CN110781404A - Friend relationship chain matching method, system, computer equipment and readable storage medium - Google Patents
Friend relationship chain matching method, system, computer equipment and readable storage medium Download PDFInfo
- Publication number
- CN110781404A CN110781404A CN201910917137.6A CN201910917137A CN110781404A CN 110781404 A CN110781404 A CN 110781404A CN 201910917137 A CN201910917137 A CN 201910917137A CN 110781404 A CN110781404 A CN 110781404A
- Authority
- CN
- China
- Prior art keywords
- user
- users
- content
- matching
- weight coefficient
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000005065 mining Methods 0.000 claims abstract description 41
- 230000015654 memory Effects 0.000 claims description 35
- 230000006399 behavior Effects 0.000 claims description 31
- 230000000007 visual effect Effects 0.000 claims description 13
- 238000012216 screening Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 4
- 230000006403 short-term memory Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000007787 long-term memory Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 235000010627 Phaseolus vulgaris Nutrition 0.000 description 2
- 244000046052 Phaseolus vulgaris Species 0.000 description 2
- 235000019013 Viburnum opulus Nutrition 0.000 description 2
- 244000071378 Viburnum opulus Species 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 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
- G06F16/9536—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)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (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 friend relationship chain matching method, which comprises the steps of obtaining behavior information of a user through a mobile terminal; configuring mining conditions according to the behavior information, and mining a plurality of users to be selected which accord with the mining conditions in the behavior information of other users except the user; pushing the multiple users to be selected to a friend recommendation list in an instant messaging tool of the users; receiving selection operation of the user for one or more to-be-selected users; and establishing a friend relation chain between the user and the selected one or more to-be-selected users according to the selection operation. The friend relationship chain matching in the embodiment of the invention does not need manual intervention of a user, and matches friends through the behavior information, so that the matching accuracy is higher.
Description
Technical Field
The embodiment of the invention relates to the field of computer data processing, in particular to a friend relationship chain matching method, a friend relationship chain matching system, a friend relationship chain matching computer device and a computer readable storage medium.
Background
The instant messaging software aims to help people establish a friend relation chain and solve the problem of remote communication between people by establishing the friend relation chain. The number and quality of friend relationship chains can greatly affect the retention and liveness of users on the instant messaging platform. In general, friends can be added manually by inputting other user IDs, or corresponding friends can be matched according to the phone numbers of the contacts in the address list. However, only the friend relationship chain is established in the above manner, and a friend relationship chain with a certain scale and high quality cannot be established.
To solve the above problems, the present inventors have currently recognized solutions of: (1) the user inputs search conditions, such as gender, region, age and the like, queries the users meeting the search conditions according to the search conditions input by the user, and recommends the searched users to the users. (2) And taking the personal basic information filled in during the registration of the user as a searching condition, inquiring similar users according to the searching condition, and recommending the searched users to the user.
However, the above solutions all have certain technical drawbacks: in the solution (1), the matching of the friend relationship chain requires manual intervention of a user, and when searching friends, a user unfamiliar with the system may not search a satisfactory result, thereby affecting user experience; the method (2) for automatically matching the friend relationship chain for the user according to the personal basic information such as the gender, the age and the like filled in during registration has low accuracy, and the problems of incomplete filling, false filling and the like of the user information can occur.
Disclosure of Invention
In view of this, an object of the embodiments of the present invention is to provide a method, a system, a computer device, and a computer readable storage medium for matching a friend relationship chain, so as to solve the problem of manual intervention of matching the friend relationship chain and the problem of low accuracy of automatically matching the friend relationship chain.
In order to achieve the above object, an embodiment of the present invention provides a method for matching a friend relationship chain, including the following steps:
an acquisition step, in which behavior information of a user is acquired through a mobile terminal;
a mining step, configured mining conditions according to the behavior information, and mining a plurality of users to be selected according with the mining conditions in the behavior information of other users except the user;
pushing, namely pushing the multiple users to be selected to a friend recommendation list in an instant messaging tool of the users;
a receiving step, namely receiving the selection operation of the user for one or more to-be-selected users; and
and a relation chain establishing step, namely establishing a friend relation chain between the user and the selected one or more to-be-selected users according to the selection operation.
Preferably, the behavior information includes page access records and/or interest type APP usage information; the excavating step comprises:
acquiring the content subject of each accessed page according to the page access record, and configuring a weight coefficient for each content subject according to the occurrence frequency of each content subject;
setting the weight coefficient range of each content theme by taking the weight coefficient of each content theme as a center;
and matching a plurality of users to be selected according with the requirements according to each content theme and the weight coefficient range corresponding to each content theme.
Preferably, the friend recommendation list includes the recommended degree of each user to be selected; the pushing step comprises the following steps:
calculating a matching degree coefficient of each to-be-selected user and the user according to the weight coefficient of each content theme corresponding to each to-be-selected user, wherein the matching degree coefficient is used for determining the recommendation degree of each to-be-selected user in a friend recommendation list;
the matching degree coefficient calculation formula is as follows:
wherein, P
iα is a constant value which is a matching coefficient of a user i to be selected and the user, β
jWeight coefficient, δ, for topic of content j
ijIs the ratio between the weight coefficient of the content subject j in the user and the weight coefficient of the content subject j in the user i to be selected, the ratio is less than or equal to 1, m isThe total number of content topics.
Preferably, the behavior information includes page access records and/or interest type APP usage information; the excavating step comprises:
acquiring the content subject of each accessed page according to the page access record to obtain n content subjects;
configuring a weight coefficient for each content theme according to the occurrence number of each content theme;
defining an N-dimensional parameter vector according to N content topics of the user, wherein the weight coefficients of the N content topics are respectively arranged at corresponding positions of the N-dimensional parameter vector, and N is more than or equal to N;
calculating the predicted matching values of the M interest tags according to the N-dimensional parameter vector and the long-term and short-term memory network model;
screening M effective interest tags of which the predicted matching values are higher than a preset threshold value according to the predicted matching values of the M interest tags;
setting the weight coefficient range of each effective interest label by taking the predicted matching value of each effective interest label as a center;
and matching a plurality of users to be selected according to the m effective interest tags and the weight coefficient range corresponding to each effective interest tag.
Preferably, if the number of the multiple users to be selected is greater than a preset threshold, the pushing step includes:
screening part of users to be selected from the plurality of users to be selected according to the basic user information of the users;
and pushing the screened part of the users to be selected to a friend recommendation list of the instant messaging tool of the users.
Preferably, the pushing step comprises:
mapping the weight coefficient of each content subject in each user to be selected into a corresponding subject interest index;
defining visual information according to each topic interest index in each user to be selected;
and pushing the visual information corresponding to each user to be selected to a friend recommendation list in the instant messaging tool of the user, wherein the visual information corresponding to each user to be selected is displayed in a column of the corresponding user to be selected in the friend recommendation list.
Preferably, the method further comprises a friend recommendation list adjusting step of:
recording a plurality of personal pages of a plurality of interested users clicked into by the user through the friend recommendation list;
defining weight coefficients for the interested users according to the access duration and the access times of each personal page;
readjusting the weight coefficient of each content subject of the user according to the weight coefficient of each interested user and the weight coefficient of each content subject of each interested user;
recalculating the matching degree coefficients of the plurality of users to be selected and the users according to the adjusted weight coefficient of each content theme; and
and adjusting the order of the multiple users to be selected in the friend recommendation list based on the matching degree coefficient obtained by recalculation.
In order to achieve the above object, an embodiment of the present invention further provides a friend relationship chain matching system, including:
the acquisition module is used for acquiring the behavior information of the user through the mobile terminal;
the mining module is used for configuring mining conditions according to the behavior information and mining a plurality of users to be selected which accord with the mining conditions in the behavior information of other users except the user;
the pushing module is used for pushing the multiple users to be selected to a friend recommendation list in an instant messaging tool of the users;
the receiving module is used for receiving the selection operation of the user aiming at one or more users to be selected; and
and the relationship chain establishing module is used for establishing a friend relationship chain between the user and the selected one or more to-be-selected users according to the selection operation.
In order to achieve the above object, an embodiment of the present invention further provides a computer device, a memory of the computer device, a processor, and a computer program stored on the memory and executable on the processor, where the computer program, when executed by the processor, implements the steps of the buddy relationship chain matching method as described above.
To achieve the above object, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, where the computer program is executable by at least one processor, so as to cause the at least one processor to execute the steps of the buddy relationship chain matching method described above.
According to the friend relationship chain matching method, the friend relationship chain matching system, the computer equipment and the computer readable storage medium, the interest and hobbies of the user are comprehensively analyzed by collecting the behavior information (such as browsing information on a browser) of the user, then the mining condition is set, the user meeting the mining condition is mined from the data information of other massive users except the user, then the friend relationship chain matching is carried out without manual intervention of the user, the behavior information can represent the real life state of the user, the interest orientation of the user can be better analyzed, friends are matched through the behavior information, and the matching accuracy is higher.
Drawings
Fig. 1 is a flowchart of a friend relationship chain matching method according to a first embodiment of the present invention.
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 friend relationship chain matching method according to the present invention.
Fig. 8 is a flowchart of a second friend relationship chain matching method according to an embodiment of the present invention.
Fig. 9 is a schematic diagram of program modules of a friend relationship chain matching system according to a third embodiment of the present invention.
Fig. 10 is a schematic diagram of a hardware structure of a fourth embodiment of the computer apparatus according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the description relating to "first", "second", etc. in the present invention is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
The following embodiment will exemplarily be described with the computer apparatus 2 as an execution subject.
Example one
Referring to fig. 1, a flowchart illustrating steps of a friend relationship chain matching method according to an embodiment of the present invention is shown. It is to be understood that the flow charts in the embodiments of the present method are not intended to limit the order in which the steps are performed. The details are as follows.
And step S100, acquiring the behavior information of the user through the mobile terminal.
The behavior information comprises page access records and interest type APP use information, such as the use frequency and the use duration of each interest type APP.
The interest class APP is as follows: gaming type APPs (royal glory, running kart, etc.), learning type APPs (english fluent speech, hundred word chop, bean, etc.), investment type APPs (snowball, sky fund, etc.), and the like.
Step S102, mining conditions are configured according to the behavior information, and a plurality of users to be selected which meet the mining conditions are mined in the behavior information of other users except the user.
In an exemplary embodiment, taking the behavior information as a page access record as an example, as shown in fig. 2, step S102 may further include:
step S102A1, obtaining the content subject of each accessed page according to the page access record, and configuring a weight coefficient for each content subject according to the occurrence frequency of each content subject;
step S102A2, setting the weight coefficient range of each content theme by taking the weight coefficient of each content theme as the center;
and step S102A3, matching a plurality of users to be selected according to the content topics and the weight coefficient range corresponding to each content topic.
For example, assuming that the weighting factor is 0 to 100, 4 content topics are obtained according to the page access record, the weighting factor of the first content topic is 75, the weighting factor of the second content topic is 30, the weighting factor of the third content topic is 22, and the weighting factor of the fourth content topic is 60. Centering on the weighting factors of the 4 content topics, for example, the weighting factor range of the first content topic is set to 75 ± 5 (including endpoints), the weighting factor range of the second content topic is set to 30 ± 5 (including endpoints), the weighting factor range of the third content topic is set to 22 ± 5 (including endpoints), the weighting factor range of the fourth content topic is set to 60 ± 5 (including endpoints), and then users within the above ranges according to the corresponding respective topic contents of the other users are taken as candidate users. For example, user A: the weighting coefficient of the first content theme is 71, the weighting coefficient of the second content theme is 32, the weighting coefficient of the third content theme is 21, and the weighting coefficient of the fourth content theme is 65, so that the user A can be used as a user to be selected; and a user B: the weighting coefficient of the first content theme is 71, the weighting coefficient of the second content theme is 32, the weighting coefficient of the third content theme is 21, and the weighting coefficient of the fourth content theme is 66.
In another exemplary embodiment, as shown in fig. 3, step S102 may further include:
step S102B1, obtaining the content subject of each accessed page according to the page access record, and configuring a weight coefficient for each content subject according to the occurrence frequency of each content subject;
step S102B2, screening a plurality of effective content topics with weight coefficients higher than a preset threshold value according to the weight coefficient of each content topic;
step S102B3, setting the weight coefficient range of each effective content subject by taking the weight coefficient of each effective content subject as the center;
and step S102B4, matching a plurality of users to be selected according to the effective content topics and the weight coefficient range corresponding to each effective content topic.
Step S104, pushing the multiple users to be selected to a friend recommendation list in the instant messaging tool of the users.
In an exemplary embodiment, the friend recommendation list includes recommended degrees of all users to be selected; as shown in fig. 4, the step S104 may further include the steps of:
step S104A1, calculating the matching degree coefficient of each user to be selected and the user according to the weight coefficient of each content theme (or effective content theme) corresponding to each user to be selected;
step S104A2, determining the recommendation degree of each user to be selected in the friend recommendation list according to the matching degree coefficient of each user to be selected and the user. Specifically, the matching degree coefficient of each user to be selected can be calculated by the following formula:
wherein, P
iα is a constant value which is a matching coefficient of a user i to be selected and the user, β
jIs the weight coefficient, δ, of the subject of content (or effective subject of content) j
ijThe ratio between the weight coefficient of the content subject (or the effective content subject) j in the user and the weight coefficient of the content subject (or the effective content subject) j in the user i to be selected is smaller than or equal to 1, and m is the total number of the content subjects.
In an exemplary embodiment, as shown in fig. 5, the step S104 may further include the steps of:
step S104B1, mapping the weight coefficient of each content subject (or effective content subject) in each user to be selected into a corresponding subject interest index;
step S104B2, visual information (such as characters, images and the like) is defined according to each topic interest index in each user to be selected;
step S104B3, pushing the visual information corresponding to each user to be selected to a friend recommendation list in the instant messaging tool of the user, where the visual information corresponding to each user to be selected is displayed in a column of the friend recommendation list where the corresponding user to be selected is located.
Namely, the user to be selected and the visual information are pushed to a friend recommendation list in the instant messaging tool of the user.
In an exemplary embodiment, as shown in fig. 6, the step S104 may further include the steps of:
step S104C1, judging whether the number of the multiple users to be selected is larger than a preset threshold value;
step S104C2, if the current time is not greater than the preset threshold, pushing the multiple users to be selected to a friend recommendation list in the instant messaging tool of the user;
and step S104C3, if the number of the users is larger than the preset threshold, screening part of the users to be selected from the plurality of users to be selected according to the basic user information of the users, and pushing the screened part of the users to be selected to a friend recommendation list of the instant messaging tool of the users.
The basic user information of the user includes, but is not limited to, age, gender, occupation, income range, geographical location, etc.
Configuring additional mining conditions by using the basic user information of the user, such as configuring an age range taking the age of the user as the center, a related occupation range taking the occupation of the user as the center, an extended income range taking the income range of the user as the center, and an address range taking the address position of the user as the center. If the user is: the financial building with the 35 year old male, the profession IT and the address position Shenzhen city XX can be configured with the following additional mining conditions: age 30-40, male, computer industry, 100 km in XX financial mansion. And screening out a plurality of users to be selected which accord with the condition from the plurality of users to be selected according to the additional mining condition.
And if the candidate users meeting the conditions are not matched from the candidate users through the additional mining conditions, modifying the additional mining conditions, such as expanding the range and deleting some items (such as deleting 'occupation').
And step S106, receiving the selection operation of the user for one or more to-be-selected users.
The user can input a selection instruction (such as single or continuous multiple mouse clicking operation and touch operation) through a graphical interface provided by the instant messaging tool.
And step S108, establishing a friend relation chain between the user and the selected one or more to-be-selected users according to the selection operation.
For example, the instant messaging tool sends request information for establishing a friend relationship chain aiming at one of the candidate users (hereinafter referred to as a target user) according to a selection instruction input by the user. After receiving the request information, the computer device sends request information of 'friend applying for joining' to the target user, and after the target user sends response information of 'agreement', a friend relation chain is established between the user and the target user.
In an exemplary embodiment, as shown in fig. 7, the method may further include a friend recommendation list adjusting step S110, where the step S110 may further include the steps of:
step S110A1, recording a plurality of personal pages of a plurality of interested users clicked by the user through the friend recommendation list;
step S110A2, defining weight coefficients for the interested users according to the access duration and the access times of each personal page;
step S110A3, readjusting the weighting coefficients of the users for the content topics according to the weighting coefficients of the interested users and the weighting coefficients of the content topics of the interested users;
step S110A4, recalculating the matching degree coefficients of the multiple users to be selected and the users according to the adjusted weight coefficient of each content theme; and
step S110a5, adjusting the order of the multiple users to be selected in the friend recommendation list based on the matching degree coefficient obtained by the recalculation.
Certainly, the step S110 is only an exemplary scheme for rearranging the friend recommendation table, and the embodiment may also adjust the friend recommendation list through other schemes, such as: and when the user clicks a certain topic interest index, taking the topic interest index as a single consideration factor, and carrying out the sequence of the plurality of users to be selected in the friend recommendation list.
Example two
Referring to fig. 8, a flowchart illustrating steps of a friend relationship chain matching method according to a second embodiment of the present invention is shown. It is to be understood that the flow charts in the embodiments of the present method are not intended to limit the order in which the steps are performed. The details are as follows.
And step S200, acquiring the behavior information of the user through the mobile terminal.
The behavior information comprises page access records and interest type APP use information, such as the use frequency and the use duration of each interest type APP.
The interest class APP is as follows: gaming type APPs (royal glory, running kart, etc.), learning type APPs (english fluent speech, hundred word chop, bean, etc.), investment type APPs (snowball, sky fund, etc.), and the like.
Step S202, obtaining the content subject of each accessed page according to the page access record in the behavior information to obtain n content subjects.
Step S204, according to the occurrence frequency of each content theme, a weight coefficient is configured for each content theme.
Step S206, defining an N-dimensional parameter vector according to N content topics of the user, wherein the weight coefficients of the N content topics are respectively arranged at the corresponding positions of the N-dimensional parameter vector, and N is larger than or equal to N.
For example, N content topics may be configured in advance, where N is a positive integer greater than 1, and the step S200 obtains that the user relates to N content topics and does not relate to other content topics (i.e., non-appeared content topics). Wherein the weighting factor of other content topics may be set to a fixed value, such as 0, in the N-dimensional parameter vector.
And S208, calculating the predicted matching values of the M interest tags according to the N-dimensional parameter vector and a Long Short-term memory network model (LSTM).
Specifically, the steps of calculating the predicted matching values of the M interest tags are as follows:
(1) output h according to the previous moment
t-1And the current input x
tTo obtain f
tValue to determine whether to let the last time learn the information C
t-1By or in part by:
f
t＝σ(W
f[x
t,h
t-1]+b
f) Wherein f is
t∈[0,1]The selection weight W of the node at time t to the cell memory at time t-1
fWeight matrix for forgetting gate, b
fBias term for forgetting gate, h
t-1Hidden layer state information representing a t-1 node, a nonlinear function σ (x) being 1/(1+ e)
-x)；
(2) The sigmoid is used to decide which values to update,and used to generate new candidate values through the tanh layer
It may be added to the memory cell state as a candidate generated by the current layer, and the two generated values are combined for updating:
i
t＝σ(W
i[x
t,h
t-1]+b
i) Wherein i
t∈[0,1]The selection weight of the node at time t to the current node information, b
iFor input of offset terms of gates, W
iFor the weight matrix of the input gate, the nonlinear function σ (x) is 1/(1+ e)
-x)；
Current node input information
Wherein
In order to be a term of the offset,
a weight matrix representing the information to be updated, tanh being a hyperbolic tangent activation function, x
tRepresenting the input vector, h, of the LSTM neural network node at time t
t-1Hidden layer state information representing a t-1 node;
update the old memory cell state, add new information:
currently output memory information
Wherein C is
t-1Memory information representing a t-1 node, f
tSelection weight of node pair representing time t to cell memory at time t-1, i
tRepresenting the selection weight of the node at the time t to the current node information;
(3) outputting an LSTM model;
o
t＝σ(W
o[x
t,h
t-1]+b
o) Wherein o is
t∈[0,1]Selection right of node cell memory information representing t timeHeavy, b
oFor biasing of output gates, W
oIs a weight matrix of the output gates,
representing a vector x
tAnd h
t-1Concatenated vector, i.e. | x
t|+|h
t-1Vector in | dimension.
h
t＝o
t·tanh(C
t)
x
tAn input vector representing an LSTM neural network node at the time t, namely an N-dimensional parameter vector in the embodiment; h is
tThe output vector of the LSTM neural network node at time t, that is, the predicted matching values for M interest tags in this embodiment.
Step S210, screening out M effective interest tags of which the predicted matching values are higher than a preset threshold value according to the predicted matching values of the M interest tags;
step S212, setting the weight coefficient range of each effective interest label by taking the prediction matching value of each effective interest label as the center.
And step S214, matching a plurality of users to be selected according to the m effective interest tags and the weight coefficient range corresponding to each effective interest tag.
Step S216, the multiple users to be selected are pushed to the friend recommendation list in the instant messaging tool of the user.
In an exemplary embodiment, the friend recommendation list includes recommended degrees of all users to be selected; the step S216 further includes the steps of:
and calculating a matching degree coefficient of each to-be-selected user and the user according to the predicted matching value of each interest tag corresponding to each to-be-selected user, wherein the matching degree coefficient is used for determining the recommendation degree of each to-be-selected user in the friend recommendation list.
In an exemplary embodiment, the step S216 further includes the steps of:
(1) judging that the number of the users to be selected is larger than a preset threshold value;
(2) if the current time is not greater than the preset threshold, pushing the multiple users to be selected to a friend recommendation list in the instant messaging tool of the user;
(3) if the current user information is larger than the preset threshold value, screening part of users to be selected from the plurality of users to be selected according to the basic user information of the users, and pushing the screened part of users to be selected to a friend recommendation list of an instant messaging tool of the users;
the basic user information of the user includes, but is not limited to, age, gender, occupation, income range, geographical location, etc.
Configuring additional mining conditions by using the basic user information of the user, such as configuring an age range taking the age of the user as the center, a related occupation range taking the occupation of the user as the center, an extended income range taking the income range of the user as the center, and an address range taking the address position of the user as the center. If the user is: the financial building with the 35 year old male, the profession IT and the address position Shenzhen city XX can be configured with the following additional mining conditions: age 30-40, male, computer industry, 100 km in XX financial mansion. And screening out a plurality of users to be selected which accord with the condition from the plurality of users to be selected according to the additional mining condition.
And if the candidate users meeting the conditions are not matched from the candidate users through the additional mining conditions, modifying the additional mining conditions, such as expanding the range and deleting some items (such as deleting 'occupation').
Step S218 receives a selection operation of the user for one or more users to be selected.
The user can input a selection instruction (such as single or continuous multiple mouse clicking operation and touch operation) through a graphical interface provided by the instant messaging tool.
Step S220 establishes a friend relationship chain between the user and the selected one or more users to be selected according to the selection operation.
The instant messaging tool sends request information for establishing a friend relationship chain aiming at one user to be selected (hereinafter referred to as a target user) according to a selection instruction input by the user. After receiving the request information, the computer device sends request information of 'friend applying for joining' to the target user, and after the target user sends response information of 'agreement', a friend relation chain is established between the user and the target user.
EXAMPLE III
Continuing to refer to fig. 9, a third embodiment of a buddy relationship chain matching system according to the present invention is shown. In this embodiment, the buddy 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 implement the present invention and implement the buddy relationship chain matching method described above. The program module referred to in the embodiments of the present invention refers to a series of computer program instruction segments capable of performing a specific function, and is more suitable for describing the execution process of the buddy relationship chain matching system 20 in a storage medium than the program itself. The following description will specifically describe the functions of the program modules of the present embodiment:
an obtaining module 200, configured to obtain behavior information of a user through a mobile terminal.
The behavior information comprises page access records and interest type APP use information, such as the use frequency and the use duration of each interest type APP.
And the mining module 202 is configured to configure mining conditions according to the behavior information, and mine a plurality of users to be selected that meet the mining conditions in the behavior information of other users except the user.
In the exemplary embodiment, mining module 202 is further configured to: acquiring the content subject of each accessed page according to the page access record, and configuring a weight coefficient for each content subject according to the occurrence frequency of each content subject; setting the weight coefficient range of each content theme by taking the weight coefficient of each content theme as a center; and matching a plurality of users to be selected according with the requirements according to each content theme and the weight coefficient range corresponding to each content theme.
Wherein, the friend recommendation list includes the recommended degree of each user to be selected, and the mining module 202 is further configured to:
calculating a matching degree coefficient of each to-be-selected user and the user according to the weight coefficient of each content theme corresponding to each to-be-selected user, wherein the matching degree coefficient is used for determining the recommendation degree of each to-be-selected user in a friend recommendation list; specifically, the matching degree coefficient of each user to be selected can be calculated by the following formula:
wherein, P
iα is a constant value which is a matching coefficient of a user i to be selected and the user, β
jWeight coefficient, δ, for topic of content j
ijThe ratio of the weight coefficient of the content subject j in the user to the weight coefficient of the content subject j in the user i to be selected is less than or equal to 1, and m is the total number of the content subjects.
In the exemplary embodiment, mining module 202 is further configured to: acquiring the content subject of each accessed page according to the page access record to obtain n content subjects; configuring a weight coefficient for each content theme according to the occurrence number of each content theme; defining an N-dimensional parameter vector according to N content topics of the user, wherein the weight coefficients of the N content topics are respectively arranged at corresponding positions of the N-dimensional parameter vector, and N is more than or equal to N; calculating the predicted matching values of the M interest tags according to the N-dimensional parameter vector and the long-term and short-term memory network model; screening M effective interest tags of which the predicted matching values are higher than a preset threshold value according to the predicted matching values of the M interest tags, and setting a weight coefficient range of each effective interest tag by taking the predicted matching value of each effective interest tag as a center; and matching a plurality of users to be selected according to the m effective interest tags and the weight coefficient range corresponding to each effective interest tag.
In the exemplary embodiment, mining module 202 is further configured to: if the number of the users to be selected is larger than a preset threshold value, screening partial users to be selected from the users to be selected according to the basic user information of the users; and pushing the screened part of the users to be selected to a friend recommendation list of the instant messaging tool of the users.
The pushing module 204 is configured to push the multiple users to be selected to a friend recommendation list in the instant messaging tool of the user.
In an exemplary embodiment, the push module 204 is further configured to: mapping the weight coefficient of each content subject in each user to be selected into a corresponding subject interest index; defining visual information according to each topic interest index in each user to be selected; and pushing the visual information corresponding to each user to be selected to a friend recommendation list in the instant messaging tool of the user, wherein the visual information corresponding to each user to be selected is displayed in a column of the corresponding user to be selected in the friend recommendation list.
A receiving module 206, configured to receive a selection operation of the user for one or more users to be selected.
The user can input a selection instruction (such as single or continuous multiple mouse clicking operation and touch operation) through a graphical interface provided by the instant messaging tool.
And the relationship chain establishing module 208 is configured to establish a friend relationship chain between the user and the selected one or more users to be selected according to the selection operation.
The instant messaging tool sends request information for establishing a friend relationship chain aiming at one user to be selected (hereinafter referred to as a target user) according to a selection instruction input by the user. After receiving the request information, the computer device sends request information of 'friend applying for joining' to the target user, and after the target user sends response information of 'agreement', a friend relation chain is established between the user and the target user.
In an exemplary embodiment, the buddy relationship chain matching system 20 may further include a recommendation list adjustment module 210 for: recording a plurality of personal pages of a plurality of interested users clicked into by the user through the friend recommendation list; defining weight coefficients for the interested users according to the access duration and the access times of each personal page; readjusting the weight coefficient of each content subject of the user according to the weight coefficient of each interested user and the weight coefficient of each content subject of each interested user; recalculating the matching degree coefficients of the plurality of users to be selected and the users according to the adjusted weight coefficient of each content theme; and adjusting the order of the multiple users to be selected in the friend recommendation list based on the matching degree coefficient obtained by recalculation.
Example four
Fig. 10 is a schematic diagram of a hardware architecture of a computer device according to a fourth embodiment of the present invention. In the present embodiment, the computer device 2 is a device capable of automatically performing numerical calculation and/or information processing in accordance with a preset or stored instruction. The computer device 2 may be a rack server, a blade server, a tower server or a rack server (including an independent server or a server cluster composed of a plurality of servers), and the like. As shown, the computer device 2 includes, but is not limited to, at least a memory 21, a processor 22, a network interface 23, and a buddy relationship chain matching system 20, communicatively coupled to each other via a system bus. Wherein:
in this embodiment, the memory 21 includes at least one type of computer-readable storage medium including a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the storage 21 may be an internal storage unit of the computer device 2, such as a hard disk or a memory of the computer device 2. In other embodiments, 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), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. provided on the computer device 20. Of course, the memory 21 may also comprise both internal and external memory units of the computer device 2. In this embodiment, the memory 21 is generally used to store an operating system and various application software installed in the computer device 2, for example, the program code of the buddy relationship chain matching system 20 in the third embodiment. Further, the memory 21 may also be used to temporarily store various types of data that have been output or are to be output.
Processor 22 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 22 is typically used to control the overall operation of the computer device 2. In this embodiment, the processor 22 is configured to run program codes stored in the memory 21 or process data, for example, run the buddy relationship chain matching system 20, so as to implement the buddy relationship chain matching method of the first embodiment or the second embodiment.
The network interface 23 may comprise a wireless network interface or a wired network interface, and the network interface 23 is generally used for establishing communication connection between the computer device 2 and other electronic apparatuses. For example, the network interface 23 is used to connect the computer device 2 to an external terminal through a network, establish a data transmission channel and a communication connection between the computer device 2 and the external terminal, and the like. The network may be a wireless or wired network such as an Intranet (Intranet), the Internet (Internet), a Global System of Mobile communication (GSM), Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Bluetooth (Bluetooth), Wi-Fi, and the like.
It is noted that fig. 10 only shows the computer device 2 with components 20-23, but it is to be understood that not all of the shown components are required to be implemented, and that more or less components may be implemented instead.
In this embodiment, the buddy relationship chain matching system 20 stored in the memory 21 may be further divided into one or more program modules, and the one or more program modules are stored in the memory 21 and executed by one or more processors (in this embodiment, the processor 22) to complete the present invention.
For example, fig. 9 is a schematic diagram illustrating program modules of a third embodiment of the buddy relationship chain matching system 20, in which the buddy relationship chain-based matching system 20 may be divided into an obtaining module 200, a mining module 202, a pushing module 204, a receiving module 206, a relationship chain establishing module 208, and a recommendation list adjusting module 210. The program module referred to in the present invention refers to a series of computer program instruction segments capable of performing specific functions, and is more suitable than a program for describing the execution process of the buddy relationship chain matching system 20 in the computer device 2. The specific functions of the program modules 200 and 210 have been described in detail in the third embodiment, and are not described herein again.
EXAMPLE five
The present embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application mall, etc., on which a computer program is stored, which when executed by a processor implements corresponding functions. The computer-readable storage medium of this embodiment is used to store the buddy relationship chain matching system 20, and when executed by a processor, implements the buddy relationship chain matching method of the first embodiment or the second embodiment.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A method for matching a friend relationship chain, the method comprising:
an acquisition step, in which behavior information of a user is acquired through a mobile terminal;
a mining step, configured mining conditions according to the behavior information, and mining a plurality of users to be selected according with the mining conditions in the behavior information of other users except the user;
pushing, namely pushing the multiple users to be selected to a friend recommendation list in an instant messaging tool of the users;
a receiving step, namely receiving the selection operation of the user for one or more to-be-selected users; and
and a relation chain establishing step, namely establishing a friend relation chain between the user and the selected one or more to-be-selected users according to the selection operation.
2. The friend relationship chain matching method of claim 1, wherein the behavior information comprises page access records and/or interest-class APP usage information; the excavating step comprises:
acquiring the content subject of each accessed page according to the page access record, and configuring a weight coefficient for each content subject according to the occurrence frequency of each content subject;
setting the weight coefficient range of each content theme by taking the weight coefficient of each content theme as a center;
and matching a plurality of users to be selected according with the requirements according to each content theme and the weight coefficient range corresponding to each content theme.
3. The method of matching friend relationship chains according to claim 2, wherein the friend recommendation list includes recommended degrees of each user to be selected; the pushing step comprises the following steps:
calculating a matching degree coefficient of each to-be-selected user and the user according to the weight coefficient of each content theme corresponding to each to-be-selected user, wherein the matching degree coefficient is used for determining the recommendation degree of each to-be-selected user in a friend recommendation list;
the matching degree coefficient calculation formula is as follows:
wherein, P
iα is a constant value which is a matching coefficient of a user i to be selected and the user, β
jWeight coefficient, δ, for topic of content j
ijThe ratio of the weight coefficient of the content subject j in the user to the weight coefficient of the content subject j in the user i to be selected is less than or equal to 1, and m is the total number of the content subjects.
4. The friend relationship chain matching method of claim 1, wherein the behavior information comprises page access records and/or interest-class APP usage information; the excavating step comprises:
acquiring the content subject of each accessed page according to the page access record to obtain n content subjects;
configuring a weight coefficient for each content theme according to the occurrence number of each content theme;
defining an N-dimensional parameter vector according to N content topics of the user, wherein the weight coefficients of the N content topics are respectively arranged at corresponding positions of the N-dimensional parameter vector, and N is more than or equal to N;
calculating the predicted matching values of the M interest tags according to the N-dimensional parameter vector and the long-term and short-term memory network model;
screening M effective interest tags of which the predicted matching values are higher than a preset threshold value according to the predicted matching values of the M interest tags;
setting the weight coefficient range of each effective interest label by taking the predicted matching value of each effective interest label as a center;
and matching a plurality of users to be selected according to the m effective interest tags and the weight coefficient range corresponding to each effective interest tag.
5. The method for matching a friend relationship chain according to any one of claims 1 to 4, wherein if the number of the multiple users to be selected is greater than a preset threshold, the pushing step includes:
screening part of users to be selected from the plurality of users to be selected according to the basic user information of the users;
and pushing the screened part of the users to be selected to a friend recommendation list of the instant messaging tool of the users.
6. The buddy relationship chain matching method according to claim 5, wherein said pushing step comprises:
mapping the weight coefficient of each content subject in each user to be selected into a corresponding subject interest index;
defining visual information according to each topic interest index in each user to be selected;
and pushing the visual information corresponding to each user to be selected to a friend recommendation list in the instant messaging tool of the user, wherein the visual information corresponding to each user to be selected is displayed in a column of the corresponding user to be selected in the friend recommendation list.
7. The method of matching a buddy relationship chain according to claim 6, further comprising a buddy recommendation list adjustment step of:
recording a plurality of personal pages of a plurality of interested users clicked into by the user through the friend recommendation list;
defining weight coefficients for the interested users according to the access duration and the access times of each personal page;
readjusting the weight coefficient of each content subject of the user according to the weight coefficient of each interested user and the weight coefficient of each content subject of each interested user;
recalculating the matching degree coefficients of the plurality of users to be selected and the users according to the adjusted weight coefficient of each content theme; and
and adjusting the order of the multiple users to be selected in the friend recommendation list based on the matching degree coefficient obtained by recalculation.
8. A buddy relationship chain matching system, comprising:
the acquisition module is used for acquiring the behavior information of the user through the mobile terminal;
the mining module is used for configuring mining conditions according to the behavior information and mining a plurality of users to be selected which accord with the mining conditions in the behavior information of other users except the user;
the pushing module is used for pushing the multiple users to be selected to a friend recommendation list in an instant messaging tool of the users;
the receiving module is used for receiving the selection operation of the user aiming at one or more users to be selected; and
and the relationship chain establishing module is used for establishing a friend relationship chain between the user and the selected one or more to-be-selected users according to the selection operation.
9. A computer device having a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the buddy relationship chain matching method of any of claims 1-7.
10. A computer-readable storage medium, having stored therein a computer program, the computer program being executable by at least one processor to cause the at least one processor to perform the steps of the buddy relationship chain matching method according to any of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910917137.6A CN110781404B (en) | 2019-09-26 | Friend relation chain matching method, system, computer equipment and readable storage medium | |
| PCT/CN2019/117556 WO2021056734A1 (en) | 2019-09-26 | 2019-11-12 | Friendship chain matching method and system, computer device, and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910917137.6A CN110781404B (en) | 2019-09-26 | Friend relation chain matching method, system, computer equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110781404A true CN110781404A (en) | 2020-02-11 |
| CN110781404B CN110781404B (en) | 2024-07-02 |
Family
ID=
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112883073A (en) * | 2021-03-22 | 2021-06-01 | 北京同邦卓益科技有限公司 | Data screening method, device, equipment, readable storage medium and product |
| CN113420230A (en) * | 2020-12-31 | 2021-09-21 | 深圳市镜玩科技有限公司 | Matching consultation pushing method based on group chat, related device, equipment and medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7231419B1 (en) * | 2001-10-19 | 2007-06-12 | Outlooksoft Corporation | System and method for adaptively selecting and delivering recommendations to a requester |
| CN102915309A (en) * | 2011-08-03 | 2013-02-06 | 腾讯科技（深圳）有限公司 | Friend relation chain matching method and equipment in instant messaging tool |
| GB201412195D0 (en) * | 2014-07-09 | 2014-08-20 | Jaguar Land Rover Ltd | Generating contact identifier recommendations |
| CN104008109A (en) * | 2013-02-26 | 2014-08-27 | 南京邮电大学 | User interest based Web information push service system |
| CN105468598A (en) * | 2014-08-18 | 2016-04-06 | 大连民族学院 | Friend recommendation method and device |
| CN105635210A (en) * | 2014-10-30 | 2016-06-01 | 腾讯科技（武汉）有限公司 | Network information recommending method and device, and reading system |
| US20160239738A1 (en) * | 2013-10-23 | 2016-08-18 | Tencent Technology (Shenzhen) Company Limited | Question recommending method, apparatus and system |
| CN107808314A (en) * | 2016-09-09 | 2018-03-16 | 腾讯科技（深圳）有限公司 | User recommends method and device |
| CN109544396A (en) * | 2019-01-10 | 2019-03-29 | 腾讯科技（深圳）有限公司 | Account recommended method, device, server, terminal and storage medium |
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7231419B1 (en) * | 2001-10-19 | 2007-06-12 | Outlooksoft Corporation | System and method for adaptively selecting and delivering recommendations to a requester |
| CN102915309A (en) * | 2011-08-03 | 2013-02-06 | 腾讯科技（深圳）有限公司 | Friend relation chain matching method and equipment in instant messaging tool |
| CN104008109A (en) * | 2013-02-26 | 2014-08-27 | 南京邮电大学 | User interest based Web information push service system |
| US20160239738A1 (en) * | 2013-10-23 | 2016-08-18 | Tencent Technology (Shenzhen) Company Limited | Question recommending method, apparatus and system |
| GB201412195D0 (en) * | 2014-07-09 | 2014-08-20 | Jaguar Land Rover Ltd | Generating contact identifier recommendations |
| CN105468598A (en) * | 2014-08-18 | 2016-04-06 | 大连民族学院 | Friend recommendation method and device |
| CN105635210A (en) * | 2014-10-30 | 2016-06-01 | 腾讯科技（武汉）有限公司 | Network information recommending method and device, and reading system |
| CN107808314A (en) * | 2016-09-09 | 2018-03-16 | 腾讯科技（深圳）有限公司 | User recommends method and device |
| CN109544396A (en) * | 2019-01-10 | 2019-03-29 | 腾讯科技（深圳）有限公司 | Account recommended method, device, server, terminal and storage medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113420230A (en) * | 2020-12-31 | 2021-09-21 | 深圳市镜玩科技有限公司 | Matching consultation pushing method based on group chat, related device, equipment and medium |
| CN113420230B (en) * | 2020-12-31 | 2023-07-21 | 深圳市仁凯网络科技有限公司 | Group chat-based matching consultation pushing method, related device, equipment and medium |
| CN112883073A (en) * | 2021-03-22 | 2021-06-01 | 北京同邦卓益科技有限公司 | Data screening method, device, equipment, readable storage medium and product |
| CN112883073B (en) * | 2021-03-22 | 2024-04-05 | 北京同邦卓益科技有限公司 | Data screening method, device, equipment, readable storage medium and product |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021056734A1 (en) | 2021-04-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110502608B (en) | Man-machine conversation method and man-machine conversation device based on knowledge graph | |
| TWI677828B (en) | Business customization device, method, and computer readable storage media based on data source | |
| CN110263152B (en) | Text classification method, system and computer equipment based on neural network | |
| CN108520041B (en) | Industry classification method and system of text, computer equipment and storage medium | |
| CN110489507B (en) | Method, device, computer equipment and storage medium for determining similarity of interest points | |
| US9881000B1 (en) | Avoiding sentiment model overfitting in a machine language model | |
| CN110659667A (en) | Picture classification model training method and system and computer equipment | |
| CN113220657B (en) | Data processing method and device and computer equipment | |
| CN110674391B (en) | Product data pushing method and system based on big data and computer equipment | |
| CN111984792A (en) | Website classification method and device, computer equipment and storage medium | |
| CN111369313A (en) | Processing method and device for house-ordering failure order, computer equipment and storage medium | |
| CN111680165A (en) | Information matching method and device, readable storage medium and electronic equipment | |
| CN112070550A (en) | Keyword determination method, device and equipment based on search platform and storage medium | |
| CN111651666A (en) | User theme recommendation method and device, computer equipment and storage medium | |
| CN111930891B (en) | Knowledge graph-based search text expansion method and related device | |
| CN108427701B (en) | Method for identifying help information based on operation page and application server | |
| CN112734307A (en) | Online real-time enterprise portrait generation method, device, equipment and storage medium | |
| CN112765450A (en) | Recommended content determining method, recommended content determining device and storage medium | |
| CN112650940A (en) | Recommendation method and device of application program, computer equipment and storage medium | |
| CN111475720A (en) | Recommendation method, recommendation device, server and storage medium | |
| CN110781404B (en) | Friend relation chain matching method, system, computer equipment and readable storage medium | |
| CN113961811B (en) | Event map-based conversation recommendation method, device, equipment and medium | |
| CN110781404A (en) | Friend relationship chain matching method, system, computer equipment and readable storage medium | |
| CN116010670A (en) | Data catalog recommendation method, device and application based on data blood relationship | |
| US11321375B2 (en) | Text object management system |
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 | ||
| GR01 | Patent grant |