。
支付业务的示例性特征列表中可以包括如下特征：支付业务流中所有包上下行的时间间隔的均值、支付业务流中所有包上下行的时间间隔的熵、支付业务的使用时间和终端类型。其中，支付业务流中所有包上下行的时间间隔的均值、支付业务流中所有包上下行的时间间隔的熵和支付业务的使用时间可以是数据分析网元根据支付业务的业务传输数据得到的；终端类型可以是数据分析网元根据支付业务的业务传输数据关联的网络数据得到的。
数据分析网元得到多个特征列表后，可以将这些特征列表进行混合，或者将新得到的特征列表整合到现有特征列表集合中，并求并集，得到没有重复特征的特征总列表。
例如，上面所述的视频业务和支付业务的特征列表中的特征进行混合后可以得到的特征总列表如表1所示。
表1特征总列表
特征
使用时间
流中首个包的大小
流中所有包大小的均值
流中所有包大小的熵
流中所有包上下行的时间间隔的均值
流中所有包上下行的时间间隔的熵
终端类型
终端位置
小区标识
基于特征总列表，数据分析网元可以为各个特征分配索引。表1所示的特征总列表中的特征与索引的对应关系如表2所示。
表2特征与索引对应关系
特征 索引
使用时间 1
流中首个包的大小 2
流中所有包大小的均值 3
流中所有包大小的熵 4
流中所有包上下行的时间间隔的均值 5
流中所有包上下行的时间间隔的熵 6
终端类型 7
终端位置 8
小区(Cell)标识 9
数据分析网元得到多个业务类型的特征索引总列表后，基于该特征索引总列表，可以根据不同业务类型对应的特征列表，得到不同业务类型对应的特征索引列表。
例如，基于表2所示的特征索引总列表，得到的支付业务的特征索引列表和视频业务的特征索引列表如表3所示。
表3支付业务和视频业的特征索引列表
业务类型 特征索引列表
支付业务 {1，5，6，7}
视频业务 {1，2，3，4，8，9}
可选的，可以将特征索引列表扩展到二进制空间上。假设特征总列表中的特征个数为n，那么每个特征索引列表可以表示为一个n维的二进制字符串。
例如，表2所示的特征总列表包括9个特征，则可以通过长度为9的二进制字符串来表示特征索引列表。例如，支付业务的二进制特征索引列表可以表示为100011100，视频业务的二进制特征索引列表可以表示为111100011。
数据分析网元得到的多个特征索引列表可以组成一个特征索引列表集合，可以将该特征索引列表集合称为第一特征索引列表集合。
同一个业务类型可以对应多个特征列表。相应地，同一个业务类型可以对应多个特征索引列表。
例如，不同地理位置下，网络的拥塞情况可能不一样，这使得用户使用支付业务的时间不同，数据分析网元根据训练数据生成的支付业务对应的特征列表可以是多个。
例如，在早上7:00到下午17:00的工作时间段，城市A中使用支付业务的用户群体的数量大约为10万用户，数据分析网元对该城市的训练数据进行大数据分析之后，支付业务对应的特征索引列表为表4所示。
表4支付业务的特征列表(城市A，早上7:00到下午17:00)
Figure PCTCN2018107337-appb-000001
在下午17:00到晚上21:00的下班时间段，城市A中使用支付业务的用户群体的数量大大增加到50万用户，数据分析网元对该城市的训练数据进行大数据分析之后，支付业务对应的特征索引列表为表5所示。
表5支付业务的特征索引列表(城市A，下午17:00到晚上21:00)
Figure PCTCN2018107337-appb-000002
在晚上21:00到早上7:00的时间段，城市A中使用支付业务的用户群体大大缩减到2万用户，数据分析网元对该城市的训练数据进行大数据分析之后，支付业务对应的特征索引列表为表6所示。
表6支付业务的特征索引列表(城市A，晚上21:00到早上7:00)
Figure PCTCN2018107337-appb-000003
从表4至表6中看出，在网络繁忙和网络空闲时，即便是相同的地理位置下，该支付业务的特征列表也不相同。
根据表2所示的特征与索引的对应关系，图4至图6中的支付业务的特征列表对应的特征索引列表如表7所示。
表7城市A中支付业务的特征索引列表
Figure PCTCN2018107337-appb-000004
Figure PCTCN2018107337-appb-000005
本申请实施例中，每个业务类型可以有唯一的业务标识。体现到特征索引列表上为：一个特征索引列表对应一个的业务标识。若多个特征列表对应一个业务类型，体现到特征索引列表上为：多个特征索引列表对应一个业务标识。
如表7中的支付业务的3个特征索引列表与业务标识的对应关系如表8所示。即支付业务的业务标识对应特征索引列表-1、特征索引列表-2和特征索引列表-3。或者可以说，特征索引列表-1、特征索引列表-2和特征索引列表-3均对应支付业务的业务标识。
表8支付业务的业务标识与多个特征索引列表的对应关系
Figure PCTCN2018107337-appb-000006
应理解，表8只是多个特征索引列表对应同一个业务标识的一种示例，不应对特征索引列表与业务标识的对应关系的表现形式或存储形式构成限制。例如，支付业务的业务标识与多个特征索引列表的对应关系可以如表9所示。
表9支付业务的业务标识与多个特征索引列表的对应关系
业务标识 特征索引列表
支付业务的业务标识 特征索引列表-1
支付业务的业务标识 特征索引列表-2
支付业务的业务标识 特征索引列表-3
由于网络数据中可以包括业务类型对应的DNN，因此，数据分析网元得到业务类型的特征索引列表以及该特征索引列表与业务标识的对应关系后，数据分析网元还可以得到该业务类型对应的DNN与该业务类型的业务标识的对应关系。
DNN、业务标识和特征索引列表三者之间的对应关系的示例如表10所示，
表10DNN、业务标识和特征索引列表之间的对应关系
Figure PCTCN2018107337-appb-000007
应理解，表10中的DNN、业务标识和特征索引列表之间的对应关系的表现形式只是一种示例，不应对本申请实施例构成限制。DNN、业务标识和特征索引列表之间的对应关系还可以有其他表现形式，例如，如表11所示。
表11DNN、业务标识和特征索引列表之间的对应关系
DNN 业务标识 特征索引列表
DNN-1 业务标识1 {1，5，6，7}
DNN-1 业务标识2 {1，2，3，4，8，9}
DNN-2 业务标识3 {1，4，7，…，19}
DNN-2 业务标识3 {1，2，3，…，1000}
DNN-3 业务标识4 {1，2，3，…，200}
表10或表11中包括5个特征索引列表，这5个特征索引列表分别有唯一对应的业务标识，这5个特征索引列表对应的4个业务类型分属于3个不同的DNN。
应理解，表10和表11中所示的特征索引列表的数量5、特征索引的最大数量1000、DNN的数量3以及每个DNN网络所对应的业务标识数量仅是示例，不应构成本申请实施例的限制。
S206，数据分析网元向数据库网元发送第一信息。相应地，数据库网元接收第一信息。
可选地，第一信息中还可以包括特征与索引的对应关系。例如，第一信息中可以包括如表2所示的对应关系。这样，数据库网元可以获知第一特征索引集合中每个特征索引列表中的特征索引对应的是哪个特征。
可选的，数据库网元接收第一信息后，可以存储第一信息。
在一种可能的设计中，数据库网元接收第一信息之后，数据库网元存储第一信息可通过如下方式实现：数据库网元可以将业务标识作为数据索引信息，存储每个业务标识所对应的特征索引列表以及每个业务标识所对应的DNN。
在另外一种可能的设计中，数据库网元接收第一信息之后，数据库网元存储第一信息可通过如下方式实现：数据库网元可以将DNN作为数据索引信息，存储每个DNN所对应的业务标识、以及每个业务标识所对应的特征索引列表。
S207，数据库网元向控制面网元发送第一信息。相应地，控制面网元接收第一信息。
数据分析网元向数据库网元发送的第一信息中包括特征与索引的对应关系时，数据库网元向控制面网元发送的第一信息中也可以包括特征与索引的对应关系。
控制面网元可以是AMF网元、SMF网元或PCF网元，或其他控制面功能网元。例如，控制网元可以是图1中所示的AMF网元140、SMF网元150或PCF网元160。
可选的，控制面网元接收第一信息后，可以保存第一信息。
当控制面网元为SMF网元或PCF网元时，数据库网元可以直接将第一信息下发至SMF网元或PCF网元，或者，也可以通过网络开放功能(Network Exposure Function，NEF)网元将第一信息下发至SMF网元或PCF网元。
S208，终端发起已有会话的修改流程或者发起新的会话建立流程。为了后续描述方便，将该会话称为第一会话。
可选地，第一会话可以是业务数据流(Service Data Flow)。第一会话可以由一个IP五元组进行标识。
UE发起第一会话时会携带与该第一会话关联的DNN。为了后续描述方便，可以将与第一会话关联的DNN称为第一DNN。
S209，控制面网元根据第一DNN，从第一信息中查询得到第二信息，第二信息包括与第一DNN对应的第二特征索引列表集合和第二特征索引列表集合中每个特征索引列表对应的业务标识。
具体而言，控制面网元可以根据第一DNN，对本地保存的第一信息进行筛选，匹配出与第一DNN对应的特征索引列表和业务标识。从第一信息中筛选得到的与第一DNN 对应的特征索引列表组成第二特征索引列表集合。
控制面网元根据第二特征索引列表集合与筛选得到的业务标识生成第二信息，第二信息包括第二特征索引列表集合与筛选得到的业务标识。
例如，控制面网元从数据库网元接收的第一信息包括表11所示的内容时，如果第一DNN为DNN-1，则控制面网元可以根据表11中生成第二信息，第二信息可以包括表12所示的内容。
表12第二信息包括的业务标识和特征索引列表
业务标识 特征索引列表
业务标识1 {1，5，6，7}
业务标识2 {1，2，3，4，8，9}
可选地，控制面网元从数据库网元接收的第一信息中包括特征与索引的对应关系时，控制面网元向用户面网元发送的第二信息中也可以包括该对应关系。
这样，用户面网元可以本地保存特征与索引的对应关系，后续控制面网元再次向用户面网元发送业务类型对应的第二信息的时候，第二信息可以只包括业务类型对应的特征索引列表，用户面网元可以根据保存的特征与索引的对应关系来获取特征索引列表对应的特征列表。
S210，控制面网元向用户面网元发送第二信息。相应地，用户面网元接收第二信息。
用户面网元包括但不限于UPF网元。例如，用户面网元可以是图1中所示的UPF网元130。
进一步地，向用户面网元发送第二信息的控制面网元可以是SMF网元。
进一步地，SMF网元从数据库网元接收第一信息之后，终端发起第一会话时，SMF网元根据第一信息确定第二信息，并将第二信息发送至用户面网元。
或者，PCF网元从数据库网元接收第一信息之后，终端发起第一会话时，SMF网元从PCF网元获取PCF网元根据第一信息确定的第二信息，SMF网元并将第二信息发送至UPF网元。
上述控制面网元向用户面网元发送第二信息的实现方式只是示例，不应对本申请实施例构成限制。
S211，用户面网元接收终端的业务传输数据。
应理解，该业务传输数据可以是上行业务传输数据，也可以是下行的业务传输数据。
应理解，S211也可以位于S209或S210之前。
S212，用户面网元根据第二信息获取业务传输数据中的特征值。
例如，用户面网元从业务传输数据中获取第二特征索引列表集合中每个特征索引列表对应的特征值列表。
例如，第二特征索引列表集合中包括表12中的特征索引列表，且表12中的特征索引为表2中的索引时，用户面网元可以从业务传输数据中获取特征索引1、2、3、4、5和6对应的特征“使用时间”、“流中首个包的大小”、“流中所有包大小的均值”、“流中所有包大小的熵”、“流中所有包上下行的时间间隔的均值”和“流中所有包上下行的时间间隔的熵”对应的特征值。
例如，用户面网元可以从业务传输数据中如表13所示的特征值。
表13根据业务传输数据获得的特征值
特征 特征索引 特征值
使用时间 1 早上9:00
流中首个包的大小 2 20比特
流中所有包大小的均值 3 30比特
流中所有包大小的熵 4 2
流中所有包上下行的时间间隔的均值 5 10毫秒
流中所有包上下行的时间间隔的熵 6 1.5
终端类型 7  
终端位置 8  
小区标识 9  
由表13可以看出，由于终端类型、终端位置和小区标识都属于网络数据，因此用户面网元无法根据业务传输数据获得特征索引7、8、9分别对应的终端类型、终端位置和小区标识的特征值，接下来，用户面网元执行S213。
S213，用户面网元向数据库网元发送第三信息，第三信息携带第一业务标识集合。相应地，数据库网元接收用户面网元发送的第三信息。
例如，用户面网元从业务传输数据中获取特征值后，确定第二特征索引列表集合中不能根据业务传输数据得到特征值的所有特征索引，为了后面描述方便，将第二特征索引列表集合中不能根据业务传输数据得到特征值的特征索引组成的特征索引列表称为第一网络数据特征索引列表。
由于训练数据中包括网络数据，因此，根据训练数据生成特征索引列表时，特征索引列表中可能会有对应网络数据的特征索引。与网络数据对应的特征索引对应的特征值无法从业务传输数据中获取。用户面网元可以将从业务传输数据中不能获取到特征值的特征索引筛选出来，得到第一网络数据特征索引列表。
例如，用户面网元从业务传输数据中得不到表12中的特征索引7、8和9对应的特征“终端类型”、“终端位置”和“小区标识”所对应的特征值。也就是说，特征索引7、8和9组成如表14所示的第一网络数据特征索引列表。
表14第一网络数据特征索引列表
特征索引
7
8
9
其中，用户面网元得到第一网络数据特征索引列表后，可以去掉第一网络数据索引列表中重复的特征索引，得到不包含重复特征索引的第一网络数据特征索引列表。
用户面网元确定第一网络数据特征索引列表后，可以确定第一网络数据特征索引列表中每个特征索引所属的特征索引列表对应的业务标识。第一网络数据特征索引列表中所有特征索引对应的业务标识组成第一业务标识集合。
例如，表12中不能根据业务传输数据得到特征值的特征索引7对应的业务标识为业 务标识1，表12中不能根据业务传输数据得到特征值的索引8和9对应的业务标识为业务标识2，从而可以得到如图表15所示的第一网络数据特征索引列表与业务标识的对应关系。
表15第一网络数据特征索引列表与业务标识的对应关系
索引 业务标识
7 业务标识1
8 业务标识2
9 业务标识2
用户面网元可以根据表15得到包括业务标识1和业务标识2的第一业务标识集合，如表16所示。
表16第一业务标识集合
业务标识
业务标识1
业务标识2
S214，数据库网元收集第一会话的网络数据。
第一会话的网络数据可以包括发起第一会话的终端的类型、该终端发起第一会话的时间、该终端所属的小区标识，等等。
应理解，本申请实施例并不限制S214的位置，可选地，S214可以位于S208与S213之间任何位置。
S215，数据库网元向用户面网元发送网络数据特征值列表。相应地，用户面网元接收该网络数据特征值列表。
具体而言，数据库网元收集第一会话的网络数据，并且接收用户面网元发送的第三消息后，可以确定第一业务标识集合中每个业务标识对应的特征索引列表中与网络数据对应的特征索引。第一业务标识集合中所有业务标识对应的特征索引列表中与网络数据对应的特征索引组成的特征列表可以称为第二网络数据特征索引列表。
数据库网元确定第二网络数据特征索引列表后，从收集的第一会话的网络数据中获取第二网络数据特征索引列表中每个特征索引对应的特征的特征值。从第一会话的网络数据中得到的与第二网络数据特征索引列表中每个特征索引对应的特征值组成的特征值列表可以称为网络数据特征值列表。
例如，第一业务标识集合包括表16中的业务标识1和业务标识2时，数据库网元可以从第一会话的网络数据中获取特征“终端类型”、“终端位置”和“小区标识”对应的网络数据特征值。
数据库网元获取的网络数据特征值列表的一种示例为：数据库网元根据表16的第一业务标识集合，获取该第一业务标识集合中包括业务标识1和业务标识2；进一步地，数据库网元根据S206获取的第一信息查询业务标识1对应的特征索引7“终端类型”属于网络数据，数据库网元根据S214获取的网络数据确定“终端类型”对应的特征值。同样的，数据库网元根据业务标识2对应的特征索引8“终端位置”和特征索引9“小区标识”根据S214获取的网络数据确定“终端位置”和“小区标识”对应的特征值。
数据库网元获取的网络数据特征值列表的一个示例如表17所示。
表17第一业务标识集合对应的网络数据特征值列表
业务标识 特征索引 特征值
业务标识1 7 Huawei P10
业务标识2 8 海淀区
业务标识2 9 Cell ID-1
数据库网元可以向用户面网元发送如表17所示的网络数据特征值列表。
S216，用户面网元向数据分析网元发送第二特征索引列表集合以及第二特征索引列表集合中的每个特征索引列表对应的特征值列表。该第二特征索引列表集合以及所述第二特征索引列表集合中的每个特征索引列表对应的特征值列表与第一会话对应.
用户面网元向数据分析网元发送的特征值中，不仅包含业务传输数据的特征值，还可以包括网络数据特征值。相应地，数据分析网元从用户面网元接收上述特征值。
例如，用户面网元可以根据表13和表17向数据分析网元发送如表18所示的特征值列表，该特征值列表与第一会话对应。
表18第一会话对应的特征值列表
特征索引列表 特征值列表
{1，5，6，7} {早上9:00，10毫秒，1.5，Huawei P10
{1，2，3，4，8，9} {早上9:00，20比特，30比特，2，海淀，Cell ID-1}
S217，数据分析网元根据从用户面网元接收的第二特征索引列表集合以及所述第二特征索引列表集合中的每个特征索引列表对应的特征值列表，确定第一会话中数据包的业务类型。
具体而言，数据分析网元可以将用户面网元发送报的第二特征索引列表集合以及第二特征索引列表集合中的每个特征索引列表对应的特征值列表，作为S205中生成的大数据模型的输入参数，大数据模型的输出结果则是该第一会话中的数据包对应的业务类型。
虽然S216中用户面网元向数据分析网元发送的特征值列表中即使同时包括了业务标识1和业务标识2对应的的特征索引列表集合以及每个特征索引列表对应的特征值列表，但是数据分析网元确定的业务类型只能是二者之一，即，用户面网元发送的特征索引列表集合以及每个特征索引列表对应的特征值列表与唯一的业务类型对应。
S218，数据分析网元向用户面网元发送S217中确定得到的业务类型。相应地，用户面网元接收该业务类型。
本申请实施例中，各个网元之间分工合作，共同完成了业务类型的识别。此外，因为数据库网元可以通过分布式部署方式，并靠近应用服务器和核心网网元部署，因此，有助于降低获取训练数据和下发第一信息的时延。
本申请实施例的通信方法中，数据分析网元可以根据终端的网络数据和业务传输数据确定终端的业务类型，从而可以提高识别准确率。
本申请实施例中，可选地，第一信息中还可以包括第一特征索引列表集合中每个特征索引列表对应的以下至少一种信息：网络切片类型、SSC模式、PDU会话类型。
若第一信息还包括网络切片类型、SSC模式、PDU会话类型中至少一种信息，则在S209中，控制面网元从第一信息中查询得到第二信息时，控制面网元不仅可以根据第一会话的DNN，还可以根据第一会话的网络切片类型、SSC模式、PDU会话类型中至少一 种信息筛选得到第二信息。
换句话说，就是从第一信息中筛选得到的第二信息，且第二信息中的第二特征索引列表集合中的每个特征索引列表均对应第一会话的DNN，且对应第一会话的网络切片类型、SSC模式、PDU会话类型中至少一种信息。
这样，可以得到更为准确的第二信息，从而有助于提高用户面网元根据第二信息获取的特征值的准确性，最终有助于提高业务类型识别的准确率。
本申请实施例中，可选地，若数据库网元确定的第一业务标识集合为空，则本申请实施例中，可以没有S213和S215，甚至可以没有S214。
本申请实施例中，可选地，在S213中，第三信息还可以携带以下至少一种信息：用户面网元接收第一会话的业务传输数据的时间、第一会话的会话标识、第一会话对应的终端的标识、第一会话对应的终端的IP地址、第一会话对应的终端的端口、第一会话对应的业务服务器的IP地址、业务服务器中与第一会话对应的端口、第一会话的业务传输数据的业务传输协议。
这样，数据库网元可以进一步根据第三信息中携带的这至少一种信息，获取满足该至少一种信息的网络数据的特征值。例如，用户面网元向数据库网元发送的第三信息可以携带终端的IP地址，该终端的IP地址用于标识终端，数据库网元根据终端的IP地址确定终端的网络数据。从而可以进一步提高业务类型识别的准确率。
本申请实施例的S214中，数据库网元收集第一会话的网络数据时，还可以根据第一会话对应的DNN、终端的IP、终端的ID、PDU会话ID等一种或多种信息收集第一会话的网络数据。
本申请实施例的S213和S215中，用户面网元可以直接与数据库网元通信，也可以通过SMF网元与数据库网元通信。
图3是本申请一个实施例的通信方法的示意性交互流程图。应理解，图3示出了通信方法的步骤或操作，但这些步骤或操作仅是示例，本申请实施例还可以执行其他操作或者图3中的各个操作的变形。此外，图3中的各个步骤可以按照与图3呈现的不同的顺序来执行，并且有可能并非要执行图3中的全部操作。
S301至S312，可以参考图2中的S210至S212，为了简洁，此处不再赘述。
S313，用户面网元向数据库网元发送第三信息，第三信息携带网络数据特征索引列表。相应地，数据库网元接收用户面网元发送的第三信息。
例如，用户面网元从业务传输数据中获取特征值后，确定第二特征索引列表集合中不能根据业务传输数据得到特征值的所有特征索引。第二特征索引列表集合中不能根据业务传输数据得到特征值的特征索引组成网络数据特征索引列表。
换句话说，由于训练数据中包括网络数据，因此，根据训练数据生成特征索引列表时，特征索引列表中可能会有对应网络数据的特征索引。与网络数据对应的特征索引对应的特征值从业务传输数据中是获取不到的。用户面网元可以将从业务传输数据中不能获取到特征值的特征索引筛选出来，得到网络数据特征索引列表。
例如，用户面网元从业务传输数据中得不到表12中的特征索引7、8和9对应的特征“终端类型”、“终端位置”和“小区标识”所对应的特征值。也就是说，特征索引7、8和9组成网络数据特征索引列表。
其中，用户面网元得到网络数据特征索引列表后，可以去掉该网络数据特征索引列表中重复的特征索引，得到不包含重复特征索引的网络数据特征索引列表。
S314可以参考图2中的S214，此处不再赘述。
S315，数据库网元向用户面网元发送网络数据特征值列表。相应地，用户面网元从数据库网元接收网络数据特征值列表。
例如，数据库网元从收集的第一会话的网络数据中获取网络数据特征索引列表中每个特征索引对应的特征的特征值。从第一会话的网络数据中得到的与网络数据特征索引列表中每个特征索引对应的特征值组成的特征值列表可以称为网络数据特征值列表。
例如，网络数据特征索引列表中包含特征索引7、8和9时，数据库网元可以从第一会话的网络数据中获取特征“终端类型”、“终端位置”和“小区标识”对应的网络数据特征值。
S316至S318，可以参考图2中的S216至S218，此处不再赘述。
图4是本申请一个实施例的通信方法的示意性交互流程图。应理解，图4示出了通信方法的步骤或操作，但这些步骤或操作仅是示例，本申请实施例还可以执行其他操作或者图4中的各个操作的变形。此外，图4中的各个步骤可以按照与图4呈现的不同的顺序来执行，并且有可能并非要执行图4中的全部操作。
S401至S412，可以参考图2中的S210至S212，为了简洁，此处不再赘述。
S413，用户面网元向数据库网元发送第三信息，第三信息用于请求第一会话对应的网络数据。相应地，数据库网元接收用户面网元发送的第三信息。
例如，用户面网元从业务传输数据中获取特征值后，确定第二特征索引列表集合中有无不能根据业务传输数据得到特征值的特征索引。
若第二特征索引列表集合中有不能根据业务传输数据得到特征值的特征索引，则用户面网元向数据库网元发送第三信息，请求第一会话的网络数据，为了后续描述方便，将第二特征索引列表集合中有不能根据业务传输数据得到特征值的特征索引组成的索引列表称为网络数据特征索引列表。
因为训练数据中包括网络数据，所以，根据训练数据生成特征索引列表时，特征索引列表中可能会有对应网络数据的特征索引。也就是说，不能根据业务传输数据得到的特征值可以从网络数据中获取。因此，用户面网元可以向数据库网元发送请求网络数据的第三信息。
例如，用户面网元从业务传输数据中得不到表12中的特征索引7、8和9对应的特征“终端类型”、“终端位置”和“小区标识”所对应的特征值。则，用户面网元向数据库网元发送第三信息，请求第一会话的网络数据。
例如，第三信息可以包括用户面网元接收第一会话的业务传输数据的时间、第一会话的会话标识、第一会话对应的终端的标识、第一会话对应的终端的IP地址、第一会话对应的终端的端口、第一会话对应的业务服务器的IP地址、业务服务器中与第一会话对应的端口、第一会话的业务传输数据的业务传输协议，等等。
S414，数据库网元可以根据第三信息收集第一会话的网络数据。
例如，数据库网元可以收集满足以下至少一个条件的网络数据：用户面网元接收第一会话的业务传输数据的时间、第一会话的会话标识、第一会话对应的终端的标识、第一会话对应的终端的IP地址、第一会话对应的终端的端口、第一会话对应的业务服务器的IP 地址、业务服务器中与第一会话对应的端口、第一会话的业务传输数据的业务传输协议。
S415，数据库网元向用户面网元发送网络数据。相应地，用户面网元从数据库网元接收网络数据。
用户面网元从数据库网元接收第一会话的网络数据后，从第一会话的网络数据中获取网络数据特征索引列表中的特征索引对应的特征的特征值。网络数据特征索引列表中的特征索引对应的特征的特征值组成的列表称为网络数据特征值列表。
S416至S418，可以参考图2中的S216至S218，此处不再赘述。
图5是本申请一个实施例的通信方法的示意性交互流程图。应理解，图5示出了通信方法的步骤或操作，但这些步骤或操作仅是示例，本申请实施例还可以执行其他操作或者图5中的各个操作的变形。此外，图5中的各个步骤可以按照与图5呈现的不同的顺序来执行，并且有可能并非要执行图5中的全部操作。
S501至S506，可以分别参考S201至S206中相应的步骤，为了简洁，此处不再赘述。
S507可以参考S208，为了简洁，此处不再赘述。
S508，控制面网元向数据库网元发送第一会话的DNN。相应地，数据库网元接收控制面网元发送的第一会话的DNN。
S509，数据库网元根据第一会话的DNN，从第一信息中查询得到第二信息，第二信息包括第二特征索引列表集合以及第二特征列表集合中每个特征索引列表对应的业务类型的业务标识。
数据库网元根据与第一会话关联的第一DNN，从第一信息中查询得到第二信息，第二信息包括与第一DNN对应的第二特征索引列表集合和第二特征索引列表集合中每个特征索引列表对应的业务标识。
换句话说，数据库网元可以根据第一DNN，对本地保存的第一信息进行筛选，匹配出与第一DNN对应的特征索引列表和业务标识。从第一信息中筛选得到的与第一DNN对应的特征索引列表组成第二特征索引列表集合。
数据库网元根据第二特征索引列表集合与筛选得到的业务标识生成第二信息，第二信息包括第二特征索引列表集合与筛选得到的业务标识。
例如，数据库网元从数据分析网元接收的第一信息包括表11所示的内容时，如果第一DNN为DNN-1，则数据库网元可以根据表11中生成第二信息，第二信息可以包括表12所示的内容。
可选地，数据库网元从数据分析网元接收的第一信息中包括特征与索引的对应关系时，数据库网元向控制面网元发送的第二信息中也可以包括该对应关系。
这样，控制面网元可以本地保存特征总列表，后续数据库网元再次向控制面网元发送业务类型对应的第二信息的时候，第二信息可以只包括业务类型对应的特征索引列表。控制面网元可以向用户面网元发送特征与索引的对应关系，以便于用户面网元可以根据该对应关系来获取第二信息中的特征索引列表对应的特征列表。
S510，数据库网元向控制面网元发送第二信息。相应地，控制面网元接收数据库网元发送的第二信息。
S511至S519可以参考S210至S218中相应的步骤。为了简洁，此处不再赘述。
本申请实施例中，可选地，在S508中，控制面网元还可以向数据库网元发送第一会 话的以下至少一种信息：网络切片类型、SSC模式、PDU会话类型。相应地，数据库网元还从CPF网元接收第一会话的上述至少一种信息。
对应地，在S509中，数据库网元从第一信息中查询第二信息时，除了可以根据第一会话的DNN，还可以根据第一会话的上述至少一种信息，获取第二信息。这样，有助于得到更准确的第二信息，从而有助于提高业务类型识别的准确率。
本申请实施例中，可选地，第二信息还可以包括第二特征索引列表集合中的每个特征索引列表对应的以下至少一种信息：DNN、网络切片类型、服务和SSC模式、PDU会话类型。
第二信息还包括第二特征索引列表集合中的每个特征索引列表对应的上述至少一种信息时，若本终端发起第二会话或其他终端发起第二会话时，控制面网元可以根据第二特征索引列表集合中的每个特征索引列表对应的上述至少一种信息，判断第二特征索引列表集合中是否已包含第二会话对应的特征索引列表。
若控制面网元根据第二特征索引列表集合中的每个特征索引列表对应的上述至少一种信息，判断第二特征索引列表集合中已包含第二会话对应的特征索引列表，则控制面网元可以不用再向数据库网元请求第二信息，从而有助于提高业务类型识别的效率。
图6是本申请一个实施例的通信方法的示意性交互流程图。应理解，图6示出了通信方法的步骤或操作，但这些步骤或操作仅是示例，本申请实施例还可以执行其他操作或者图6中的各个操作的变形。此外，图6中的各个步骤可以按照与图6呈现的不同的顺序来执行，并且有可能并非要执行图6中的全部操作。
S601至S613，可以参考图5中的S501至S513，为了简洁，此处不再赘述。
S614至S616，可以参考图3中的S313至S315，为了简洁，此处不再赘述。
S617至S619，可以参考图5中的S517至S519，为了简洁，此处不再赘述。
图7是本申请一个实施例的通信方法的示意性交互流程图。应理解，图7示出了通信方法的步骤或操作，但这些步骤或操作仅是示例，本申请实施例还可以执行其他操作或者图7中的各个操作的变形。此外，图7中的各个步骤可以按照与图7呈现的不同的顺序来执行，并且有可能并非要执行图7中的全部操作。
S701至S713，可以参考图5中的S501至S513，为了简洁，此处不再赘述。
S714至S716，可以参考图4中的S413至S415，为了简洁，此处不再赘述。
S717至S719，可以参考图5中的S517至S519，为了简洁，此处不再赘述。
图2所示的通信方法中，可选地，当应用平台上的应用数据发生改变，例如应用版本升级时，数据库网元可以重新执行S201至S207。
图3所示的通信方法中，可选地，当应用平台上的应用数据发生改变，例如应用版本升级时，数据库网元可以重新执行S301至S307。
图4所示的通信方法中，可选地，当应用平台上的应用数据发生改变，例如应用版本升级时，数据库网元可以重新执行S401至S407。
图5所示的通信方法中，可选地，当应用平台上的应用数据发生改变，例如应用版本升级时，数据库网元可以重新执行S501至S506。
图6所示的通信方法中，可选地，当应用平台上的应用数据发生改变，例如应用版本升级时，数据库网元可以重新执行S601至S606。
图7所示的通信方法中，可选地，当应用平台上的应用数据发生改变，例如应用版本升级时，数据库网元可以重新执行S701至S706。
上面结合图2至图7介绍了本申请实施例的通信方法的示意性交互流程图，下面结合图8至图13介绍本申请实施例的单侧通信方法。
图8是本申请一个实施例的通信方法的示意性流程图。应理解，图8示出了通信方法的步骤或操作，但这些步骤或操作仅是示例，本申请实施例还可以执行其他操作或者图8中的各个操作的变形。此外，图8中的各个步骤可以按照与图8呈现的不同的顺序来执行，并且有可能并非要执行图8中的全部操作。
S801，数据库网元获取训练数据，训练数据包括业务传输数据和网络数据。
例如，图2中的S201至S203，图3中的S301至S303，图4中的S401至S403，图5中的S501至S503，图6中的S601至S603，图7中的S701至S703。
S802，数据库网元向数据分析网元发送训练数据。
例如，图2中的S204，图3中的S304，图4中的S404，图5中的S504，图6中的S604，图7中的S704。
S803，数据库网元从数据分析网元接收第一信息，第一信息包括第一特征索引列表集合、第一特征索引列表集合中的每个特征索引列表对应的业务标识和业务标识对应的DNN。
例如，图2中的S206，图3中的S306，图4中的S406，图5中的S506，图6中的S606，图7中的S706。
可选地，图8所示的通信方法还可以包括：数据库网元向控制面网元发送第一信息。
例如，图2中的S207，图3中的S307，图4中的S407。
或者，可选地，图8所示的通信方法还可以包括：数据库网元从控制面网元接收第一会话的DNN；数据库网元根据第一会话的DNN，从第一信息中查询得到第二信息，第二信息包括与第一会话的DNN对应的第二特征索引列表集合以及第二特征索引列表集合中的每个特征索引列表对应的业务标识；数据库网元向控制面网元发送第二信息。
例如，图5中的S509，图6中的S609，图7中的S709。
可选地，图8所示的通信方法还可以包括：数据库网元从用户面网元接收第三信息，第三信息包括第一业务标识集合；数据库网元从第一信息中，查询得到第一业务标识集合中的每个业务标识对应的特征索引列表；数据库网元根据第一业务标识集合中的每个业务标识对应的特征索引列表，从网络数据中查询得到第一业务标识集合中每个业务标识对应的网络数据特征值列表；数据库网元向用户面网元发送第一业务标识集合中每个业务标识对应的网络数据特征值列表。
例如，图2中的S213至S215，图5中的S514至S516。
图9是本申请一个实施例的通信方法的示意性流程图。应理解，图9示出了通信方法的步骤或操作，但这些步骤或操作仅是示例，本申请实施例还可以执行其他操作或者图9中的各个操作的变形。此外，图9中的各个步骤可以按照与图9呈现的不同的顺序来执行，并且有可能并非要执行图9中的全部操作。
S901，数据分析网元从数据库网元接收训练数据，训练数据包括业务传输数据和网络数据。
例如，图2中的S204，图3中的S304，图4中的S404，图5中的S504，图6中的S604，图7中的S704。
S902，数据分析网元根据训练数据确定第一信息，第一信息包括第一特征索引列表集合以及第一特征索引列表集合中的每个特征索引列表对应的业务标识和业务标识对应的DNN。
例如，图2中的S205，图3中的S305，图4中的S405，图5中的S505，图6中的S605，图7中的S705。
S903，数据分析网元向数据库网元发送第一信息。
例如，图2中的S206，图3中的S306，图4中的S406，图5中的S506，图6中的S606，图7中的S706。
图10是本申请一个实施例的通信方法的示意性流程图。应理解，图10示出了通信方法的步骤或操作，但这些步骤或操作仅是示例，本申请实施例还可以执行其他操作或者图10中的各个操作的变形。此外，图10中的各个步骤可以按照与图10呈现的不同的顺序来执行，并且有可能并非要执行图10中的全部操作。
S1001，控制面网元从数据库网元接收第一信息，第一信息包括第一特征索引列表集合以及第一特征索引列表集合中的每个特征索引列表对应的业务标识和业务标识对应的DNN。
例如，图2中的S207，图3中的S307，图4中的S407。
1002，控制面网元根据第一会话的DNN，从第一信息中查询得到第二信息，第二信息包括与第一会话的DNN对应的第二特征索引列表集合和第二特征索引列表中的每个特征索引列表对应的业务标识。
例如，图2中的S209，图3中的S309，图4中的S409。
1003，控制面网元向用户面网元发送第二信息。
例如，图2中的S210，图3中的S310，图4中的S410。
图11是本申请一个实施例的通信方法的示意性流程图。应理解，图11示出了通信方法的步骤或操作，但这些步骤或操作仅是示例，本申请实施例还可以执行其他操作或者图11中的各个操作的变形。此外，图11中的各个步骤可以按照与图11呈现的不同的顺序来执行，并且有可能并非要执行图11中的全部操作。
S1101，控制面网元向数据库网元发送第一会话的DNN。
例如，图5中的S508，图6中的S608，图7中的S708。
S1102，控制面网元从数据库网元接收第二信息，第二信息包括第二特征索引列表集合和第二特征索引列表集合中的每个特征索引列表对应的业务标识，业务标识与DNN对应。
例如，图5中的S510，图6中的S610，图7中的S710。
S1103，控制面网元向用户面网元发送第二信息。
例如，图5中的S511，图6中的S611，图7中的S711。
可选地，控制面网元从数据库网元接收第二信息之前，该通信方法还可以包括：控制面网元向数据库网元发送第一会话的以下至少一种信息：网络切片类型、SSC模式、PDU会话类型。
图12是本申请一个实施例的通信方法的示意性流程图。应理解，图12示出了通信方法的步骤或操作，但这些步骤或操作仅是示例，本申请实施例还可以执行其他操作或者图12中的各个操作的变形。此外，图12中的各个步骤可以按照与图12呈现的不同的顺序来执行，并且有可能并非要执行图12中的全部操作。
S1201，用户面网元从控制面网元接收第二信息，第二信息包括第二特征索引列表集合以及第二特征索引列表集合中的每个特征索引列表对应的业务标识。
例如，图2中的S210，图5中的S511。
S1202，用户面网元接收第一会话的业务传输数据。
例如，图2中的S211，图5中的S512。
S1203，用户面网元确定第二特征索引列表集合中不能根据业务传输数据得到特征值的特征索引列表对应的业务标识，得到第一业务标识集合；并向数据库网元发送第三信息，第三信息包括第一业务标识集合。
例如，图2中的S213，图5中的S514。
S1204，用户面网元从数据库网元接收第一业务标识集合中每个业务标识对应的网络数据特征值列表。
例如，图2中的S215，图5中的S516。
图13是本申请一个实施例的通信方法的示意性流程图。应理解，图13示出了通信方法的步骤或操作，但这些步骤或操作仅是示例，本申请实施例还可以执行其他操作或者图13中的各个操作的变形。此外，图13中的各个步骤可以按照与图13呈现的不同的顺序来执行，并且有可能并非要执行图13中的全部操作。
S1301，用户面网元从控制面网元接收第二信息，第二信息包括第二特征索引列表集合以及第二特征索引列表集合中的每个特征索引列表对应的业务标识。
例如，图3中的S310，图6中的S611。
S1302，用户面网元接收第一会话的业务传输数据。
例如，图3中的S311，图6中的S612。
S1303，用户面网元确定第二特征索引列表集合中不能根据业务传输数据得到特征值的特征索引，得到网络数据特征索引列表；并向数据库网元发送网络数据特征索引列表。
例如，图3中的S313，图6中的S614。
S1304，用户面网元从数据库网元接收网络数据特征索引列表对应的网络数据特征值列表。
例如，图3中的S315，图6中的S616。
本申请一个实施例的数据库网元的示意性结构图如图14所示。应理解，图14示出的数据库网元1400仅是示例，本申请实施例的数据库网元还可包括其他模块或单元，或者包括与图14中的各个模块的功能相似的模块，或者并非要包括图14中所有模块。
处理模块1401，用于获取训练数据，训练数据包括业务传输数据和网络数据。
发送模块1402，用于向数据分析网元发送训练数据。
接收模块1403，用于从数据分析网元接收第一信息，第一信息包括第一特征索引列表集合、第一特征索引列表集合中的每个特征索引列表对应的业务标识和业务标识对应的数据网络名称DNN。
可选地，第一信息还可以包括第一特征索引列表集合中的每个特征索引列表对应的以下至少一种信息：网络切片类型、SSC模式、PDU会话类型。
可选地，发送模块1402还可以用于：向控制面网元发送第一信息。
可选地，接收模块还可以用于：从控制面网元接收第一会话的DNN；
相应地，处理模块1401还用于：根据第一会话的DNN，从第一信息中查询得到第二信息，第二信息包括与第一会话的DNN对应的第二特征索引列表集合以及第二特征索引列表集合中的每个特征索引列表对应的业务标识。
发送模块还用于：向控制面网元发送第二信息。
可选地，接收模块1403还可以用于：从控制面网元接收第一会话的以下至少一种信息：网络切片类型、SSC模式、PDU会话类型。
相应地，处理模块1401具体用于：根据第一会话的DNN和第一会话的所述至少一种信息，从第一信息中查询得到第二信息。
可选地，接收模块1403还可以用于：从用户面网元接收第三信息，第三信息包括第一业务标识集合。
相应地，处理模块1401还用于：
从第一信息中，查询得到第一业务标识集合中的每个业务标识对应的特征索引列表；
根据第一业务标识集合中的每个业务标识对应的特征索引列表，从网络数据中查询得到第一业务标识集合中每个业务标识对应的网络数据特征值列表。
发送模块1402还用于：向所述用户面网元发送所述第一业务标识集合中每个业务标识对应的网络数据特征值列表。
可选地，第三信息还可以包括以下至少一种信息：所述用户面网元接收第一会话的业务传输数据的时间、所述第一会话的会话标识、所述第一会话对应的终端的标识、所述第一会话对应的终端的互联网协议IP地址、所述第一会话对应的终端的端口、所述第一会话对应的业务服务器的IP地址、所述业务服务器中与所述第一会话对应的端口、所述第一会话的业务传输数据的业务传输协议。
应理解，图14中的数据库网元1400所包括的各个模块可以用于实现图2至图7中任意一个所示的通信方法中由数据库网元执行的相应步骤，为了简洁，此处不再赘述。
本申请一个实施例的数据分析网元的示意性结构图如图15所示。应理解，图15示出的数据分析网元1500仅是示例，本申请实施例的数据分析网元还可包括其他模块或单元，或者包括与图15中的各个模块的功能相似的模块，或者并非要包括图15中所有模块。
接收模块1501，用于从数据库网元接收训练数据，训练数据包括业务传输数据和网络数据。
处理模块1502，用于根据训练数据确定第一信息，第一信息包括第一特征索引列表集合以及第一特征索引列表集合中的每个特征索引列表对应的业务标识和业务标识对应的DNN。
发送模块1503，用于向数据库网元发送第一信息。
可选地，第一信息还可以包括所述第一特征索引列表集合中的每个特征索引列表对应的以下至少一种信息：网络切片类型、SSC模式、PDU会话类型。
应理解，图15中的数据分析网元1500所包括的各个模块可以用于实现图2至图7中 任意一个所示的通信方法中由数据分析网元执行的相应步骤，为了简洁，此处不再赘述。
本申请一个实施例的控制面网元的示意性结构图如图16所示。应理解，图16示出的控制面网元1600仅是示例，本申请实施例的控制面网元还可包括其他模块或单元，或者包括与图16中的各个模块的功能相似的模块，或者并非要包括图16中所有模块。
接收模块1601，用于从数据库网元接收第一信息，第一信息包括第一特征索引列表集合以及第一特征索引列表集合中的每个特征索引列表对应的业务标识和业务标识对应的DNN。
处理模块1602，用于根据第一会话的DNN，从第一信息中查询得到第二信息，第二信息包括与第一会话的DNN对应的第二特征索引列表集合和第二特征索引列表中的每个特征索引列表对应的业务标识。
发送模块1603，用于向用户面网元发送第二信息。
可选地，第一信息还可以包括第一特征索引列表集合中的每个特征索引列表对应的以下至少一种信息：网络切片类型、SSC模式、PDU会话类型。
相应地，处理模块1602具体用于：根据第一会话的DNN和第一会话的网络切片类型、SSC模式、PDU会话类型中的至少一种信息，从第一信息中查询得到第二信息。
应理解，图16中的控制面网元1600所包括的各个模块可以用于实现图2、图3或图4所示的通信方法中由控制面网元执行的相应步骤，为了简洁，此处不再赘述。
本申请一个实施例的控制面网元的示意性结构图如图17所示。应理解，图17示出的控制面网元1700仅是示例，本申请实施例的控制面网元还可包括其他模块或单元，或者包括与图17中的各个模块的功能相似的模块，或者并非要包括图17中所有模块。
发送模块1701，用于向数据库网元发送第一会话的DNN。
接收模块1702，用于从数据库网元接收第二信息，第二信息包括第二特征索引列表集合和第二特征索引列表集合中的每个特征索引列表对应的业务标识，业务标识与第一会话的DNN对应。
发送模块1701还用于向用户面网元发送第二信息。
可选地，发送模块1701还可以用于：向数据库网元发送第一会话的以下至少一种信息：网络切片类型、SSC模式、PDU会话类型。
应理解，图17中的控制面网元1700所包括的各个模块可以用于实现图5、图6或图7所示的通信方法中由控制面网元执行的相应步骤，为了简洁，此处不再赘述。
本申请一个实施例的用户面网元的示意性结构图如图18所示。应理解，图18示出的用户面网元1800仅是示例，本申请实施例的用户面网元还可包括其他模块或单元，或者包括与图18中的各个模块的功能相似的模块，或者并非要包括图18中所有模块。
接收模块1801，用于从控制面网元接收第二信息，第二信息包括第二特征索引列表集合以及第二特征索引列表集合中的每个特征索引列表对应的业务标识。
接收模块1801还用于接收第一会话的业务传输数据。
处理模块1802，用于确定第二特征索引列表集合中不能根据所述业务传输数据得到特征值的特征索引列表对应的业务标识，得到第一业务标识集合。
发送模块1803，用于向数据库网元发送第三信息，第三信息包括第一业务标识集合。
接收模块1801还用于从数据库网元接收第一业务标识集合中每个业务标识对应的网 络数据特征值列表。
可选地，第三信息还包括以下至少一种信息：用户面处理接收第一会话的业务传输数据的时间、第一会话的会话标识、第一会话对应的终端的标识、第一会话对应的终端的IP地址、第一会话对应的终端的端口、第一会话对应的业务服务器的IP地址、业务服务器中与第一会话对应的端口、第一会话对应的业务传输数据的业务传输协议。
应理解，图18中的用户面网元1800所包括的各个模块可以用于实现图2或图5所示的通信方法中由用户面网元执行的相应步骤，为了简洁，此处不再赘述。
本申请一个实施例的用户面网元的示意性结构图如图19所示。应理解，图19示出的用户面网元1900仅是示例，本申请实施例的用户面网元还可包括其他模块或单元，或者包括与图19中的各个模块的功能相似的模块，或者并非要包括图19中所有模块。
接收模块1901，用于从控制面网元接收第二信息，第二信息包括第二特征索引列表集合以及第二特征索引列表集合中的每个特征索引列表对应的业务标识。
接收模块1901还用于接收第一会话的业务传输数据。
处理模块1902，用于确定第二特征索引列表集合中不能根据业务传输数据得到特征值的特征索引，得到网络数据特征索引列表。
发送模块1903，用于向数据库网元发送网络数据特征索引列表。
接收模块1901还用于从数据库网元接收网络数据特征索引列表对应的网络数据特征值列表。
可选地，第三信息可以包括以下至少一种信息：用户面处理接收第一会话的业务传输数据的时间、第一会话的会话标识、第一会话对应的终端的标识、第一会话对应的终端的IP地址、第一会话对应的终端的端口、第一会话对应的业务服务器的IP地址、业务服务器中与第一会话对应的端口、第一会话对应的业务数据的业务传输协议。
应理解，图19中的用户面网元1900所包括的各个模块可以用于实现图3或图6所示的通信方法中由用户面网元执行的相应步骤，为了简洁，此处不再赘述。
图20是本申请一个实施例的数据库网元的示意性结构图。应理解，图20示出的数据库网元2000仅是示例，本申请实施例的数据库网元还可包括其他模块或单元，或者包括与图20中的各个模块的功能相似的模块，或者并非要包括图20中所有模块。
其中，处理器2020可以用于实现图14中的处理模块1401执行的操作或步骤，发送器2040可以用于实现图14中的发送模块1402执行的操作或步骤，接收器2030可以用于实现图14中的接收模块1403执行的操作或步骤。
接收器2030和发送器2040可以集成在一起，称为收发器。
可选地，数据库网元2000也可以包括存储器2010，用于存储处理器2020执行的程序代码。其中，处理器2020中可以集成有存储器。
图21是本申请一个实施例的数据分析网元的示意性结构图。应理解，图21示出的数据分析网元2100仅是示例，本申请实施例的数据分析网元还可包括其他模块或单元，或者包括与图21中的各个模块的功能相似的模块，或者并非要包括图21中所有模块。
其中，处理器2120可以用于实现图15中的处理模块1502执行的操作或步骤，发送器2140可以用于实现图15中的发送模块1503执行的操作或步骤，接收器2130可以用于实现图15中的接收模块1501执行的操作或步骤。
接收器2130和发送器2140可以集成在一起，称为收发器。
可选地，数据分析网元2100也可以包括存储器2110，用于存储处理器2120执行的程序代码。其中，处理器2120中可以集成有存储器。
图22是本申请一个实施例的控制面网元的示意性结构图。应理解，图22示出的控制面网元2200仅是示例，本申请实施例的控制面网元还可包括其他模块或单元，或者包括与图22中的各个模块的功能相似的模块，或者并非要包括图22中所有模块。
其中，处理器2220可以用于实现图16中的处理模块1602执行的操作或步骤，发送器2240可以用于实现图16中的发送模块1603执行的操作或步骤，接收器2230可以用于实现图16中的接收模块1601执行的操作或步骤。
接收器2230和发送器2240可以集成在一起，称为收发器。
可选地，控制面网元2200也可以包括存储器2210，用于存储处理器2220执行的程序代码。其中，处理器2220中可以集成有存储器。
图23是本申请一个实施例的控制面网元的示意性结构图。应理解，图23示出的控制面网元2300仅是示例，本申请实施例的控制面网元还可包括其他模块或单元，或者包括与图23中的各个模块的功能相似的模块，或者并非要包括图23中所有模块。
其中，发送器2340可以用于实现图17中的发送模块1701执行的操作或步骤，接收器2330可以用于实现图17中的接收模块1702执行的操作或步骤。
接收器2330和发送器2340可以集成在一起，称为收发器。
可选地，控制面网元2300也可以包括存储器2310和处理器2320。存储器2310用于存储程序代码，处理器2320用于执存储器2310中存储的程序代码，
其中，处理器2320中可以集成有存储器2310。
图24是本申请一个实施例的用户面网元的示意性结构图。应理解，图24示出的用户面网元2400仅是示例，本申请实施例的用户面网元还可包括其他模块或单元，或者包括与图24中的各个模块的功能相似的模块，或者并非要包括图24中所有模块。
其中，处理器2420可以用于实现图18中的处理模块1802执行的操作或步骤，发送器2440可以用于实现图18中的发送模块1803执行的操作或步骤，接收器2430可以用于实现图18中的接收模块1801执行的操作或步骤。
接收器2430和发送器2440可以集成在一起，称为收发器。
可选地，用户面网元2400也可以包括存储器2410，用于存储处理器2420执行的程序代码。其中，处理器2420中可以集成有存储器。
图25是本申请一个实施例的用户面网元的示意性结构图。应理解，图25示出的用户面网元2500仅是示例，本申请实施例的用户面网元还可包括其他模块或单元，或者包括与图25中的各个模块的功能相似的模块，或者并非要包括图25中所有模块。
其中，处理器2520可以用于实现图19中的处理模块1902执行的操作或步骤，发送器2540可以用于实现图19中的发送模块1903执行的操作或步骤，接收器2530可以用于实现图19中的接收模块1901执行的操作或步骤。
接收器2530和发送器2540可以集成在一起，称为收发器。
可选地，用户面网元2500也可以包括存储器2510，用于存储处理器2520执行的程序代码。其中，处理器2520中可以集成有存储器。
图26是本申请一个实施例的芯片系统的示意性结构图。应理解，图26示出的芯片系统2600仅是示例，本申请实施例的芯片系统还可包括其他模块或单元，或者包括与图26中的各个模块的功能相似的模块，或者并非要包括图26中所有模块。
芯片系统2600包括处理器2610，用于支持前述数据库网元、数据分析网元、控制面网元或用户面网元实现对应的通信方法中所涉及的功能，例如，生成或处理上述通信方法中所涉及的信息。
其中，芯片系统2600可以包括一个或多个处理器2600，本申请对此不作限制。
可选地，所述芯片系统2600还包括存储器2620，存储器2620用于保存数据库网元、数据分析网元、控制面网元或用户面网元必要的程序指令和数据。该芯片系统可以由芯片构成，也可以包含芯片和其他分立器件。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机程序指令时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质，(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质(例如固态硬盘Solid State Disk(SSD))等。

Claims (30)

  1. 一种通信方法，其特征在于，包括：
    数据库网元获取训练数据，所述训练数据包括业务传输数据和网络数据；
    所述数据库网元向数据分析网元发送所述训练数据；
    所述数据库网元从所述数据分析网元接收第一信息，所述第一信息包括第一特征索引列表集合、所述第一特征索引列表集合中的每个特征索引列表对应的业务标识和所述业务标识对应的数据网络名称DNN。
  2. 根据权利要求1所述的通信方法，其特征在于，所述第一信息还包括所述第一特征索引列表集合中的每个特征索引列表对应的以下至少一种信息：网络切片类型、会话和业务连续性SSC模式、分组数据单元PDU会话类型。
  3. 根据权利要求1或2所述的通信方法，其特征在于，所述通信方法还包括：
    所述数据库网元向控制面网元发送所述第一信息。
  4. 根据权利要求1或2所述的通信方法，其特征在于，所述通信方法还包括：
    所述数据库网元从控制面网元接收第一会话的DNN；
    所述数据库网元根据所述第一会话的DNN，从所述第一信息中查询得到第二信息，所述第二信息包括与所述第一会话的DNN对应的第二特征索引列表集合以及所述第二特征索引列表集合中的每个特征索引列表对应的业务标识；
    所述数据库网元向所述控制面网元发送所述第二信息。
  5. 根据权利要求4所述的通信方法，其特征在于，所述通信方法还包括：
    所述数据库网元从所述控制面网元接收所述第一会话的以下至少一种信息：网络切片类型、SSC模式、PDU会话类型；
    其中，所述数据库网元根据所述第一会话的DNN，从所述第一信息中查询得到第二信息，包括：
    所述数据库网元根据所述第一会话的DNN和所述第一会话的所述至少一种信息，从所述第一信息中查询得到所述第二信息。
  6. 根据权利要求1至5中任一项所述的通信方法，其特征在于，所述通信方法还包括：
    所述数据库网元从用户面网元接收第三信息，所述第三信息包括第一业务标识集合；
    所述数据库网元从所述第一信息中，查询得到所述第一业务标识集合中的每个业务标识对应的特征索引列表；
    所述数据库网元根据所述第一业务标识集合中的每个业务标识对应的特征索引列表，从网络数据中查询得到所述第一业务标识集合中每个业务标识对应的网络数据特征值列表；
    所述数据库网元向所述用户面网元发送所述第一业务标识集合中每个业务标识对应的网络数据特征值列表。
  7. 根据权利要求6所述的通信方法，其特征在于，所述第三信息还包括以下至少一种信息：所述用户面网元接收第一会话的业务传输数据的时间、所述第一会话的会话标识、 所述第一会话对应的终端的标识、所述第一会话对应的终端的互联网协议IP地址、所述第一会话对应的终端的端口、所述第一会话对应的业务服务器的IP地址、所述业务服务器中与所述第一会话对应的端口、所述第一会话的业务传输数据的业务传输协议。
  8. 一种通信方法，其特征在于，包括：
    数据分析网元从数据库网元接收训练数据，所述训练数据包括业务传输数据和网络数据；
    所述数据分析网元根据所述训练数据确定第一信息，所述第一信息包括第一特征索引列表集合以及所述第一特征索引列表集合中的每个特征索引列表对应的业务标识和所述业务标识对应的数据网络名称DNN；
    所述数据分析网元向所述数据库网元发送所述第一信息。
  9. 根据权利要求8所述的通信方法，其特征在于，所述第一信息还包括所述第一特征索引列表集合中的每个特征索引列表对应的以下至少一种信息：网络切片类型、会话和业务连续性SSC模式、分组数据单元PDU会话类型。
  10. 一种通信方法，其特征在于，包括：
    控制面网元从数据库网元接收第一信息，所述第一信息包括第一特征索引列表集合以及所述第一特征索引列表集合中的每个特征索引列表对应的业务标识和所述业务标识对应的数据网络名称DNN；
    所述控制面网元根据第一会话的DNN，从所述第一信息中查询得到第二信息，所述第二信息包括与所述第一会话的DNN对应的第二特征索引列表集合和所述第二特征索引列表中的每个特征索引列表对应的业务标识；
    所述控制面网元向用户面网元发送所述第二信息。
  11. 根据权利要求10所述的通信方法，其特征在于，所述第一信息还包括所述第一特征索引列表集合中的每个特征索引列表对应的以下至少一种信息：网络切片类型、会话和业务连续性SSC模式、分组数据单元PDU会话类型；
    其中，所述控制面网元根据第一会话的DNN，从所述第一信息中查询得到第二信息，包括：
    所述控制面网元根据所述第一会话的DNN和所述第一会话的网络切片类型、SSC模式、PDU会话类型中的至少一种信息，从所述第一信息中查询得到所述第二信息。
  12. 一种通信方法，其特征在于，包括：
    控制面网元向数据库网元发送第一会话的数据网络名称DNN；
    所述控制面网元从数据库网元接收第二信息，所述第二信息包括第二特征索引列表集合和所述第二特征索引列表集合中的每个特征索引列表对应的业务标识，所述业务标识与所述DNN对应；
    所述控制面网元向用户面网元发送所述第二信息。
  13. 根据权利要求12所述的通信方法，其特征在于，所述控制面网元从所述数据库网元接收所述第二信息之前，所述通信方法还包括：
    所述控制面网元向所述数据库网元发送所述第一会话的以下至少一种信息：网络切片类型、会话和业务连续性SSC模式、分组数据单元PDU会话类型。
  14. 一种通信方法，其特征在于，包括：
    用户面网元从控制面网元接收第二信息，所述第二信息包括第二特征索引列表集合以及所述第二特征索引列表集合中的每个特征索引列表对应的业务标识；
    所述用户面网元接收第一会话的业务传输数据；
    所述用户面网元确定所述第二特征索引列表集合中不能根据所述业务传输数据得到特征值的特征索引列表对应的业务标识，得到第一业务标识集合；
    所述用户面网元向数据库网元发送第三信息，所述第三信息包括所述第一业务标识集合；
    所述用户面网元从所述数据库网元接收所述第一业务标识集合中每个业务标识对应的网络数据特征值列表。
  15. 根据权利要求14所述的通信方法，其特征在于，所述第三信息还包括以下至少一种信息：所述用户面处理接收所述第一会话的业务传输数据的时间、所述第一会话的会话标识、所述第一会话对应的终端的标识、所述第一会话对应的终端的互联网协议IP地址、所述第一会话对应的终端的端口、所述第一会话对应的业务服务器的IP地址、所述业务服务器中与所述第一会话对应的端口、所述第一会话对应的业务传输数据的业务传输协议。
  16. 一种数据库网元，其特征在于，包括：
    处理模块，用于获取训练数据，所述训练数据包括业务传输数据和网络数据；
    发送模块，用于向数据分析网元发送所述训练数据；
    接收模块，用于从所述数据分析网元接收第一信息，所述第一信息包括第一特征索引列表集合、所述第一特征索引列表集合中的每个特征索引列表对应的业务标识和所述业务标识对应的数据网络名称DNN。
  17. 根据权利要求16所述的数据库网元，其特征在于，所述第一信息还包括所述第一特征索引列表集合中的每个特征索引列表对应的以下至少一种信息：网络切片类型、会话和业务连续性SSC模式、分组数据单元PDU会话类型。
  18. 根据权利要求16或17所述的数据库网元，其特征在于，所述发送模块还用于：向控制面网元发送所述第一信息。
  19. 根据权利要求16或17所述的数据库网元，其特征在于，所述接收模块还用于：从控制面网元接收第一会话的DNN；
    所述处理模块还用于：根据所述第一会话的DNN，从所述第一信息中查询得到第二信息，所述第二信息包括与所述第一会话的DNN对应的第二特征索引列表集合以及所述第二特征索引列表集合中的每个特征索引列表对应的业务标识；
    所述发送模块还用于：向所述控制面网元发送所述第二信息。
  20. 根据权利要求19所述的数据库网元，其特征在于，所述接收模块还用于：从所述控制面网元接收所述第一会话的以下至少一种信息：网络切片类型、SSC模式、PDU会话类型；
    其中，所述处理模块具体用于：根据所述第一会话的DNN和所述第一会话的所述至少一种信息，从所述第一信息中查询得到所述第二信息。
  21. 根据权利要求16至20中任一项所述的数据库网元，其特征在于，所述接收模块还用于：从用户面网元接收第三信息，所述第三信息包括第一业务标识集合；
    所述处理模块还用于：从所述第一信息中，查询得到所述第一业务标识集合中的每个业务标识对应的特征索引列表；
    所述处理模块还用于：根据所述第一业务标识集合中的每个业务标识对应的特征索引列表，从网络数据中查询得到所述第一业务标识集合中每个业务标识对应的网络数据特征值列表；
    所述发送模块还用于：向所述用户面网元发送所述第一业务标识集合中每个业务标识对应的网络数据特征值列表。
  22. 根据权利要求21所述的数据库网元，其特征在于，所述第三信息还包括以下至少一种信息：所述用户面网元接收第一会话的业务传输数据的时间、所述第一会话的会话标识、所述第一会话对应的终端的标识、所述第一会话对应的终端的互联网协议IP地址、所述第一会话对应的终端的端口、所述第一会话对应的业务服务器的IP地址、所述业务服务器中与所述第一会话对应的端口、所述第一会话的业务传输数据的业务传输协议。
  23. 一种数据分析网元，其特征在于，包括：
    接收模块，用于从数据库网元接收训练数据，所述训练数据包括业务传输数据和网络数据；
    处理模块，用于根据所述训练数据确定第一信息，所述第一信息包括第一特征索引列表集合以及所述第一特征索引列表集合中的每个特征索引列表对应的业务标识和所述业务标识对应的数据网络名称DNN；
    发送模块，用于向所述数据库网元发送所述第一信息。
  24. 根据权利要求23所述的数据分析网元，其特征在于，所述第一信息还包括所述第一特征索引列表集合中的每个特征索引列表对应的以下至少一种信息：网络切片类型、会话和业务连续性SSC模式、分组数据单元PDU会话类型。
  25. 一种控制面网元，其特征在于，包括：
    接收模块，用于从数据库网元接收第一信息，所述第一信息包括第一特征索引列表集合以及所述第一特征索引列表集合中的每个特征索引列表对应的业务标识和所述业务标识对应的数据网络名称DNN；
    处理模块，用于根据第一会话的DNN，从所述第一信息中查询得到第二信息，所述第二信息包括与所述第一会话的DNN对应的第二特征索引列表集合和所述第二特征索引列表中的每个特征索引列表对应的业务标识；
    发送模块，用于向用户面网元发送所述第二信息。
  26. 根据权利要求25所述的控制面网元，其特征在于，所述第一信息还包括所述第一特征索引列表集合中的每个特征索引列表对应的以下至少一种信息：网络切片类型、会话和业务连续性SSC模式、分组数据单元PDU会话类型；
    其中，所述处理模块具体用于：根据所述第一会话的DNN和所述第一会话的网络切片类型、SSC模式、PDU会话类型中的至少一种信息，从所述第一信息中查询得到所述第二信息。
  27. 一种控制面网元，其特征在于，包括：
    发送模块，用于向数据库网元发送第一会话的数据网络名称DNN；
    接收模块，用于从数据库网元接收第二信息，所述第二信息包括第二特征索引列表集 合和所述第二特征索引列表集合中的每个特征索引列表对应的业务标识，所述业务标识与所述DNN对应；
    所述发送模块还用于向用户面网元发送所述第二信息。
  28. 根据权利要求27所述的控制面网元，其特征在于，发送模块还用于：向所述数据库网元发送所述第一会话的以下至少一种信息：网络切片类型、会话和业务连续性SSC模式、分组数据单元PDU会话类型。
  29. 一种用户面网元，其特征在于，包括：
    接收模块，用于从控制面网元接收第二信息，所述第二信息包括第二特征索引列表集合以及所述第二特征索引列表集合中的每个特征索引列表对应的业务标识；
    所述接收模块还用于接收第一会话的业务传输数据；
    处理模块，用于确定所述第二特征索引列表集合中不能根据所述业务传输数据得到特征值的特征索引列表对应的业务标识，得到第一业务标识集合；
    发送模块，用于向数据库网元发送第三信息，所述第三信息包括所述第一业务标识集合；
    所述接收模块还用于从所述数据库网元接收所述第一业务标识集合中每个业务标识对应的网络数据特征值列表。
  30. 根据权利要求29所述的用户面网元，其特征在于，所述第三信息还包括以下至少一种信息：所述用户面处理接收所述第一会话的业务传输数据的时间、所述第一会话的会话标识、所述第一会话对应的终端的标识、所述第一会话对应的终端的互联网协议IP地址、所述第一会话对应的终端的端口、所述第一会话对应的业务服务器的IP地址、所述业务服务器中与所述第一会话对应的端口、所述第一会话对应的业务传输数据的业务传输协议。
PCT/CN2018/107337 2017-09-30 2018-09-25 通信方法及其通信设备 Ceased WO2019062710A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP18863523.9A EP3683714B1 (en) 2017-09-30 2018-09-25 Communication method and communication device thereof
US16/824,859 US11451286B2 (en) 2017-09-30 2020-03-20 Communication method and communications device thereof

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710916010.3 2017-09-30
CN201710916010.3A CN110019511B (zh) 2017-09-30 2017-09-30 通信方法及其通信设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/824,859 Continuation US11451286B2 (en) 2017-09-30 2020-03-20 Communication method and communications device thereof

Publications (1)

Publication Number Publication Date
WO2019062710A1 true WO2019062710A1 (zh) 2019-04-04

Family

ID=65900648

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/107337 Ceased WO2019062710A1 (zh) 2017-09-30 2018-09-25 通信方法及其通信设备

Country Status (4)

Country Link
US (1) US11451286B2 (zh)
EP (1) EP3683714B1 (zh)
CN (1) CN110019511B (zh)
WO (1) WO2019062710A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109600790B (zh) * 2017-09-30 2021-09-14 华为技术有限公司 获取特征参数的方法和装置
CN113597021B (zh) 2020-04-30 2023-11-17 华为技术有限公司 一种通信方法、装置及系统
CN114826867B (zh) * 2021-01-28 2023-11-17 华为技术有限公司 处理数据的方法、装置、系统及存储介质
CN115188114B (zh) * 2022-07-01 2023-09-01 日立楼宇技术（广州）有限公司 一种门禁信息同步方法、装置、设备及存储介质
US12501355B2 (en) * 2023-11-10 2025-12-16 GM Global Technology Operations LLC Method and system for smart guided selection of networks

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102158345A (zh) * 2010-06-23 2011-08-17 青岛海信传媒网络技术有限公司 一种数据管理方法、装置和系统
CN105357739A (zh) * 2011-12-13 2016-02-24 华为技术有限公司 一种通信方法及设备
CN106792563A (zh) * 2015-11-23 2017-05-31 中兴通讯股份有限公司 一种多媒体广播多播业务处理方法及系统
CN106921507A (zh) * 2015-12-25 2017-07-04 株式会社日立制作所 在无线通信网络中对用户投诉进行预测的方法和装置

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101072116B (zh) * 2007-04-28 2011-07-20 华为技术有限公司 业务选择方法、装置、系统及客户端应用服务器
CN101605348B (zh) * 2008-11-24 2012-07-18 中国移动通信集团广东有限公司 一种数据业务模拟方法及应用系统
CN104349380B (zh) * 2013-08-08 2018-12-04 中兴通讯股份有限公司 信息交互、分流处理方法、装置、基站、rnc及终端
WO2015113291A1 (zh) 2014-01-29 2015-08-06 华为技术有限公司 无线网络数据处理装置和无线网络系统
CN105307058B (zh) * 2014-06-09 2019-06-18 中兴通讯股份有限公司 业务配置数据的处理方法及装置
US10880180B2 (en) * 2015-09-16 2020-12-29 Huawei Technologies Co., Ltd. Method and apparatus for data analytics management
CN107027134A (zh) * 2016-02-01 2017-08-08 上海无线通信研究中心 一种用户自定义的无线通信网络方法及系统
WO2018236164A1 (ko) * 2017-06-21 2018-12-27 엘지전자(주) 무선 통신 시스템에서 서비스 요청 절차 수행 방법 및 이를 위한 장치
US10779254B2 (en) * 2017-08-16 2020-09-15 Electronics And Telecommunications Research Institute Service request method for 5G local service

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102158345A (zh) * 2010-06-23 2011-08-17 青岛海信传媒网络技术有限公司 一种数据管理方法、装置和系统
CN105357739A (zh) * 2011-12-13 2016-02-24 华为技术有限公司 一种通信方法及设备
CN106792563A (zh) * 2015-11-23 2017-05-31 中兴通讯股份有限公司 一种多媒体广播多播业务处理方法及系统
CN106921507A (zh) * 2015-12-25 2017-07-04 株式会社日立制作所 在无线通信网络中对用户投诉进行预测的方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3683714A4

Also Published As

Publication number Publication date
EP3683714A1 (en) 2020-07-22
US20200220602A1 (en) 2020-07-09
EP3683714B1 (en) 2022-11-30
CN110019511B (zh) 2021-10-22
US11451286B2 (en) 2022-09-20
EP3683714A4 (en) 2020-10-14
CN110019511A (zh) 2019-07-16

Similar Documents

Publication Publication Date Title
CN109792598B (zh) 支持网络分片的漫游环境中用于终端附接和创建归属路由pdu会话的方法和设备
CN112672383B (zh) 通信方法和网络设备
EP3683714B1 (en) Communication method and communication device thereof
CN109600243B (zh) 数据分析方法和装置
CN111132271B (zh) 一种pdu会话的动态调整方法、装置
WO2019062498A1 (zh) 获取特征参数的方法和装置
WO2022033115A1 (zh) 一种通信方法和通信装置
CN109995836B (zh) 缓存决策方法及装置
CN108111320B (zh) 一种本地业务计费方法、服务器和计费网关
WO2019062496A1 (zh) 数据分析方法和数据分析装置
US12238154B2 (en) Multicast session establishment method and network device
WO2021135187A1 (zh) 一种切片控制方法及装置
CN117676916A (zh) 通信资源管理方法、装置、系统及存储介质
CN120812542A (zh) 感知数据的收集方法、装置、设备、系统及存储介质
EP3148255A1 (en) Network device and method for allocating access point names
CN116112945A (zh) 一种通信方法及装置
US10271218B2 (en) Enable access point availability prediction
WO2023206048A1 (zh) 数据处理方法及系统，ai管理装置及存储介质
CN119487879A (zh) 感知数据提供方法、装置、设备、存储介质及程序产品
WO2023098624A1 (zh) 通信方法、装置及可读存储介质
CN114785626B (zh) 数据管理的方法和装置
WO2020052463A1 (zh) 通信方法和网元
US20200177512A1 (en) Network architecture with control plane node
WO2026066338A1 (zh) 通信方法及装置
CN120835321A (zh) 数据处理方法、装置、设备及存储介质

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2018863523

Country of ref document: EP

Effective date: 20200319

NENP Non-entry into the national phase

Ref country code: DE