WO2017157536A1 - Systèmes de communication de données et procédés de fonctionnement de systèmes de communication de données - Google Patents

Systèmes de communication de données et procédés de fonctionnement de systèmes de communication de données Download PDF

Info

Publication number
WO2017157536A1
WO2017157536A1 PCT/EP2017/025053 EP2017025053W WO2017157536A1 WO 2017157536 A1 WO2017157536 A1 WO 2017157536A1 EP 2017025053 W EP2017025053 W EP 2017025053W WO 2017157536 A1 WO2017157536 A1 WO 2017157536A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
user identifiers
identifiers
graph
single customer
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/EP2017/025053
Other languages
English (en)
Inventor
Jason ATLAS
Fady Kalo
Jiefei MA
Pourya SABER
Seyiang CHUA
Timothy Ashley ABRAHAM
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.)
Adbrain Ltd
Original Assignee
Adbrain 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
Priority claimed from US15/073,717 external-priority patent/US20170272362A1/en
Priority claimed from GB1604649.2A external-priority patent/GB2548563A/en
Application filed by Adbrain Ltd filed Critical Adbrain Ltd
Publication of WO2017157536A1 publication Critical patent/WO2017157536A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/18—Information format or content conversion, e.g. adaptation by the network of the transmitted or received information for the purpose of wireless delivery to users or terminals
    • H04W4/185—Information format or content conversion, e.g. adaptation by the network of the transmitted or received information for the purpose of wireless delivery to users or terminals by embedding added-value information into content, e.g. geo-tagging
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H04W28/10—Flow control between communication endpoints
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • 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
    • G06Q10/40—Business processes related to social networking or social networking services
    • G06Q10/44—Identification of trends within social networks, e.g. identification of trending topics
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • 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
    • H04L67/50—Network services
    • H04L67/53—Network services using third party service providers

Definitions

  • the present disclosure relates to data communication systems, and also to methods of operating aforesaid data communication systems; for example, the present disclosure relates to data communication systems employing data mining, wherein the data mining involves creating non-overlapping groups of user identifiers representing a single user. Moreover, the present disclosure discloses methods of operating data communication systems for controlling data flows to multiple users that are coupled via data communication networks of the aforesaid data communication systems. Furthermore, the present disclosure relates to computer program products comprising non-transitory computer-readable storage media having computer-readable instructions stored thereon, the computer- readable instructions being executable by a computerized device comprising processing hardware to execute the aforesaid methods.
  • the user activities include, for example, social networking, executing e-commerce transactions, communicating data, providing and/or receiving entertainment, and so forth.
  • the user activities include, for example, social networking, executing e-commerce transactions, communicating data, providing and/or receiving entertainment, and so forth.
  • a given user can connect to a given data communication network and access information therefrom, for example data content, using multiple devices coupled to the given data communication network, wherein the multiple devices are located at mutually different spatial locations.
  • many data mining companies analyze and utilize data pertaining to activities of users coupled to the Internet® in order to derive substantial information relating to personalities of the users, spatial locations of the user, shopping preferences of the users, personal interests of the users, trends associated with the users, and so forth .
  • Such analyzed data namely information, assists the data mining companies to plan customer-centric marketing strategies, such as targeted advertising campaigns, targeting a specific demographic area, targeting a group of users, providing improvements in data communication network data delivery performance, providing technical data processing improvements, and so forth .
  • customer-centric marketing strategies such as targeted advertising campaigns, targeting a specific demographic area, targeting a group of users, providing improvements in data communication network data delivery performance, providing technical data processing improvements, and so forth .
  • redundant user activity data in respect of mutually different user devices; the size of user activity data increases substantially, though it is not of much relevance to data mining companies for identifying trends, and user preferences in comparison to multiple devices' data is of a single user only.
  • An ability to identify and present to individuals or organizations a probabilistic graph of user profile is a nascent field, with considerable activity presently being expended to improve such ability.
  • IP Internet Protocol
  • IMEI International Mobile Equipment Identity
  • a given user may use a web browsing application such as, but not limiting to, the Internet Explorer®, Google Chrome®, and the like for accessing various websites.
  • Some websites save cookies or browsing history of the given user.
  • the cookies may include a fragment of text or information sent to the web browsing application while the given user is accessing a given user-selected website.
  • Various models to calculate a probability of a same given user accessing the Internet® through multiple devices are based on IP address identification and use of cookies.
  • Many existing techniques use cookies to identify various relationships such as, a relationship between various activities of the user, a relationship of the user with multiple devices, and so forth. However, determination of such relationships across multiple websites using cookies may present privacy concerns for the users.
  • every user connected to a data communication network such as the Internet® has a digital identity including online information related to the user.
  • Certain methods of analyzing the digital identity also involve scrutinizing Internet® usage data for all the devices using a same given IP address.
  • the techniques that adopt the analysis of Internet® usage frequency count across multiple devices may be highly inaccurate, since a given user may not make use of the given user's devices equally.
  • the present disclosure seeks to provide improved methods, systems, and computer program products involving data mining.
  • the present disclosure further seeks to provide improved systems and methods that utilize improved techniques for probabilistic true mapping of unique users to IP-based devices.
  • the present disclosure seeks to provide an improved device graph clustering process for disambiguating differentiated algorithms into a normalized process for visualization and data mining purposes.
  • a method of controlling data flows within a data communication system is disclosed .
  • a data communication system for controlling data flows is disclosed .
  • a non-transitory tangible computer readable medium comprising instructions for controlling data flows is disclosed.
  • a method of identifying relationships between a number of users and a number of devices connected to a network is disclosed .
  • a system for identifying relationships between a plurality of users and a plurality of devices connected to a network is disclosed.
  • the data communication system includes a data communication network to which a plurality of users are coupled when the data communication system is in operation, wherein the data communication system includes at least one data server for use in implementing the method, wherein the plurality of users have associated therewith corresponding user identifiers (IDs), and wherein the plurality of users interact with the data communication system by using a plurality of user devices, wherein the method comprises steps of:
  • a data communication system for controlling data flows, wherein the data communication system includes a data communication network to which a plurality of users are coupled when the data communication system is in operation, wherein the data communication system includes at least one data server for use in implementing the method, wherein the plurality of users have associated therewith corresponding user identifiers, and wherein the plurality of users interact with the data communication system by using a plurality of user devices, wherein the data communication system is operable to: (i) receive the plurality of user identifiers (IDs);
  • (v) use the mapping function for selectively controlling distribution of data content to the plurality of users.
  • a method of identifying relationships between a plurality of users and a plurality of devices connected to a network comprising : at a server:
  • a transceiving module receiving, by a transceiving module, a plurality of user identifiers (IDs) associated with the plurality of users present in the network;
  • IDs user identifiers
  • the comparing by an identity mapping module, the determined plurality of matched pairs of user identifiers (IDs) with each of the received plurality of user identifiers (IDs) to create a first graph, wherein the first graph comprises one or more of the plurality of matched pairs of user identifiers (IDs) overlapped with the received plurality of user identifiers and a similarity score, wherein the similarity score is determined based on the comparison of the matched pairs of user identifiers (IDs) with the plurality of user identifiers;
  • mapping by the identity mapping module, the plurality of user identifiers (IDs) of the first graph onto at least one single customer view identifier, wherein each distinct single customer view identifier is mapped to at least one user identifier of the plurality of user identifiers (IDs);
  • the identity mapping module creating, by the identity mapping module, a second graph based on the mapping of the plurality of user identifiers (IDs) of the first graph onto the at least one single customer view identifier, the second graph comprises a plurality of single customer view identifiers, wherein each single customer view identifier of the plurality of single customer view identifiers in the second graph represent a single user and one or more user identifiers mapped to the single customer view identifier belongs to same user of the plurality of users; and
  • the identity mapping module identifying, by the identity mapping module, at least one user associated with one or more of the plurality of computing devices based on the plurality of single customer view identifiers in the second graph, wherein the at least one single customer view identifier comprises browsing event including at least one of browsing history, timestamp information, images, uniform resource locators, images, cookie information, and device identifier.
  • a system for identifying relationship between a plurality of users and a plurality of devices connected to a network comprising : a server comprising : a transceiving module configured to receive a plurality of user identifiers (IDs) associated with the plurality of users present in the network; a data retrieving module configured to determine a plurality of matched pairs of user identifiers; and
  • an identity mapping module configured to :
  • the first graph comprises one or more of the plurality of matched pairs of user identifiers overlapped with the received plurality of user identifiers and a similarity score, wherein the similarity score is determined based on the comparison of the matched pairs of user identifiers with the plurality of user identifiers;
  • the second graph comprises a plurality of single customer view identifiers, wherein each single customer view identifier of the plurality of single customer view identifiers in the second graph represent a single user and one or more user identifiers mapped to the single customer view identifier belongs to same user of the plurality of users;
  • the identity mapping module identify, by the identity mapping module, at least one user associated with one or more of the plurality of computing devices based on the plurality of single customer view identifiers in the second graph, wherein the at least one single customer view identifier comprises browsing event including at least one of browsing history, timestamp information, images, uniform resource locators, images, cookie information, and device identifier.
  • a computer program product comprising non-transitory computer-readable storage media having computer-readable instructions stored thereon, the computer-readable instructions being executable by a computerized device comprising processing hardware to execute the aforesaid methods.
  • FIGS. 1A-1C are illustrations of various exemplary data communication systems, in accordance with various embodiments of the present disclosure, wherein :
  • FIG. 2 is an illustration of a block diagram of a server (or data server), in accordance with an embodiment of the present disclosure
  • FIG. 3 is an illustration of a block diagram of a computing device (or a user device), in accordance with an embodiment of the present disclosure
  • FIG. 4 is a flowchart illustrating an exemplary method for creating non-overlapping groups of user identifiers representing a single user, in accordance with an embodiment of the present disclosure.
  • FIG. 5 is a flowchart illustrating an exemplary method for selectively controlling distribution of data to a number of users in a data communication network, in accordance with an embodiment of the present disclosure.
  • an underlined number is employed to represent an item over which the underlined number is positioned or an item to which the underlined number is adjacent.
  • a non-underlined number relates to an item identified by a line linking the non-underlined number to the item.
  • the non- underlined number is used to identify a general item at which the arrow is pointing.
  • a module, device, or a system may be implemented in programmable hardware devices such as, processors, digital signal processors, central processing units, field programmable gate arrays, programmable array logic, programmable logic devices, cloud processing systems, or the like.
  • the devices/modules may also be implemented in software for execution by various types of processors.
  • An identified device/module may include executable code and may, for example, comprise one or more physical or logical blocks of computer instructions, which may, for example, be organized as an object, procedure, function, or other construct. Nevertheless, the executable of an identified device / module need not be physically located together, but may comprise disparate instructions stored in different locations which, when joined logically together, comprise the device and achieve the stated purpose of the device.
  • An executable code of a device could be a single instruction, or many instructions, and may even be distributed over several different code segments, among different applications, and across several memory devices.
  • operational data may be identified and illustrated herein within the device, and may be embodied in any suitable form and organized within any suitable type of data structure. The operational data may be collected as a single data set, or may be distributed over different locations including over different storage devices, and may exist, at least partially, as electronic signals on a system or network.
  • a "computing device” or user device includes a single device or a combination of multiple devices, which may be capable of communicating, and exchanging one or messages with other devices present in a network.
  • a "User Interface” or a “Graphical User Interface” can include an interface on a display, such as a screen, of the computing device enabling a user to interact with the device or computing device.
  • a “database” refers to a single or multiple modules or devices including hardware, software, firmware, or combination of these that can be configured to store user identifiers, matched pairs of the user identifiers, device identifiers, browsing history of the users, browsing events including browsing history of the users on various devices, and so forth.
  • an "Input / Output module” refers to a single or multiple modules or devices including hardware, software, firmware, or combination of these that can be configured to receive an input from a user or to present an output to the user.
  • a "memory” refers to a single or multiple modules or devices including hardware, software, firmware, or combination of these that can be configured to store instructions that can be executed by other modules / devices.
  • a "central processing unit” refers to a single or multiple modules or devices including a software, hardware, firmware or combination of these, that is configured to execute instructions stored in the memory.
  • a “data communication system” refers to a network of devices and/or users.
  • the data communication system may include a data communication network to which a number of users are coupled when the data communication system is in operation.
  • the data communication network may include a data server.
  • Each of the users has an associated user device to connect to the data communication network.
  • a "user identifier” refers to one or more elements of information that are capable of defining a user or a plurality of users (for example a group of users).
  • a "user identifier" may include familiar subject matter such as, but not limited to, a login identifier (ID), a password, a phone number, an image identifier, a name, a date of birth of a user, and so forth.
  • the user identifier (ID) is alternatively a hybrid identifier including one or more elements of information that are subjected to a grouping or clustering transformation.
  • the transformation is determined by applying one or more pre-determined rules.
  • the transformations are implemented in an adaptive manner, for example in a recursive manner, as a function of matching results generated by employing methods of user identification pursuant to the present disclosure.
  • Certain categories of user identifier (ID) relate to user-defined information, for example a password, an access code, a user- selected bio-identification (e.g. choice of fingerprint of a user-selected finger); these are referred to as "variant categories" of ID.
  • Other categories relate to historical information that cannot be altered by the user, for example date-of-birth, an original family name at birth; these are referred to as "invariant categories" of ID.
  • IP to ID this is the most general use of User Identity. For the vast majority of cases, an IP does not resolve to a single individual, but the collection of ID's serving one purpose of category;
  • HouseHold a Household is identified using a variety of techniques, including behavior, and event timing, there can thereby be created a picture of a House Hold; such categorization gives much more granularity in respect of a given customer;
  • Family this grouping is a more of a meta-group, as opposed to a physical one.
  • a household can be a collection of adults living together.
  • a Family is meant to be a demographic identity linked to marketing and advertising needs. For purposes of describing embodiments of the present disclosure, such a definition of Family is beneficially employed .
  • a group consisting of parents and children living together in a household could also be regarded as being a Family;
  • FIGS. 1A-1C there are illustrated data communication systems lOOA-lOOC, in accordance with various embodiments of the present disclosure.
  • the data communication system 100A primarily includes a plurality of computing devices (or user devices) 104A-104N associated with a plurality of users 102A-102N.
  • the terms "user device” and “computing device” are used interchangeably on account of mutual similarities in their functionality and structure.
  • each of the users 102A-102N may connect to a network 110 (also referred as a data communication network 110) for accessing information using their associated computing devices 104A-104N.
  • a network 110 also referred as a data communication network 110
  • the users are coupled to the data communication network 110 when the data communication system is in operation .
  • Each of the computing devices 104A-104N also has an associated device identifier.
  • An example of the device identifier may include an International Mobile Equipment Identity (IM EI) .
  • a given user of the plurality of users 102A-102N uses more than one computing device for accessing the network 110 by using same or different user IDs.
  • the user 102A can use the computing device 104A and the computing device 104B for accessing the network 110.
  • the user 102B can use computing device 104B and 104N for accessing the network 110.
  • each of the users 102A-102N may have more than one associated user IDs.
  • examples of the user identifiers may include such as, but not limited to, a login identifier (ID), a password, a phone number, an image identifier, a name, date of birth of a user, and so forth .
  • Examples of the computing devices 102A-102N include cell phones, phablet computers, tablet computers, desktop computers, a personal digital assistant ( PDA), and so forth .
  • a typical example of the computing device is a wireless data access-enabled device, for example, an iPHON E® smart phone, a BLACKBERRY® smart phone, a N EXUS ON ETM smart phone, an iPAD® device, and so forth, that is capable of sending and receiving data in a wireless manner using protocols like the Internet Protocol, or IP, and the wireless application protocol, or WAP.
  • IP Internet Protocol
  • WAP wireless application protocol
  • the computing devices 102A-102N may be connected to the network 110 using wired or wireless technologies.
  • the network 110 may include, such as, but are not limited to, Local Area Networks (LANs), Wide Area Networks (WANs), Metropolitan Area Networks (MANs), Wireless LANs (WLANs), Wireless WANs (WWANs), Wireless MANs (WMANs), the Internet®, second generation (2G) telecommunication networks, third generation (3G®) telecommunication networks, fourth generation (4G®) telecommunication networks, and Worldwide Interoperability for Microwave Access (WiMAX®) networks.
  • LANs Local Area Networks
  • WANs Wide Area Networks
  • MANs Metropolitan Area Networks
  • WLANs Wireless WANs
  • WMANs Wireless MANs
  • the Internet® second generation (2G) telecommunication networks
  • third generation (3G®) telecommunication networks third generation
  • 4G® fourth generation
  • the data communication system 100A also includes a server 108 (or a data server 108) connected to the network 110. Furthermore, the terms server and data server are used interchangeably without change in their meaning due to similarity in their functionality and structure.
  • the server 108 further includes an identity management system 106A.
  • the identity management system 106A is operable to identify and establish relationship between the users 102A-102N and the computing devices 104A-104N connected to or present in the network 110.
  • the identity management system 106A is operable to identify and establish relationship between the users 102A-102N and the computing devices 104A-104N based on browsing events including such as, but not limiting to, browsing history, timestamp information, website information, uniform resource locators, device identifiers, images, and so forth.
  • the identity management system 106A is operable, namely configured, to receive a number of user identifiers (IDs) associated with the plurality of users 102A-102N present in the data communication network 110.
  • the identity management system 106A is further configured to determine a number of matched pairs of user identifiers.
  • the matched pairs of user identifiers are pre-defined and pre-stored in a database of the server 108.
  • the user identifiers are received from one of the computing devices 104A-104N .
  • the matched pairs of the user identifiers are pre-stored in a database using a Parquet format or a file system.
  • the storing of the matched pairs in Parquet format may maintain integrity of the associations and meta-information in information, for example a first graph or a second graph, displayed to the users 102A-102N .
  • the Parquet format is a column oriented binary file format, which is considered to be very efficient for storing large scale data and executing queries.
  • the data communication system and primarily the identity management system 106A are operable, namely are configured, to compare the determined matched pairs (P) of the user identifiers (IDs) with each of the received user identifiers (IDs).
  • the identity management system 106A is also configured to determine a similarity score for the matched pairs and the user identifiers.
  • the similarity score for the matched pairs and the user identifiers may have a numeric value for example, in a range of 0 to 1.
  • the similarity score may indicate a probability of two or more user IDs being associated with one user based on a mapping of the matched pairs and the user identifiers.
  • the value of the similarity score is "1" if there is 100 percent probability and the value of the similarity score is "0" is probability is zero.
  • the similarity score value may be selected from the following : “High”, “Low”, “Very Low”, and “Very High”.
  • An identity management system 106A may further set a pre-defined minimum and maximum probability threshold. For example, the minimum probability threshold is 0.1, the maximum probability threshold is 0.9, then if the probability is below 0.1 then the similarity score is "Very Low”, and when the probability is more than 0.9, then the similarity score while comparing the user IDs is "Very High”.
  • the similarity score may be determined by using suitable methods such as, but not limited to, methods based on correlation, neural network methods, multi-dimensional correlation, clustering methods, Kalman Filtering, regression based methods, association rule learning methods, dependency modeling, anomaly detection, outlier/change/deviation detection methods, summarization methods, classification methods, and so forth.
  • suitable methods such as, but not limited to, methods based on correlation, neural network methods, multi-dimensional correlation, clustering methods, Kalman Filtering, regression based methods, association rule learning methods, dependency modeling, anomaly detection, outlier/change/deviation detection methods, summarization methods, classification methods, and so forth.
  • a similarity score between two vertices x and y is determined by using the following equation : ⁇ ' ) " M IM // 112 wherein I ⁇ l l is the Euclidean distance.
  • similarity score may be determined using cosine similarity for real-valued vectors, as used for retrieving information for scoring similarity between documents in a vector space model .
  • the cosine method is used, and may be enhanced by using cluster analysis methods. This way, the similarity scores, and the associations and their respective "strengths" may be determined.
  • the following exemplary cosine equation may be used to determine the similarity score:
  • the cosine equation can be normalized with cluster analysis methods to handle lack of triangulation in the cosine.
  • the identity management system 106A is also operable, namely configured, to map the user identifiers onto at least one single customer view identifier (SCV_ID).
  • a single customer view ID may be based on browsing event including browsing history, timestamp information, uniform resource locators, website information, device ID and so forth.
  • the browsing event may include information monitored by or collected from various devices or software applications such as, but not limiting to, routers, gateways, computing devices 104A-104N, data monitoring software, in the network 110. Such collection of information is achieved by analyzing DNS (digital network signaling) routing information of data packets conveying a data payload, irrespective of whether or not the payload is encrypted .
  • DNS digital network signaling
  • the SCV_ID may also indicate a linking of a user identity or user identifier to a device (or device identifier).
  • the identity can be an internet protocol (IP) address or any other unique Data/networking element or device, that can be mapped to all the other devices and systems associated with the user, for example, user 102B.
  • IP internet protocol
  • multiple users may be mapped onto a single SCV_ID.
  • the single SCV_ID may represent and indicate that the multiple users IDs that are being mapped onto the same SCV_ID belong to a same user.
  • an SCV_ID represent a single user and one or more user identifiers mapped to the SCV_ID belongs to same user of the users 102A-102N .
  • Each single customer view identifier is distinctly mapped, namely has a matching score that is greater than a pre-defined threshold, to at least one user identifier of the user identifiers, to generate a mapping function "F".
  • each SCV ID is mapped, with a score greater than a pre-defined threshold, to at least one user identifier of the user identifiers, to generate a distinct mapping function "F", such that each user identifier can be mapped to at most one SCV ID.
  • the threshold is adaptively varied, for example when performing computations recursively to find a best mapping is user identification (IDs) to user activities.
  • the threshold is set, at least in part, depending upon a nature of activities against which the user identifications are being matched.
  • a distinct SCV_ID represents a single unique user and may be based on the browsing event, or a plurality of browsing events, across multiple devices 104A-104N .
  • the mapping function "F" may be determined using suitable analysis methods and/or computational methods based on correlation, neural network methods, multi-dimensional correlation, clustering methods, Kalman Filtering, regression based methods, association rule learning methods, dependency modeling, anomaly detection, outlier/change/deviation detection methods, summarization methods, classification methods, and so forth, as aforementioned .
  • the mapping function "F" may be determined using multidimensional correlation method and model to identify relationships between the user devices 104A-104N, single customer view IDs and the user identifiers of the users 102A-102N .
  • the identity management system 106A is also operable, namely configured, to use the mapping function for selectively controlling distribution of data content to the users 102A-102N .
  • the data content is presented on associated user devices 104A-104N of the users 102A-102N. Examples of the data content may include, such as, but not limited to, advertisements, surveys, entertainment data like movies, songs, news, and so forth.
  • the identity management system 106A is configured to repeat, for example iteratively, the process of comparing the determined matched pairs of the user identifiers with each of the received user identifiers and determining the similarity scores, and mapping the user identifiers onto at least one single customer view identifier for achieving a distinct mapping in the mapping function "F".
  • the mapping function "F" may indicate relationship of the user IDs and various device identifiers of the user devices that are being used for accessing the data communication network by multiple users.
  • the identity management system 106A is operable, namely configured, to compare the determined matched pairs of user identifiers with each of the received user identifiers to create a first graph.
  • the first graph may include one or more of the matched pairs "P" of user identifiers overlapped with the received user identifiers and a similarity score.
  • the similarity score may be determined based on the comparison of the matched pairs of user identifiers with the received user identifiers.
  • the identity management system 106A is further configured to map the user identifiers of the first graph onto at least one single customer view identifier. Each distinct SCV_ID is mapped to at least one user identifier of the user identifiers.
  • the identity management system 106A is further operable, namely configured, to create a second graph based on the mapping of the user identifiers of the first graph onto the at least one single customer view identifier.
  • the second graph may include a number of SCV_IDs.
  • one or more of the single customer view identifiers are in the received user identifiers.
  • one or more of the user identifiers mapping to a same single customer view identifier are absent in the second graph.
  • the second graph is empty when there is not enough information about the user identifiers, or the user identifiers are found not to have a mapping to another device.
  • the second graph is an empty graph when the identity management system 106A determines that some of the user IDs are bots, or suspicious. This may avoid giving false positives in the second graph.
  • the single graph includes at least one singleton match, thereby eliminating empty graphs.
  • the identity management system 106A is configured to present or display the second graph on a computing device such as the computing device 104B of the user 102B.
  • the second graph or an output graph may be presented on the computing device 104A of the user 102A.
  • an SCV_ID in the second graph represent a single user and one or more user identifiers mapped to the SCV_ID belongs to same user of the users 102A-102N .
  • one or more of the user identifiers mapping to a same SCV_ID are absent in the second graph.
  • the identity management system 106A is operable, namely configured, to identifying at least one user associated with one or more of the computing devices 104A-104N based on the single customer view identifiers in the second graph.
  • a single customer view identifier of the multiple single customer view identifiers in the second graph may represent a single user and one or more user identifiers mapped to the single customer view identifier belongs to a same user of the multiple users 102A-102N .
  • an identity management system 106B may be present in a cloud network 110 or on any network device in the network 110.
  • an identity management system 106C may be present on a computing device itself.
  • the identity management system 106C may be present on the computing device 104A as shown in FIG. 1C.
  • the functionality of the identity management systems 106B- 106C is similar to the identity management device 106A as described in the foregoing with reference to FIG. 1A.
  • FIG. 2 there is shown a block diagram 200 of a server 202, in accordance with an embodiment of the present disclosure.
  • the server 202 primarily includes an identity management system 204, an Input / Output module 214, a memory 216, a central processing module or unit (CPU) 218, and a network interfacing module 220.
  • the server 202 may be a single device or may include more than one devices including software, hardware, firmware, or combination of these.
  • the system or modules of the server 202 may be individual device or combination of devices capable of performing one or more functions.
  • the identity management system 204 is operable, namely configured to identify a relationship between a number of users (such as the users 102A- 102N ) and a number of devices (such as the computing devices 104A- 104N ) connected to the network 110 (or a data communication network 110) .
  • the identity management system 204 includes a transceiving module 206, a data retrieving module 208, an identity mapping module 210, and a database 212.
  • the transceiving module 206 is configured to receive a number of user identifiers (IDs) associated with a number of users (such as the users 102A- 102N ) present in a network (such as the network 110) .
  • IDs user identifiers
  • the data retrieving module 208 is configured to determine a number of matched pairs of user identifiers, for example to determine a plurality of such matched pairs.
  • the matched pairs of user identifiers are predefined and pre-stored in a database of the server 202 or of a remotely located device in the network 110.
  • the data retrieving module 208 is operable, namely configured, to retrieve the matched pairs of user identifiers from the database 212.
  • the identity mapping module 210 is operable, namely configured, to compare the determined matched pairs of user identifiers with each of the received user identifiers and determine a similarity score for the matched pairs and the user identifiers (IDs or UIIDs) .
  • the identity mapping module 210 is also operable, namely configured, to map the user identifiers onto at least one single customer view identifier (SCV_ID) . Each single customer view identifier is distinctly mapped to at least one user identifier of the received user identifiers to generate a mapping function "F".
  • the identity mapping module 210 is operable, namely configured, to use the mapping function for selectively controlling distribution of data content to the users 102A- 102N .
  • the transceiving module 206 of the server 202 may send the mapping to another device or server in the network 110.
  • the another server may control distribution of data content to the users in the network based on the received mapping function and SCV_IDs. For example, if a user John is attached to four computing devices like laptop, phones and so forth, then the server may decide to send content, such as a survey or an advertisement, to only one of the devices associated with John, for example to conserve data communication bandwidth, network energy consumption, to reduce data communication network response latency, and so forth.
  • the identity mapping module 210 is operable, namely configured, to compare the determined matched pairs of user identifiers with each of the received user identifiers to create a first graph.
  • the first graph may include one or more of the matched pairs of user identifiers overlapped with the received user identifiers and a similarity score.
  • the similarity score may be determined based on the comparison of the matched pairs of user identifiers with the received user identifiers.
  • the user identifiers are received from one of the computing devices 104A-104N.
  • the identity mapping module 210 is further operable, namely configured, to map the user identifiers of the first graph onto at least one single customer view identifier. Each distinct SCV_ID is mapped to at least one user identifier of the user identifiers.
  • the identity mapping module 210 is further operable, namely configured, to create a second graph based on the mapping of the user identifiers of the first graph onto the at least one single customer view identifier (SCV_ID).
  • the second graph may include a number of SCV_IDs.
  • the single customer view ID may be based on browsing event including browsing history, timestamp information, images, uniform resource locators, images, cookie information, and device identifier monitored from devices such as routers, monitoring applications in the network 110.
  • the second graph includes the SCV_IDs such that one or more of the SCV_IDs are in the received user identifiers. In another embodiment, one or more of the user identifiers that are mapping to a same SCV_ID are not in the second graph.
  • a single customer view identifier of the plurality of single customer view identifiers in the second graph represent a single user, and one or more user identifiers mapped to the single customer view identifier belong to a same given user of the users 102A- 102N .
  • the identity mapping module 210 is also operable, namely configured, to identify at least one user associated with one or more of the computing devices 104A-104N based on the single customer view identifiers in the second graph. For example, if there are four SCV_IDs "A”, “B”, “C”, and “D” and there are eight user IDs i.e., "John”, “Tim”, “Ross”, “Sara”, “Rachel”, “Joey”, “Monica”, and "Jack”.
  • This may help the server 202 to control distribution of content such as advertisements, surveys, movies, songs, etc. to the one or more of the users 102A-102N .
  • the server 202 may send content to only one computing or user device associated with the three user IDs "John", “Tim”, and "Sara".
  • the ID's themselves may be hybrid user identifications derived from a plurality of elements by applying a transformation, wherein the transformation performs clustering or grouping of the elements, and the transformation itself can be made adaptive depending upon earlier matching results achieved, for example in a recursive manner, to obtain a best mapping of IDs to various user performed events (for example Internet® surfing activities).
  • This maps back to the way we categorize individuals - from IP, to HH, to Family, to User.
  • the ability to achieve finer and finer grained views allows us to make the most pivots off the data .
  • the transceiving module 206 is operable, namely configured, to send to or present the second graph on a computing device of a user.
  • the second graph or an output graph may be presented at the computing device 104A of the user 102A.
  • an SCV_ID of the plurality of SCV_IDs in the second graph represent a single user.
  • one or more user identifiers mapped to the SCV_ID belongs to same user of the plurality of users 102A-102N .
  • a "memory" refers to a single or multiple modules or devices including hardware, software, firmware, or combination of these that can be configured to store instructions that can be executed by other modules/devices.
  • the central processing module 218 may include a single or multiple modules or devices including a software, hardware, firmware or combination of these, that is configured to execute instructions stored in the memory 216.
  • the network interfacing module 220 may enable the server 202 to establish connection with the network 110 or/and with other network devices such as the computing devices 104A- 104N present in the network 110.
  • the network 110 may include Internet® .
  • FIG. 3 there is provided an illustration of a block diagram 300 that represents a computing device 302, in accordance with an embodiment of the present disclosure.
  • the computing device 302 primarily includes an identity management system 304, an input/output module 314, a memory 316, a central processing module or unit (CPU) 318, and a network interfacing module 320.
  • the computing device 302 may include software, hardware, firmware, or combination of these.
  • the system or modules of the computing device 302 may be individual device or combination of devices capable of performing one or more functions as described below.
  • the identity management system 304 is operable, namely configured, to identify a relationship between a number of users (such as the users 102A- 102N ) and a number of devices (such as the computing devices 104A- 104N ) connected to the network 110.
  • the identity management system 304 includes a transceiving module 306, a data retrieving module 308, an identity mapping module 310, and a database 312.
  • the transceiving module 306 is operable, namely configured , to receive a number of user identifiers (IDs) associated with a number of users (such as the users 102A- 102N) present in a network (such as the network 110).
  • IDs user identifiers
  • the data retrieving module 308 is operable, namely configured, to determine a plurality of matched pairs of user identifiers.
  • the matched pairs of user identifiers are pre-defined and pre-stored in a database of the computing device 302 or of a remotely located device in the network 110.
  • the data retrieving module 308 is configured to retrieve the matched pairs of user identifiers from the database 312.
  • the identity mapping module 310 is operable, namely configured, to compare the determined plurality of matched pairs of user identifiers with each of the received plurality of user identifiers to create a first graph.
  • the first graph may include one or more of the plurality of matched pairs of user identifiers overlapped with the received user identifiers and a similarity score.
  • the similarity score may be determined based on the comparison of the matched pairs of user identifiers with the received user identifiers.
  • the user identifiers are received from one of the computing devices 104A-104N .
  • the identity mapping module 310 is further operable, namely configured, to map the user identifiers of the first graph onto at least one single customer view identifier (SCV_ID). Each distinct SCV_ID is mapped to at least one user identifier of the user identifiers.
  • the identity mapping module 210 is further operable, namely configured, to create a second graph based on the mapping of the plurality of user identifiers of the first graph onto the at least one single customer view identifier (SCV_ID).
  • the second graph may include a number of SCV_IDs.
  • the second graph includes the SCV_IDs such that one or more of the SCV_IDs are in the received user identifiers.
  • one or more of the user identifiers mapping to a same SCV_ID are not in the second graph.
  • the identity mapping module 310 is also operable, namely configured, to identify at least one user associated with one or more of the computing devices 104A-104N based on the single customer view identifiers in the second graph. As aforementioned, the identity mapping module 310 is also operable to apply one or more threshold to determine whether or not there is an association between the at least one user with one or more of the computing devices 104A-104N; whether or not the threshold is satisfied determines whether or not there is a distinct association.
  • the functionality and structure of the identity mapping module 310 is similar to the identity mapping module 210 of FIG. 2.
  • the Input / Output module 314 is operable configured to present or display the second graph on the computing device 302 of a user.
  • the second graph or an output graph may be presented at the computing device 104A of the user 102A.
  • an SCV_ID of the plurality of SCV_IDs in the second graph represent a single user.
  • one or more user identifiers mapped to the SCV_ID belongs to same user of the users 102A- 102N .
  • a "memory" refers to a single or multiple modules or devices including hardware, software, firmware, or combination of these that can be configured to store instructions that can be executed by other modules/devices.
  • the central processing module 318 may include a single or multiple modules or devices including a software, hardware, firmware or combination of these, that is configured to execute instructions stored in the memory 316.
  • the network interfacing module320 may enable the computing device 302 to establish connection with the network 110 or/and with other network devices such as the computing devices 104A- 104N present in the network 110.
  • FIG. 4 there is shown a flowchart illustrating an exemplary method 400 of creating non-overlapping groups of user identifiers representing a single user, in accordance with an embodiment of the present disclosure.
  • the method 400 may be implemented or performed by an identity management system such as, the identity management systems 106A- 106C, 204, and 304 as described with reference to FIGs. 1A-1C, 2 and 3.
  • the identity management system may be a single device or may be a combination of multiple devices including software, hardware, firmware, or combination of these.
  • the identity management system may further include following modules or devices i.e. , a transceiving module, a database, a data retrieving module, and an identity mapping module. Each of these modules can be a device or a combination of multiple devices.
  • the identity management system may be present or implemented on a computing device or a server or on any network device in the network.
  • a plurality of user identifiers are received .
  • the user identifiers may be associated with a plurality of users.
  • the transceiving module receives the user identifiers.
  • a number of matched pairs of user identifiers are determined .
  • the matched pairs of user identifiers are determined from a database such as a database of a server.
  • the matched pairs of the user identifiers are compared with received user identifiers to create a first graph (or a relevant graph).
  • the identity mapping module compares the matched pairs of the user identifiers with the received user identifiers to create the first graph and determine similarity score.
  • SCV_ID single customer view identifier
  • the identity mapping module maps the user identifiers of the first graph onto at least one SCV_ID.
  • the identity mapping module creates a second graph based on the mapping .
  • At a step 412 at least one user associated with one or more computing devices is identified based on the SCV_IDs present in the second graph.
  • the identity mapping module of the identity management system identifies the at least one user associated with the one or more computing devices based on the SCV_IDs present in the second graph.
  • FIG. 5 there is shown a flowchart illustrating an exemplary method 500 of creating non-overlapping groups of user identifiers representing a single user, in accordance with an embodiment of the present disclosure.
  • the user identifiers are associated with one or more users, for example the users 102A-102N as described in the foregoing with reference to FIG. 1A, who are either accessing or have accessed a data communication system.
  • the data communication system includes a data communication network (or the network 110).
  • the users may be coupled or connected to the data communication network when the data communication system is in operation.
  • the data communication system may include at least one data server, such as the server 108, for use in implementing the method 500.
  • the users have associated therewith corresponding user identifiers (IDs or UIIDs).
  • the users can interact with the data communication system by using a number of associated user devices, for example computing devices 104A-104N.
  • the method 500 may be implemented or performed by an identity management system such as, the identity management systems 106A-106C, 204, and 304 as discussed with reference to FIGs. 1A-1C, 2 and 3.
  • the identity management system may be a single device or may be a combination of multiple devices including software, hardware, firmware, or combination of these.
  • the identity management system may further include following modules or devices i.e., a transceiving module, a database, a data retrieving module, and an identity mapping module. Each of these modules can be a device or a combination of multiple devices.
  • the identity management system may be present or implemented on a user device or the data server or on any network device in the data communication network.
  • a number of user identifiers are received .
  • the transceiving module receives the user identifiers.
  • the user IDs are received from a computing device/user device.
  • the user IDs are retrieved from a database of the data server.
  • a number of matched pairs of user identifiers are determined.
  • the matched pairs of user IDs are determined from a database such as the database of the data server.
  • the matched pairs of the user IDs are compared with each of the received user IDs to determine a similarity score for the matched pairs and the user IDs.
  • the identity mapping module compares the matched pairs of the user identifiers with each of the received user identifiers to determine one or more similarity scores, for example plurality of similarity scores.
  • the user IDs are mapped onto at least one single customer view identifier (SCV_ID).
  • a single customer view ID may be based on browsing event including browsing history, timestamp information, uniform resource locators, website information, device ID, images, and such like in a device.
  • multiple users may be mapped onto a single SCV_ID.
  • the single SCV_ID may represent and indicate that the multiple users IDs that are being mapped onto the same SCV_ID belong to a same user.
  • an SCV_ID represent a single user and one or more user identifiers mapped to the SCV_ID belongs to same user of the users.
  • a mapping function "F" is generated. Furthermore, each customer view identifier is distinctly mapped to at least one user identifier of the plurality of user identifiers to generate a mapping function "F". Furthermore, in an embodiment, the identity management system maps each single customer view identifier to at least one user identifier of the plurality of user identifiers, to generate a mapping function "F".
  • a distinct SCV_ID may represent a single unique user and may be based on the browsing event across multiple devices. Multiple user IDs may be mapped to a single distinct SCV_ID.
  • the mapping function "F” may be determined using suitable analysis methods and/or computational methods based on correlation, neural network based methods, multi-dimensional correlation, clustering methods, and so forth. In an exemplary scenario, the mapping function "F" may be determined using one or more multidimensional correlation methods and models to identify relationships between the user devices, single customer view IDs and the user identifiers of the users.
  • the steps 508 and 510 may be iteratively performed for achieving a distinct mapping in the mapping function "F".
  • the mapping function "F" may indicate relationship of the user IDs and various device identifiers of the user devices that are being used for accessing the data communication network by multiple users.
  • Kalman Filtering also known as linear quadratic estimation (LQE)
  • LQE linear quadratic estimation
  • the Kalman filter is named after Rudolf Kalman, one of the primary developers of its theory.
  • An Expectation-maximization algorithm is an iterative method to find a maximum likelihood of estimates of parameters in statistical models using unobserved or hidden variables. Moreover, Expectation-maximization has numerous applications in technology, including but not limited to, data clustering in machine learning, segmentation and object recognition in computer vision, natural language processing. Furthermore, Expectation-maximization is capable of estimating the best values for parameters based on observed data via unobserved data. Optionally, it can be employed in an iterative manner, until the parameter values converge for obtaining most stable results for mappings determining relationship and associations for the user identifications (ID's).
  • ID's user identifications
  • the expectation-maximization algorithm operates on a statistical model with a set of observed data (for example, the scores between IDs), a set of assumed unobserved data and a vector of parameters (for example, the user- identifier to SCV ID mappings) with a likelihood function.
  • the algorithm works in a two-step process. In the expectation step, the algorithm computes the expected value of the log likelihood function with respect to the conditional distribution of unobserved data given the observed data under the current estimate of the parameters. In the maximization step, it finds the parameters that maximizes the log likelihood. The two steps iterates until convergence.
  • mapping function "F" may be determined using suitable analysis methods and/or computational methods based on correlation, neural network methods, multi-dimensional correlation, clustering methods, Kalman Filtering, regression based methods, association rule learning methods, dependency modeling, anomaly detection, outlier/change/deviation detection methods, summarization methods, classification methods, and so forth, as aforementioned .
  • Kalman Filterimg Expectation Maximization techniques can be employed in embodiments of the present disclosure.
  • Kalman filters have numerous applications in technology.
  • a common application for Kalman filters is for guidance, navigation and control of vehicles, particularly aircraft and spacecraft.
  • Kalman filters are a widely applied concept intime series analysis used in fields such as signal processing and econometrics.
  • Kalman filters are also employed for robotic motion planning and control, and they are sometimes included in trajectory optimization.
  • Kalman filter are capable of providing a model needed for making estimates of the current state of a given system and issuing updated commands.
  • the Kalman filters are employed in a recursive iterative manner, until parameters of the Kalman filters converge for obtaining most stable results for mappings determining relationships and associations for the user identifications (ID's). Similar consideration pertain for other types of filter than just Kalman-type filters.
  • the Kalman filter algorithm works in a two-step process.
  • the Kalman filter produces estimates of the current state variables, along with their uncertainties. Once the outcome of the next measurement (necessarily corrupted with some amount of error, including random noise) is observed, these estimates are updated using a weighted average, with more weight being given to estimates with higher certainty.
  • the algorithm is recursive, for example as aforementioned . It can run in real time, using only the present input measurements and the previously calculated state and its uncertainty matrix; no additional past information is required.
  • the mapping function "F" may be used for selectively controlling distribution of data, such as advertising content, surveys, movies, and so forth, to the users.
  • the server may send the advertising content to users 102B, 102C, and 102D or to their associated devices 104B, 104C, and 104D, respectively.
  • the mapping function and/or the second graph is sent to another device in a network such as another server device connected to the data communication network. Thereafter, the another device may control distribution of data to the users 102A-102N in the network 110. For example, another server device may select few of the users 102A-102N to send a survey on their associated user devices.
  • a customer or a client user may want to create non-overlapping groups of user identifiers, which may represent a single user.
  • the customer may want to create this to understand reach of his/her advertising campaign.
  • the customer should be able to count the number of individuals who have seen an advertisement. Therefore to identify a single user from a list of user identifiers (UIID) or received user identifiers i.e.
  • UID user identifiers
  • a first graph or a relevant graph including matched pairs overlapped with input user identifiers is created based on the input user identifiers.
  • "#IsSeed true” means a user identifier (or a UIID or ID) is in the received user identifiers set.
  • the similarity score may have a numeric value like 0.1, 0.2, 0.5, and so forth based on a probability of the matched pairs and the user identifiers.
  • Such numerical values are suitable for feeding into algorithms, for example the aforementioned Kalman filter, as parameter values.
  • a second graph (or an output map or an SCV_Map) may be created or requested.
  • An exemplary output map or second map format may look like "
  • a user identifier provided is in the matched pairs, then it should be in the output map or the second graph.
  • a user identifier (of the first graph) should only appear against one SCV_ID.
  • each distinct SCV_ID should be mapped to at least one user identifier from the received user identifiers.
  • user identifiers with the same SCV_ID must be in a connected graph in the determined matched pairs of user identifiers.
  • user identifiers with the same SCV_ID do not necessarily have to be a connected graph in the output graph.
  • singletons, an SCV_ID mapped to a single user identifier mapped to a single user identifier can be returned.
  • the disclosed method may be implemented when an input is a mixture of IDs or UIIDs, some of which are the matched pairs some are not.
  • the disclosed method may also be used to return a same single customer view if UIID is in the same cluster multiple times.
  • the present disclosure provides multi-staged, clustering methods to first derive data aggregate data from one or more data sources, and then via clustering, group those together into a unified output. Whether the output is for Single Consumer View, or to provide a means to provide aggregate views for demographics, time, geographies, and other critical data elements is now also possible, via a multistage approach to extract the core data (beyond ETL, this is to put into use for disclosed methods), getting one result set from the extraction, and using the extraction, or combination of extractions to provide a secondary result that would not be possible without first examining and providing contextual understanding to the initial data result.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Signal Processing (AREA)
  • Data Mining & Analysis (AREA)
  • Game Theory and Decision Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

La présente invention porte sur un système de communication de données et sur des procédés de commande de flux de données dans un système de communication de données. Le système de communication de données comprend un réseau de communication de données auquel des utilisateurs sont couplés lorsque le système de communication de données est en fonctionnement. Le système de communication de données comprend également un serveur de données. Les utilisateurs ont des identifiants d'utilisateur associés et peuvent interagir avec le système par le biais de dispositifs d'utilisateur ou les identifiants d'utilisateur sont dérivés de manière transformée à partir d'informations décrivant les utilisateurs. Le procédé consiste : à recevoir les identifiants d'utilisateur ; à déterminer des paires appariées des identifiants d'utilisateur ; à comparer les paires appariées des identifiants d'utilisateur avec chacun des identifiants d'utilisateur reçus et à déterminer un score de similarité pour les paires appariées et les identifiants d'utilisateur ; à mapper les identifiants d'utilisateur sur au moins un identifiant de vue client unique, chaque identifiant de vue client étant distinctement (à savoir, à l'intérieur d'un seuil de mappage) mappé avec un ou plusieurs identifiants d'utilisateur pour générer une fonction de mappage ; et à utiliser la fonction de mappage pour commander de façon sélective la distribution d'un contenu de données aux utilisateurs.
PCT/EP2017/025053 2016-03-18 2017-03-20 Systèmes de communication de données et procédés de fonctionnement de systèmes de communication de données Ceased WO2017157536A1 (fr)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US15/073,717 2016-03-18
GB1604649.2 2016-03-18
US15/073,717 US20170272362A1 (en) 2016-03-18 2016-03-18 Data communication systems and methods of operating data communication systems
GB1604649.2A GB2548563A (en) 2016-03-18 2016-03-18 Data communication systems and methods of operating data communication systems

Publications (1)

Publication Number Publication Date
WO2017157536A1 true WO2017157536A1 (fr) 2017-09-21

Family

ID=58398139

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2017/025053 Ceased WO2017157536A1 (fr) 2016-03-18 2017-03-20 Systèmes de communication de données et procédés de fonctionnement de systèmes de communication de données

Country Status (1)

Country Link
WO (1) WO2017157536A1 (fr)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120041939A1 (en) * 2010-07-21 2012-02-16 Lior Amsterdamski System and Method for Unification of User Identifiers in Web Harvesting
US8438184B1 (en) * 2012-07-30 2013-05-07 Adelphic, Inc. Uniquely identifying a network-connected entity
US20130124309A1 (en) * 2011-11-15 2013-05-16 Tapad, Inc. Managing associations between device identifiers

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120041939A1 (en) * 2010-07-21 2012-02-16 Lior Amsterdamski System and Method for Unification of User Identifiers in Web Harvesting
US20130124309A1 (en) * 2011-11-15 2013-05-16 Tapad, Inc. Managing associations between device identifiers
US8438184B1 (en) * 2012-07-30 2013-05-07 Adelphic, Inc. Uniquely identifying a network-connected entity

Similar Documents

Publication Publication Date Title
US12608423B2 (en) Methods and systems for associating internet devices
Zhou et al. Structure based user identification across social networks
Olmezogullari et al. Pattern2Vec: Representation of clickstream data sequences for learning user navigational behavior
Yang et al. Semi-supervised multi-modal clustering and classification with incomplete modalities
Aggarwal et al. Evolutionary network analysis: A survey
Deng et al. A user identification algorithm based on user behavior analysis in social networks
Ma et al. Improving recommender systems by incorporating social contextual information
US9514248B1 (en) System to group internet devices based upon device usage
Jiang et al. Fema: flexible evolutionary multi-faceted analysis for dynamic behavioral pattern discovery
US7953676B2 (en) Predictive discrete latent factor models for large scale dyadic data
US11671436B1 (en) Computational framework for modeling adversarial activities
US20170272362A1 (en) Data communication systems and methods of operating data communication systems
Zuva et al. A survey of recommender systems techniques, challenges and evaluation metrics
Moradi et al. A trust-aware recommender algorithm based on users overlapping community structure
Yang et al. Bi-directional joint inference for user links and attributes on large social graphs
Chen et al. A novel social recommendation method fusing user’s social status and homophily based on matrix factorization techniques
Dougnon et al. Inferring social network user profiles using a partial social graph
Khan et al. Collaborative filtering based online recommendation systems: A survey
KR20250039471A (ko) 콘텐츠 추천 방법 및 장치, 디바이스, 매체, 및 프로그램 제품
Singh et al. A survey on the generation of recommender systems
Chen et al. Learning user preference from heterogeneous information for store-type recommendation
Wang et al. Link prediction in heterogeneous collaboration networks
Zhang et al. Improving augmented reality using recommender systems
Liu et al. Collaborative prediction for multi-entity interaction with hierarchical representation
CN108389113B (zh) 一种协同过滤推荐方法和系统

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

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

Ref document number: 17712707

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 16.01.2019)

122 Ep: pct application non-entry in european phase

Ref document number: 17712707

Country of ref document: EP

Kind code of ref document: A1