Multi-source data fusion methods, devices, electronic equipment and storage media

Abstract

This application proposes a multi-source data fusion method, apparatus, electronic device, and storage medium. The method includes: determining individual viewing data belonging to different individuals based on voiceprint data in family viewing data, and determining first feature data corresponding to each individual viewing data; determining individual internet access data belonging to different individuals based on user agent information in family internet access logs, and determining second feature data corresponding to each individual internet access data based on the business characteristics of the accessed applications or the website tags of the accessed links in each individual internet access data; determining individual viewing data and individual internet access data belonging to the same family member based on the first feature data and the second feature data of each individual internet access data; and fusing the individual viewing data and individual internet access data corresponding to each family member to generate behavioral data corresponding to each family member. This improves the accuracy of distinguishing behavioral data among family members.

Description

Technical Field

[0001] This application relates to the field of big data technology, and in particular to a method, apparatus, electronic device and storage medium for multi-source data fusion. Background Technology

[0002] The home is an important place for people's lives, and a large number of family members' behavioral characteristics are contained in family life. However, there are one-to-many or one-to-many-one relationships between family members and devices, which makes it impossible to accurately determine the behavioral data corresponding to each family member.

[0003] Therefore, there is an urgent need for an accurate data fusion method to improve the accuracy of behavioral data for each family member. Summary of the Invention

[0004] This application aims to at least partially address one of the technical problems in the related art.

[0005] Therefore, the first objective of this application is to propose a multi-source data fusion method to improve the accuracy of distinguishing behavioral data of family members.

[0006] The second objective of this application is to propose a multi-source data fusion device.

[0007] The third objective of this application is to propose an electronic device.

[0008] The fourth objective of this application is to provide a computer-readable storage medium.

[0009] The fifth objective of this application is to provide a computer program product.

[0010] To achieve the above objectives, the first aspect of this application proposes a multi-source data fusion method, comprising:

[0011] Acquire family movie viewing data and family internet browsing logs within a preset time period;

[0012] Based on voiceprint data in family movie viewing data, we can identify individual movie viewing data belonging to different groups and determine the first feature data corresponding to each individual movie viewing data.

[0013] Based on user agent information in family internet access logs, identify personal internet access data belonging to different individuals, and based on the business characteristics of accessed applications or website tags of accessed links in each personal internet access data, determine the second feature data corresponding to each personal internet access data.

[0014] Based on the first feature data corresponding to each individual's movie viewing data and the second feature data corresponding to each individual's internet access data, the movie viewing data and internet access data of individuals belonging to the same family member are determined.

[0015] The personal movie-watching data and personal internet browsing data of each family member are merged to generate behavioral data for each family member.

[0016] To achieve the above objectives, a second aspect of this application provides a source data fusion apparatus, comprising:

[0017] The acquisition module is used to acquire family movie viewing data and family internet access logs within a preset time period;

[0018] The first determining module is used to determine the individual movie-watching data belonging to different objects based on the voiceprint data in the family movie-watching data, and to determine the first feature data corresponding to each individual movie-watching data.

[0019] The second determination module is used to determine the personal internet data belonging to different objects based on the user agent information in the family internet log, and to determine the second feature data corresponding to each personal internet data based on the business characteristics of the accessed application or the website tags of the accessed links in each personal internet data.

[0020] The third determining module is used to determine the movie viewing data and internet access data of individuals belonging to the same family member based on the first feature data corresponding to each individual's movie viewing data and the second feature data corresponding to each individual's internet access data.

[0021] The fusion module is used to merge the personal movie-watching data and personal internet access data of each family member to generate behavioral data for each family member.

[0022] To achieve the above objectives, a third aspect of this application provides an electronic device comprising:

[0023] At least one processor; and

[0024] A memory that is communicatively connected to at least one processor; wherein,

[0025] The memory stores instructions that can be executed by at least one processor, which enables the at least one processor to perform the methods of the above embodiments.

[0026] To achieve the above objectives, a fourth aspect of this application provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the method according to the above embodiments.

[0027] To achieve the above objectives, a fifth aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the methods of the above embodiments.

[0028] The multi-source data fusion method, apparatus, electronic device, and storage medium provided in this application, after acquiring family viewing data and family internet logs within a preset time period, can determine individual viewing data belonging to different individuals based on voiceprint data in the family viewing data, and determine the first feature data corresponding to each individual viewing data. Simultaneously, based on user agent information in the family internet logs, it can determine individual internet data belonging to different individuals, and based on the business characteristics of the accessed applications or the website tags of the accessed links in each individual internet data, it can determine the second feature data corresponding to each individual internet data. Then, based on the first feature data and the second feature data corresponding to each individual viewing data, it can determine the individual viewing data and individual internet data belonging to the same family member, and fuse the individual viewing data and individual internet data corresponding to each family member to generate behavioral data corresponding to each family member. Thus, firstly, individual viewing data and individual internet data are divided using a finer-grained classification standard, and then, based on the first feature data and the second feature data corresponding to each individual viewing data, the individual viewing data and individual internet data are aggregated to determine the individual viewing data and individual internet data belonging to the same family member. This improves the accuracy of distinguishing the behavioral data of family members.

[0029] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0030] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0031] Figure 1 A flowchart illustrating a multi-source data fusion method provided in an embodiment of this application;

[0032] Figure 2 A flowchart illustrating another multi-source data fusion method provided in an embodiment of this application;

[0033] Figure 3 This is a schematic diagram of the structure of a multi-source data fusion device provided in an embodiment of this application. Detailed Implementation

[0034] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0035] The multi-source data fusion method and apparatus of this application are described below with reference to the accompanying drawings.

[0036] The multi-source data fusion method of this application embodiment is executed by the multi-source data fusion device (hereinafter referred to as the fusion device) provided in this application embodiment. The device can be configured in computer equipment or terminal equipment to improve the accuracy of determining the behavioral data of each family member.

[0037] There are currently one-to-many and many-to-one relationships between family members and devices. For example, mobile phones, personal computers (PCs), and set-top boxes can be used by multiple family members, and a single family member may simultaneously use multiple mobile phones, PCs, and other terminal devices. This means that operational data generated on a particular device may not entirely correspond to the behavior data of a single family member, or data generated by different devices may actually belong to the same family member. Methods that differentiate behavior data from different family members based on time have a high probability of overlap, affecting the accuracy of distinguishing behavior data from different family members.

[0038] Considering that family members' user preferences remain relatively constant over a period of time, the content browsed and applications used by a particular family member should be correlated, although there may be some differences in the content browsed and applications used by different family members. In this application, feature data corresponding to behavioral data from different sources is extracted, and then these feature data are matched to distinguish the behavioral data corresponding to each family member. This approach is unaffected by one-to-many or one-to-many relationships between family members and devices, accurately distinguishing the behavioral data corresponding to different family members.

[0039] Figure 1 This is a flowchart illustrating a multi-source data fusion method provided in an embodiment of this application.

[0040] like Figure 1 As shown, this multi-source data fusion method includes the following steps:

[0041] Step 101: Obtain family movie viewing data and family internet access logs within the preset time period.

[0042] When family members access the internet via broadband or through other connected devices (such as iOS devices, Android devices, IoT devices (like smart speakers and smart appliances), wearable devices (like watches and fitness trackers), etc.), the router records network access information in its logs. Therefore, the entire family's internet access logs can be retrieved from the router manager.

[0043] When family members watch movies on internet TV, they can receive voice control commands via remote control and send these commands to the set-top box to change the content being played. The set-top box then generates and saves viewing data based on the voiceprint data in the voice control commands, the viewed program content, and the viewing time. This allows the collection of family viewing data.

[0044] Step 102: Based on the voiceprint data in the family movie viewing data, determine the individual movie viewing data belonging to different objects, and determine the first feature data corresponding to each individual movie viewing data.

[0045] In this application, family viewing data can be segmented based on the time when each voiceprint data is received to obtain individual viewing data. For example, the data generated between the time when the nth voiceprint data is received and the time when the (n+1)th voiceprint data is received can be identified as the individual viewing data corresponding to the nth voiceprint data.

[0046] In this application, the voiceprint information of each family member is different. Therefore, any voiceprint recognition algorithm can be used to identify the voiceprint data corresponding to each individual's movie-watching data, and the movie-watching data corresponding to different voiceprint data can be merged to obtain at least one individual movie-watching data corresponding to different objects.

[0047] Next, after quantifying the individual viewing data, arbitrary feature extraction methods (such as Principal Component Analysis (PCA), Linear Decision Analysis (LDA), and Multidimensional Scaling Analysis (MDS)) are used to extract features from the individual viewing data to determine the first feature data corresponding to the individual viewing data. The first feature data may include viewing time period, program type, etc. Program type may include shopping, fitness, food, learning, technology, etc.

[0048] Step 103: Based on the user agent information in the family internet access log, determine the personal internet access data belonging to different objects, and based on the business characteristics of the accessed applications or the website tags of the accessed links in each personal internet access data, determine the second feature data corresponding to each personal internet access data.

[0049] In this application, the family internet access log contains multiple records of personal internet access data, and each record contains User Agent information. User Agent analysis tools can be used to parse the User Agent in each record to determine the browser, browser engine, platform name, platform manufacturer, operating system, IP address, MAC address, and other information used by the user corresponding to that User Agent. Then, if any two User Agents correspond to users with identical browser, browser engine, platform name, platform manufacturer, operating system, IP address, and MAC address information, it is determined that the personal internet access data corresponding to those two User Agents belong to the same entity.

[0050] Optionally, if the personal internet access data is internet access data generated by accessing an application, the personal internet access data is parsed to determine the business characteristics of the accessed application. Then, based on the application type relationship table, the application type associated with the business characteristics is determined. Finally, based on the application domain associated with the application type, the second feature data corresponding to the personal internet access data is generated.

[0051] One possible implementation is to use DPI (Deep Packet Inspection) technology to identify each individual's internet browsing data and determine the business characteristics (i.e., the business characteristics of the accessed applications) contained within the data. These business characteristics can include application names, keywords, etc. Then, a pre-defined application type relationship table can be queried to determine the application type associated with that business characteristic. Application types can include online games, social networks, self-media, cloud notes, email, app stores, instant messaging, fitness trackers, smartwatch upgrades, smart home appliance settings, etc. Next, the application domain associated with each application type can be pre-defined in the system. This allows for the determination of the application domain associated with each application type, and the generation of second-feature data based on the application domain, internet access time, etc. Application domains can include shopping, fitness, food, learning, technology, etc.

[0052] Optionally, if the personal internet access data consists of data generated from accessing links, the personal internet access data is parsed to extract the website tags of the links. Then, based on a business tag relationship table, the business tags associated with the website tags are determined. Finally, based on the application domain associated with the business tags, second feature data corresponding to the personal internet access data is generated.

[0053] One possible implementation is to identify website tags visited by users by recognizing URL information in logs. These website tags can include things like the website name. Then, a pre-set business tag relationship table can be queried to determine the business tags associated with each website tag. These business tags can include information such as the website's main business and website type. Next, the application domain associated with each business tag can be pre-defined in the system. This allows for the determination of the application domain associated with each business tag, and the generation of second-feature data based on the application domain, online time period, etc. These application domains can include shopping, fitness, food, learning, technology, etc.

[0054] It should be noted that the objects identified in this application are virtual, and multiple objects may correspond to the same family member.

[0055] Optionally, the first feature data and the second feature data can be quantized to facilitate subsequent processing steps.

[0056] Step 104: Based on the first feature data corresponding to each individual's movie viewing data and the second feature data corresponding to each individual's internet access data, determine the movie viewing data and internet access data belonging to the same family member.

[0057] In this application, clustering algorithms (such as twostep clustering, K-means clustering, hierarchical clustering, etc.) can be used to cluster the first feature data corresponding to each individual's movie viewing data and the second feature data corresponding to each individual's internet access data to obtain objects belonging to the same class.

[0058] For example, the first feature data corresponding to individual movie-watching data belonging to the same individual can be grouped into one category, and the second feature data corresponding to individual internet browsing data belonging to the same individual can be grouped into another category. Then, based on the first and second feature data of the samples contained in each category, the distance between categories is determined, and the categories are merged based on the distance between categories. This process is continued until multiple large categories are obtained.

[0059] It is understandable that each cluster obtained from the final clustering corresponds to a family member. The personal movie-watching data corresponding to each first feature data and the personal internet access data corresponding to each second feature data contained in each cluster correspond to a family member.

[0060] For example, personal internet access data 1 and personal internet access data 2 belong to object NID1, personal internet access data 3 and personal internet access data 4 belong to object NID2, personal movie viewing data 1 and personal movie viewing data 2 belong to object XID1, and personal movie viewing data 3 and personal movie viewing data 4 belong to object XID2. After clustering based on the characteristics (first characteristic data or second characteristic data) of the above data, it is determined that personal internet access data 1, personal internet access data 2, personal movie viewing data 1, and personal movie viewing data 2 belong to the same category, and personal internet access data 3, personal internet access data 4, and personal movie viewing data 3, and personal movie viewing data 4 belong to the same category. Therefore, it can be determined that object NID1 and object XID1 belong to the same family member OID1, and object NID2 and object XID2 belong to the same family member OID2. Family member OID1 corresponds to personal internet access data 1, personal internet access data 2, personal movie viewing data 1, and personal movie viewing data 2. Family member OID2 corresponds to personal internet access data 3, personal internet access data 4, and personal movie viewing data 3, and personal movie viewing data 4.

[0061] Step 105: Merge the personal movie-watching data and personal internet access data of each family member to generate behavioral data for each family member.

[0062] In this application, the personal movie-watching data and personal internet access data of each family member are merged to generate behavioral data for each family member.

[0063] In this application, after obtaining family movie-watching data and family internet logs within a preset time period, the system can determine individual movie-watching data belonging to different individuals based on voiceprint data in the family movie-watching data, and determine the first feature data corresponding to each individual movie-watching data. Simultaneously, based on user agent information in the family internet logs, it can determine individual internet access data belonging to different individuals, and based on the business characteristics of the accessed applications or the website tags of the accessed links in each individual internet access data, it can determine the second feature data corresponding to each individual internet access data. Then, based on the first feature data and the second feature data corresponding to each individual movie-watching data, it can determine the individual movie-watching data and individual internet access data belonging to the same family member, and merge the individual movie-watching data and individual internet access data corresponding to each family member to generate behavioral data corresponding to each family member. Thus, by first dividing individual movie-watching data and individual internet access data using a finer-grained classification standard, and then aggregating the individual movie-watching data and individual internet access data based on the first feature data and the second feature data corresponding to each individual movie-watching data, it can determine the individual movie-watching data and individual internet access data belonging to the same family member. This improves the accuracy of distinguishing the behavioral data of family members.

[0064] Figure 2This is a flowchart illustrating a multi-source data fusion method provided in an embodiment of this application.

[0065] like Figure 2 As shown, this multi-source data fusion method includes the following steps:

[0066] Step 201: Obtain family movie viewing data and family internet access logs within a preset time period.

[0067] Step 202: Based on the voiceprint data in the family movie viewing data, determine the individual movie viewing data belonging to different objects, and determine the first feature data corresponding to each individual movie viewing data.

[0068] Step 203: Based on the user agent information in the family internet access log, determine the personal internet access data belonging to different objects, and based on the business characteristics of the accessed applications or the website tags of the accessed links in each personal internet access data, determine the second feature data corresponding to each personal internet access data.

[0069] Step 204: Based on the first feature data corresponding to each individual's movie viewing data and the second feature data corresponding to each individual's internet access data, determine the movie viewing data and internet access data belonging to the same family member.

[0070] Step 205: Merge the personal movie-watching data and personal internet access data of each family member to generate behavioral data for each family member.

[0071] The specific implementation process of steps 201-205 in this application can be found in the detailed description of any embodiment of this application, and will not be repeated here.

[0072] Step 206: Perform profile processing based on the behavioral data of each family member to obtain a user profile for each family member.

[0073] In this application, the behavioral data of each family member can be processed based on any profiling algorithm to obtain a user profile for each family member.

[0074] Understandably, on the one hand, the behavioral data for each family member in this application includes data on application access through various devices, access connection data, and viewing data, thus enhancing the richness of the behavioral data. On the other hand, by first using finer-grained segmentation criteria to divide individual viewing data and individual internet access data, and then aggregating these data based on the first feature data corresponding to each individual viewing data point and the second feature data corresponding to each individual internet access data point, the individual viewing data and individual internet access data are determined to belong to the same family member. This improves the accuracy of distinguishing family member behavioral data. Furthermore, creating user profiles based on richer and more accurate family member behavioral data helps improve the accuracy of the user profiles corresponding to each family member.

[0075] In this application, after obtaining family movie-watching data and family internet logs within a preset time period, the system identifies individual movie-watching data belonging to different individuals based on voiceprint data within the family movie-watching data, and determines the first feature data corresponding to each individual's movie-watching data. Simultaneously, based on user agent information in the family internet logs, the system identifies individual internet access data belonging to different individuals, and determines the second feature data corresponding to each individual's internet access data based on the business characteristics of the accessed applications or the website tags of the accessed links. Then, based on the first and second feature data corresponding to each individual's movie-watching data, the system identifies individual movie-watching and internet access data belonging to the same family member. Finally, the individual movie-watching and internet access data corresponding to each family member are merged to generate behavioral data corresponding to each family member. This behavioral data is then used for profiling to obtain a user profile for each family member. Therefore, using richer and more accurate behavioral data of family members to create user profiles improves the accuracy of the user profiles for each family member.

[0076] To achieve the above embodiments, this application also proposes a multi-source data fusion device.

[0077] Figure 3 This is a schematic diagram of the structure of a multi-source data fusion device provided in an embodiment of this application.

[0078] like Figure 3 As shown, the multi-source data fusion device includes an acquisition module 310, a first determination module 320, a second determination module 330, a third determination module 340, and a fusion module 350.

[0079] The acquisition module 310 is used to acquire family movie viewing data and family internet access logs within a preset time period;

[0080] The first determining module 320 is used to determine the individual viewing data belonging to different objects based on the voiceprint data in the family viewing data, and to determine the first feature data corresponding to each individual viewing data.

[0081] The second determining module 330 is used to determine personal internet data belonging to different objects based on user agent information in the family internet log, and to determine the second feature data corresponding to each personal internet data based on the business characteristics of the accessed application or the website tags of the accessed links in each personal internet data.

[0082] The third determining module 340 is used to determine the personal movie-watching data and personal internet access data belonging to the same family member based on the first feature data corresponding to each individual's movie-watching data and the second feature data corresponding to each individual's internet access data.

[0083] The fusion module 350 is used to merge the personal movie viewing data and personal internet access data of each family member to generate behavioral data for each family member.

[0084] Furthermore, in one possible implementation of this application embodiment, the second determining module 330 is used for:

[0085] When personal internet data is internet data generated by accessing applications, the personal internet data is parsed to determine the business characteristics of the accessed applications.

[0086] Based on the application type relationship table, determine the application types associated with business characteristics;

[0087] Based on the application domain associated with the application type, second feature data corresponding to personal internet access data is generated.

[0088] Furthermore, in one possible implementation of this application embodiment, the second determining module 330 is used for:

[0089] When personal internet data consists of data generated from accessing links, the personal internet data is parsed to extract the website tags of the links;

[0090] Based on the business tag relationship table, determine the business tags associated with website tags;

[0091] Based on the application domain associated with business tags, second feature data corresponding to personal internet access data is generated.

[0092] Furthermore, in one possible implementation of this application embodiment, a portrait module is also included, used for:

[0093] Based on the behavioral data of each family member, a user profile is obtained for each family member.

[0094] It should be noted that the foregoing explanation of the multi-source data fusion method embodiment also applies to the multi-source data fusion device of this embodiment, and will not be repeated here.

[0095] In this application, after obtaining family movie-watching data and family internet logs within a preset time period, the system can determine individual movie-watching data belonging to different individuals based on voiceprint data in the family movie-watching data, and determine the first feature data corresponding to each individual movie-watching data. Simultaneously, based on user agent information in the family internet logs, it can determine individual internet access data belonging to different individuals, and based on the business characteristics of the accessed applications or the website tags of the accessed links in each individual internet access data, it can determine the second feature data corresponding to each individual internet access data. Then, based on the first feature data and the second feature data corresponding to each individual movie-watching data, it can determine the individual movie-watching data and individual internet access data belonging to the same family member, and merge the individual movie-watching data and individual internet access data corresponding to each family member to generate behavioral data corresponding to each family member. Thus, by first dividing individual movie-watching data and individual internet access data using a finer-grained classification standard, and then aggregating the individual movie-watching data and individual internet access data based on the first feature data and the second feature data corresponding to each individual movie-watching data, it can determine the individual movie-watching data and individual internet access data belonging to the same family member. This improves the accuracy of distinguishing the behavioral data of family members.

[0096] To implement the above embodiments, this application also proposes an electronic device, including: a processor and a memory communicatively connected to the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method provided in the foregoing embodiments.

[0097] To implement the above embodiments, this application also proposes a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided in the foregoing embodiments.

[0098] To implement the above embodiments, this application also proposes a computer program product, including a computer program that, when executed by a processor, implements the methods provided in the foregoing embodiments.

[0099] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0100] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0101] This application is intended to provide an implementation scheme for users to selectively prevent the use or access to their personal information data. Specifically, this application is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0102] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0103] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0104] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0105] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0106] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0107] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0108] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0109] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A multi-source data fusion method, characterized in that, The method includes: Acquire family movie viewing data and family internet browsing logs within a preset time period; Based on the voiceprint data in the family movie-watching data, individual movie-watching data belonging to different objects are determined, and the first feature data corresponding to each individual movie-watching data is determined; Based on the user agent information in the family internet access log, determine the personal internet access data belonging to different objects, and based on the business characteristics of the accessed application or the website tags of the accessed links in each personal internet access data, determine the second feature data corresponding to each personal internet access data. Based on the first feature data corresponding to each individual's movie viewing data and the second feature data corresponding to each individual's internet access data, the movie viewing data and internet access data belonging to the same family member are determined. The personal movie-watching data and personal internet access data of each family member are merged to generate behavioral data for each family member.

2. The method as described in claim 1, characterized in that, The step of determining the second feature data corresponding to each individual's internet access data based on the service characteristics of the accessed applications in each individual's internet access data includes: In the case where the personal internet data is internet data generated by accessing an application, the personal internet data is parsed to determine the business characteristics of the accessed application; Based on the application type relationship table, determine the application type associated with the business characteristics; Based on the application domain associated with the application type, second feature data corresponding to the personal internet access data is generated.

3. The method as described in claim 1, characterized in that, The step of determining the second feature data corresponding to each individual's internet access data based on the website tags corresponding to the access links in each individual's internet access data includes: In the case where the personal internet data is internet data generated by accessing links, the personal internet data is parsed to extract the website tags of the links; Based on the business tag relationship table, determine the business tags associated with the website tags; Based on the application domain associated with the business tag, second feature data corresponding to the personal internet access data is generated.

4. The method as described in claim 1, characterized in that, Also includes: Based on the behavioral data of each family member, a user profile is obtained for each family member.

5. A multi-source data fusion device, characterized in that, The device includes: The acquisition module is used to acquire family movie viewing data and family internet access logs within a preset time period; The first determining module is used to determine individual movie-watching data belonging to different objects based on the voiceprint data in the family movie-watching data, and to determine the first feature data corresponding to each individual movie-watching data. The second determining module is used to determine personal internet data belonging to different objects based on the user agent information in the family internet log, and to determine the second feature data corresponding to each personal internet data based on the business characteristics of the accessed application or the website tags of the accessed links in each personal internet data. The third determining module is used to determine the personal movie-watching data and personal internet access data belonging to the same family member based on the first feature data corresponding to each personal movie-watching data and the second feature data corresponding to each personal internet access data. The fusion module is used to merge the personal movie-watching data and personal internet access data of each family member to generate behavioral data for each family member.

6. The apparatus as claimed in claim 5, characterized in that, The second determining module is used for: In the case where the personal internet data is internet data generated by accessing an application, the personal internet data is parsed to determine the business characteristics of the accessed application; Based on the application type relationship table, determine the application type associated with the business characteristics; Based on the application domain associated with the application type, second feature data corresponding to the personal internet access data is generated.

7. The apparatus as claimed in claim 5, characterized in that, The second determining module is used for: In the case where the personal internet data is internet data generated by accessing links, the personal internet data is parsed to extract the website tags of the links; Based on the business tag relationship table, determine the business tags associated with the website tags; Based on the application domain associated with the business tag, second feature data corresponding to the personal internet access data is generated.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-4.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-4.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-4.

Images