CN112800331A - User recommendation method, device, equipment and storage medium - Google Patents
User recommendation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112800331A CN112800331A CN202110144196.1A CN202110144196A CN112800331A CN 112800331 A CN112800331 A CN 112800331A CN 202110144196 A CN202110144196 A CN 202110144196A CN 112800331 A CN112800331 A CN 112800331A
- Authority
- CN
- China
- Prior art keywords
- user
- recommended
- recommendation
- score
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 230000000694 effects Effects 0.000 claims abstract description 30
- 238000004590 computer program Methods 0.000 claims description 18
- 230000003993 interaction Effects 0.000 claims description 16
- 230000000903 blocking effect Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 230000006399 behavior Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000008846 dynamic interplay Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
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
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a user recommendation method, a device, equipment and a storage medium, wherein the method comprises the following steps: drawing the pulse recommendation data aiming at the recommended user from a preset pulse recommendation pool, and returning the pulse recommendation data to the terminal; receiving operation information aiming at the recommended user and sent by the terminal; the operation information is generated by a feedback operation acted on the recommended user by the terminal user; and updating the recommendation degree information of the recommended user according to the operation information. By combining user behaviors and user feedback on the basis of the existing user related tether of the existing user recommendation mode, user relationship data are pushed from multiple dimensions, and the user recommendation effect is guaranteed.
Description
Technical Field
The invention relates to the technical field of data mining, in particular to a user recommendation method, device, equipment and storage medium.
Background
The user relationship recommendation is to recommend more interested users to the user based on the user data so as to guide the user to pay attention, improve the user attention rate and realize the expansion of the integral relationship chain data.
However, if the recommended personal data to the user cannot arouse the interest of the user, not only the attention rate cannot be increased, but also the recommended personal data causes some interference to the user. The current user recommendation mode is generally based on second-degree friend recommendation and the like, and multi-dimensional calculation is not involved, so that the recommendation effect is low.
Disclosure of Invention
In view of the above problems, embodiments of the present invention are proposed to provide a user recommendation method, apparatus, device and storage medium that overcome or at least partially solve the above problems.
In order to solve the above problem, an embodiment of the present invention discloses a user recommendation method, where the method includes:
drawing the pulse recommendation data aiming at the recommended user from a preset pulse recommendation pool, and returning the pulse recommendation data to the terminal; the personal recommendation data is pulled according to the recommendation degree information of the recommended user;
receiving operation information aiming at the recommended user and sent by the terminal; the operation information is generated by a feedback operation acted on the recommended user by the terminal user;
and updating the recommendation degree information of the recommended user according to the operation information.
Optionally, the updating the recommendation degree information of the recommended user according to the operation information includes:
updating the recommended score of the recommended user according to the operation information;
the updating the recommended score of the recommended user according to the operation information comprises:
acquiring a recommended score of the recommended user before updating;
and if the operation information is the viewing operation aiming at the recommended user, updating the recommended score of the recommended user to be the recommended score before updating minus a preset score threshold value.
Optionally, the method further comprises:
if the operation information is the attention operation information aiming at the recommended user, deleting the recommended user from a preset personal recommendation pool;
and if the operation information is the operation stopping information aiming at the recommended user, deleting the recommended user from a preset personal recommendation pool.
Optionally, before the step of pulling the personal recommendation data for the recommended user from the preset personal recommendation pool, the method further includes:
acquiring user information of the recommended user, and generating recommendation degree information according to the user information;
and updating the recommended user to a preset personal recommendation pool according to the recommendation degree information.
Optionally, the user information of the recommended user includes a user type and a user activity; the generating recommendation degree information according to the user information includes:
generating relationship degree information according to the user type and the user activity, and acquiring a weighted value of the recommended user in a preset relationship recommendation pool;
and generating recommendation degree information of the recommended user by adopting the weight value and the relationship degree information.
Optionally, the user type includes at least one of: the method comprises the following steps of (1) a user attention type, a user blocking type, a user friend type, a common attention type of user friends, a friend type of user friends and an attention type of user attention; and the recommended users with the user types of user attention or user block types are not in the preset personal recommendation pool.
Optionally, the relationship degree information includes first relationship degree information and second relationship degree information; the generating of the relationship degree information according to the user type and the user activity degree comprises:
and generating first relationship degree information according to the user type of the recommended user, and generating second relationship degree information according to the user activity.
Optionally, the first degree of relationship information is determined by a first relationship score; the generating of the first interpersonal relationship degree information according to the user type of the recommended user includes:
if the user type of the recommended user is a friend type of the user, determining a current first-personal-relationship score according to a preset first score;
and/or if the user type of the recommended user is the common concern type of the friends of the user, determining the current first personal relationship score according to the number of the friends of the user who concern the recommended user together and a preset second score;
and/or if the user type of the recommended user is the friend type of the friends of the user, determining the current first personal relationship score according to the number of common friends and a preset third score;
and/or if the user type of the recommended user is an attention type concerned by the user, determining the current first personal relationship score according to the number of common attention and a preset fourth score.
Optionally, the second relationship degree information is determined by a second relationship score; generating second relationship degree information according to the user activity degree, including:
if the recommended user has the release dynamics in the preset time period, acquiring the time of the release dynamics and the interaction condition in the preset time period, and calculating a second relationship score according to the time of the release dynamics and the interaction condition in the preset time period;
further comprising:
and filtering recommended users without dynamic release in a preset time period.
Optionally, the obtaining the weighted value of the recommended user in the preset personal recommendation pool includes:
judging whether the recommended user exists in a preset personal recommendation pool or not;
if the recommended user exists in a preset pulse recommendation pool, acquiring a weight value of the recommended user; the weight value is determined by the recommendation pool score of the recommended user in a preset interpersonal recommendation pool;
and if the recommended user does not exist in the interpersonal recommendation pool, setting the weight value of the recommended user as a preset initial threshold value.
Optionally, the recommendation degree information is determined by a recommended score; the updating the recommended user to a preset personal recommendation pool according to the recommendation degree information comprises:
and updating the sequence of the recommended user in a preset pulse recommendation pool by adopting the recommended score, and updating or inserting the recommended user into the preset pulse recommendation pool according to the updated sequence.
The embodiment of the invention also discloses a user recommendation device, which comprises:
the system comprises a personal recommendation data pulling module, a terminal and a personal recommendation data extracting module, wherein the personal recommendation data pulling module is used for pulling the personal recommendation data aiming at recommended users from a preset personal recommendation pool and returning the personal recommendation data to the terminal; the personal recommendation data is pulled according to the recommendation degree information of the recommended user;
the operation information receiving module is used for receiving the operation information which is sent by the terminal and aims at the recommended user; the operation information is generated by a feedback operation acted on the recommended user by the terminal user;
and the recommendation degree information updating module is used for updating the recommendation degree information of the recommended user according to the operation information.
Optionally, the recommendation degree information is determined by a recommended score; the recommendation degree information updating module comprises:
the recommended score updating submodule is used for updating the recommended score of the recommended user according to the operation information;
optionally, the recommended score updating sub-module includes:
a recommended score obtaining unit, configured to obtain a recommended score of the recommended user before updating;
and the recommended score updating unit is used for updating the recommended score of the recommended user to be the recommended score before updating minus a preset score threshold value if the operation information is the viewing operation aiming at the recommended user.
Optionally, the recommendation degree information updating module further includes:
the first recommended user deleting submodule is used for deleting the recommended user from a preset personal recommendation pool if the operation information is the attention operation information aiming at the recommended user;
and the second recommended user deleting submodule is used for deleting the recommended user from a preset personal recommendation pool if the operation information is the operation stopping information aiming at the recommended user.
Optionally, before the step of pulling the personal recommendation data for the recommended user from the preset personal recommendation pool, the method further includes:
the recommendation degree information generation module is used for acquiring the user information of the recommended user and generating recommendation degree information according to the user information;
and the recommended user updating module is used for updating the recommended user to a preset interpersonal recommendation pool according to the recommendation degree information.
Optionally, the user information of the recommended user includes a user type and a user activity; the recommendation degree information generation module comprises:
the relationship degree information generation submodule is used for generating relationship degree information according to the user type and the user activity;
the weighted value obtaining submodule is used for obtaining the weighted value of the recommended user in a preset personal recommendation pool;
and the recommendation degree information generation submodule is used for generating recommendation degree information of the recommended user by adopting the weight value and the relationship degree information.
Optionally, the user type includes at least one of: the method comprises the following steps of (1) a user attention type, a user blocking type, a user friend type, a common attention type of user friends, a friend type of user friends and an attention type of user attention; and the recommended users with the user types of user attention or user block types are not in the preset personal recommendation pool.
Optionally, the relationship degree information includes first relationship degree information and second relationship degree information; the human relationship degree information generation submodule comprises:
a first-vein relation degree information generating unit, configured to generate first-vein relation degree information according to the user type of the recommended user;
and the second relationship degree information generating unit is used for generating second relationship degree information according to the user activity.
Optionally, the first degree of relationship information is determined by a first relationship score; the first-person relationship degree information generating unit includes:
a first-context-relationship-score determining subunit, configured to determine, if the user type of the recommended user is a user friend type, a current first context score according to a preset first score;
the first-context-relationship-score determining subunit is further configured to determine, if the user type of the recommended user is a common concern type of friends of the user, a current first-context-relationship score according to the number of friends of the user who concern the recommended user together and a preset second score;
the first-personality-relationship-score determining subunit is further configured to determine, if the user type of the recommended user is a friend type of a friend of the user, a current first-personality-relationship score according to the number of common friends and a preset third score;
and the first-personal-relationship-score determining subunit is further configured to determine, if the user type of the recommended user is an attention type concerned by the user, a current first-personal-relationship score according to the number of common attentions and a preset fourth score.
Optionally, the second relationship degree information is determined by a second relationship score; the second relationship degree information generation unit includes:
the second relationship score determining subunit is configured to, if the recommended user has a release dynamics in a preset time period, obtain time of the release dynamics and an interaction condition in the preset time period, and calculate a second relationship score according to the time of the release dynamics and the interaction condition in the preset time period;
optionally, the second relationship degree information generating unit further includes:
and the recommended user filtering subunit is used for filtering the recommended users without dynamic release in a preset time period.
Optionally, the weight value obtaining sub-module includes:
the recommended user judging unit is used for judging whether the recommended user exists in a preset interpersonal recommendation pool or not;
the weight value obtaining unit is used for obtaining the weight value of the recommended user if the recommended user exists in a preset pulse recommendation pool; the weight value is determined by the recommendation pool score of the recommended user in a preset interpersonal recommendation pool;
and the weight value setting unit is used for setting the weight value of the recommended user as a preset initial threshold value if the recommended user does not exist in the interpersonal recommendation pool.
Optionally, the recommended user updating module includes:
and the recommended user updating submodule is used for updating the sequence of the recommended user in a preset pulse recommendation pool by adopting the recommended score and updating or inserting the recommended user into the preset pulse recommendation pool according to the updated sequence.
The embodiment of the invention also discloses a device, which comprises: a processor, a memory and a computer program stored on the memory and capable of running on the processor, the computer program when executed by the processor implementing the steps of any of the user recommendation methods.
The embodiment of the invention also discloses a computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and the computer program is used for realizing the steps of any user recommendation method when being executed by a processor.
The embodiment of the invention has the following advantages:
in the embodiment of the invention, the server can pull the pulse recommendation data from the pulse recommendation pool and return the pulse recommendation data to the user terminal, and when the user terminal detects the feedback operation aiming at the returned recommended user, the recommendation degree information of the recommended user can be updated according to the operation information sent by the user terminal so as to further update the pulse recommendation pool. By combining user behaviors and user feedback on the basis of the existing user related tether of the existing user recommendation mode, user relationship data are pushed from multiple dimensions, and the user recommendation effect is guaranteed.
Drawings
FIG. 1 is a flow chart of steps of an embodiment of a user recommendation method of the present invention;
FIG. 2 is a flow chart of steps in another embodiment of a user recommendation method of the present invention;
FIG. 3 is a diagram of an application scenario of a user recommendation method in an embodiment of the present invention;
fig. 4 is a block diagram of an embodiment of a user recommendation device according to the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
One of the core ideas of the embodiment of the invention is to calculate the first degree/second degree relationship of the recommended user according to the friend relationship, the attention relationship and the like of the user, calculate and sort the recommended score of the recommended user by combining the posting condition in the user terminal and the client behavior, and dynamically adjust the attention strategy of the user for the recommended user in an experimental mode.
Referring to fig. 1, a flowchart illustrating steps of an embodiment of a user recommendation method according to the present invention is shown, which may specifically include the following steps:
at present, many social applications can be applied to various mobile terminals or PC clients such as mobile phones and tablet computers, so that users can communicate with other users through the social applications. In practical applications, the server may recommend more users to the end user during the use of the registered social application, so as to improve the user stickiness and universality of the social application.
In an embodiment of the invention, a server can pull a recommended user and return the recommended user to a terminal, and in one case, the server can pull the recommended user passively and return the personal recommendation data to the terminal passively; in another case, the server may actively pull the recommended users and return the personal recommendation data to the active terminal.
The pulled personal recommendation data may be a preset number of user data pulled according to the recommended information, and specifically may be a limited number of pieces of recommended user data pulled in the order from high to low according to the recommended score. It should be noted that the value of the preset number may be determined according to actual situations, and the embodiment of the present invention is not limited thereto.
102, receiving operation information aiming at the recommended user, which is sent by the terminal; the operation information is generated by a feedback operation acted on the recommended user by the terminal user;
the server responds to the recommended user acquisition request to pull the pulse recommendation data from the preset pulse recommendation pool, and after the user terminal receives the pulse recommendation data returned by the server, the terminal user can operate the recommended user in the returned pulse recommendation data so as to update the pulse recommendation pool according to the operation of the terminal user.
Specifically, the operation of the terminal user on the recommended user may be detected by the user terminal, and then the feedback information detected by the user terminal may include operation information corresponding to the feedback operation of the recommended user, so as to update the recommendation degree information of the recommended user through the operation information.
And 103, updating the recommendation degree information of the recommended user according to the operation information.
The recommendation degree information may be used to indicate a pushing degree of the recommended user in the preset personal recommendation pool, and may be specifically determined by a recommended score of the recommended user.
In practical applications, the server updates the recommendation degree information of the recommended user, which can be substantially represented as processing the recommended score of the recommended user according to the operation information. If the operation information is the viewing operation information for the recommended user, which indicates that the terminal user has viewed the recommended user but does not pay attention to or prevent the recommended user, the recommended score of the recommended user before updating can be obtained, and the recommended score of the recommended user is updated to be the recommended score before updating minus a preset score threshold.
The recommended score for determining the recommended degree information can be obtained by summarizing the relationship score and the weight value, and the weight value can be determined by the recommendation pool score of the recommended user in the relationship recommendation pool, and the recommended score of the recommended user is processed, which is essentially processing the recommendation pool score of the recommended user, namely subtracting a preset score threshold from the recommendation pool score of the recommended user.
In a particular implementation, the preset score threshold may be an initial recommendation pool score (e.g., 1000) when the recommended user is not in the demographic recommendation pool, for the purpose of placing the ranking of the recommended users that have been pushed to the end user in the demographic recommendation pool at a later point.
In an alternative embodiment, if the updated recommended score is a negative number, it indicates that the end user is not interested in the recommended user, and the recommended user is not recommended any more, which may be mainly represented as deleting the recommended user from the personal recommendation pool.
In an embodiment of the present invention, the operation information corresponding to the feedback operation of the recommended user may include, in addition to the viewing operation information, focused operation information, blocked operation information, and the like.
If the operation information is the attention operation information for the recommended user, which indicates that the terminal user pays attention to the recommended user, the recommended user can be deleted from the preset personal recommendation pool at this moment; if the operation information is the operation blocking information for the recommended user, the operation blocking information indicates that the terminal user has blocked the recommended user, that is, the terminal user does not want to pay attention to the recommended user, and at this time, the recommended user can be deleted from the preset personal recommendation pool.
In the embodiment of the invention, the server can pull the pulse recommendation data from the pulse recommendation pool and return the pulse recommendation data to the user terminal, and when the user terminal detects the feedback operation aiming at the returned recommended user, the recommendation degree information of the recommended user can be updated according to the operation information sent by the user terminal so as to further update the pulse recommendation pool. By combining user behaviors and user feedback on the basis of the existing user related tether of the existing user recommendation mode, user relationship data are pushed from multiple dimensions, and the user recommendation effect is guaranteed.
Referring to fig. 2, a flowchart illustrating steps of another embodiment of a user recommendation method according to the present invention is shown, which may specifically include the following steps:
in an embodiment of the present invention, the rule of pulling the recommended data is to pull the data of the recommended user according to recommendation degree information (i.e. the recommended score sequence, which is generally from high to low), and before the server pulls the recommended data from the preset personal recommendation pool, the server needs to determine recommendation degree information, i.e. the recommended score, of the recommended user, which may be specifically expressed as determining the recommended score according to the user information of the recommended user.
In one embodiment of the present invention, step 201 may include the following sub-steps:
a substep S11 of generating relationship degree information according to the user type and the user activity;
specifically, the relationship degree information may be generated according to the user information of the recommended user, so as to be used for determining the recommendation degree information of the recommended user.
In an embodiment of the present invention, the user information of the recommended user may include a user type and a user activity of the recommended user, and then the first relationship degree information and the second relationship degree information may be obtained according to the user type and the user activity of the recommended user, respectively. Wherein the first relationship degree information may be determined by the first relationship score, and the second relationship degree information may be determined by the second relationship score.
In particular implementations, the user type of the recommended user may include at least one of: a user attention type, a user block type, a user friend type, a common attention type of the user friends, a friend type of the user friends, and an attention type of the user attention.
The user attention type may refer to a user who the user actively pays attention to, the user blocking type may refer to a user who the user has blocked, the user friend type may refer to a friend on an address list of the user, the common attention type of friends of the user may refer to a user who has attention of more than two friends, the friend type of friends of the user may refer to a user who has attention of more than two friends, and the attention type of the user attention may refer to a user who has attention of more than two friends in common.
It should be noted that the recommended users with the user types of user attention or user block are not in the preset personal recommendation pool.
In an embodiment of the present invention, the first membership degree is determined according to a user type of a recommended user, and the specific steps may include determining a current first membership score according to a preset first score if the user type of the recommended user is a friend type of the user; if the user type of the recommended user is the common concern type of the friends of the user, determining a current first-personal relationship score according to the number of the friends of the user who commonly concern the recommended user and a preset second score; if the user type of the recommended user is the friend type of the friends of the user, determining the current first personal relationship score according to the number of common friends and a preset third score; if the user type of the recommended user is the attention type concerned by the user, the current first-person relationship score can be determined according to the number of common attention and the preset fourth score.
In practical application, if the recommended user is a friend of the user, the current first-personal-relationship score may be recorded as a preset first score (for example, 50 scores); if the recommended user is a common concern of the friends of the user, assuming that N is the number of the friends who concern the recommended user (where N > is 2), the score of the current first personal relationship score may be marked as N × 10 (i.e., a preset second score); if the recommended user is a friend of the user, assuming that N is the number of common friends (where N > is 2), that is, the number of friends in the terminal user friend who are friends with the recommended user, the score of the current first personal relationship score may be marked as N × 8 (that is, a preset third score); if the recommended user is the user's attention, assuming that N is the number of users paying attention (where N > is 2), that is, the number of users paying attention to the recommended user among the users paying attention to the end user, the score of the current first personal relationship score may be denoted as N × 5 (that is, a preset fourth score).
It should be noted that the user type of the recommended user may be not only one of the user types, but also any combination among the user types, when the user type of the recommended user is any combination type, the current first-pulse relationship degree of the recommended user may be accumulated according to the score that meets the type, the total first-pulse relationship degree obtained by accumulation does not exceed 100, and if the score exceeds 100, 100 is taken as the total first-pulse relationship degree; and the specific value of each score can be dynamically adjusted, so that the embodiment of the invention is not limited by any combination form among user types and the specific value of the score.
In one embodiment of the invention, after the relevant relationship of the recommended user is calculated in a classification type (can be updated regularly), the first relationship score can also be calculated in combination with the user activity of the recommended user in a superposition manner. The user activity may refer to a situation that the recommended user publishes the dynamic state, such as a time interval of publishing the dynamic state, a number of publishing the dynamic state, a frequency of publishing the dynamic state, a situation of dynamic interaction, and the like.
In a specific implementation, a second relationship degree is obtained according to the activity of the user, the second relationship degree can be determined by a second relationship score, and the second relationship score can be expressed as a posting score and a posting interaction score calculated by combining the posting conditions of the recommended users.
In practical application, if the recommended user has the release dynamics in the preset time period, the time of the release dynamics and the interaction condition in the preset time period can be obtained, and the second relationship score is calculated according to the time of the release dynamics and the interaction condition in the preset time period. That is, the posting score can be calculated according to the posting time, and the posting interaction score can be calculated according to the interaction condition in the preset time period, so that the second interpersonal relationship score can be determined according to the posting score and the posting interaction score.
As an example, the rules for posting scores may be as follows: a recommended user who posted a post within a preset time period (e.g., 10 days in the past), may calculate a posting score by the time of the last posting (assuming N days ago, where 0 ═ N < ═ 9), which may be specifically expressed as (10-N) × 10; the rules for posting interaction scores may be as follows: assuming that N is the total number of praise/comment that the recommended user has made in the past 10 days, the item score may be N, and 100 is taken if N is greater than 100.
In a preferred embodiment, the filtering may be performed according to the user activity of the recommended user, and the main performance may be to determine whether the recommended user has a distribution dynamics within a preset time period (for example, 10 days in the past), and if the recommended user has not distributed dynamics within the 10 days in the past, filter the recommended user having no distribution dynamics within the preset time period, that is, delete the recommended user, and not write the recommended user into the human-vein recommendation pool.
And a substep S12, obtaining a weight value of the recommended user in a preset relationship recommendation pool, and generating recommendation degree information of the recommended user by adopting the weight value and the relationship degree information.
The weight value can refer to the recommended degree of the recommended user in the relationship recommendation pool, at the moment, the recommended user is updated in the relationship recommendation pool according to the weight value and the relationship degree of the relationship between the recommended user and the relationship recommendation pool, and the relationship data of the user can be calculated from multiple dimensions.
Specifically, for the determination of the weight value, it may be first determined whether the recommended user exists in a preset personal recommendation pool; in one case, if the recommended user exists in the preset personal recommendation pool, the weight value of the recommended user may be obtained, and the weight value may be determined by the score of the recommendation pool in which the recommended user exists in the preset personal recommendation pool; in another case, if the recommended user does not exist in the personal recommendation pool, the weighted value of the recommended user may be set to be a preset initial threshold (for example, 1000, a value of the preset initial threshold may be determined according to actual needs). The recommendation pool score is the same as the weight value, and both the recommendation pool score and the weight value can be used for defining the recommended degree of the recommended user in the popularity recommendation pool, and can also represent the front degree of recommendation sequencing of the recommended user in the popularity recommendation pool.
In practical application, if the recommended user exists in the popularity recommendation pool, the weight value of the recommended user may be obtained, wherein if the recommendation pool score is X, the weight value may be rounded by X/1000 and then multiplied by 1000, otherwise, the initial weight value of the user may be set to 10000.
in an embodiment of the present invention, the recommended score (used for representing the recommendation degree of the recommended user) of the recommended user may be obtained by summarizing the weight value and the relationship score, then the recommended score is adopted to update the ranking of the recommended user in the preset relationship recommendation pool, and the recommended user is updated or inserted into the preset relationship recommendation pool according to the updated ranking.
And step 203, pulling the pulse recommendation data from a preset pulse recommendation pool according to the recommended scores of the recommended users.
In an embodiment of the present invention, the server may actively or passively pull the personal recommendation data and return the personal recommendation data to the terminal, where the pulled personal recommendation data may be a preset number of user data pulled according to the recommended information, and specifically may be represented by pulling a limited number of pieces of recommended user data in an order from high to low according to the recommended score.
In a preferred embodiment, after the recommended user data is returned to the terminal, the recommendation degree information of the recommended user may also be updated according to the feedback of the user, that is, the recommended score of the recommended user is updated, and the specific implementation steps may be as shown in step 103, which are not described here to avoid content encumbrance.
In the embodiment of the invention, the first-degree/second-degree relationship of the recommended user is calculated according to the friend relationship, the attention relationship and the like of the user, the recommended scores of the recommended user are calculated and sorted according to the posting condition in the user terminal and the client behavior, and the attention strategy of the user for the recommended user is dynamically adjusted in an experimental mode.
Referring to fig. 3, which shows an application scenario diagram of the user recommendation method implemented in the present invention, assuming that a is one of recommended users pulled by a server from a preset personal recommendation pool, and B is a terminal user, if a is to be recommended to B, the recommendation process may be as follows:
in the embodiment of the present invention, assuming that the recommended user a is a friend of the terminal user B, and the recommended user a and the terminal user B have 2 common friends, and the terminal user B has 3 friends focusing on the recommended user a together, the relationship degree information (which may be determined by the first relationship score) of the recommended user a may be 50+2 + 10+3 + 8-94; assuming that recommended user a is 2 days before the last post update, the posting score may be (10-2) × 10 ═ 80; assuming that the total number of praise/comment posted by the recommended user a for 10 days is 50, the posting interaction score may be 50;
in summary, the popularity relationship score of the recommended user a may be 94+80+50 ═ 224, and assuming that the recommended user a does not exist in the popularity recommendation pool, the initial weight value is 10000, and the recommended score obtained by the final aggregation may be 10224;
and if the recommended user A is checked by the terminal user B after the recommended user A is pushed to the terminal user B (namely under the condition that the terminal user B does not block or pay attention to the recommended user A), updating the recommended score of the recommended user A to be 10224-1000-9224 (which essentially processes the recommendation pool score for determining the weight value in the recommended score) so as to achieve the effect of pushing other recommended users which are not pushed in the popularity recommendation pool to the terminal user B in the following step.
It should be noted that, by applying the user recommendation method of the embodiment of the present invention, the attention rate of the recommended user can be increased, and the attention rate of the recommended user is increased by 5% through experiments and statistics.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Referring to fig. 4, a block diagram of a user recommendation device according to an embodiment of the present invention is shown, which may specifically include the following modules:
the personal recommendation data pulling module 401 is configured to pull the personal recommendation data for the recommended user from a preset personal recommendation pool, and return the personal recommendation data to the terminal; the personal recommendation data is pulled according to the recommendation degree information of the recommended user;
an operation information receiving module 402, configured to receive operation information, which is sent by the terminal and is for the recommended user; the operation information is generated by a feedback operation acted on the recommended user by the terminal user;
a recommendation degree information updating module 403, configured to update the recommendation degree information of the recommended user according to the operation information.
In an embodiment of the present invention, before pulling the personal recommendation data for the recommended user from the preset personal recommendation pool, the following modules may be further included:
the recommendation degree information generation module is used for acquiring the user information of the recommended user and generating recommendation degree information according to the user information;
and the recommended user updating module is used for updating the recommended user to a preset interpersonal recommendation pool according to the recommendation degree information.
In an embodiment of the present invention, the user information of the recommended user includes a user type and a user activity; the recommendation degree information generating module may include the following sub-modules:
the relationship degree information generation submodule is used for generating relationship degree information according to the user type and the user activity;
the weighted value obtaining submodule is used for obtaining the weighted value of the recommended user in a preset personal recommendation pool;
and the recommendation degree information generation submodule is used for generating recommendation degree information of the recommended user by adopting the weight value and the relationship degree information.
In one embodiment of the invention, the user type comprises at least one of: the method comprises the following steps of (1) a user attention type, a user blocking type, a user friend type, a common attention type of user friends, a friend type of user friends and an attention type of user attention; and the recommended users with the user types of user attention or user block types are not in the preset personal recommendation pool.
In an embodiment of the present invention, the relationship degree information includes first relationship degree information and second relationship degree information; the personal relationship degree information generation submodule may include the following units:
a first-vein relation degree information generating unit, configured to generate first-vein relation degree information according to the user type of the recommended user;
and the second relationship degree information generating unit is used for generating second relationship degree information according to the user activity.
In one embodiment of the invention, the first degree of relationship information is determined by a first relationship score; the first-person relationship degree information generating unit may include the following sub-units:
a first-context-relationship-score determining subunit, configured to determine, if the user type of the recommended user is a user friend type, a current first context score according to a preset first score;
the first-context-relationship-score determining subunit is further configured to determine, if the user type of the recommended user is a common concern type of friends of the user, a current first-context-relationship score according to the number of friends of the user who concern the recommended user together and a preset second score;
the first-personality-relationship-score determining subunit is further configured to determine, if the user type of the recommended user is a friend type of a friend of the user, a current first-personality-relationship score according to the number of common friends and a preset third score;
and the first-personal-relationship-score determining subunit is further configured to determine, if the user type of the recommended user is an attention type concerned by the user, a current first-personal-relationship score according to the number of common attentions and a preset fourth score.
In one embodiment of the invention, the second relationship degree information is determined by a second relationship score; the second relationship degree information generation unit may include the following sub-units:
the second relationship score determining subunit is configured to, if the recommended user has a release dynamics in a preset time period, obtain time of the release dynamics and an interaction condition in the preset time period, and calculate a second relationship score according to the time of the release dynamics and the interaction condition in the preset time period;
in an embodiment of the present invention, the second relationship degree information generating unit may further include the following sub-units:
and the recommended user filtering subunit is used for filtering the recommended users without dynamic release in a preset time period.
In an embodiment of the present invention, the weight value obtaining submodule may include the following units:
the recommended user judging unit is used for judging whether the recommended user exists in a preset interpersonal recommendation pool or not;
the weight value obtaining unit is used for obtaining the weight value of the recommended user if the recommended user exists in a preset pulse recommendation pool; the weight value is determined by the recommendation pool score of the recommended user in a preset interpersonal recommendation pool;
and the weight value setting unit is used for setting the weight value of the recommended user as a preset initial threshold value if the recommended user does not exist in the interpersonal recommendation pool.
In one embodiment of the present invention, the recommended user update module may include the following sub-modules:
and the recommended user updating submodule is used for updating the sequence of the recommended user in a preset pulse recommendation pool by adopting the recommended score and updating or inserting the recommended user into the preset pulse recommendation pool according to the updated sequence.
In one embodiment of the invention, the recommendation degree information is determined by a recommended score; the recommendation degree information updating module 403 may include the following sub-modules:
the recommended score updating submodule is used for updating the recommended score of the recommended user according to the operation information;
in one embodiment of the present invention, the recommended score updating sub-module may include the following elements:
a recommended score obtaining unit, configured to obtain a recommended score of the recommended user before updating;
and the recommended score updating unit is used for updating the recommended score of the recommended user to be the recommended score before updating minus a preset score threshold value if the operation information is the viewing operation aiming at the recommended user.
In an embodiment of the present invention, the recommendation degree information updating module 403 may further include the following sub-modules:
the first recommended user deleting submodule is used for deleting the recommended user from a preset personal recommendation pool if the operation information is the attention operation information aiming at the recommended user;
and the second recommended user deleting submodule is used for deleting the recommended user from a preset personal recommendation pool if the operation information is the operation stopping information aiming at the recommended user.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
An embodiment of the present invention further provides an apparatus, including:
the user recommendation method comprises a processor, a memory and a computer program which is stored in the memory and can run on the processor, wherein when the computer program is executed by the processor, each process of the user recommendation method embodiment is realized, the same technical effect can be achieved, and in order to avoid repetition, the description is omitted here.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when being executed by a processor, the computer program implements each process of the user recommendation method embodiment, and can achieve the same technical effect, and in order to avoid repetition, the details are not repeated here.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The user recommendation method, device, apparatus and storage medium provided by the present invention are introduced in detail, and a specific example is applied in the description to explain the principle and the implementation of the present invention, and the description of the above embodiment is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (14)
1. A user recommendation method, the method comprising:
drawing the pulse recommendation data aiming at the recommended user from a preset pulse recommendation pool, and returning the pulse recommendation data to the terminal; the personal recommendation data is pulled according to the recommendation degree information of the recommended user;
receiving operation information aiming at the recommended user and sent by the terminal; the operation information is generated by a feedback operation acted on the recommended user by the terminal user;
and updating the recommendation degree information of the recommended user according to the operation information.
2. The method of claim 1, further comprising, prior to pulling the personal recommendation data for the recommended user from a preset personal recommendation pool:
acquiring user information of the recommended user, and generating recommendation degree information according to the user information;
and updating the recommended user to a preset personal recommendation pool according to the recommendation degree information.
3. The method of claim 2, wherein the user information of the recommended users comprises user type and user activity; the generating recommendation degree information according to the user information includes:
generating relationship degree information according to the user type and the user activity, and acquiring a weighted value of the recommended user in a preset relationship recommendation pool;
and generating recommendation degree information of the recommended user by adopting the weight value and the relationship degree information.
4. The method of claim 3,
the user type includes at least one of: the method comprises the following steps of (1) a user attention type, a user blocking type, a user friend type, a common attention type of user friends, a friend type of user friends and an attention type of user attention; and the recommended users with the user types of user attention or user block types are not in the preset personal recommendation pool.
5. The method according to claim 4, wherein the degree of relationship information includes first degree of relationship information and second degree of relationship information; the generating of the relationship degree information according to the user type and the user activity degree comprises:
and generating first relationship degree information according to the user type of the recommended user, and generating second relationship degree information according to the user activity.
6. The method of claim 5, wherein the first degree of relationship information is determined by a first relationship score; the generating of the first interpersonal relationship degree information according to the user type of the recommended user includes:
if the user type of the recommended user is a friend type of the user, determining a current first-personal-relationship score according to a preset first score;
and/or if the user type of the recommended user is the common concern type of the friends of the user, determining the current first personal relationship score according to the number of the friends of the user who concern the recommended user together and a preset second score;
and/or if the user type of the recommended user is the friend type of the friends of the user, determining the current first personal relationship score according to the number of common friends and a preset third score;
and/or if the user type of the recommended user is an attention type concerned by the user, determining the current first personal relationship score according to the number of common attention and a preset fourth score.
7. The method of claim 3, wherein the second context relationship degree information is determined by a second context relationship score; generating second relationship degree information according to the user activity degree, including:
if the recommended user has the release dynamics in the preset time period, acquiring the time of the release dynamics and the interaction condition in the preset time period, and calculating a second relationship score according to the time of the release dynamics and the interaction condition in the preset time period;
further comprising:
and filtering recommended users without dynamic release in a preset time period.
8. The method according to claim 3, wherein the obtaining the weighted value of the recommended user in a preset personal recommendation pool comprises:
judging whether the recommended user exists in a preset personal recommendation pool or not;
if the recommended user exists in a preset pulse recommendation pool, acquiring a weight value of the recommended user; the weight value is determined by the recommendation pool score of the recommended user in a preset interpersonal recommendation pool;
and if the recommended user does not exist in the interpersonal recommendation pool, setting the weight value of the recommended user as a preset initial threshold value.
9. The method of claim 2, wherein the recommendation degree information is determined by a recommended score; the updating the recommended user to a preset personal recommendation pool according to the recommendation degree information comprises:
and updating the sequence of the recommended user in a preset pulse recommendation pool by adopting the recommended score, and updating or inserting the recommended user into the preset pulse recommendation pool according to the updated sequence.
10. The method according to claim 1, wherein the updating the recommendation degree information of the recommended user according to the operation information comprises:
updating the recommended score of the recommended user according to the operation information;
the updating the recommended score of the recommended user according to the operation information comprises:
acquiring a recommended score of the recommended user before updating;
and if the operation information is the viewing operation aiming at the recommended user, updating the recommended score of the recommended user to be the recommended score before updating minus a preset score threshold value.
11. The method of claim 10, further comprising:
if the operation information is the attention operation information aiming at the recommended user, deleting the recommended user from a preset personal recommendation pool;
and if the operation information is the operation stopping information aiming at the recommended user, deleting the recommended user from a preset personal recommendation pool.
12. A user recommendation apparatus, the apparatus comprising:
the system comprises a personal recommendation data pulling module, a terminal and a personal recommendation data extracting module, wherein the personal recommendation data pulling module is used for pulling the personal recommendation data aiming at recommended users from a preset personal recommendation pool and returning the personal recommendation data to the terminal; the personal recommendation data is pulled according to the recommendation degree information of the recommended user;
the operation information receiving module is used for receiving the operation information which is sent by the terminal and aims at the recommended user; the operation information is generated by a feedback operation acted on the recommended user by the terminal user;
and the recommendation degree information updating module is used for updating the recommendation degree information of the recommended user according to the operation information.
13. An apparatus, comprising: processor, memory and computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the user recommendation method as claimed in any one of claims 1-10.
14. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the user recommendation method according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110144196.1A CN112800331A (en) | 2021-02-02 | 2021-02-02 | User recommendation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110144196.1A CN112800331A (en) | 2021-02-02 | 2021-02-02 | User recommendation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112800331A true CN112800331A (en) | 2021-05-14 |
Family
ID=75813715
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110144196.1A Pending CN112800331A (en) | 2021-02-02 | 2021-02-02 | User recommendation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112800331A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714135A (en) * | 2013-12-18 | 2014-04-09 | 东软集团股份有限公司 | MapReduce recommendation method and system of second-degree interpersonal relationships of massive users |
| CN104156392A (en) * | 2014-07-09 | 2014-11-19 | 中电科华云信息技术有限公司 | Personalized recommendation method and system for friends and applications |
| CN105245435A (en) * | 2015-09-28 | 2016-01-13 | 广州市百果园网络科技有限公司 | Friend recommending method and system |
| CN107368520A (en) * | 2017-06-06 | 2017-11-21 | 成都移智有方科技有限公司 | Towards the human connection Managed Solution of University Enterprise resource integration platform |
| CN109859064A (en) * | 2019-01-31 | 2019-06-07 | 北京俩俩科技有限公司 | Friend recommendation method and system based on hail fellow relationship |
| CN110837598A (en) * | 2019-11-11 | 2020-02-25 | 腾讯科技（深圳）有限公司 | Information recommendation method, device, equipment and storage medium |
| CN110929170A (en) * | 2019-11-22 | 2020-03-27 | 腾讯科技（深圳）有限公司 | Friend recommendation method, device, equipment and storage medium for social group |
-
2021
- 2021-02-02 CN CN202110144196.1A patent/CN112800331A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714135A (en) * | 2013-12-18 | 2014-04-09 | 东软集团股份有限公司 | MapReduce recommendation method and system of second-degree interpersonal relationships of massive users |
| CN104156392A (en) * | 2014-07-09 | 2014-11-19 | 中电科华云信息技术有限公司 | Personalized recommendation method and system for friends and applications |
| CN105245435A (en) * | 2015-09-28 | 2016-01-13 | 广州市百果园网络科技有限公司 | Friend recommending method and system |
| CN107368520A (en) * | 2017-06-06 | 2017-11-21 | 成都移智有方科技有限公司 | Towards the human connection Managed Solution of University Enterprise resource integration platform |
| CN109859064A (en) * | 2019-01-31 | 2019-06-07 | 北京俩俩科技有限公司 | Friend recommendation method and system based on hail fellow relationship |
| CN110837598A (en) * | 2019-11-11 | 2020-02-25 | 腾讯科技（深圳）有限公司 | Information recommendation method, device, equipment and storage medium |
| CN110929170A (en) * | 2019-11-22 | 2020-03-27 | 腾讯科技（深圳）有限公司 | Friend recommendation method, device, equipment and storage medium for social group |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11128582B2 (en) | Emoji recommendation method and apparatus | |
| CN106844404B (en) | Message display method and terminal equipment | |
| CN111330279B (en) | Strategy decision model training method and device for game AI | |
| WO2014194642A1 (en) | Systems and methods for matching users | |
| JP2018530848A (en) | Distribution method, apparatus and system for promotion information | |
| US20130311556A1 (en) | System and Method for Generating Theme Based Dynamic Groups | |
| US10478728B2 (en) | Information processing system, server, program, and information processing method | |
| US10992611B2 (en) | Topic classified presentation for a message in a message cluster | |
| JP6522129B2 (en) | Information processing method and device | |
| US10511679B2 (en) | Method of determining and transmitting potentially viral media items based on the velocity measure of another media item exceeding a velocity threshold set for that type of media item | |
| US9621507B2 (en) | Control method and apparatus for data display | |
| CN111581521A (en) | Group member recommendation method, device, server, storage medium and system | |
| CN112418899A (en) | Display control method and device for advertisement space | |
| CN109885720B (en) | Music on demand interaction method, medium, device and computing equipment | |
| CN109241450B (en) | Screen locking content recommendation method and device | |
| CN110248211B (en) | Live broadcast room message current limiting method and device, electronic equipment and storage medium | |
| CN112907384B (en) | Interaction method, device and equipment of social account and storage medium | |
| CN112800331A (en) | User recommendation method, device, equipment and storage medium | |
| US10872121B2 (en) | Systems and methods for matching users | |
| CN107886112B (en) | Object clustering method and device and storage equipment | |
| CN109327488B (en) | Network information pushing method and device and server | |
| CN112836127B (en) | Method and device for recommending social users, storage medium and electronic equipment | |
| CN104811365B (en) | Message delivery method, system and server based on real-time communication social group | |
| CN116983624A (en) | Recommendation method and device for game strategy, electronic equipment and storage medium | |
| CN111126614B (en) | Attribution method, attribution device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |