WO2021056734A1 - 好友关系链匹配方法、系统、计算机设备及可读存储介质 - Google Patents

好友关系链匹配方法、系统、计算机设备及可读存储介质 Download PDF

Info

Publication number
WO2021056734A1
WO2021056734A1 PCT/CN2019/117556 CN2019117556W WO2021056734A1 WO 2021056734 A1 WO2021056734 A1 WO 2021056734A1 CN 2019117556 W CN2019117556 W CN 2019117556W WO 2021056734 A1 WO2021056734 A1 WO 2021056734A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
content
weight coefficient
users
candidate
Prior art date
Application number
PCT/CN2019/117556
Other languages
English (en)
French (fr)
Inventor
房小颖
徐小方
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2021056734A1 publication Critical patent/WO2021056734A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06F16/9536—Search customisation based on social or collaborative filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/01—Social networking

Definitions

  • the embodiments of the present application relate to the field of computer data processing, and in particular to a method, system, computer device, and non-volatile computer-readable storage medium for matching a friend relationship chain.
  • Instant messaging software aims to help people establish a friendship chain, and solve the problem of long-distance communication between people by establishing a friendship chain.
  • the number and quality of friendship chains will affect the retention and activity of users on the instant messaging platform to a large extent. Under normal circumstances, you can manually add friends directly by entering other user IDs, or you can match the corresponding friends according to the phone numbers of each contact in the address book. However, it is impossible to establish a friend relationship chain with a certain scale and high quality only by establishing a friend relationship chain in the above-mentioned manner.
  • the solutions currently known by the inventors are: (1) The user enters search conditions, such as entering search conditions such as gender, region, age, etc., searches for eligible users according to the search conditions entered by the user, and searches The user who arrives is recommended to this user. (2) The basic personal information filled in by the user during registration is used as the search condition, and similar users are searched according to the search condition, and the searched user is recommended to the user.
  • solution (1) friend relationship chain matching requires user manual intervention, when searching for friends, users who are not familiar with the system may not be able to search for satisfactory results, thus Affect the user experience; solution (2), this is based on the basic personal information such as gender, age and other personal information filled in during registration, automatically matching the friend relationship chain for the user, the accuracy is low, because the user information may be filled in incompletely, filled in false information, etc. problem.
  • the purpose of the embodiments of the present application is to provide a friend relationship chain matching method, system, computer equipment, and non-volatile computer-readable storage medium, to solve the problem of manual intervention in matching the friend relationship chain and automatically matching the friend relationship chain The problem of low accuracy.
  • an embodiment of the present application provides a friend relationship chain matching method, which includes the following steps:
  • the user's behavior information is obtained through the mobile terminal
  • a mining condition is configured according to the behavior information, and a plurality of candidate users that meet the mining conditions are mined from the behavior information of users other than the user;
  • Pushing step pushing the multiple candidate users to the friend recommendation list in the user's instant messaging tool
  • the receiving step is to receive the user's selection operation for one or more of the candidate users.
  • a relationship chain establishment step is to establish a friend relationship chain between the user and the selected one or more candidate users according to the selection operation.
  • an embodiment of the present application also provides a friend relationship chain matching system, which includes:
  • the obtaining module is used to obtain the user's behavior information through the mobile terminal;
  • the mining module is configured to configure mining conditions according to the behavior information, and mine multiple candidate users that meet the mining conditions from the behavior information of users other than the user;
  • a push module configured to push the multiple candidate users to the friend recommendation list in the user's instant messaging tool
  • the receiving module is configured to receive the user's selection operation for one or more of the candidate users.
  • the relationship chain establishment module is used to establish a friend relationship chain between the user and the selected one or more candidate users according to the selection operation.
  • an embodiment of the present application further provides a computer device, the computer device including a memory, a processor, and computer-readable instructions stored in the memory and running on the processor, the When the computer-readable instructions are executed by the processor, the following steps are implemented:
  • the user's behavior information is obtained through the mobile terminal
  • a mining step configuring mining conditions according to the behavior information, and mining multiple candidate users that meet the mining conditions from the behavior information of users other than the user;
  • Pushing step pushing the multiple candidate users to the friend recommendation list in the user's instant messaging tool
  • the receiving step is to receive the user's selection operation for one or more of the candidate users.
  • a relationship chain establishment step is to establish a friend relationship chain between the user and the selected one or more candidate users according to the selection operation.
  • the embodiments of the present application also provide a non-volatile computer-readable storage medium, the non-volatile computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions may Is executed by at least one processor, so that the at least one processor executes the following steps:
  • the user's behavior information is obtained through the mobile terminal
  • a mining step configuring mining conditions according to the behavior information, and mining multiple candidate users that meet the mining conditions from the behavior information of users other than the user;
  • Pushing step pushing the multiple candidate users to the friend recommendation list in the user's instant messaging tool
  • the receiving step is to receive the user's selection operation for one or more of the candidate users.
  • a relationship chain establishment step is to establish a friend relationship chain between the user and the selected one or more candidate users according to the selection operation.
  • the friend relationship chain matching method, system, computer equipment, and non-volatile computer-readable storage medium comprehensively analyze the user’s behavior by collecting user behavior information (for example, browsing information on the browser, etc.) Interests and hobbies, and then set mining conditions, mining users who meet the mining conditions from the data information of other massive users..., and then match the friend relationship chain without manual intervention by the user, and the above-mentioned behavior information can be Representing the real life state of a user, the user’s interest orientation can be more analyzed, and friends can be matched through these behavioral information, and the matching accuracy is higher.
  • user behavior information for example, browsing information on the browser, etc.
  • FIG. 1 is a flowchart of Embodiment 1 of a method for matching a friend relationship chain of this application.
  • Fig. 2 is a flowchart of step S102 in Fig. 1 in an exemplary embodiment.
  • Fig. 3 is a flowchart of step S102 in Fig. 1 in another exemplary embodiment.
  • Fig. 4 is a flowchart of step S104 in Fig. 1 in an exemplary embodiment.
  • Fig. 5 is a flowchart of step S104 in Fig. 1 in another exemplary embodiment.
  • Fig. 6 is a flowchart of step S104 in Fig. 1 in another exemplary embodiment.
  • FIG. 7 is a flowchart of step S110 in the first embodiment of the method for matching a friend relationship chain of this application.
  • FIG. 8 is a flowchart of Embodiment 2 of a method for matching a friend relationship chain of the application.
  • Fig. 9 is a schematic diagram of the program modules of the third embodiment of the friend relationship chain matching system of this application.
  • FIG. 10 is a schematic diagram of the hardware structure of the fourth embodiment of the computer equipment of this application.
  • FIG. 1 shows a flowchart of the steps of a method for matching a friend relationship chain in the first embodiment of the present application. It can be understood that the flowchart in this method embodiment is not used to limit the order of execution of the steps. details as follows.
  • Step S100 Obtain user behavior information through the mobile terminal.
  • the behavior information includes page access records and interest-based APP usage information, such as the frequency and duration of use of each interest-based APP.
  • the hobby apps such as game apps (King of Glory, Kart, etc.), learning apps (English Fluent Talk, Hundred Words, Douban, etc.), investment apps (Xueqiu, Tiantian Fund, etc.), etc.
  • Step S102 Configure mining conditions according to the behavior information, and mine multiple candidate users that meet the mining conditions from the behavior information of users other than the user.
  • step S102 may further include:
  • step S102A1 the content theme of each visited page is obtained according to the page access record, and a weight coefficient is configured for each content theme according to the number of appearances of each content theme;
  • Step S102A2 setting the weight coefficient range of each content theme with the weight coefficient of each content theme as the center;
  • step S102A3 according to each content topic and the weight coefficient range corresponding to each content topic, multiple candidate users that meet the requirements are matched.
  • weight coefficient For example, suppose the weight coefficient is 0-100, and 4 content themes are obtained according to the page access records.
  • the weight coefficient of the first content theme is 75
  • the weight coefficient of the second content theme is 30, and the weight coefficient of the third content theme is 22.
  • the weight coefficient of the fourth content topic is 60.
  • Taking the weight coefficients of these 4 content topics as the center for example, set the weight coefficient range of the first content topic to 75 ⁇ 5 (including the end point), and set the weight coefficient range of the second content topic to 30 ⁇ 5 (including the end point) , Set the weight coefficient range of the third content theme to 22 ⁇ 5 (including endpoints), and set the weight coefficient range of the fourth content theme to 60 ⁇ 5 (including endpoints), and then set the corresponding theme content in other users
  • the users within the above range are regarded as candidate users.
  • user A the weight coefficient of the first content theme is 71, the weight coefficient of the second content theme is 32, the weight coefficient of the third content theme is 21, and the weight coefficient of the fourth content theme is 65, then user A can be used as User to be selected;
  • User B The weight coefficient of the first content theme is 71, the weight coefficient of the second content theme is 32, the weight coefficient of the third content theme is 21, and the weight coefficient of the fourth content theme is 66. Because user B The weight coefficient of the fourth content topic of is outside the weight coefficient range, and all do not meet the requirements, so user B does not belong to the candidate user.
  • step S102 may further include:
  • Step S102B1 Obtain the content theme of each visited page according to the page access record, and configure a weight coefficient for each content theme according to the number of occurrences of each content theme; Step S102B2, filter out the weight according to the weight coefficient of each content theme A number of effective content topics with coefficients higher than the preset threshold; step S102B3, centering on the weight coefficient of each effective content topic, set the weight coefficient range of each effective content topic; step S102B4, according to each effective content
  • the theme and the weight coefficient range corresponding to each effective content theme match multiple candidate users who meet the requirements.
  • Step S104 Push the multiple candidate users to the friend recommendation list in the user's instant messaging tool.
  • the friend recommendation list includes the recommended relationship of each candidate user; as shown in FIG. 4, the step S104 may further include the steps:
  • Step S104A1 according to the weight coefficient of each content theme (or effective content theme) corresponding to each user to be selected, calculate the matching coefficient of each user to be selected and the user;
  • Step S104A2 Determine the recommendation degree of each candidate user in the friend recommendation list according to the matching coefficient of each candidate user and the user.
  • the matching coefficient of each candidate user can be calculated by the following formula:
  • P i is the matching coefficient between the candidate user i and the user
  • ⁇ is a constant
  • ⁇ j is the weight coefficient of the content topic (or effective content topic) j
  • ⁇ ij is "the content topic in the user (or The ratio between the weight coefficient of the effective content topic) j and the weight coefficient of the content topic (or effective content topic) j in the candidate user i”, the ratio is less than or equal to 1
  • m is the total number of content topics.
  • the step S104 may further include the steps:
  • Step S104B1 map the weight coefficient of each content topic (or effective content topic) in each candidate user to a corresponding topic interest index
  • Step S104B2 define visual information (such as text, image, etc.) according to each subject interest index in each candidate user;
  • Step S104B3 Push the visual information corresponding to each candidate user to the friend recommendation list in the user's instant messaging tool, and the visual information corresponding to each candidate user is displayed in the friend recommendation list corresponding to the candidate user Where the field is located.
  • the candidate user and the visual information are pushed to the friend recommendation list in the user's instant messaging tool.
  • the step S104 may further include the steps:
  • Step S104C1 judging whether the number of the multiple users to be selected is greater than a preset threshold
  • Step S104C2 if it is not greater than the preset threshold, push the multiple candidate users to the friend recommendation list in the user's instant messaging tool;
  • Step S104C3 if it is greater than the preset threshold, select some of the candidate users from the plurality of candidate users according to the basic user information of the user, and push the selected portion of the candidate users to the The user’s instant messaging tool’s friend recommendation list.
  • the basic user information of the user includes, but is not limited to, age, gender, occupation, income range, geographic location, etc.
  • Configure additional mining conditions based on the user’s basic user information such as configuring an age range centered on the user’s age, a related occupation range centered on the user’s occupation, an extended income range centered on the user’s income range, and a user’s address location as the center.
  • the address range of the center If the user is: a 35-year-old male, occupation is IT, and the address is Shenzhen XX Financial Building, additional mining conditions can be configured: age 30-40, male, computer industry, within 100 kilometers of XX Financial Building. According to the additional mining condition, a plurality of candidate users that meet the conditions are screened out among the plurality of candidate users.
  • the additional mining conditions are modified, such as expanding the scope and deleting some items (for example, deleting "occupation").
  • Step S106 Receive the user's selection operation for one or more of the candidate users.
  • the user can input selection instructions (such as single or continuous multiple mouse click operations, touch operations) through the graphical interface interface provided by the instant messaging tool.
  • selection instructions such as single or continuous multiple mouse click operations, touch operations
  • Step S108 According to the selection operation, a friend relationship chain is established between the user and the selected one or more candidate users.
  • the instant messaging tool sends a request for establishing a friend relationship chain for one of the candidate users (hereinafter referred to as the "target user") according to the selection instruction input by the user.
  • the computer device After receiving the request information, the computer device will send a request message of "friend request to join” to the target user, and after the target user sends a response message of "approval”, establish a friend relationship between the user and the target user chain.
  • the method may further include a friend recommendation list adjustment step S110, and the step S110 may further include the following steps: step S110A1, recording the user through the friend recommendation list Click to enter the multiple personal pages of multiple interested users; step S110A2, according to the visit time and number of visits on each personal page, define a weight coefficient for these interested users; step S110A3, according to the weight of each interested user Coefficients and the weight coefficients of each content theme of each interested user, readjust the weight coefficient of the user for each content theme; step S110A4, recalculate the plurality of candidate selections according to the adjusted weight coefficient of each content theme The matching coefficient between the user and the user; step S110A5, based on the recalculated matching coefficient, adjust the order of the multiple candidate users in the friend recommendation list.
  • step S110A1 recording the user through the friend recommendation list Click to enter the multiple personal pages of multiple interested users
  • step S110A2 according to the visit time and number of visits on each personal page, define a weight coefficient for these interested users
  • step S110A3
  • step S110 is only an exemplary solution for rearranging the friend recommendation table.
  • other solutions can also be used to adjust the friend recommendation list. For example, when the user clicks on a topic interest index, the topic interest index is taken as the single consideration factor. The order of the multiple candidate users in the friend recommendation list.
  • FIG. 8 shows a flowchart of the steps of the method for matching a friend relationship chain in the second embodiment of the present application. It can be understood that the flowchart in this method embodiment is not used to limit the order of execution of the steps. details as follows.
  • Step S200 Obtain user behavior information through the mobile terminal.
  • the behavior information includes page visit records, interest-based APP usage information, such as the frequency and duration of use of each interest-based APP.
  • the hobby apps such as game apps (King of Glory, Kart, etc.), learning apps (English Fluent Talk, Hundred Words, Douban, etc.), investment apps (Xueqiu, Tiantian Fund, etc.), etc.
  • Step S202 Obtain the content theme of each visited page according to the page access record in the behavior information to obtain n content themes.
  • step S204 a weight coefficient is configured for each content theme according to the number of appearances of each content theme.
  • Step S206 Define an N-dimensional parameter vector according to the n content themes of the user, and the weight coefficients of the n content themes are respectively placed at corresponding positions of the N-dimensional parameter vector, where N ⁇ n.
  • N content themes may be pre-configured, where N is a positive integer greater than 1, and it is obtained through step S200 that the user is involved in n content themes, and no other content themes are involved (that is, content themes that do not appear).
  • the weight coefficients of other content topics can be set to a fixed value, such as 0, in the N-dimensional parameter vector.
  • Step S208 Calculate the predicted matching values of M interest tags according to the N-dimensional parameter vector and the Long Short-Term Memory (LSTM) network model (LSTM).
  • LSTM Long Short-Term Memory
  • the steps of calculating the predicted matching values of M interest tags are as follows:
  • C t-1 t-1 represents the memory information of the node
  • f t represents the choice of the node at time t time t-1 of the memory cell weight
  • i t t represents the time node selection Information and the current node
  • o t ⁇ (W o [x t ,h t-1 ]+b o ), where o t ⁇ [0,1] represents the selection weight of the node cell memory information at time t, and b o is the bias of the output gate , W o is the weight matrix of the output gate, Represents the vector after the concatenation of the vectors x t and h t-1 , that is, a vector of
  • x t represents the input vector of the LSTM neural network node at time t, that is, the N-dimensional parameter vector in this embodiment;
  • h t is the output vector of the LSTM neural network node at time t, that is, the prediction matching for M interest tags in this embodiment value.
  • Step S210 according to the predicted matching values of the M interest tags, filter out m effective interest tags whose predicted matching values are higher than a preset threshold;
  • Step S212 centering on the predicted matching value of each effective interest tag, set the weight coefficient range of each effective interest tag.
  • Step S214 According to the m effective interest tags and the weight coefficient range corresponding to each effective interest tag, multiple candidate users that meet the requirements are matched.
  • step S216 the multiple candidate users are pushed to the friend recommendation list in the user's instant messaging tool.
  • the friend recommendation list includes the recommended relationship of each candidate user; the step S216 further includes the steps:
  • the matching degree coefficient between each candidate user and the user is calculated, and the matching degree coefficient is used to determine the recommendation of each candidate user in the friend recommendation list degree.
  • step S216 further includes the steps:
  • the basic user information of the user includes, but is not limited to, age, gender, occupation, income range, geographic location, etc.
  • Configure additional mining conditions based on the user’s basic user information such as configuring an age range centered on the user’s age, a related occupation range centered on the user’s occupation, an extended income range centered on the user’s income range, and a user’s address location as the center.
  • the address range of the center If the user is: a 35-year-old male, occupation is IT, and the address is Shenzhen XX Financial Building, additional mining conditions can be configured: age 30-40, male, computer industry, within 100 kilometers of XX Financial Building. According to the additional mining condition, a plurality of candidate users that meet the conditions are screened out among the plurality of candidate users.
  • the additional mining conditions are modified, such as expanding the scope and deleting some items (for example, deleting "occupation").
  • Step S218 receives the user's selection operation for one or more of the candidate users.
  • the user can input selection instructions (such as single or continuous multiple mouse click operations, touch operations) through the graphical interface interface provided by the instant messaging tool.
  • selection instructions such as single or continuous multiple mouse click operations, touch operations
  • Step S220 according to the selection operation, establish a friend relationship chain between the user and the selected one or more candidate users.
  • the instant messaging tool sends a request for establishing a friend relationship chain for one of the candidate users (hereinafter referred to as "target user") according to the selection instruction input by the user.
  • target user the candidate users
  • the computer device After receiving the request information, the computer device will send a request message of "friend request to join” to the target user, and after the target user sends a response message of "approval”, establish a friend relationship between the user and the target user chain.
  • FIG. 9 shows a schematic diagram of the program modules of Embodiment 3 of the friend relationship chain matching system of the present application.
  • the friend relationship chain matching system 20 may include or be divided into one or more program modules, and the one or more program modules are stored in a storage medium and executed by one or more processors to This application is completed, and the above-mentioned friend relationship chain matching method can be realized.
  • the program module referred to in the embodiments of the present application refers to a series of computer-readable instruction segments that can complete specific functions. The following description will specifically introduce the functions of each program module in this embodiment:
  • the obtaining module 200 is used to obtain user behavior information through a mobile terminal.
  • the behavior information includes page access records and interest-based APP usage information, such as the frequency and duration of use of each interest-based APP.
  • the mining module 202 is configured to configure mining conditions according to the behavior information, and mine multiple candidate users that meet the mining conditions from the behavior information of users other than the user.
  • the mining module 202 is further configured to: obtain the content topic of each visited page according to the page access record, and configure a weight coefficient for each content topic according to the number of occurrences of each content topic;
  • the weight coefficient of each content theme is the center, and the weight coefficient range of each content theme is set; according to each content theme and the weight coefficient range corresponding to each content theme, multiple candidate users who meet the requirements are matched.
  • the friend recommendation list includes the recommended relationship of each candidate user, and the mining module 202 is also used for:
  • the matching coefficient of each candidate user can be calculated by the following formula:
  • P i is the matching coefficient between the candidate user i and the user
  • ⁇ is a constant
  • ⁇ j is the weight coefficient of the content topic j
  • ⁇ ij is the “weight coefficient of the content topic j in the user” and “waiting Select the ratio between the weight coefficient of content topic j in user i, the ratio is less than or equal to 1
  • m is the total number of content topics.
  • the mining module 202 is further configured to: obtain the content topic of each visited page according to the page access record, so as to obtain n content topics; according to the number of occurrences of each content topic, for each content topic
  • the content theme configures weight coefficients; according to the n content themes of the user, an N-dimensional parameter vector is defined, and the weight coefficients of the n content themes are respectively placed at the corresponding positions of the N-dimensional parameter vector, N ⁇ n;
  • calculate the predicted matching value of M interest tags according to the predicted matching value of M interest tags, filter out m effective interests whose predicted matching value is higher than the preset threshold Label, centering on the predicted matching value of each valid interest tag, set the weight coefficient range of each valid interest tag; according to m valid interest tags and the weight coefficient range corresponding to each valid interest tag, match those that meet the requirements Multiple users to be selected.
  • the mining module 202 is further configured to: if the number of the plurality of users to be selected is greater than a preset threshold, filter out the plurality of users to be selected according to the basic user information of the users Part of the candidate users; push the selected candidate users to the friend recommendation list of the user's instant messaging tool.
  • the pushing module 204 is configured to push the multiple candidate users to the friend recommendation list in the user's instant messaging tool.
  • the push module 204 is further used to: map the weight coefficient of each content topic in each candidate user to a corresponding topic interest index; define the visualization according to each topic interest index in each candidate user Information; push the visual information corresponding to each candidate user to the friend recommendation list in the user's instant messaging tool, and the visual information corresponding to each candidate user is displayed in the friend recommendation list where the corresponding candidate user is located Field.
  • the receiving module 206 is configured to receive the user's selection operation for one or more of the candidate users.
  • the user can input selection instructions (such as single or continuous multiple mouse click operations, touch operations) through the graphical interface interface provided by the instant messaging tool.
  • selection instructions such as single or continuous multiple mouse click operations, touch operations
  • the relationship chain establishment module 208 is configured to establish a friend relationship chain between the user and the selected one or more candidate users according to the selection operation.
  • the instant messaging tool sends a request for establishing a friend relationship chain for one of the candidate users (hereinafter referred to as "target user") according to the selection instruction input by the user.
  • target user the candidate users
  • the computer device After receiving the request information, the computer device will send a request message of "friend request to join” to the target user, and after the target user sends a response message of "approval”, establish a friend relationship between the user and the target user chain.
  • the friend relationship chain matching system 20 may further include a recommendation list adjustment module 210, configured to record multiple personal pages of multiple interested users that the user clicks to enter through the friend recommendation list; Define the weight coefficient for these interested users according to the length of visit and the number of visits on each personal page; readjust the user according to the weight coefficient of each interested user and the weight coefficient of each content topic of each interested user Weighting coefficients for each content theme; recalculating the matching coefficients between the multiple candidate users and the users according to the adjusted weighting coefficients for each content theme; and adjusting the matching coefficients based on the recalculated matching coefficients The order of multiple candidate users in the friend recommendation list is described.
  • a recommendation list adjustment module 210 configured to record multiple personal pages of multiple interested users that the user clicks to enter through the friend recommendation list; Define the weight coefficient for these interested users according to the length of visit and the number of visits on each personal page; readjust the user according to the weight coefficient of each interested user and the weight coefficient of each content topic of each interested user Weighting coefficients for each content theme;
  • the computer device 2 is a device that can automatically perform numerical calculation and/or information processing in accordance with pre-set or stored instructions.
  • the computer device 2 may be a rack server, a blade server, a tower server, or a cabinet server (including an independent server or a server cluster composed of multiple servers).
  • the computer device 2 at least includes, but is not limited to, a memory 21, a processor 22, a network interface 23, and a friend relationship chain matching system 20 that can communicate with each other through a system bus. among them:
  • the memory 21 includes at least one type of non-volatile computer-readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), Random access memory (RAM), static random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disk, optical disk Wait.
  • the memory 21 may be an internal storage unit of the computer device 2, for example, a hard disk or a memory of the computer device 2.
  • the memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a smart media card (SMC), and a secure digital (Secure Digital, SMC) equipped on the computer device 20. SD) card, flash card (Flash Card), etc.
  • the memory 21 may also include both the internal storage unit of the computer device 2 and its external storage device.
  • the memory 21 is generally used to store the operating system and various application software installed in the computer device 2, such as the program code of the friend relationship chain matching system 20 in the third embodiment.
  • the memory 21 can also be used to temporarily store various types of data that have been output or will be output.
  • the processor 22 may be a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments.
  • the processor 22 is generally used to control the overall operation of the computer device 2.
  • the processor 22 is used to run the program code or process data stored in the memory 21, for example, to run the friend relationship chain matching system 20, to implement the friend relationship chain matching method of the first or second embodiment.
  • the network interface 23 may include a wireless network interface or a wired network interface, and the network interface 23 is generally used to establish a communication connection between the computer device 2 and other electronic devices.
  • the network interface 23 is used to connect the computer device 2 with an external terminal through a network, and establish a data transmission channel and a communication connection between the computer device 2 and the external terminal.
  • the network may be Intranet, Internet, Global System of Mobile Communication (GSM), Wideband Code Division Multiple Access (WCDMA), 4G network, 5G Network, Bluetooth (Bluetooth), Wi-Fi and other wireless or wired networks.
  • FIG. 10 only shows the computer device 2 with components 20-23, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.
  • the friend relationship chain matching system 20 stored in the memory 21 may also be divided into one or more program modules, and the one or more program modules are stored in the memory 21 and consist of one Or executed by multiple processors (in this embodiment, the processor 22) to complete the application.
  • FIG. 9 shows a schematic diagram of the program modules of the third embodiment of the friend relationship chain matching system 20.
  • the friend relationship chain matching system 20 can be divided into an acquisition module 200, a mining module 202, The pushing module 204, the receiving module 206, the relationship chain establishing module 208, and the recommendation list adjusting module 210.
  • the program module referred to in this application refers to a series of computer-readable instruction segments that can complete specific functions. The specific functions of the program modules 200-210 have been described in detail in the third embodiment, and will not be repeated here.
  • This embodiment also provides a non-volatile computer-readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disks, optical disks, servers, App application malls, etc., on which storage There are computer-readable instructions, and the corresponding functions are realized when the program is executed by the processor.
  • a non-volatile computer-readable storage medium such as flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory ( SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disks, optical disks, servers, App application malls, etc., on
  • the non-volatile computer-readable storage medium of this embodiment is used to store the friend relationship chain matching system 20, and the processor executes the following steps: obtaining step, obtaining user behavior information through a mobile terminal; and mining step, according to the behavior information Configure mining conditions, mining multiple candidate users that meet the mining conditions from the behavior information of users other than the user; a push step, pushing the multiple candidate users to the user's instant messaging tool In the friend recommendation list in the list; the receiving step is to receive the user's selection operation for one or more of the candidate users; the relationship chain establishment step, according to the selection operation, between the user and the selected one or more Establish a friendship chain between the users to be selected.

Abstract

一种好友关系链匹配方法，所述方法包括通过移动终端获取用户的行为信息（S100）；根据所述行为信息配置挖掘条件，在所述用户之外的其它用户的行为信息中挖掘符合所述挖掘条件的多个待选用户（S102）；将所述多个待选用户推送到所述用户的即时通信工具中的好友推荐列表中（S104）；接收所述用户针对其中一个或多个待选用户的选择操作（S106）；根据所述选择操作，在所述用户和被选择的一个或多个待选用户之间建立好友关系链（S108）。本方法所述的好友关系链匹配，无需用户手动干预，且通过这些行为信息来匹配好友，匹配准确度更高。

Description

好友关系链匹配方法、系统、计算机设备及可读存储介质
本申请申明2019年09月26日递交的申请号为201910917137.6、名称为“好友关系链匹配方法、系统、计算机设备及可读存储介质”的中国专利申请的优先权，该中国专利申请的整体内容以参考的方式结合在本申请中。
技术领域
本申请实施例涉及计算机数据处理领域，尤其涉及一种好友关系链匹配方法、系统、计算机设备及非易失性计算机可读存储介质。
背景技术
即时通信软件旨在帮助人们建立好友关系链，通过建立好友关系链解决人与人之的远距离沟通问题。好友关系链的数量和质量在很大程度上会影响用户在即时通讯平台上的留存和活跃度。通常情况下，可以通过输入其他用户ID直接手工添加好友，也可以根据通讯录里的各个联系人的电话号码，匹配对应的好友。然而，仅通过上述方式建立好友关系链，无法建立具有一定规模且质量较高的好友关系链。
为解决上述问题，本发明人目前所了解的解决方式是：(1)用户输入查找条件，如输入性别、地区、年龄等查找条件，根据用户输入的查找条件查询符合条件的用户，并将查找到的用户推荐给该用户。(2)将用户注册时填写的个人基本信息作为查找条件，并根据该查找条件查询相似的用户，并将查找到的用户推荐给该用户。
然而，发明人意识到上述解决方式均存在一定的技术缺陷：解决方式(1)，好友关系链匹配需要用户手动干预，搜索好友时，不熟悉系统的用户则可能搜索不到满意的结果，从而影响用户体验；解决方式(2)，这种根据在注册时填写的性别、年龄等个人基本信息为用户自动匹配好友关系链，准确度较低，因为用户资料可能出现填写不全、填写虚假资料等问题。
发明内容
有鉴于此，本申请实施例的目的是提供一种好友关系链匹配方法、系统、计算机设备及非易失性计算机可读存储介质，解决匹配好友关系链手动干预的问题以及自动匹配好友关系链准确度较低的问题。
为实现上述目的，本申请实施例提供了一种好友关系链匹配方法，包括以下步骤：
获取步骤，通过移动终端获取用户的行为信息；
挖掘步骤，根据所述行为信息配置挖掘条件，在所述用户之外的其它用户的行为信息 中挖掘符合所述挖掘条件的多个待选用户；
推送步骤，将所述多个待选用户推送到所述用户的即时通信工具中的好友推荐列表中；
接收步骤，接收所述用户针对其中一个或多个待选用户的选择操作；及
关系链建立步骤，根据所述选择操作，在所述用户和被选择的一个或多个待选用户之间建立好友关系链。
为实现上述目的，本申请实施例还提供了好友关系链匹配系统，包括：
获取模块，用于通过移动终端获取用户的行为信息；
挖掘模块，用于根据所述行为信息配置挖掘条件，在所述用户之外的其它用户的行为信息中挖掘符合所述挖掘条件的多个待选用户；
推送模块，用于将所述多个待选用户推送到所述用户的即时通信工具中的好友推荐列表中；
接收模块，用于接收所述用户针对其中一个或多个待选用户的选择操作；及
关系链建立模块，用于根据所述选择操作在所述用户和被选择的一个或多个待选用户之间建立好友关系链。
为实现上述目的，本申请实施例还提供了一种计算机设备，所述计算机设备包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机可读指令，所述计算机可读指令被处理器执行时实现以下步骤：
获取步骤，通过移动终端获取用户的行为信息；
挖掘步骤，根据所述行为信息配置挖掘条件，在所述用户之外的其它用户的行为信息中挖掘符合所述挖掘条件的多个待选用户；
推送步骤，将所述多个待选用户推送到所述用户的即时通信工具中的好友推荐列表中；
接收步骤，接收所述用户针对其中一个或多个待选用户的选择操作；及
关系链建立步骤，根据所述选择操作，在所述用户和被选择的一个或多个待选用户之间建立好友关系链。
为实现上述目的，本申请实施例还提供了一种非易失性计算机可读存储介质，所述非易失性计算机可读存储介质内存储有计算机可读指令，所述计算机可读指令可被至少一个处理器所执行，以使所述至少一个处理器执行如下步骤：
获取步骤，通过移动终端获取用户的行为信息；
挖掘步骤，根据所述行为信息配置挖掘条件，在所述用户之外的其它用户的行为信息中挖掘符合所述挖掘条件的多个待选用户；
推送步骤，将所述多个待选用户推送到所述用户的即时通信工具中的好友推荐列表中；
接收步骤，接收所述用户针对其中一个或多个待选用户的选择操作；及
关系链建立步骤，根据所述选择操作，在所述用户和被选择的一个或多个待选用户之间建立好友关系链。
本申请实施例提供的好友关系链匹配方法、系统、计算机设备及非易失性计算机可读存储介质，通过收集用户的行为信息(例如，浏览器上的浏览信息等)，来综合分析用户的兴趣爱好，再设置挖掘条件，用户之外的其它海量用户的资料信息中挖掘符合所述挖掘条件的用户...，然后进行好友关系链匹配，而无需用户手动干预，且上述这些行为信息可以代表一个用户的真实生活状态，更加能分析出该用户的兴趣取向，通过这些行为信息来匹配好友，匹配准确度更高。
附图说明
图1为本申请好友关系链匹配方法实施例一的流程图。
图2为图1中步骤S102在示例性实施例中的流程图。
图3为图1中步骤S102在另一示例性实施例中的流程图。
图4为图1中步骤S104在示例性实施例中的流程图。
图5为图1中步骤S104在另一示例性实施例中的流程图。
图6为图1中步骤S104在另一示例性实施例中的流程图。
图7为本申请好友关系链匹配方法实施例一中步骤S110的流程图。
图8为本申请好友关系链匹配方法实施例二的流程图。
图9为本申请好友关系链匹配系统实施例三的程序模块示意图。
图10为本申请计算机设备实施例四的硬件结构示意图。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本申请，并不用于限定本申请。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
需要说明的是，在本申请中涉及“第一”、“第二”等的描述仅用于描述目的，而不能理解为指示或暗示其相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。另外，各个实施例之间的技术方案可以相互结合，但是必须是以本领域普通技术人员能够实现为基础，当技术方案的结合出现相互矛盾或无法实现时应当认为这种技术方案的结合不存在，也不在本申请要求的保护范围之内。
以下实施例将以计算机设备2为执行主体进行示例性描述。
实施例一
参阅图1，示出了本申请实施例一之好友关系链匹配方法的步骤流程图。可以理解， 本方法实施例中的流程图不用于对执行步骤的顺序进行限定。具体如下。
步骤S100，通过移动终端获取用户的行为信息。
所述行为信息包括页面访问记录、兴趣类APP使用信息，如各个兴趣类APP的使用频率和使用时长等。
所述兴趣类APP，如：游戏类APP(王者荣耀、跑跑卡丁车等)、学习类APP(英语流利说、百词斩、豆瓣等)、投资类APP(雪球、天天基金等)等。
步骤S102，根据所述行为信息配置挖掘条件，在所述用户之外的其它用户的行为信息中挖掘符合所述挖掘条件的多个待选用户。
在示例性的实施例中，以行为信息为页面访问记录为例，如图2所示，步骤S102可以进一步包括：
步骤S102A1，根据页面访问记录获取每个被访问页面的内容主题，根据每个内容主题的出现次数，为每个内容主题配置权重系数；
步骤S102A2，以每个内容主题的权重系数为中心，设置所述每个内容主题的权重系数范围；
步骤S102A3，根据每个内容主题以及每个内容主题对应的权重系数范围，匹配符合要求的多个待选用户。
举例而言，假设权重系数为0～100，根据页面访问记录得到4个内容主题，第一内容主题的权重系数为75，第二内容主题的权重系数为30，第三内容主题的权重系数为22，第四内容主题的权重系数为60。以这4个内容主题的权重系数为中心，如将第一内容主题的权重系数范围设置为75±5(包括端点)，将第二内容主题的权重系数范围设置为30±5(包括端点)，将第三内容主题的权重系数范围设置为22±5(包括端点)，将第四内容主题的权重系数范围设置为60±5(包括端点)，然后根据其他用户中的对应的各个主题内容在上述范围内的用户作为待选用户。如，用户A：第一内容主题的权重系数为71，第二内容主题的权重系数为32，第三内容主题的权重系数为21，第四内容主题的权重系数为65，则用户A可以作为待选用户；用户B：第一内容主题的权重系数为71，第二内容主题的权重系数为32，第三内容主题的权重系数为21，第四内容主题的权重系数为66，由于用户B的第四内容主题的权重系数在权重系数范围之外，所有不符合要求，因此用户B不属于待选用户。
在另一示例性的实施例中，如图3所示，步骤S102可以进一步包括：
步骤S102B1，根据页面访问记录获取每个被访问页面的内容主题，根据每个内容主题的出现次数，为每个内容主题配置权重系数；步骤S102B2，根据每个内容主题的权重系数，筛选出权重系数高于预设阀值的若干个有效内容主题；步骤S102B3，以每个有效内容主题的权重系数为中心，设置所述每个有效内容主题的权重系数范围；步骤S102B4，根据每个有效内容主题以及每个有效内容主题对应的权重系数范围，匹配符合要求的多个待选用户。
步骤S104，将所述多个待选用户推送到所述用户的即时通信工具中的好友推荐列表中。
在示例性的实施例中，所述好友推荐列表中包括各个待选用户的被推荐系度；如图4所示，所述步骤S104可以进一步包括步骤：
步骤S104A1，根据每个待选用户对应的各个内容主题(或有效内容主题)的权重系数，计算每个待选用户和所述用户的匹配度系数；
步骤S104A2，根据每个待选用户和所述用户的匹配度系数，确定好友推荐列表中各个待选用户的被推荐度。具体的，各个待选用户的匹配度系数可以通过如下公式计算得到：
Figure PCTCN2019117556-appb-000001
其中，P i为待选用户i和所述用户的匹配度系数，α为常量，β j为内容主题(或有效内容主题)j的权重系数，δ ij为“所述用户中内容主题(或有效内容主题)j的权重系数”和“待选用户i中内容主题(或有效内容主题)j的权重系数”之间的比值，该比值小于或等于1，m为内容主题的总数量。
在示例性的实施例中，如图5所示，所述步骤S104可以进一步包括步骤：
步骤S104B1，将每个待选用户中各个内容主题(或有效内容主题)的权重系数映射为相应的主题兴趣指数；
步骤S104B2，据每个待选用户中的各个主题兴趣指数定义可视化信息(如文字、图像等)；
步骤S104B3，将每个待选用户对应的可视化信息推送到所述用户的即时通信工具中的好友推荐列表中，每个待选用户对应的可视化信息被显示在好友推荐列表中的对应待选用户所在栏位。
即，将所述待选用户以及可视化信息推送到所述用户的即时通信工具中的好友推荐列表中。
在示例性的实施例中，如图6所示，所述步骤S104可以进一步包括步骤：
步骤S104C1，判断所述多个待选用户的数量是否大于预设阀值；
步骤S104C2，如果不大于所述预设阈值，将所述多个待选用户推送到所述用户的即时通信工具中的好友推荐列表中；
步骤S104C3，如果大于所述预设阈值，根据所述用户的基本用户信息从所述多个待选用户中筛选出部分待选用户，并将该被筛选出的部分待选用户推送到所述用户的即时通信工具的好友推荐列表中。
所述用户的基本用户信息，包括但不限于，年龄、性别、职业、收入范围、地理位置等。
以所述用户的基本用户信息配置附加挖掘条件，如配置以用户年龄为中心的年龄范围、以用户职业为中的相关职业范围、以用户收入范围为中心的扩展收入范围、以用户地址位置为中心的地址范围。如果用户为：35岁男性、职业为IT、地址位置为深圳市XX金融大厦，可以配置附加挖掘条件为：年龄30-40岁、男、计算机行业、处于XX金融大厦100公里范围。通过该附加挖掘条件在所述多个待选用户中，筛选出符合条件的若干个待选用户。
如果通过附加挖掘条件从所述待选用户中匹配不到符合条件的待选用户，则修改附加挖掘条件，如扩大范围、删除一些项目(如，删除“职业”)。
步骤S106，接收所述用户针对其中一个或多个待选用户的选择操作。
用户可以通过即时通信工具提供的图像界面接口输入选择指令(如单次或连续多个点击鼠标操作、触控操作)。
步骤S108，根据所述选择操作，在所述用户和被选择的一个或多个待选用户之间建立好友关系链。
例如，即时通信工具根据用户输入的选择指令发送针对其中一个待选用户(下称“目标用户”)的建立好友关系链的请求信息。计算机设备接收到该请求信息后会向该目标用户发送“好友申请加入”的请求信息，并在该目标用户发出“同意”的响应信息之后，在所述用户和该目标用户之间建立好友关系链。
在示例性的实施例中，如图7所示，所述方法还可以包括好友推荐列表调整步骤S110，所述步骤S110可以进一步包括如下步骤：步骤S110A1，记录所述用户通过所述好友推荐列表点击进入的多个感兴趣用户的多个个人页面；步骤S110A2，根据在每个个人页面的访问时长和访问次数，为这些感兴趣用户定义权重系数；步骤S110A3，根据每个感兴趣用户的权重系数和每个感兴趣用户的各个内容主题的权重系数，重新调整所述用户对各个内容主题的权重系数；步骤S110A4，根据调整后的各个内容主题的权重系数，重新计算所述多个待选用户与所述用户的匹配度系数；步骤S110A5，基于该重新计算得到的匹配度系数，调整所述多个待选用户在好友推荐列表中的次序。
当然步骤S110仅是好友推荐表重排的示例性方案，本实施例还可以通过其他方案调整好友推荐列表，如：当用户点击某个主题兴趣指数时，则以主题兴趣指数为单一考量因素，对所述多个待选用户在好友推荐列表中的次序。
实施例二
参阅图8，示出了本申请实施例二之好友关系链匹配方法的步骤流程图。可以理解，本方法实施例中的流程图不用于对执行步骤的顺序进行限定。具体如下。
步骤S200，通过移动终端获取用户的行为信息。
所述行为信息包括页面访问记录、兴趣类APP使用信息，如各个兴趣类APP的使用频 率和使用时长等。
所述兴趣类APP，如：游戏类APP(王者荣耀、跑跑卡丁车等)、学习类APP(英语流利说、百词斩、豆瓣等)、投资类APP(雪球、天天基金等)等。
步骤S202，根据所述行为信息中的页面访问记录获取每个被访问页面的内容主题，以得到n个内容主题。
步骤S204，根据每个内容主题的出现次数，为每个内容主题配置权重系数。
步骤S206，根据所述用户的n个内容主题，定义一个N维参数向量，所述n个内容主题的权重系数分别置于所述N维参数向量的相应位置处，N≥n。
示例性的，可以预先配置N个内容主题，N为大于1的正整数，通过步骤S200获取所述用户涉及到了n个内容主题，未涉及到其他内容主题(即未出现的内容主题)。其中，其他内容主题的权重系数在所述N维参数向量中可以被设置为一固定数值，如0。
步骤S208，根据所述N维参数向量和长短期记忆网络模型(LSTM，Long Short-Term Memory)，计算M个兴趣标签的预测匹配值。
具体的，计算M个兴趣标签的预测匹配值的步骤如下：
(1)根据上一时刻的输出h t-1和当前输入x t来得到f t值，以决定是否让上一时刻学到的信息C t-1通过或部分通过：
f t＝σ(W f[x t,h t-1]+b f)，其中f t∈[0,1]，表示t时刻的节点对t-1时刻细胞记忆的选择权重，W f为遗忘门的权重矩阵，b f为遗忘门的偏置项，h t-1表示t-1节点的隐层状态信息，非线性函数σ(x)＝1/(1+e -x)；
(2)通过sigmoid来决定哪些值用来更新，并通过tanh层用来生成新的候选值
Figure PCTCN2019117556-appb-000002
它作为当前层产生的候选值可能会添加到记忆单元状态中，把这两部分产生的值结合来进行更新：
i t＝σ(W i[x t,h t-1]+b i)，其中i t∈[0,1]表示t时刻的节点对当前节点信息的选择权重，b i为输入门的偏置项，W i为输入门的权重矩阵，非线性函数σ(x)＝1/(1+e -x)；
当前节点输入信息
Figure PCTCN2019117556-appb-000003
其中
Figure PCTCN2019117556-appb-000004
为偏置项，
Figure PCTCN2019117556-appb-000005
表示待更新信息的权重矩阵，tanh为双曲正切激活函数，x t表示t时刻LSTM神经网络节点的输入向量，h t-1表示t-1节点的隐层状态信息；
对旧的记忆单元状态进行更新，添加新信息：
当前输出记忆信息
Figure PCTCN2019117556-appb-000006
其中C t-1表示t-1节点的记忆信息，f t表示t时刻的节点对t-1时刻细胞记忆的选择权重，i t表示t时刻的节点对当前节点信息的选择权重；
(3)LSTM模型输出；
o t＝σ(W o[x t,h t-1]+b o)，其中o t∈[0,1]表示t时刻的节点细胞记忆信息的选择权重，b o为输出门的偏置，W o为输出门的权重矩阵，
Figure PCTCN2019117556-appb-000007
表示向量x t和h t-1拼接后的向量，即|x t|+|h t-1|维的向量。
h t＝o t·tanh(C t)
x t表示t时刻LSTM神经网络节点的输入向量，即本实施例中的N维参数向量；h t为t时刻LSTM神经网络节点的输出向量，即本实施例中针对M个兴趣标签的预测匹配值。
步骤S210，根据M个兴趣标签的预测匹配值，筛选出预测匹配值高于预设阀值的m个有效兴趣标签；
步骤S212，以所述每个有效兴趣标签的预测匹配值为中心，设置每个有效兴趣标签的权重系数范围。
步骤S214，根据m个有效兴趣标签以及每个有效兴趣标签对应的权重系数范围，匹配符合要求的多个待选用户。
步骤S216所述多个待选用户推送到所述用户的即时通信工具中的好友推荐列表中。
在示例性的实施例中，所述好友推荐列表中包括各个待选用户的被推荐系度；所述步骤S216进一步包括步骤：
根据每个待选用户对应的各个兴趣标签的预测匹配值，计算每个待选用户和所述用户的匹配度系数，所述匹配度系数用于确定好友推荐列表中各个待选用户的被推荐度。
在示例性的实施例中，所述步骤S216进一步包括步骤：
(1)判断所述多个待选用户的数量大于预设阀值；
(2)如果不大于所述预设阈值，将所述多个待选用户推送到所述用户的即时通信工具中的好友推荐列表中；
(3)如果大于所述预设阈值，根据所述用户的基本用户信息从所述多个待选用户中筛选出部分待选用户，并将该被筛选出的部分待选用户推送到所述用户的即时通信工具的好友推荐列表中；
所述用户的基本用户信息，包括但不限于，年龄、性别、职业、收入范围、地理位置等。
以所述用户的基本用户信息配置附加挖掘条件，如配置以用户年龄为中心的年龄范围、 以用户职业为中的相关职业范围、以用户收入范围为中心的扩展收入范围、以用户地址位置为中心的地址范围。如果用户为：35岁男性、职业为IT、地址位置为深圳市XX金融大厦，可以配置附加挖掘条件为：年龄30-40岁、男、计算机行业、处于XX金融大厦100公里范围。通过该附加挖掘条件在所述多个待选用户中，筛选出符合条件的若干个待选用户。
如果通过附加挖掘条件从所述待选用户中匹配不到符合条件的待选用户，则修改附加挖掘条件，如扩大范围、删除一些项目(如，删除“职业”)。
步骤S218收所述用户针对其中一个或多个待选用户的选择操作。
用户可以通过即时通信工具提供的图像界面接口输入选择指令(如单次或连续多个点击鼠标操作、触控操作)。
步骤S220据所述选择操作，在所述用户和被选择的一个或多个待选用户之间建立好友关系链。
即时通信工具根据用户输入的选择指令发送针对其中一个待选用户(下称“目标用户”)的建立好友关系链的请求信息。计算机设备接收到该请求信息后会向该目标用户发送“好友申请加入”的请求信息，并在该目标用户发出“同意”的响应信息之后，在所述用户和该目标用户之间建立好友关系链。
实施例三
请继续参阅图9，示出了本申请好友关系链匹配系统实施例三的程序模块示意图。在本实施例中，好友关系链匹配系统20可以包括或被分割成一个或多个程序模块，一个或者多个程序模块被存储于存储介质中，并由一个或多个处理器所执行，以完成本申请，并可实现上述好友关系链匹配方法。本申请实施例所称的程序模块是指能够完成特定功能的一系列计算机可读指令段。以下描述将具体介绍本实施例各程序模块的功能：
获取模块200，用于通过移动终端获取用户的行为信息。
所述行为信息包括页面访问记录、兴趣类APP使用信息，如各个兴趣类APP的使用频率和使用时长等。
挖掘模块202，用于根据所述行为信息配置挖掘条件，在所述用户之外的其它用户的行为信息中挖掘符合所述挖掘条件的多个待选用户。
在示例性的实施例中，挖掘模块202还用于：根据所述页面访问记录获取每个被访问页面的内容主题，根据每个内容主题的出现次数，为每个内容主题配置权重系数；以每个内容主题的权重系数为中心，设置所述每个内容主题的权重系数范围；根据每个内容主题以及每个内容主题对应的权重系数范围，匹配符合要求的多个待选用户。
其中，所述好友推荐列表中包括各个待选用户的被推荐系度，挖掘模块202还用于：
根据每个待选用户对应的各个内容主题的权重系数，计算每个待选用户和所述用户的 匹配度系数，所述匹配度系数用于确定好友推荐列表中各个待选用户的被推荐度；具体的，各个待选用户的匹配度系数可以通过如下公式计算得到：
Figure PCTCN2019117556-appb-000008
其中，P i为待选用户i和所述用户的匹配度系数，α为常量，β j为内容主题j的权重系数，δ ij为“所述用户中内容主题j的权重系数”和“待选用户i中内容主题j的权重系数”之间的比值，该比值小于或等于1，m为内容主题的总数量。
在示例性的实施例中，挖掘模块202还用于：根据所述页面访问记录获取每个被访问页面的内容主题，以得到n个内容主题；根据每个内容主题的出现次数，为每个内容主题配置权重系数；根据所述用户的n个内容主题，定义一个N维参数向量，所述n个内容主题的权重系数分别置于所述N维参数向量的相应位置处，N≥n；根据所述N维参数向量和长短期记忆网络模型，计算M个兴趣标签的预测匹配值；根据M个兴趣标签的预测匹配值，筛选出预测匹配值高于预设阀值的m个有效兴趣标签，以所述每个有效兴趣标签的预测匹配值为中心，设置每个有效兴趣标签的权重系数范围；根据m个有效兴趣标签以及每个有效兴趣标签对应的权重系数范围，匹配符合要求的多个待选用户。
在示例性的实施例中，挖掘模块202还用于：如果所述多个待选用户的数量大于预设阀值，根据所述用户的基本用户信息从所述多个待选用户中筛选出部分待选用户；将该被筛选出的部分待选用户推送到所述用户的即时通信工具的好友推荐列表中。
推送模块204，用于将所述多个待选用户推送到所述用户的即时通信工具中的好友推荐列表中。
在示例性的实施例中，推送模块204还用于：将每个待选用户中各个内容主题的权重系数映射为相应的主题兴趣指数；根据每个待选用户中的各个主题兴趣指数定义可视化信息；将每个待选用户对应的可视化信息推送到所述用户的即时通信工具中的好友推荐列表中，每个待选用户对应的可视化信息被显示在好友推荐列表中的对应待选用户所在栏位。
接收模块206，用于接收所述用户针对其中一个或多个待选用户的选择操作。
用户可以通过即时通信工具提供的图像界面接口输入选择指令(如单次或连续多个点击鼠标操作、触控操作)。
关系链建立模块208，用于根据所述选择操作在所述用户和被选择的一个或多个待选用户之间建立好友关系链。
即时通信工具根据用户输入的选择指令发送针对其中一个待选用户(下称“目标用户”)的建立好友关系链的请求信息。计算机设备接收到该请求信息后会向该目标用户发送“好友申请加入”的请求信息，并在该目标用户发出“同意”的响应信息之后，在所述用户和该目标用户之间建立好友关系链。
在示例性的实施例中，好友关系链匹配系统20还可以包括推荐列表调整模块210，用于：记录所述用户通过所述好友推荐列表点击进入的多个感兴趣用户的多个个人页面；根据在每个个人页面的访问时长和访问次数，为这些感兴趣用户定义权重系数；根据每个感兴趣用户的权重系数和每个感兴趣用户的各个内容主题的权重系数，重新调整所述用户对各个内容主题的权重系数；根据调整后的各个内容主题的权重系数，重新计算所述多个待选用户与所述用户的匹配度系数；及基于该重新计算得到的匹配度系数，调整所述多个待选用户在好友推荐列表中的次序。
实施例四
参阅图10，是本申请实施例四之计算机设备的硬件架构示意图。本实施例中，所述计算机设备2是一种能够按照事先设定或者存储的指令，自动进行数值计算和/或信息处理的设备。该计算机设备2可以是机架式服务器、刀片式服务器、塔式服务器或机柜式服务器(包括独立的服务器，或者多个服务器所组成的服务器集群)等。如图所示，所述计算机设备2至少包括，但不限于，可通过系统总线相互通信连接存储器21、处理器22、网络接口23、以及好友关系链匹配系统20。其中：
本实施例中，存储器21至少包括一种类型的非易失性计算机可读存储介质，所述可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等。在一些实施例中，存储器21可以是计算机设备2的内部存储单元，例如该计算机设备2的硬盘或内存。在另一些实施例中，存储器21也可以是计算机设备2的外部存储设备，例如该计算机设备20上配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)等。当然，存储器21还可以既包括计算机设备2的内部存储单元也包括其外部存储设备。本实施例中，存储器21通常用于存储安装于计算机设备2的操作系统和各类应用软件，例如实施例三的好友关系链匹配系统20的程序代码等。此外，存储器21还可以用于暂时地存储已经输出或者将要输出的各类数据。
处理器22在一些实施例中可以是中央处理器(Central Processing Unit，CPU)、控制器、微控制器、微处理器、或其他数据处理芯片。该处理器22通常用于控制计算机设备2的总体操作。本实施例中，处理器22用于运行存储器21中存储的程序代码或者处理数据，例如运行好友关系链匹配系统20，以实现实施例一或二的好友关系链匹配方法。
所述网络接口23可包括无线网络接口或有线网络接口，该网络接口23通常用于在所述计算机设备2与其他电子装置之间建立通信连接。例如，所述网络接口23用于通过网络将所述计算机设备2与外部终端相连，在所述计算机设备2与外部终端之间的建立数据传输通道和通信连接等。所述网络可以是企业内部网(Intranet)、互联网(Internet)、全球移 动通讯系统(Global System of Mobile communication，GSM)、宽带码分多址(Wideband Code Division Multiple Access，WCDMA)、4G网络、5G网络、蓝牙(Bluetooth)、Wi-Fi等无线或有线网络。
需要指出的是，图10仅示出了具有部件20-23的计算机设备2，但是应理解的是，并不要求实施所有示出的部件，可以替代的实施更多或者更少的部件。
在本实施例中，存储于存储器21中的所述好友关系链匹配系统20还可以被分割为一个或者多个程序模块，所述一个或者多个程序模块被存储于存储器21中，并由一个或多个处理器(本实施例为处理器22)所执行，以完成本申请。
例如，图9示出了所述实现好友关系链匹配系统20实施例三的程序模块示意图，该实施例中，所述基于好友关系链匹配系统20可以被划分为获取模块200、挖掘模块202、推送模块204、接收模块206、关系链建立模块208和推荐列表调整模块210。其中，本申请所称的程序模块是指能够完成特定功能的一系列计算机可读指令段。所述程序模块200-210的具体功能在实施例三中已有详细描述，在此不再赘述。
实施例五
本实施例还提供一种非易失性计算机可读存储介质，如闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘、服务器、App应用商城等等，其上存储有计算机可读指令，程序被处理器执行时实现相应功能。本实施例的非易失性计算机可读存储介质用于存储好友关系链匹配系统20，被处理器执行如下步骤：获取步骤，通过移动终端获取用户的行为信息；挖掘步骤，根据所述行为信息配置挖掘条件，在所述用户之外的其它用户的行为信息中挖掘符合所述挖掘条件的多个待选用户；推送步骤，将所述多个待选用户推送到所述用户的即时通信工具中的好友推荐列表中；接收步骤，接收所述用户针对其中一个或多个待选用户的选择操作；关系链建立步骤，根据所述选择操作，在所述用户和被选择的一个或多个待选用户之间建立好友关系链。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种好友关系链匹配方法，所述方法包括：
    获取步骤，通过移动终端获取用户的行为信息；
    挖掘步骤，根据所述行为信息配置挖掘条件，在所述用户之外的其它用户的行为信息中挖掘符合所述挖掘条件的多个待选用户；
    推送步骤，将所述多个待选用户推送到所述用户的即时通信工具中的好友推荐列表中；
    接收步骤，接收所述用户针对其中一个或多个待选用户的选择操作；及
    关系链建立步骤，根据所述选择操作，在所述用户和被选择的一个或多个待选用户之间建立好友关系链。
  2. 根据权利要求1所述的好友关系链匹配方法，所述行为信息包括页面访问记录和/或兴趣类APP使用信息；所述挖掘步骤包括：
    根据所述页面访问记录获取每个被访问页面的内容主题，根据每个内容主题的出现次数，为每个内容主题配置权重系数；
    以每个内容主题的权重系数为中心，设置所述每个内容主题的权重系数范围；
    根据每个内容主题以及每个内容主题对应的权重系数范围，匹配符合要求的多个待选用户。
  3. 根据权利要求2所述的好友关系链匹配方法，所述好友推荐列表中包括各个待选用户的被推荐系度；所述推送步骤包括：
    根据每个待选用户对应的各个内容主题的权重系数，计算每个待选用户和所述用户的匹配度系数，所述匹配度系数用于确定好友推荐列表中各个待选用户的被推荐度；
    所述匹配度系数计算公式如下：
    Figure PCTCN2019117556-appb-100001
    其中，P i为待选用户i和所述用户的匹配度系数，α为常量，β j为内容主题j的权重系数，δ ij为“所述用户中内容主题j的权重系数”和“待选用户i中内容主题j的权重系数”之间的比值，该比值小于或等于1，m为内容主题的总数量。
  4. 根据权利要求1所述的好友关系链匹配方法，所述行为信息包括页面访问记录和/或兴趣类APP使用信息；所述挖掘步骤包括：
    根据所述页面访问记录获取每个被访问页面的内容主题，以得到n个内容主题；
    根据每个内容主题的出现次数，为每个内容主题配置权重系数；
    根据所述用户的n个内容主题，定义一个N维参数向量，所述n个内容主题的权重系数分别置于所述N维参数向量的相应位置处，N≥n；
    根据所述N维参数向量和长短期记忆网络模型，计算M个兴趣标签的预测匹配值；
    根据M个兴趣标签的预测匹配值，筛选出预测匹配值高于预设阀值的m个有效兴趣标签；
    以所述每个有效兴趣标签的预测匹配值为中心，设置每个有效兴趣标签的权重系数范围；
    根据m个有效兴趣标签以及每个有效兴趣标签对应的权重系数范围，匹配符合要求的多个待选用户。
  5. 根据权利要求1所述的好友关系链匹配方法，如果所述多个待选用户的数量大于预设阀值，所述推送步骤包括：
    根据所述用户的基本用户信息从所述多个待选用户中筛选出部分待选用户；
    将该被筛选出的部分待选用户推送到所述用户的即时通信工具的好友推荐列表中。
  6. 根据权利要求5所述的好友关系链匹配方法，所述推送步骤包括：
    将每个待选用户中各个内容主题的权重系数映射为相应的主题兴趣指数；
    根据每个待选用户中的各个主题兴趣指数定义可视化信息；
    将每个待选用户对应的可视化信息推送到所述用户的即时通信工具中的好友推荐列表中，每个待选用户对应的可视化信息被显示在好友推荐列表中的对应待选用户所在栏位。
  7. 根据权利要求6所述的好友关系链匹配方法，还包括好友推荐列表调整步骤：
    记录所述用户通过所述好友推荐列表点击进入的多个感兴趣用户的多个个人页面；
    根据在每个个人页面的访问时长和访问次数，为这些感兴趣用户定义权重系数；
    根据每个感兴趣用户的权重系数和每个感兴趣用户的各个内容主题的权重系数，重新调整所述用户对各个内容主题的权重系数；
    根据调整后的各个内容主题的权重系数，重新计算所述多个待选用户与所述用户的匹配度系数；及
    基于该重新计算得到的匹配度系数，调整所述多个待选用户在好友推荐列表中的次序。
  8. 一种好友关系链匹配系统，包括：
    获取模块，用于通过移动终端获取用户的行为信息；
    挖掘模块，用于根据所述行为信息配置挖掘条件，在所述用户之外的其它用户的行为信息中挖掘符合所述挖掘条件的多个待选用户；
    推送模块，用于将所述多个待选用户推送到所述用户的即时通信工具中的好友推荐列表中；
    接收模块，用于接收所述用户针对其中一个或多个待选用户的选择操作；及
    关系链建立模块，用于根据所述选择操作在所述用户和被选择的一个或多个待选用户之间建立好友关系链。
  9. 一种计算机设备，所述计算机设备包括存储器、处理器及存储在所述存储器上并可 在所述处理器上运行的计算机可读指令，所述计算机可读指令被处理器执行时实现以下步骤：
    获取步骤，通过移动终端获取用户的行为信息；
    挖掘步骤，根据所述行为信息配置挖掘条件，在所述用户之外的其它用户的行为信息中挖掘符合所述挖掘条件的多个待选用户；
    推送步骤，将所述多个待选用户推送到所述用户的即时通信工具中的好友推荐列表中；
    接收步骤，接收所述用户针对其中一个或多个待选用户的选择操作；及
    关系链建立步骤，根据所述选择操作，在所述用户和被选择的一个或多个待选用户之间建立好友关系链。
  10. 根据权利要求9所述的计算机设备，所述行为信息包括页面访问记录和/或兴趣类APP使用信息；所述挖掘步骤包括：
    根据所述页面访问记录获取每个被访问页面的内容主题，根据每个内容主题的出现次数，为每个内容主题配置权重系数；
    以每个内容主题的权重系数为中心，设置所述每个内容主题的权重系数范围；
    根据每个内容主题以及每个内容主题对应的权重系数范围，匹配符合要求的多个待选用户。
  11. 根据权利要求10所述的计算机设备，所述好友推荐列表中包括各个待选用户的被推荐系度；所述推送步骤包括：
    根据每个待选用户对应的各个内容主题的权重系数，计算每个待选用户和所述用户的匹配度系数，所述匹配度系数用于确定好友推荐列表中各个待选用户的被推荐度；
    所述匹配度系数计算公式如下：
    Figure PCTCN2019117556-appb-100002
    其中，P i为待选用户i和所述用户的匹配度系数，α为常量，β j为内容主题j的权重系数，δ ij为“所述用户中内容主题j的权重系数”和“待选用户i中内容主题j的权重系数”之间的比值，该比值小于或等于1，m为内容主题的总数量。
  12. 根据权利要求9所述的计算机设备，所述行为信息包括页面访问记录和/或兴趣类APP使用信息；所述挖掘步骤包括：
    根据所述页面访问记录获取每个被访问页面的内容主题，以得到n个内容主题；
    根据每个内容主题的出现次数，为每个内容主题配置权重系数；
    根据所述用户的n个内容主题，定义一个N维参数向量，所述n个内容主题的权重系数分别置于所述N维参数向量的相应位置处，N≥n；
    根据所述N维参数向量和长短期记忆网络模型，计算M个兴趣标签的预测匹配值；
    根据M个兴趣标签的预测匹配值，筛选出预测匹配值高于预设阀值的m个有效兴趣标签；
    以所述每个有效兴趣标签的预测匹配值为中心，设置每个有效兴趣标签的权重系数范围；
    根据m个有效兴趣标签以及每个有效兴趣标签对应的权重系数范围，匹配符合要求的多个待选用户。
  13. 根据权利要求9所述的计算机设备，如果所述多个待选用户的数量大于预设阀值，所述推送步骤包括：
    根据所述用户的基本用户信息从所述多个待选用户中筛选出部分待选用户；
    将该被筛选出的部分待选用户推送到所述用户的即时通信工具的好友推荐列表中。
  14. 根据权利要求13所述的计算机设备，所述推送步骤包括：
    将每个待选用户中各个内容主题的权重系数映射为相应的主题兴趣指数；
    根据每个待选用户中的各个主题兴趣指数定义可视化信息；
    将每个待选用户对应的可视化信息推送到所述用户的即时通信工具中的好友推荐列表中，每个待选用户对应的可视化信息被显示在好友推荐列表中的对应待选用户所在栏位。
  15. 根据权利要求14所述的计算机设备，还包括好友推荐列表调整步骤：
    记录所述用户通过所述好友推荐列表点击进入的多个感兴趣用户的多个个人页面；
    根据在每个个人页面的访问时长和访问次数，为这些感兴趣用户定义权重系数；
    根据每个感兴趣用户的权重系数和每个感兴趣用户的各个内容主题的权重系数，重新调整所述用户对各个内容主题的权重系数；
    根据调整后的各个内容主题的权重系数，重新计算所述多个待选用户与所述用户的匹配度系数；及
    基于该重新计算得到的匹配度系数，调整所述多个待选用户在好友推荐列表中的次序。
  16. 一种非易失性计算机可读存储介质，所述非易失性计算机可读存储介质内存储有计算机可读指令，所述计算机可读指令可被至少一个处理器所执行，以使所述至少一个处理器执行如下步骤：
    获取步骤，通过移动终端获取用户的行为信息；
    挖掘步骤，根据所述行为信息配置挖掘条件，在所述用户之外的其它用户的行为信息中挖掘符合所述挖掘条件的多个待选用户；
    推送步骤，将所述多个待选用户推送到所述用户的即时通信工具中的好友推荐列表中；
    接收步骤，接收所述用户针对其中一个或多个待选用户的选择操作；及
    关系链建立步骤，根据所述选择操作，在所述用户和被选择的一个或多个待选用户之间建立好友关系链。
  17. 根据权利要求16所述的非易失性计算机可读存储介质，所述行为信息包括页面访 问记录和/或兴趣类APP使用信息；所述挖掘步骤包括：
    根据所述页面访问记录获取每个被访问页面的内容主题，根据每个内容主题的出现次数，为每个内容主题配置权重系数；
    以每个内容主题的权重系数为中心，设置所述每个内容主题的权重系数范围；
    根据每个内容主题以及每个内容主题对应的权重系数范围，匹配符合要求的多个待选用户。
  18. 根据权利要求16所述的非易失性计算机可读存储介质，所述好友推荐列表中包括各个待选用户的被推荐系度；所述推送步骤包括：
    根据每个待选用户对应的各个内容主题的权重系数，计算每个待选用户和所述用户的匹配度系数，所述匹配度系数用于确定好友推荐列表中各个待选用户的被推荐度；
    所述匹配度系数计算公式如下：
    Figure PCTCN2019117556-appb-100003
    其中，P i为待选用户i和所述用户的匹配度系数，α为常量，β j为内容主题j的权重系数，δ ij为“所述用户中内容主题j的权重系数”和“待选用户i中内容主题j的权重系数”之间的比值，该比值小于或等于1，m为内容主题的总数量。
  19. 根据权利要求16所述的非易失性计算机可读存储介质，所述行为信息包括页面访问记录和/或兴趣类APP使用信息；所述挖掘步骤包括：
    根据所述页面访问记录获取每个被访问页面的内容主题，以得到n个内容主题；
    根据每个内容主题的出现次数，为每个内容主题配置权重系数；
    根据所述用户的n个内容主题，定义一个N维参数向量，所述n个内容主题的权重系数分别置于所述N维参数向量的相应位置处，N≥n；
    根据所述N维参数向量和长短期记忆网络模型，计算M个兴趣标签的预测匹配值；
    根据M个兴趣标签的预测匹配值，筛选出预测匹配值高于预设阀值的m个有效兴趣标签；
    以所述每个有效兴趣标签的预测匹配值为中心，设置每个有效兴趣标签的权重系数范围；
    根据m个有效兴趣标签以及每个有效兴趣标签对应的权重系数范围，匹配符合要求的多个待选用户。
  20. 根据权利要求18所述的非易失性计算机可读存储介质，如果所述多个待选用户的数量大于预设阀值，所述推送步骤包括：
    根据所述用户的基本用户信息从所述多个待选用户中筛选出部分待选用户；
    将该被筛选出的部分待选用户推送到所述用户的即时通信工具的好友推荐列表中。
PCT/CN2019/117556 2019-09-26 2019-11-12 好友关系链匹配方法、系统、计算机设备及可读存储介质 WO2021056734A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910917137.6A CN110781404A (zh) 2019-09-26 2019-09-26 好友关系链匹配方法、系统、计算机设备及可读存储介质
CN201910917137.6 2019-09-26

Publications (1)

Publication Number Publication Date
WO2021056734A1 true WO2021056734A1 (zh) 2021-04-01

Family

ID=69384731

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/117556 WO2021056734A1 (zh) 2019-09-26 2019-11-12 好友关系链匹配方法、系统、计算机设备及可读存储介质

Country Status (2)

Country Link
CN (1) CN110781404A (zh)
WO (1) WO2021056734A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113420230B (zh) * 2020-12-31 2023-07-21 深圳市仁凯网络科技有限公司 基于群聊的匹配咨询推送方法、相关装置、设备及介质
CN112883073B (zh) * 2021-03-22 2024-04-05 北京同邦卓益科技有限公司 数据筛选方法、装置、设备、可读存储介质以及产品

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101916286A (zh) * 2010-08-23 2010-12-15 宇龙计算机通信科技(深圳)有限公司 一种信息推荐方法及系统
CN105468598A (zh) * 2014-08-18 2016-04-06 大连民族学院 好友推荐方法及装置
CN109544396A (zh) * 2019-01-10 2019-03-29 腾讯科技（深圳）有限公司 账号推荐方法、装置、服务器、终端及存储介质
CN110162717A (zh) * 2014-06-05 2019-08-23 网易（杭州）网络有限公司 一种推荐好友的方法和设备

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102915309B (zh) * 2011-08-03 2016-05-11 腾讯科技（深圳）有限公司 即时通信工具中好友关系链匹配方法和设备
CN105635210B (zh) * 2014-10-30 2021-04-27 腾讯科技（武汉）有限公司 网络信息的推荐方法及装置、阅读系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101916286A (zh) * 2010-08-23 2010-12-15 宇龙计算机通信科技(深圳)有限公司 一种信息推荐方法及系统
CN110162717A (zh) * 2014-06-05 2019-08-23 网易（杭州）网络有限公司 一种推荐好友的方法和设备
CN105468598A (zh) * 2014-08-18 2016-04-06 大连民族学院 好友推荐方法及装置
CN109544396A (zh) * 2019-01-10 2019-03-29 腾讯科技（深圳）有限公司 账号推荐方法、装置、服务器、终端及存储介质

Also Published As

Publication number Publication date
CN110781404A (zh) 2020-02-11

Similar Documents

Publication Publication Date Title
WO2021012783A1 (zh) 基于大数据的保单核保模型训练方法和核保风险评估方法
TWI677828B (zh) 基於資料源的業務客製裝置、方法及電腦可讀儲存介質
US8856229B2 (en) System and method for social networking
US20140040370A1 (en) Content feed for facilitating topic discovery in social networking environments
WO2020211357A1 (zh) 数据的关联分析方法、装置、计算机设备及存储介质
WO2020168851A1 (zh) 行为识别
US11483408B2 (en) Feature-based network embedding
CN111783810B (zh) 用于确定用户的属性信息的方法和装置
CN112434811A (zh) 知识图谱构建方法及装置、计算设备、存储介质
US20120284299A1 (en) Preventing leakage of information over a network
WO2021056734A1 (zh) 好友关系链匹配方法、系统、计算机设备及可读存储介质
CN111047425A (zh) 一种行为预测方法及装置
CN108319628B (zh) 一种用户兴趣确定方法及装置
CN113205189B (zh) 训练预测模型的方法、预测方法及装置
CN114119123A (zh) 信息推送的方法和装置
CN112162762A (zh) 灰度发布方法、灰度发布装置和电子设备
US10614145B2 (en) Presenting content on a webpage in a desired format
CN115099366A (zh) 分类预测方法、装置和电子设备
US11321375B2 (en) Text object management system
CN114925275A (zh) 产品推荐方法、装置、计算机设备及存储介质
US11238385B1 (en) Dynamic electronic notifications based on contextual data
CN111353864A (zh) 一种产品推荐方法、装置、服务器及存储介质
CN114818843A (zh) 数据分析的方法、装置和计算设备
US20160285885A1 (en) Contextual contacts for html5
CN113220983A (zh) 基于深度学习的选品方法和装置

Legal Events

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

Ref document number: 19946882

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19946882

Country of ref document: EP

Kind code of ref document: A1