WO2021031607A1 - 一种风险控制方法、计算机设备及可读存储介质 - Google Patents

一种风险控制方法、计算机设备及可读存储介质 Download PDF

Info

Publication number
WO2021031607A1
WO2021031607A1 PCT/CN2020/087669 CN2020087669W WO2021031607A1 WO 2021031607 A1 WO2021031607 A1 WO 2021031607A1 CN 2020087669 W CN2020087669 W CN 2020087669W WO 2021031607 A1 WO2021031607 A1 WO 2021031607A1
Authority
WO
WIPO (PCT)
Prior art keywords
risk
score
risk score
behavior data
data
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/CN2020/087669
Other languages
English (en)
French (fr)
Inventor
马家忆
沈中皓
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.)
Shanghai Bilibili Technology Co Ltd
Original Assignee
Shanghai Bilibili Technology 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 Shanghai Bilibili Technology Co Ltd filed Critical Shanghai Bilibili Technology Co Ltd
Priority to US17/636,283 priority Critical patent/US12361357B2/en
Priority to EP20854478.3A priority patent/EP4020349A4/en
Publication of WO2021031607A1 publication Critical patent/WO2021031607A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • 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
    • G06F16/21—Design, administration or maintenance of databases
    • G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
    • 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
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2455—Query execution
    • 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
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2455—Query execution
    • G06F16/24552—Database cache management
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
    • H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
    • H04L63/1425—Traffic logging, e.g. anomaly detection
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
    • H04L63/1441—Countermeasures against malicious traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
    • H04L63/1441—Countermeasures against malicious traffic
    • H04L63/1483—Countermeasures against malicious traffic service impersonation, e.g. phishing, pharming or web spoofing

Definitions

  • This application relates to the field of computer technology, and in particular to a risk control method, computer equipment and readable storage medium.
  • videos are disseminated in diversified ways, such as live webcasts and short videos.
  • Take webcast as an example. It draws on and continues the advantages of the Internet. It uses the video method to conduct online live broadcast. It can publish product display, related conferences, online training and other content on the Internet on-site, using the intuitive, interactive, and interactive features of the Internet. Unrestricted geographical features can enhance the promotion effect of the event site.
  • Internet black industry refers to an industry that has a clear division of labor and closely connected interest groups formed through network technology that seeks illegal benefits by invading computer information systems and illegally stealing computer information system data including personal information. system.
  • black industry behavior is increasingly evolving to batch and automation, which poses new challenges to risk control.
  • general business platforms often carry out discounts or cash rebates for marketing purposes.
  • Black production is heard and large-scale arbitrage is called "wool" in the industry. The most common method is to register a large number of new users to receive the platform. Activity Award.
  • the risk control system usually uses the IP black and gray list to filter out known/suspected proxy IPs, and further, depict user portraits, judge abnormal requests based on the user's most frequently used IP, and adopt higher-strength authentication to distinguish black products behavior.
  • the risk control system of an Internet company is designed as a search system.
  • the inventor found that when the number of users reaches hundreds of millions and there are a lot of behavioral data, this kind of risk control system with search as the core is only available when requested. Calculate the risk score, and the risk score required in judging the degree of risk can only be responded after the calculation is completed. Therefore, the existing risk control system cannot respond quickly.
  • a risk control method, computer equipment and readable storage medium are now provided, which independently perform the two processes of calculating the score and judging the degree of risk, ensuring the high-speed response of the risk control service.
  • This application provides a risk control method, which includes a step of calculating a risk score and a step of judging the degree of risk, wherein:
  • the step of calculating the risk score includes performing calculation processing on the user's buried point data according to a preset risk scoring rule to obtain a risk score;
  • the step of judging the degree of risk includes receiving a business request from the user, selecting a corresponding risk assessment rule and a preset threshold according to the business request, and searching for the risk assessment rule corresponding to the score obtained in the risk score calculation step
  • the risk score is used as the evaluation score, and the evaluation score is compared with the threshold corresponding to the business request to obtain the risk evaluation result.
  • the present application also provides a computer device that includes a memory, a processor, and computer-readable instructions stored in the memory and capable of running on the processor, and the processor performs calculations when the computer-readable instructions are executed Risk scoring steps and steps to judge the degree of risk, including:
  • the step of calculating the risk score includes performing calculation processing on the user's buried point data according to a preset risk scoring rule to obtain a risk score;
  • the step of judging the degree of risk includes receiving a business request from the user, selecting a corresponding risk assessment rule and a preset threshold according to the business request, and searching for the risk assessment rule corresponding to the score obtained in the risk score calculation step
  • the risk score is used as the evaluation score, and the evaluation score is compared with the threshold corresponding to the business request to obtain the risk evaluation result.
  • This application also provides a computer-readable storage medium on which computer-readable instructions are stored, and when the computer-readable instructions are executed by a processor, the steps of calculating the risk score and determining the degree of risk are realized, wherein:
  • the step of calculating the risk score includes performing calculation processing on the user's buried point data according to a preset risk scoring rule to obtain a risk score;
  • the step of judging the degree of risk includes receiving a business request from the user, selecting a corresponding risk assessment rule and a preset threshold according to the business request, and searching for the risk assessment rule corresponding to the score obtained in the risk score calculation step
  • the risk score is used as the evaluation score, and the evaluation score is compared with the threshold corresponding to the business request to obtain the risk evaluation result.
  • This application also provides a risk control system, including a risk calculation module and a risk judgment module, wherein:
  • the risk calculation module is used to calculate and process the user's buried point data according to preset risk scoring rules to obtain a risk score
  • the risk judgment module is configured to receive the business request of the user and select the corresponding risk assessment rule and preset threshold according to the business request, and find the risk assessment rule in the risk score obtained in the step of calculating the risk score.
  • the corresponding risk score is used as the evaluation score, and the evaluation score is compared with the threshold corresponding to the business request to obtain the risk evaluation result.
  • the risk assessment rules and preset thresholds corresponding to the business request can be selected according to the business request, so as to realize the addition, deletion and combination of rules without delay, and achieve the ideal risk control effect.
  • the risk score data is transmitted through the message queue processing tool to prevent data loss.
  • the expiration time is set for the risk score data in the second database, and meaningless data can be deleted, thereby increasing storage space;
  • Figure 1 is a system framework diagram corresponding to the risk control method of this application.
  • Figure 2 is a schematic diagram of the two processes in the risk control method of this application being carried out independently.
  • Fig. 3 is a specific schematic diagram of Fig. 2.
  • Fig. 4 is a flowchart of the first embodiment of the application for calculating the risk score.
  • Fig. 5 is a flowchart of a second embodiment of the application for calculating risk scores.
  • Figure 6 is a flow chart of the application for judging the degree of risk.
  • Figure 7 is a block diagram of the risk control system of the application.
  • FIG. 8 is a schematic diagram of the hardware structure of the computer equipment of the risk control method of this application.
  • first, second, third, etc. may be used in this application to describe various information, the information should not be limited to these terms. These terms are only used to distinguish the same type of information independently from each other.
  • first information may also be referred to as second information, and similarly, the second information may also be referred to as first information.
  • word “if” as used herein can be interpreted as "when” or “when” or "in response to determination”.
  • the user participates in the live broadcast and lottery activities with the help of terminal devices A, B, C, D, and E.
  • the terminal devices A, B, C, D, and E share the user’s
  • the behavior data is transmitted to the server W, and the server W receives and processes the user's buried point data and calculates the risk score.
  • the user sends a lottery service request through the terminal devices A, B, C, D, and E, and performs risk assessment in combination with the risk score via the server W, and executes the corresponding risk control strategy.
  • Only one server W is given here.
  • the application scenario here may also include multiple servers communicating with each other.
  • the server W may be a cloud server or a local server.
  • a risk control method which includes a step of calculating a risk score and a step of judging the degree of risk, where:
  • the step of calculating the risk score includes performing calculation processing on the user's buried point data according to a preset risk scoring rule to obtain a risk score;
  • the step of judging the degree of risk includes receiving a business request from the user, selecting a corresponding risk assessment rule and a preset threshold according to the business request, and searching for the risk assessment rule corresponding to the score obtained in the risk score calculation step
  • the risk score is used as the evaluation score, and the evaluation score is compared with the threshold corresponding to the business request to obtain the risk evaluation result.
  • the two processes of calculating the risk score and judging the degree of risk are carried out independently, which ensures the high-speed response of the risk control service.
  • the server W calculates the points of the terminal equipment A, B, C, D, and E according to preset risk scoring rules to obtain the complete risk score data; when judging the degree of risk, the server W selects the risk assessment rule and preset threshold corresponding to the service request according to the service request of the terminal device A, finds the score corresponding to the risk assessment rule in the risk score obtained in the step of calculating the risk score, and The risk score and the threshold corresponding to the business request are evaluated and analyzed to achieve an ideal risk control effect.
  • the server W calculates the risk score on the buried point data of the terminal devices A, B, C, D, and E, and determines the degree of risk, as follows:
  • Room page data, barrage data, lottery data and other buried data user behavior buried in the server data, including barrage connection behavior, barrage sending behavior, access to room page behavior, follow behavior, gashapon activity behavior, and treasure box collection Behavior, purchase privilege behavior, lottery behavior, sign-in behavior, gift-giving behavior, recharge behavior.
  • Buried point data transmission company-level real-time data transmission middleware realizes large-scale data collection.
  • HDFS big data system placement the embedded point data is placed into the big data file system HDFS, and persistent storage provides calculation basis.
  • Offline calculation Take the data of placing orders as input, use the MapReduce computing framework to perform calculations such as cluster analysis on user behavior, and output the data in the form of user-rule-value.
  • Real-time calculation Taking the real-time stream of data as input, calculate the risk characteristics that users can expose in a short time.
  • the risk score is output to the Kafka data queue: the production user-rule-value is output to the Kafka data queue.
  • Live risk control system consumption risk score Live risk control data service, responsible for consuming the risk score of Kafka data queue.
  • the first database stores risk scores and synchronizes processing of blocked messages from the master station.
  • Subscription database changes production enters the data queue.
  • Second database After the risk control service is consumed, it is persistently stored in the second database (redis database), and all entries have a certain expiration time according to the strategy.
  • Risk control service Responsible for processing the request and returning the judgment result of risk control.
  • LRU algorithm cache is used to alleviate the problem of excessively high QPS of the redis database for service requests during peak periods and reduce by 96%.
  • Real-time risk assessment rule configuration According to the judgment result of the risk control system, user feedback and other information, use linear regression and other methods to formulate reasonable rule thresholds and rule combinations. ,
  • S120 Calculate a risk score based on the buried point data according to a preset risk scoring rule
  • S140 The converted risk score is transmitted to the storage module via the message queue processing tool
  • the storage module stores the risk score.
  • the buried point data of S110 collects the barrage connection behavior data of terminal devices A, B, C, D, and E through the server, barrage sending behavior data, room page behavior data, attention behavior data, At least one of gashapon activity data, treasure box collection behavior data, privilege purchase behavior data, redemption behavior data, lottery behavior data, sign-in behavior data, gift giving behavior data, or recharge behavior data.
  • the gashapon event including the fantasy gashapon machine, will only appear during the event. If the cumulative use value reaches the preset value (the value depends on the event rules), you can get 1 fantasy gashapon coin.
  • Use Fantasy Gacha Coins to participate in the lucky draw of the Fantasy Gacha Machine.
  • About Fantasy Gacha Coin You can get a Fantasy Gacha Coin by giving away celebration fireworks, goldfish fat times, and a small TV for every 10 points of faith generated. After the event ends, unused Fantasy Gacha Coins will be exchanged for normal Gacha Coins at a ratio of 10 to 1. If there are less than 10 Fantasy Gacha Coins, they will not be exchanged.
  • the server W places the collected embedded point data to the big data file system HDFS, and persistent storage provides a calculation basis, and the data placed on the disk is used as the basis for the calculation of S120.
  • the calculation type of S120 includes offline calculation and/or real-time calculation, and the corresponding calculation type is selected according to different application scenarios. Multiple calculations can exist at the same time, or one of the calculation methods can be selected as needed, and the buried point data used for calculation in real-time online calculations is usually generated by users in a relatively short period of time (for example, 30 seconds, the length of time can be customized) Behavioral data, while the buried point data used for calculation in offline calculations is usually behavioral data generated by users in a relatively long period of time (for example, 24 hours, the length of time can be self-defined).
  • Historical data can be calculated according to needs, such as calculating the user's behavior statistics in the past day, the past week, and the past three months to improve accuracy and avoid misjudgments;
  • converting the risk score into a standard data format in S130 is to arrange the user account information, the risk scoring rule information, and the risk score information of the user account in a predetermined order.
  • the message queue processing tool of S140 is a kafka tool, and data is transmitted through the kafka tool to prevent data loss.
  • Figure 5 is a second embodiment of the process of calculating the risk score. The specific steps include:
  • S120 Calculate a risk score based on the buried point data according to a preset risk scoring rule
  • S140 The converted risk score is transmitted to the storage module via the message queue processing tool
  • the corresponding time limit according to the relationship between the generation time of the user behavior and the judgment result time. For example, it is necessary to judge the user behavior during the activity process. Assuming that the activity process lasts for 4 hours, the buried point data earlier than the activity start is expired data and does not need to be transmitted to The second database is no longer used to calculate the risk score; the second database (such as the redis database) sets the expiration time for the score data, which can delete the meaningless data, thereby increasing the storage space;
  • the method further includes:
  • S160 Cache the content of the second database through the LRU algorithm; use the cache to prevent system flushing, where the full name of LRU is Least recently used, and the Chinese interpretation of LRU is the least recently used.
  • the calculation type in S120 includes offline calculation and/or real-time calculation, and the corresponding calculation type is selected according to different application scenarios.
  • the query rate per second of the second database can reach 600K during the peak period, so a caching strategy is adopted. , The query rate per second request content in the second database exceeding the query rate per second is written into the local storage unit, the query rate per second in the second database is greatly reduced to 2K, and the second database query per second in the peak period is alleviated The rate is too high.
  • the steps of judging the degree of risk include:
  • S220 According to the business request, select a risk assessment rule and a preset threshold corresponding to the business request;
  • S230 Find the risk score corresponding to the risk assessment rule in the risk score obtained in the step of calculating the risk score as the assessment score;
  • S240 Determine whether the evaluation score exceeds a preset threshold; if so, execute S250; if not, execute S260;
  • the risk assessment rules in S220 are combined and matched according to business requests, and different business requests have different combinations.
  • the service rejection request in S250 may be a refusal to browse webpages, a refusal to enter the live broadcast room, and a lottery is not allowed, and the service pass request in S260 may be permission to browse webpages, allow access to the live broadcast room, and allow participation in a lottery.
  • the assessment results can also be stored for later reference or processing.
  • the risk assessment rules can be different logical combinations, and the first embodiment of the risk assessment rule and the second embodiment of the risk assessment rule will be used as examples to illustrate.
  • Risk assessment rule embodiment 1 Risk assessment rules are logic and rules
  • the preset risk scoring rules in S120 can be set according to the requirements of risk monitoring. Assuming that there are 50 preset risk scoring rules for buried point data, which are the first risk scoring rule, the second risk scoring rule, the third risk scoring rule, and the fiftieth risk scoring rule, When calculating the risk score for the first user account, the first risk score under the first risk scoring rule corresponding to the first user account is obtained, and the first user account corresponds to the second risk score under the second risk scoring rule. By analogy, the fiftieth user account corresponds to the fiftieth risk score under the fiftieth risk scoring rules.
  • the risk score will be calculated according to the preset risk scoring rules.
  • the user account will be scored in the preset risk score
  • the risk score under the rule is a non-zero value. For example, for an abnormality, the user account’s risk score under the preset risk scoring rule is 1 point. If the abnormal behavior occurs more often, the user account will be scored in the preset risk score The higher the cumulative risk score under the rule is, for example, if there are 5 exceptions, the cumulative risk score of the user account under the preset risk scoring rule is 5 points.
  • the risk score of the user account under the preset risk scoring rules is 0 points. If the buried data is not collected, the user account is in the preset risk calculation. The risk score under the scoring rules is 0.
  • the risk control system receives the lottery business request of the first user ID1, and the risk assessment rules for the configuration and lottery business request are the first risk scoring rule, the second risk scoring rule, and the fifth risk scoring rule.
  • Logical combination of rules, read ID1-first risk scoring rule -3 points, read ID1-second risk scoring rule -10 points, read ID1-fifth risk scoring rule -100 points, then calculate the total The risk score is 3+10+100 113, and the threshold corresponding to the lottery service request is 100. If the threshold is exceeded, the lottery service request of the user ID1 is rejected.
  • Risk assessment rule embodiment two, risk assessment rule is logic or rule
  • the risk control system receives the lottery business request of the first user ID1, and the risk assessment rules for the configuration and lottery business request are the first risk scoring rule, the second risk scoring rule, and the fifth risk scoring rule.
  • This application provides a risk control system 1, which includes:
  • the risk calculation module 100 is used to calculate and process the user's buried point data according to preset risk scoring rules to obtain a risk score;
  • the risk judgment module 200 is configured to receive the business request of the user and select the corresponding risk assessment rule and preset threshold according to the business request, and find the risk assessment rule corresponding to the risk score obtained in the step of calculating the risk score The risk score of is used as the evaluation score, and the evaluation score is compared with the threshold corresponding to the business request to obtain the risk evaluation result;
  • the risk calculation module 100 and the risk judgment module 200 operate independently.
  • the risk calculation module 100 includes:
  • the collection module 101 is used to collect user's buried point data
  • the calculation module 102 is configured to calculate the risk score according to the preset risk scoring rules for the buried point data
  • the conversion module 103 is configured to convert the risk score into a standard data format
  • the transmission module 104 is configured to transmit the converted risk score to the storage module via the message queue processing tool;
  • the storage module 105 is used to store the risk score.
  • the buried point data includes barrage connection behavior data, barrage sending behavior data, room page access behavior data, attention behavior data, gashapon activity data, treasure box collection behavior data, privilege purchase behavior data, At least one of redemption behavior data, lottery behavior data, sign-in behavior data, gift-giving behavior data, or recharge behavior data.
  • the conversion module 103 converts the risk score into a standard data format by arranging user account information, risk scoring rule information, and risk score information in a predetermined order.
  • the storage module 105 first stores the risk score in the first database; then transmits the risk score to the second database, and the second database sets an expiration date for the risk score.
  • the risk control system includes a buffer module 106 for caching the content of the second database through the LRU algorithm.
  • the calculation types performed by the calculation module include offline calculations and/or real-time calculations, and the corresponding calculation types are selected according to different application scenarios.
  • the risk judgment module 200 includes:
  • the receiving module 201 is used to obtain the service request of the user
  • the configuration module 202 is configured to select a risk assessment rule and a preset threshold corresponding to the business request according to the business request;
  • the reading module 203 is configured to find the risk score corresponding to the risk assessment rule in the storage module 105 as the assessment score;
  • the comparison module 204 is configured to determine whether the evaluation score exceeds a preset threshold
  • the control module 205 is configured to reject the service request or pass the service request according to the judgment result.
  • this application also provides a computer device 2, and the computer device 2 includes:
  • the memory 21 is used to store executable program codes
  • the processor 22 is configured to call the executable program code in the memory 21, and the execution steps include the above-mentioned risk control method.
  • One processor 22 is taken as an example in FIG. 8.
  • the memory 21 can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions corresponding to the risk control method in the embodiments of the present application /Module.
  • the processor 22 executes various functional applications and data processing of the computer device 2 by running non-volatile software programs, instructions, and modules stored in the memory 21, that is, implements the risk control method of the foregoing method embodiment.
  • the memory 21 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application program required by at least one function; the storage data area may store data of a user's embedded points in the computer device 2.
  • the memory 21 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices.
  • the memory 21 may optionally include a memory 21 remotely provided with respect to the processor 22, and these remote memories 21 may be connected to the risk control system 1 via a network. Examples of the aforementioned networks include but are not limited to the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
  • the one or more modules are stored in the memory 21, and when executed by the one or more processors 22, the risk control method in any of the foregoing method embodiments is executed, for example, the above-described FIG. 4- Figure 6 program.
  • the computer device 2 of the embodiment of the present application exists in various forms, including but not limited to:
  • Mobile communication equipment This type of equipment is characterized by mobile communication functions, and its main goal is to provide voice and data communications.
  • Such terminals include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones.
  • Ultra-mobile personal computer equipment This type of equipment belongs to the category of personal computers, has calculation and processing functions, and generally also has mobile Internet features.
  • Such terminals include: PDA, MID and UMPC devices, such as iPad.
  • Portable entertainment equipment This type of equipment can display and play multimedia content.
  • Such devices include: audio, video players (such as iPod), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.
  • Server A device that provides computing services.
  • the structure of a server includes a processor, hard disk, memory, system bus, etc.
  • the server is similar to a general-purpose computer architecture, but because it needs to provide highly reliable services, it is , Reliability, security, scalability, and manageability.
  • Another embodiment of the present application further provides a non-volatile computer-readable storage medium, the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more processors, such as One processor 22 in FIG. 8 may enable the above-mentioned one or more processors 22 to execute the risk control method in any of the above-mentioned method embodiments, for example, to execute the programs in FIGS. 4 to 6 described above.
  • the device embodiments described above are merely illustrative.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place. , Or it can be distributed to at least two network units. Some or all of the modules may be selected according to actual needs to achieve the objectives of the solutions of the embodiments of the present application. Those of ordinary skill in the art can understand and implement it without creative work.
  • each implementation manner can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware.
  • Those of ordinary skill in the art can understand that all or part of the processes in the methods of the foregoing embodiments can be implemented by instructing relevant hardware through computer-readable instructions.
  • the programs can be stored in a computer-readable storage medium.
  • the step of calculating the risk score includes calculating the user's buried point data according to preset risk scoring rules to obtain the risk score;
  • the step of judging the degree of risk includes receiving a business request from the user and selecting a corresponding risk assessment rule and a preset threshold according to the business request, and searching for the risk score corresponding to the risk assessment rule from the scores obtained in the risk score calculation step As the evaluation score, the evaluation score is compared with the threshold corresponding to the business request to obtain the risk evaluation result.
  • the storage medium can be a magnetic disk, an optical disc, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Quality & Reliability (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Tourism & Hospitality (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Computer Hardware Design (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Computational Linguistics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种风险控制方法、计算机设备及可读存储介质，所述方法包括计算风险得分步骤与判断风险程度步骤，其中：所述计算风险得分步骤包括依据预设风险计分规则对用户的埋点数据进行计算处理，以获取风险得分；所述判断风险程度步骤包括接收所述用户的业务请求并根据所述业务请求选择对应的风险评估规则与预设阈值，在所述计算风险得分步骤获取的得分中寻找所述风险评估规则对应的风险得分作为评估得分，并将所述评估得分与所述业务请求对应的阈值进行比较，获取风险评估结果。将计算风险得分与判断风险程度的两个过程独立进行，保证了风控服务响应的高速。

Description

[根据细则91更正 19.05.2020]　一种风险控制方法、计算机设备及可读存储介质
本申请要求于2019年08月22日提交中国专利局、申请号为201910780554.0、发明名称为“一种风险控制方法、计算机设备及可读存储介”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
本申请涉及计算机技术领域，尤其涉及一种风险控制方法、计算机设备及可读存储介质。
背景技术
随着互联网技术的发展，视频以多样化的方式进行传播，例如，网络直播、短视频等。以网络直播为例，其吸取和延续了互联网的优势，利用视讯方式进行网上现场直播，可以将产品展示、相关会议、在线培训等内容现场发布到互联网上，利用互联网的直观、交互性强、地域不受限制等特点，能够加强活动现场的推广效果。
“网络黑产”简称黑产，是指通过网络技术形成的分工明确、衔接密切的利益团体，通过入侵计算机信息系统、非法窃取包括个人信息在内的计算机信息系统数据等，谋取非法利益的产业体系。黑产为了扩大获利面，总会尽可能广撒网，因此黑产行为越来越多的向批量化和自动化演进，这就向风控提出了新的挑战。比如，一般业务平台为了营销，经常会开展优惠或者返现等活动，黑产闻风而至，大规模套利，业内称之为“薅羊毛”，最常见的手段就是大量注册新用户领取平台的活动奖励。
风控系统通常使用IP黑灰名单，过滤掉已知/嫌疑的代理IP，进一步的，描绘用户画像，根据用户最常使用的IP判断异常请求，并采取更高强度的身份验证以分辨黑产行为。
互联网公司的风控系统，被设计为一种搜索系统，发明人发现，当用户量达到数亿级别，行为数据也很多的时候，这种以搜索为核心的风控系统，在请求时才会计算风险得分，判断风险程度中所需的风险得分需经计算完成后才能响应，因此，现有的风控系统无法快速响应。
发明内容
针对的问题，现提供一种风险控制方法、计算机设备及可读存储介质，其将计算得分与判断风险程度的两个过程独立进行，保证了风控服务响应的高速。
本申请提供一种风险控制方法，其包括计算风险得分步骤与判断风险程度步骤，其中：
所述计算风险得分步骤包括依据预设风险计分规则对用户的埋点数据进行计算处理，以获取风险得分；
所述判断风险程度步骤包括接收所述用户的业务请求并根据所述业务请求选择对应的风险评估规则与预设阈值，在所述计算风险得分步骤获取的得分中寻找所述风险评估规则对应的风险得分作为评估得分，并将所述评估得分与所述业务请求对应的阈值进行比较，获取风险评估结果。
本申请还提供一种计算机设备，所述计算机设备包括存储器、处理器以及存储在存储器上并可在处理器上运行的计算机可读指令，所述处理器执行所述计算机可读指令时实现计算风险得分步骤与判断风险程度步骤，其中：
所述计算风险得分步骤包括依据预设风险计分规则对用户的埋点数据进行计算处理，以获取风险得分；
所述判断风险程度步骤包括接收所述用户的业务请求并根据所述业务请求选择对应的风险评估规则与预设阈值，在所述计算风险得分步骤获取的得分中寻找所述风险评估规则对应的风险得分作为评估得分，并将所述评估得分与所述业务请求对应的阈值进行比较，获取风险评估结果。
本申请还提供一种计算机可读存储介质，其上存储有计算机可读指令，所述计算机可读指令被处理器执行时实现计算风险得分步骤与判断风险程度步骤，其中：
所述计算风险得分步骤包括依据预设风险计分规则对用户的埋点数据进行计算处理，以获取风险得分；
所述判断风险程度步骤包括接收所述用户的业务请求并根据所述业务请求选择对应的风险评估规则与预设阈值，在所述计算风险得分步骤获取的得分中寻找所述风险评估规则对应的风险得分作为评估得分，并将所述评估得分与所述业务请求对应的阈值进行比较，获取风险评估结果。
本申请还提供一种风险控制系统，包括风险计算模块和风险判断模块，其中：
所述风险计算模块，用于依据预设风险计分规则对用户的埋点数据进行计算处理，以获取风险得分；
所述风险判断模块，用于接收所述用户的业务请求并根据所述业务请求选择对应的风险评估规则与预设阈值，在所述计算风险得分步骤获取的风险得分中寻找所述风险评估规则对应的风险得分作为评估得分，并将所述评估得分与所述业务请求对应的阈值进行比较，获取风险评估结果。
上述技术方案的有益效果：
1、本申请将计算风险得分与判断风险程度的两个过程独立进行，保证了风控服务响应的高速。
2、可以根据业务请求选择与所述业务请求相对应的风险评估规则与预设阈值，实现无延迟的规则的增删和组合，达到理想的风控效果。
3、通过消息队列处理工具传输风险得分的数据，防止数据丢失。
4、第二数据库中对于风险得分的数据进行过期时间的设置，可删除没有意义的数据，从而增加存储空间；
5、将第二数据库中风险得分的数据进行缓存，防止刷挂系统。
附图说明
图1为本申请风险控制方法所对应的系统框架图。
图2为本申请风险控制方法中两个处理过程独立进行的示意图。
图3为图2的具体示意图。
图4为本申请计算风险得分的第一实施例的流程图。
图5为本申请计算风险得分的第二实施例的流程图。
图6为本申请判断风险程度的流程图。
图7为本申请风险控制系统的模块图。
图8为本申请风险控制方法的计算机设备的硬件结构示意图。
具体实施方式
以下结合附图与具体实施例进一步阐述本申请的优点。
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本申请相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本申请的一些方面相一致的装置和方法的例子。
在本申请使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本申请。在本申请和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。还应当理解，本文中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。
应当理解，尽管在本申请可能采用术语第一、第二、第三等来描述各种信息，但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区独立进行。例如，在不脱离本申请范围的情况下，第一信息也可以被称为第二信息，类似地，第二信息也可以被称为第一信息。取决于语境，如在此所使用的词语“如果”可以被解释成为“在……时”或“当……时”或“响应于确定”。
在本申请的描述中，需要理解的是，步骤前的数字标号并不标识执行步骤的前后顺序，仅用于方便描述本申请及区别每一步骤，因此不能理解为对本申请的限制。
请参考图1所示，本申请实施例中，直播过程中，用户借助终端设备A、B、C、D、E参与直播及抽奖活动，终端设备A、B、C、D、E将用户的行为数据传送至服务器W，由服务器W接收与处理用户的埋点数据并计算风险得分。用户通过终端设备A、B、C、D、E发 出抽奖业务请求，经由服务器W结合风险得分进行风险评估，执行相应的风险控制策略。此处只给出一个服务器W，在实际应用时，此处的应用场景还可以包括多台相互通讯的服务器。服务器W可以是云端服务器，还可以是本地服务器。
请参阅图2所示，一种风险控制方法，其包括计算风险得分步骤与判断风险程度步骤，其中：
所述计算风险得分步骤包括依据预设风险计分规则对用户的埋点数据进行计算处理，以获取风险得分；
所述判断风险程度步骤包括接收所述用户的业务请求并根据所述业务请求选择对应的风险评估规则与预设阈值，在所述计算风险得分步骤获取的得分中寻找所述风险评估规则对应的风险得分作为评估得分，并将所述评估得分与所述业务请求对应的阈值进行比较，获取风险评估结果。
本申请将计算风险得分与判断风险程度的两个过程独立进行，保证了风控服务响应的高速。计算风险得分时，服务器W将终端设备A、B、C、D、E的埋点数据按照预设风险计分规则进行分别计算得分，以取得完整的风险得分的数据；判断风险程度时，服务器W根据终端设备A的业务请求选择与所述业务请求相对应的风险评估规则与预设阈值，在所述计算风险得分步骤获取的风险得分中寻找与所述风险评估规则对应的得分，并将所述风险得分与所述业务请求对应的阈值加以评估分析，达到理想的风控效果。
请参阅图3所示，服务器W对终端设备A、B、C、D、E的埋点数据计算风险得分，并判断风险程度，具体如下所述：
房间页数据、弹幕数据、抽奖数据等埋点数据：用户行为在服务器的埋点数据，包括弹幕连接行为、弹幕发送行为、访问房间页行为、关注行为、扭蛋活动行为、领取宝箱行为、购买特权行为、抽奖行为，签到行为，送礼行为，充值行为。
埋点数据传输：公司级的实时数据传输中间件，实现了数据的大规模收集。
HDFS大数据系统落盘：埋点数据落盘到大数据文件系统HDFS，持久存储提供计算依据。
离线计算：以落盘的数据为输入，对用户行为利用MapReduce计算框架进行聚类分析等计算，得到的数据以用户-规则-数值的形式输出。
统计计算：以落盘的数据为输入，对用户行为进行相对简单的统计分析计算。
实时计算：以数据的实时流为输入，对用户短时间内就可以暴露出的风险特征进行计算。
风险得分输出到kafka数据队列：生产用户-规则-数值形式的输出到Kafka数据队列。
直播风控系统消费风险得分：直播风控数据服务，负责消费Kafka数据队列的风险得分。
第一数据库：第一数据库存储风险得分，以及对主站封禁消息的同步处理。
订阅数据库变更：生产进入数据队列中。
第二数据库：经过风控服务消费后，持久化存储在第二数据库(redis数据库)中，所有条目根据策略有一定的过期时间。
风控服务：负责处理请求并返回风控的判定结果。
缓存：通过LRU算法缓存，缓解高峰时期服务请求redis数据库的QPS过高的问题，降低96％。
实时风险评估规则配置：根据风控系统的判定结果，用户反馈等多方面信息，利用线性回归等方法，制定合理的规则阈值和规则组合。、
请参阅图4所示，图4为计算风险得分的处理过程的第一实施例中，具体步骤包括：
S110：采集用户的埋点数据；
S120：将所述埋点数据根据预设风险计分规则计算风险得分；
S130：将所述风险得分转换成标准数据格式；
S140：转换后的风险得分经消息队列处理工具传输至存储模块；
S150：存储模块存储所述风险得分。
于本实施例中，所述S110的埋点数据通过服务器采集终端设备A、B、C、D、E的弹幕连接行为数据、弹幕发送行为数据、访问房间页行为数据、关注行为数据、扭蛋活动行为数据、领取宝箱行为数据、购买特权行为数据、兑换行为数据、抽奖行为数据、签到行为数据、送礼行为数据或充值行为数据中的至少一种。
扭蛋活动包括梦幻扭蛋机仅在活动期间会出现，使用价值累计达到预设值(数值视活动规则而定)的金瓜子礼物，就可以获得1枚梦幻扭蛋币。使用梦幻扭蛋币，就可以参与梦幻扭蛋机的抽奖。关于梦幻扭蛋币：通过赠送庆典烟火、金鱼胖次、小电视，每产生10点信仰值，可以获得一枚梦幻扭蛋币。活动结束后，未使用的梦幻扭蛋币将以10比1的比例兑换为普通扭蛋币，当梦幻扭蛋币不足10个的情况下，不会兑换。
上述举例仅作为说明，在实际操作时，并不对兑换行为数据做任何限定。
于S110与S120之间，还包括服务器W将采集到的埋点数据落盘到大数据文件系统HDFS，持久存储提供计算依据，且以落盘的数据作为S120计算的依据。
于本实施例中，所述S120的计算类型包括离线计算和/或实时计算，根据不同的应用场景选择相应的计算类型。多种计算可以同时存在，也可以根据需要选择其一计算方式进行，且实时在线计算中用于计算的埋点数据通常为较短时间内(例如30秒，时间长短可自行定义)用户产生的行为数据，而离线计算中用于计算的埋点数据通常为较长时间内(例如24小时，时间长短可自行定义)用户产生的行为数据。
离线计算的好处：
a.数据量丰富，对于用户行为的判定会更加精准；
b.将计算和决策隔离开，摆脱了实时性的压力；
c.可以根据需要计算历史数据，例如计算该用户近一天，近一周，近三个月的行为统计 规律，提升精度，避免误判；
实时计算的好处：在有些业务场景，黑产的行为是暂时性的，从注册账号，到在网站产生行为，到丢弃账号，仅仅需要二十分钟，就可以达到黑产的目的，这样的情况下，离线计算就毫无意义，实时计算通过打通数据通路，利用流式处理系统(如Spark Streaming)，根据特定的黑产特征，短时间聚合统计一定维度的数据，并作出相应的判定。
于本实施例中，所述S130中将风险得分转换成标准数据格式是将用户账户信息，风险计分规则信息与风险得分信息用户账户按照预定顺序排列。
于本实施例中，所述S140的消息队列处理工具为kafka工具，通过kafka工具传输数据，防止数据丢失。
请参阅图5所示，图5为计算风险得分的处理过程的第二实施例中，具体步骤包括：
S110：采集用户的埋点数据；
S120：将所述埋点数据根据预设风险计分规则计算风险得分；
S130：将所述风险得分转换成标准数据格式；
S140：转换后的风险得分经消息队列处理工具传输至存储模块；
S151：将所述风险得分存储至第一数据库；
S152：将所述风险得分传输至第二数据库，且所述第二数据库对所述风险得分设置了过期期限，
根据用户行为的产生时间与判断结果时间的关系设置相应的期限，例如需对活动过程的用户行为进行判断，假设活动过程持续4小时，早于活动开始的埋点数据为过期数据，不用传输至第二数据库，也就不再用于计算风险得分；第二数据库(例如redis数据库)中对于得分数据进行过期时间的设置，可删除没有意义的数据，从而增加存储空间；
在所述第一数据库将所述风险得分传输至所述第二数据库之后，还包括：
S160：将第二数据库的内容通过LRU算法进行缓存；通过缓存以防止刷挂系统，其中，LRU的全称为Least recently used，LRU的中文解释为最近最少使用。
于本实施例中，S120中的计算类型包括离线计算和/或实时计算，根据不同的应用场景选择相应的计算类型。
在黑产的实践中发现，一旦产生大量请求，则会刷挂(超时)风控服务，这种僵持状况下使得第二数据库的每秒查询率在高峰期能达600K，故而采取缓存的策略，将第二数据库中的超出每秒查询率的每秒查询率请求内容写入本地存储单元，将第二数据库中的每秒查询率大幅降低到2K，缓解高峰时期第二数据库的每秒查询率过高的问题。
请参阅图6所示，所述判断风险程度的步骤包括：
S210：获取用户的业务请求；
S220：根据所述业务请求，选择与所述业务请求相对应的风险评估规则与预设阈值；
S230：在所述计算风险得分步骤获取的风险得分中寻找所述风险评估规则对应的风险 得分作为评估得分；
S240：判断所述评估得分是否超出预设阈值；若是，则执行S250；若否，则执行S260；
S250：拒绝业务请求；
S260：通过业务请求。
无论是离线计算，还是实时计算，都是通过配置风险评估规则，并且在风险评估下的风险得分达到阈值之后，才会对用户账户产生封禁的判定，因此，风险评估规则的组合搭配和阈值的高低决定了风控系统拦截的精确率和召回率；风险评估规则的实时配置，成为了风控灵活的关键。于本实施例中，S220中的风险评估规则根据业务请求进行组合搭配，不同的业务请求会有不同的组合。
于本实施例中，S250中的拒绝业务请求可为拒绝浏览网页、拒绝进入直播间、不允许参加抽奖等，而S260中的通过业务请求可为允许浏览网页、允许进入直播间、允许参加抽奖等，此外，在执行风险评估结果时，也可以将评估结果进行存储，以便以后查阅或处理。
风险评估规则可为不同的逻辑组合，下面通过风险评估规则实施例一和风险评估规则实施例二分别举例说明。
风险评估规则实施例一、风险评估规则为逻辑和规则
S120中的预设风险计分规则可根据风险监控的要求设定。假设，对于埋点数据的预设风险计分规则共有50项，分别为第一风险计分规则、第二风险计分规则、第三风险计分规则、……第五十风险计分规则，在给第一用户帐户计算风险得分时，会分别取得第一用户帐户对应第一风险计分规则下的第一风险得分，第一用户帐户对应第二风险计分规则下的第二风险得分，以此类推，第五十用户帐户对应第五十风险计分规则下的第五十风险得分。
采集到埋点数据，会根据预设风险计分规则计算风险得分，在当前计分周期内，埋点数据在预设风险计分规则下判断为异常行为，则用户账户在预设风险计分规则下的风险得分为非零数值，例如，一次异常，用户账户在预设风险计分规则下的风险得分为1分，如果异常行为出现的次数越多，则用户账户在预设风险计分规则下的累计的风险得分就越高，例如，5次异常，则用户账户在预设风险计分规则下的累计风险得分为5分。而埋点数据在预设风险计分规则下判断为正常行为，则用户账户在预设风险计分规则下的风险得分为0分，未采集到埋点数据，则用户账户在预设风险计分规则下的风险得分为0。
在当前计分周期内，风险控制系统接收到第一用户ID1的抽奖业务请求，配置与抽奖业务请求的风险评估规则为第一风险计分规则、第二风险计分规则、第五风险计分规则的逻辑组合，读取ID1-第一风险计分规则-3分，读取ID1-第二风险计分规则-10分，读取ID1-第五风险计分规则-100分，则计算总风险得分3+10+100＝113，对应抽奖业务请求所设有阈值为100，超出阈值，则拒绝用户ID1的抽奖业务请求。
风险评估规则实施例二、风险评估规则为逻辑或规则
在当前计分周期内，风险控制系统接收到第一用户ID1的抽奖业务请求，配置与抽奖业 务请求的风险评估规则为第一风险计分规则、第二风险计分规则、第五风险计分规则的逻辑组合，读取ID1-第一风险计分规则-3分，读取ID1-第二风险计分规则-10分，读取ID1-第五风险计分规则-100分，第一阈值为20，第二阈值为30，第五阈值为50，则ID1-第一风险计分规则-3分＜20(第一阈值)，ID1-第二风险计分规则-10＜30(第二阈值)，ID1-第五风险计分规则-100分＞50分(第五阈值)，超出阈值，则拒绝用户ID1的抽奖业务请求。
请参阅图7所示，本申请提供一种风险控制系统1，其包括：
风险计算模块100，用于依据预设风险计分规则对用户的埋点数据进行计算处理，以获取风险得分；
风险判断模块200，用于接收所述用户的业务请求并根据所述业务请求选择对应的风险评估规则与预设阈值，在所述计算风险得分步骤获取的风险得分中寻找所述风险评估规则对应的风险得分作为评估得分，并将所述评估得分与所述业务请求对应的阈值进行比较，获取风险评估结果；
风险计算模块100与风险判断模块200独立运行。
于本实施例中，所述风险计算模块100包括：
采集模块101，用于采集用户的埋点数据；
计算模块102，用于将所述埋点数据根据预设风险计分规则计算风险得分；
转换模块103，用于将所述风险得分转换成标准数据格式；
传输模块104，用于将转换后的风险得分经消息队列处理工具传输至存储模块；
存储模块105，用于存储所述风险得分。
于本实施例中，所述埋点数据包括弹幕连接行为数据、弹幕发送行为数据、访问房间页行为数据、关注行为数据、扭蛋活动行为数据、领取宝箱行为数据、购买特权行为数据、兑换行为数据、抽奖行为数据、签到行为数据、送礼行为数据或充值行为数据中的至少一种。
于本实施例中，转换模块103是将风险得分转换成标准数据格式是将用户账户信息、风险计分规则信息与风险得分信息按照预定顺序排列。
于本实施例中，存储模块105先将所述风险得分存储至第一数据库；再将所述风险得分传输至第二数据库，且所述第二数据库对所述风险得分设置了过期期限。
于本实施例中，风险控制系统包括缓冲模块106，用于将第二数据库的内容通过LRU算法进行缓存。
于本实施例中，计算模块执行的计算类型包括离线计算和/或实时计算，根据不同的应用场景选择相应的计算类型。
风险判断模块200包括：
接收模块201，用于获取用户的业务请求；
配置模块202，用于根据所述业务请求，选择与所述业务请求相对应的风险评估规则与 预设阈值；
读取模块203，用于在存储模块105中寻找所述风险评估规则对应的风险得分作为评估得分；
比较模块204，用于判断所述评估得分是否超出预设阈值；
控制模块205，用于根据判断结果拒绝业务请求或通过业务请求。
请参阅图8所示，本申请还提供一种计算机设备2，所述计算机设备2包括：
存储器21，用于存储可执行程序代码；以及
处理器22，用于调用所述存储器21中的所述可执行程序代码，执行步骤包括上述的风险控制方法。
图8中以一个处理器22为例。
存储器21作为一种非易失性计算机可读存储介质，可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块，如本申请实施例中的风险控制方法对应的程序指令/模块。处理器22通过运行存储在存储器21中的非易失性软件程序、指令以及模块，从而执行计算机设备2的各种功能应用以及数据处理，即实现上述方法实施例风险控制方法。
存储器21可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储用户在计算机设备2的埋点数据。此外，存储器21可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实施例中，存储器21可选包括相对于处理器22远程设置的存储器21，这些远程存储器21可以通过网络连接至风险控制系统1。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
所述一个或者多个模块存储在所述存储器21中，当被所述一个或者多个处理器22执行时，执行上述任意方法实施例中的风险控制方法，例如，执行以上描述的图4-图6的程序。
上述产品可执行本申请实施例所提供的方法，具备执行方法相应的功能模块和有益效果。未在本实施例中详尽描述的技术细节，可参见本申请实施例所提供的方法。
本申请实施例的计算机设备2以多种形式存在，包括但不限于：
(1)移动通信设备：这类设备的特点是具备移动通信功能，并且以提供话音、数据通信为主要目标。这类终端包括：智能手机(例如iPhone)、多媒体手机、功能性手机，以及低端手机等。
(2)超移动个人计算机设备：这类设备属于个人计算机的范畴，有计算和处理功能，一般也具备移动上网特性。这类终端包括：PDA、MID和UMPC设备等，例如iPad。
(3)便携式娱乐设备：这类设备可以显示和播放多媒体内容。该类设备包括：音频、视频播放器(例如iPod)，掌上游戏机，电子书，以及智能玩具和便携式车载导航设备。
(4)服务器：提供计算服务的设备，服务器的构成包括处理器、硬盘、内存、系统总线等，服务器和通用的计算机架构类似，但是由于需要提供高可靠的服务，因此在处理能 力、稳定性、可靠性、安全性、可扩展性、可管理性等方面要求较高。
(5)其他具有数据交互功能的电子装置。
本申请又一实施例还提供了一种非易失性计算机可读存储介质，所述计算机可读存储介质存储有计算机可执行指令，该计算机可执行指令被一个或多个处理器执行，例如图8中的一个处理器22，可使得上述一个或多个处理器22可执行上述任意方法实施例中的风险控制方法，例如，执行以上描述的图4-图6的程序。
以上所描述的装置实施例仅仅是示意性的，其中作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到至少两个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本申请实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。
通过以上的实施方式的描述，本领域普通技术人员可以清楚地了解到各实施方式可借助软件加通用硬件平台的方式来实现，当然也可以通过硬件。本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程是可以通过计算机可读指令来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可实现计算风险得分步骤与判断风险程度步骤，其中：所述计算风险得分步骤包括依据预设风险计分规则对用户的埋点数据进行计算处理，以获取风险得分；所述判断风险程度步骤包括接收所述用户的业务请求并根据所述业务请求选择对应的风险评估规则与预设阈值，在所述计算风险得分步骤获取的得分中寻找所述风险评估规则对应的风险得分作为评估得分，并将所述评估得分与所述业务请求对应的阈值进行比较，获取风险评估结果。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-OnlyMemory，ROM)或随机存储记忆体(RandomAccessMemory，RAM)等。
最后应说明的是：以上各实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述各实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的范围。

Claims (20)

  1. 一种风险控制方法，包括计算风险得分步骤与判断风险程度步骤，其中：
    所述计算风险得分步骤包括依据预设风险计分规则对用户的埋点数据进行计算处理，以获取风险得分；
    所述判断风险程度步骤包括接收所述用户的业务请求并根据所述业务请求选择对应的风险评估规则与预设阈值，在所述计算风险得分步骤获取的得分中寻找所述风险评估规则对应的风险得分作为评估得分，并将所述评估得分与所述业务请求对应的阈值进行比较，获取风险评估结果。
  2. 根据权利要求1所述的方法，所述计算风险得分步骤包括：
    采集用户的埋点数据；
    将所述埋点数据根据预设风险计分规则计算风险得分；
    将所述风险得分转换成标准数据格式；
    转换后的得分经消息队列处理工具传输至存储模块，以供存储模块存储所述风险得分。
  3. 根据权利要求2所述的方法，所述埋点数据包括弹幕连接行为数据、弹幕发送行为数据、访问房间页行为数据、关注行为数据、扭蛋活动行为数据、领取宝箱行为数据、购买特权行为数据、兑换行为数据、抽奖行为数据、签到行为数据、送礼行为数据或充值行为数据中的至少一种。
  4. 根据权利要求2所述的方法，所述将风险得分转换成标准数据格式是将用户账户信息、风险计分规则信息与风险得分信息按照预定顺序排列。
  5. 根据权利要求2所述的方法，存储模块存储所述风险得分的步骤，具体包括：
    将所述风险得分存储至第一数据库；
    将所述风险得分传输至第二数据库，且所述第二数据库对所述风险得分设置了过期期限。
  6. 根据权利要求5所述的方法，所述风险得分传输至所述第二数据库之后，还包括：
    将第二数据库的内容通过LRU算法进行缓存。
  7. 根据权利要求2所述的方法，所述将埋点数据根据预设风险计分规则计算风险得分中的计算类型包括离线计算和/或实时计算。
  8. 根据权利要求1-7中任一项所述的方法，所述将所述评估得分与所述业务请求对应的阈值进行比较，获取风险评估结果，具体包括：
    判断所述评估得分是否超出预设阈值；
    若是，则拒绝业务请求；
    若否，则通过业务请求。
  9. 一种计算机设备，所述计算机设备，包括存储器、处理器以及存储在存储器上并可在处理器上运行的计算机可读指令，所述处理器执行所述计算机可读指令时实现计算风险 得分步骤与判断风险程度步骤，其中：
    所述计算风险得分步骤包括依据预设风险计分规则对用户的埋点数据进行计算处理，以获取风险得分；
    所述判断风险程度步骤包括接收所述用户的业务请求并根据所述业务请求选择对应的风险评估规则与预设阈值，在所述计算风险得分步骤获取的得分中寻找所述风险评估规则对应的风险得分作为评估得分，并将所述评估得分与所述业务请求对应的阈值进行比较，获取风险评估结果。
  10. 根据权利要求9所述的计算机设备，所述计算风险得分步骤包括：
    采集用户的埋点数据；
    将所述埋点数据根据预设风险计分规则计算风险得分；
    将所述风险得分转换成标准数据格式；
    转换后的得分经消息队列处理工具传输至存储模块，以供存储模块存储所述风险得分。
  11. 根据权利要求10所述的计算机设备，所述埋点数据包括弹幕连接行为数据、弹幕发送行为数据、访问房间页行为数据、关注行为数据、扭蛋活动行为数据、领取宝箱行为数据、购买特权行为数据、兑换行为数据、抽奖行为数据、签到行为数据、送礼行为数据或充值行为数据中的至少一种。
  12. 根据权利要求10所述的计算机设备，所述将风险得分转换成标准数据格式是将用户账户信息、风险计分规则信息与风险得分信息按照预定顺序排列；所述将埋点数据根据预设风险计分规则计算风险得分中的计算类型包括离线计算和/或实时计算。
  13. 根据权利要求10所述的计算机设备，存储模块存储所述风险得分的步骤，具体包括：
    将所述风险得分存储至第一数据库；
    将所述风险得分传输至第二数据库，且所述第二数据库对所述风险得分设置了过期期限；以及
    将第二数据库的内容通过LRU算法进行缓存。
  14. 根据权利要求9-13任一项所述的计算机设备，所述将所述评估得分与所述业务请求对应的阈值进行比较，获取风险评估结果，具体包括：
    判断所述评估得分是否超出预设阈值；
    若是，则拒绝业务请求；
    若否，则通过业务请求。
  15. 一种计算机可读存储介质，其上存储有计算机可读指令，所述计算机可读指令被处理器执行时实现计算风险得分步骤与判断风险程度步骤，其中：
    所述计算风险得分步骤包括依据预设风险计分规则对用户的埋点数据进行计算处理，以获取风险得分；
    所述判断风险程度步骤包括接收所述用户的业务请求并根据所述业务请求选择对应的风险评估规则与预设阈值，在所述计算风险得分步骤获取的得分中寻找所述风险评估规则对应的风险得分作为评估得分，并将所述评估得分与所述业务请求对应的阈值进行比较，获取风险评估结果。
  16. 根据权利要求15所述的计算机可读存储介质，所述计算风险得分步骤包括：
    采集用户的埋点数据；
    将所述埋点数据根据预设风险计分规则计算风险得分；
    将所述风险得分转换成标准数据格式；
    转换后的得分经消息队列处理工具传输至存储模块，以供存储模块存储所述风险得分。
  17. 根据权利要求16所述的计算机可读存储介质，所述埋点数据包括弹幕连接行为数据、弹幕发送行为数据、访问房间页行为数据、关注行为数据、扭蛋活动行为数据、领取宝箱行为数据、购买特权行为数据、兑换行为数据、抽奖行为数据、签到行为数据、送礼行为数据或充值行为数据中的至少一种；所述将风险得分转换成标准数据格式是将用户账户信息、风险计分规则信息与风险得分信息按照预定顺序排列；所述将埋点数据根据预设风险计分规则计算风险得分中的计算类型包括离线计算和/或实时计算。
  18. 根据权利要求16所述的计算机可读存储介质，存储模块存储所述风险得分的步骤，具体包括：
    将所述风险得分存储至第一数据库；
    将所述风险得分传输至第二数据库，且所述第二数据库对所述风险得分设置了过期期限；以及
    将第二数据库的内容通过LRU算法进行缓存。
  19. 根据权利要求15-18任一项所述的计算机可读存储介质，所述将所述评估得分与所述业务请求对应的阈值进行比较，获取风险评估结果，具体包括：
    判断所述评估得分是否超出预设阈值；
    若是，则拒绝业务请求；
    若否，则通过业务请求。
  20. 一种风险控制系统，包括风险计算模块和风险判断模块，其中：
    所述风险计算模块，用于依据预设风险计分规则对用户的埋点数据进行计算处理，以获取风险得分；
    所述风险判断模块，用于接收所述用户的业务请求并根据所述业务请求选择对应的风险评估规则与预设阈值，在所述计算风险得分步骤获取的风险得分中寻找所述风险评估规则对应的风险得分作为评估得分，并将所述评估得分与所述业务请求对应的阈值进行比较，获取风险评估结果。
PCT/CN2020/087669 2019-08-22 2020-04-29 一种风险控制方法、计算机设备及可读存储介质 Ceased WO2021031607A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US17/636,283 US12361357B2 (en) 2019-08-22 2020-04-29 Risk control method, computer device, and readable storage medium
EP20854478.3A EP4020349A4 (en) 2019-08-22 2020-04-29 RISK CONTROL PROCEDURE, COMPUTER DEVICE AND READABLE STORAGE MEDIA

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910780554.0A CN112418580A (zh) 2019-08-22 2019-08-22 一种风险控制方法、计算机设备及可读存储介
CN201910780554.0 2019-08-22

Publications (1)

Publication Number Publication Date
WO2021031607A1 true WO2021031607A1 (zh) 2021-02-25

Family

ID=74660115

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/087669 Ceased WO2021031607A1 (zh) 2019-08-22 2020-04-29 一种风险控制方法、计算机设备及可读存储介质

Country Status (4)

Country Link
US (1) US12361357B2 (zh)
EP (1) EP4020349A4 (zh)
CN (1) CN112418580A (zh)
WO (1) WO2021031607A1 (zh)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113010434A (zh) * 2021-04-07 2021-06-22 广州启生信息技术有限公司 一种实现轻量级应用埋点的系统和方法
CN113570166A (zh) * 2021-09-08 2021-10-29 湖南惠农科技有限公司 风控实时预测识别方法及装置
CN114297689A (zh) * 2021-12-29 2022-04-08 鲁信科技股份有限公司 一种基于隐私计算的金融风控方法、设备及存储介质
CN114490302A (zh) * 2022-03-04 2022-05-13 大庆火兔网络科技有限公司 一种基于大数据分析的威胁行为分析方法及服务器
CN114885183A (zh) * 2022-04-21 2022-08-09 武汉斗鱼鱼乐网络科技有限公司 一种识别礼包风险用户的方法、装置、介质及设备
CN115499232A (zh) * 2022-09-26 2022-12-20 重庆长安汽车股份有限公司 实名认证方法、装置、服务器及存储介质
CN117221917A (zh) * 2023-10-07 2023-12-12 中国电信股份有限公司技术创新中心 基站小区健康度评估方法、装置、计算机设备和存储介质

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112989135B (zh) * 2021-04-15 2023-03-24 杭州网易再顾科技有限公司 实时风险团伙的识别方法、介质、装置和计算设备
CN113434681A (zh) * 2021-06-30 2021-09-24 平安科技（深圳）有限公司 业务操作控制方法、装置、电子设备及介质
CN114511134B (zh) * 2021-12-30 2024-12-17 北京字跳网络技术有限公司 风控策略生成方法、设备、存储介质及程序产品
CN115102742B (zh) * 2022-06-16 2024-06-18 中移（杭州）信息技术有限公司 网络请求评估方法、装置、设备及存储介质
CN115134352B (zh) * 2022-06-27 2023-06-20 重庆长安汽车股份有限公司 一种埋点数据上传方法、装置、设备及介质
CN115730826A (zh) * 2022-11-25 2023-03-03 北京奇艺世纪科技有限公司 风险控制规则配置方法和装置、电子设备、存储介质
CN117077998A (zh) * 2023-02-02 2023-11-17 北京思创信息系统有限公司 一种隐患排查方法、系统、终端及存储介质
CN116415237B (zh) * 2023-03-03 2024-03-19 港珠澳大桥管理局 风险设备识别方法、装置、计算机设备和存储介质
US20240311381A1 (en) * 2023-03-17 2024-09-19 Ab Initio Technology Llc Using Metadata to Drive Batch and Real-Time Processing in Data Processing Systems
CN117010690B (zh) * 2023-08-04 2024-11-05 洛阳炼化宏达实业有限责任公司 基于人工智能的生产安全预警方法
CN117113356A (zh) * 2023-08-08 2023-11-24 中国人民财产保险股份有限公司 安全管控方法、系统和电子设备
CN117132001B (zh) * 2023-10-24 2024-01-23 杭银消费金融股份有限公司 一种多目标风控策略优化方法及系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107067157A (zh) * 2017-03-01 2017-08-18 北京奇艺世纪科技有限公司 业务风险评估方法、装置及风控系统
CN107147621A (zh) * 2017-04-20 2017-09-08 微医集团（浙江）有限公司 互联网医疗黄牛风险控制的实现方法
CN107679897A (zh) * 2017-09-25 2018-02-09 北京京东尚科信息技术有限公司 一种安全风险控制方法和装置
CN110033171A (zh) * 2019-03-19 2019-07-19 阿里巴巴集团控股有限公司 一种识别金融企业风险的方法、系统平台和介质

Family Cites Families (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7346575B1 (en) * 2002-01-07 2008-03-18 First Data Corporation Systems and methods for selectively delaying financial transactions
US20040199462A1 (en) * 2003-04-02 2004-10-07 Ed Starrs Fraud control method and system for network transactions
CN101996381A (zh) * 2009-08-14 2011-03-30 中国工商银行股份有限公司 一种零售资产风险的计算方法及系统
US8881289B2 (en) * 2011-10-18 2014-11-04 Mcafee, Inc. User behavioral risk assessment
US9203860B1 (en) * 2012-03-20 2015-12-01 United Services Automobile Association (Usaa) Dynamic risk engine
US9356939B1 (en) * 2013-03-14 2016-05-31 Ca, Inc. System and method for dynamic access control based on individual and community usage patterns
CN104423975B (zh) * 2013-08-21 2017-10-10 华为技术有限公司 数据处理的方法与装置
US20150066575A1 (en) * 2013-08-28 2015-03-05 Bank Of America Corporation Enterprise risk assessment
EP3078156A4 (en) * 2013-10-11 2017-07-12 Visa International Service Association Network token system
CN105516071B (zh) * 2014-10-13 2019-01-18 阿里巴巴集团控股有限公司 验证业务操作安全性的方法、装置、终端及服务器
CN106469376B (zh) * 2015-08-20 2021-12-03 创新先进技术有限公司 一种风险控制方法和设备
CN105959235B (zh) * 2016-07-21 2019-02-12 中国工商银行股份有限公司 分布式数据处理系统及方法
CN107886430A (zh) * 2017-11-29 2018-04-06 南京甄视智能科技有限公司 贷后风险控制方法和系统
US20190287182A1 (en) * 2018-03-14 2019-09-19 American Express Travel Related Services Company, Inc. Transaction Compliance Scoring System
CN108875388A (zh) * 2018-05-31 2018-11-23 康键信息技术（深圳）有限公司 实时风险控制方法、装置及计算机可读存储介质
CN109360104A (zh) * 2018-08-27 2019-02-19 平安科技（深圳）有限公司 用户类型划分方法、系统、计算机设备和存储介质
CN110033153A (zh) * 2018-12-05 2019-07-19 阿里巴巴集团控股有限公司 一种对信息推荐进行资源奖励方法、装置及设备
US10896574B2 (en) * 2018-12-31 2021-01-19 Playtika Ltd System and method for outlier detection in gaming
CN109739849B (zh) * 2019-01-02 2021-06-29 山东省科学院情报研究所 一种数据驱动的网络敏感信息挖掘与预警平台
US11233770B2 (en) * 2019-07-02 2022-01-25 Vmware Inc. User behavior based security in a software defined data center

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107067157A (zh) * 2017-03-01 2017-08-18 北京奇艺世纪科技有限公司 业务风险评估方法、装置及风控系统
CN107147621A (zh) * 2017-04-20 2017-09-08 微医集团（浙江）有限公司 互联网医疗黄牛风险控制的实现方法
CN107679897A (zh) * 2017-09-25 2018-02-09 北京京东尚科信息技术有限公司 一种安全风险控制方法和装置
CN110033171A (zh) * 2019-03-19 2019-07-19 阿里巴巴集团控股有限公司 一种识别金融企业风险的方法、系统平台和介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4020349A4

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113010434A (zh) * 2021-04-07 2021-06-22 广州启生信息技术有限公司 一种实现轻量级应用埋点的系统和方法
CN113570166A (zh) * 2021-09-08 2021-10-29 湖南惠农科技有限公司 风控实时预测识别方法及装置
CN114297689A (zh) * 2021-12-29 2022-04-08 鲁信科技股份有限公司 一种基于隐私计算的金融风控方法、设备及存储介质
CN114297689B (zh) * 2021-12-29 2022-09-20 鲁信科技股份有限公司 一种基于隐私计算的金融风控方法、设备及存储介质
CN114490302A (zh) * 2022-03-04 2022-05-13 大庆火兔网络科技有限公司 一种基于大数据分析的威胁行为分析方法及服务器
CN114885183A (zh) * 2022-04-21 2022-08-09 武汉斗鱼鱼乐网络科技有限公司 一种识别礼包风险用户的方法、装置、介质及设备
CN115499232A (zh) * 2022-09-26 2022-12-20 重庆长安汽车股份有限公司 实名认证方法、装置、服务器及存储介质
CN117221917A (zh) * 2023-10-07 2023-12-12 中国电信股份有限公司技术创新中心 基站小区健康度评估方法、装置、计算机设备和存储介质

Also Published As

Publication number Publication date
EP4020349A1 (en) 2022-06-29
US20220294821A1 (en) 2022-09-15
EP4020349A4 (en) 2022-07-20
US12361357B2 (en) 2025-07-15
CN112418580A (zh) 2021-02-26

Similar Documents

Publication Publication Date Title
WO2021031607A1 (zh) 一种风险控制方法、计算机设备及可读存储介质
CN103647800B (zh) 推荐应用资源的方法及系统
CN104539514B (zh) 消息过滤方法和装置
CN112104642B (zh) 一种异常账号确定方法和相关装置
CN111159587B (zh) 用户访问信息处理方法、装置及终端设备
CN104317804B (zh) 发布投票信息的方法和装置
US20160379122A1 (en) Recommendation algorithm optimization method, device and system
CN103106267A (zh) 基于微博的众包问答系统信息采集方法
CN110457601A (zh) 社交账号的识别方法和装置、存储介质及电子装置
JP2011191911A (ja) 広告配信装置、広告配信システム、広告配信方法、及びプログラム
CN111523035A (zh) App浏览内容的推荐方法、装置、服务器和介质
CN107368499A (zh) 一种客户标签建模及推荐方法及装置
CN110290142B (zh) 基于场景的鉴权方法、装置、服务器及存储介质
CN114840565B (zh) 抽样查询方法、装置、电子设备及计算机可读存储介质
CN114969493B (zh) 一种内容推荐方法和相关装置
WO2026007593A1 (zh) 一种数据处理方法、装置、设备、计算机可读存储介质及计算机程序产品
CN114547449A (zh) 推荐资源的确定方法、装置、服务器及计算机程序产品
US20180070194A1 (en) Systems and methods for providing an interactive community through device communication
CN115914666B (zh) 用户识别方法、装置、电子设备及非易失性存储介质
CN115714708A (zh) 无宽带用户的确定方法、装置及可读存储介质
CN116955838A (zh) 数据处理方法、装置、电子设备以及存储介质
CN115379261B (zh) 视频的发送方法、装置、电子设备及存储介质
CN112434894A (zh) 一种实时风险控制方法、计算机设备及可读存储介质
KR101151695B1 (ko) 이용자 특성에 따른 모바일 에코 시스템 및 이의 서비스 제공 방법
CN111949876B (zh) 信息处理方法及装置、电子设备和计算机可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20854478

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020854478

Country of ref document: EP

Effective date: 20220322

WWG Wipo information: grant in national office

Ref document number: 17636283

Country of ref document: US

WWW Wipo information: withdrawn in national office

Ref document number: 2020854478

Country of ref document: EP