CN113836421A - Work recommendation method and related device - Google Patents
Work recommendation method and related device Download PDFInfo
- Publication number
- CN113836421A CN113836421A CN202111141783.1A CN202111141783A CN113836421A CN 113836421 A CN113836421 A CN 113836421A CN 202111141783 A CN202111141783 A CN 202111141783A CN 113836421 A CN113836421 A CN 113836421A
- Authority
- CN
- China
- Prior art keywords
- works
- work
- target
- related works
- target terminal
- 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 48
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000004891 communication Methods 0.000 claims description 15
- 238000012216 screening Methods 0.000 claims description 4
- 230000006399 behavior Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000008569 process 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
- G06F16/9535—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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application is suitable for the technical field of data processing, provides a work recommendation method and a related device, and aims to solve the technical problem that works matched with interest tendency of a target user cannot be accurately recommended to the target user in the prior art. When the recommendation method of the works is applied to the server, the recommendation method mainly comprises the following steps: receiving a work identity and a user identity of a target user, wherein the work identity corresponds to a work clicked by the target user on a target terminal device, and the target user is a user account logged in when the target terminal device accepts the click of the work; uniquely determining the works in a preset database according to the identity of the works; determining X related works in a preset database according to the content dimension corresponding to the works; determining target terminal equipment where a target user is located according to the user identity; when the target user acquires the target content, the X related works are sent to the target terminal equipment of the target user, so that the target terminal equipment presents the related works in a content recommending mode.
Description
Technical Field
The application belongs to the technical field of data processing, and particularly relates to a work recommendation method and a related device.
Background
With the popularization and development of intelligent terminals, many users acquire required information through the intelligent terminals. For the home decoration industry, home decoration industry related information is recommended to users through software application of an intelligent terminal, meanwhile, a lot of users share own experience through the software application, and the like.
Disclosure of Invention
The application aims to provide a work recommendation method and a related device, and aims to solve the technical problem that works matched with interest tendency of a target user cannot be accurately recommended to the target user in the prior art, and achieve personalized recommendation of related works for different target users.
The application is realized as follows:
the first aspect of the present application provides a work recommendation method, which is applied to a server, and includes:
receiving a work identity and a user identity of a target user, wherein the work identity corresponds to a work clicked by the target user on a target terminal device, and the target user is a user account logged in when the target terminal device accepts the click of the work;
uniquely determining the works in a preset database according to the identity marks of the works;
determining X related works in the preset database according to the content dimension corresponding to the works, wherein X is a positive integer greater than or equal to 0;
determining the target terminal equipment where the target user is located according to the user identity;
when the target user acquires target content, X pieces of the related works are sent to the target terminal equipment of the target user, so that the target terminal equipment presents the related works in a content recommending mode.
Optionally, the content dimension includes: one or more of a creator relevance, a title relevance, a tag relevance, or a topic relevance;
the determining X related works in a preset database according to the content dimensions corresponding to the works comprises:
determining one or more author-related works related to the author relevance in the preset database; and/or the presence of a gas in the gas,
determining one or more title related works related to the title correlation in the preset database; and/or the presence of a gas in the gas,
determining one or more tag-related works related to the tag correlation in the preset database; and/or the presence of a gas in the gas,
determining one or more topic related works related to the topic relevance in the preset database;
and screening preset weights of the creator related works, the title related works, the label related works and the topic related works to obtain X related works, wherein the preset weights are associated with the target user.
Optionally, after obtaining X related works, the method further includes:
receiving operation records of the target user on the X related works, wherein the operation records comprise one or more of clicks, praise, collections and comments;
and respectively carrying out satisfaction degree scoring on the X related works according to the operation records to obtain X satisfaction degree scores.
Optionally, after the X relevant works are sent to the target terminal of the target user, the method further includes:
recording target content dimensions corresponding to Y related works with higher satisfaction degree values in X satisfaction degree values corresponding to X related works, wherein Y is a positive integer smaller than or equal to X;
and increasing the weight of the target content dimension in the preset weight.
A second aspect of the present application provides a work recommendation method, applied to a target terminal device, including:
determining the work clicked by the target user on the target terminal equipment;
reporting the work identity of the work and the user identity of the target user to a server;
receiving X related works through a return path, wherein X is a positive integer greater than or equal to 0, the return path is a communication path determined by the server according to the user identity, and the X related works are determined by the server according to the work identity;
and presenting the related works in a recommended content mode on the target terminal equipment.
Optionally, after X pieces of the related works are presented in the target terminal device in a manner of recommending content, the method further includes:
and feeding back operation records of the target user on the X related works to a server, wherein the operation records comprise one or more of clicking, praise, collecting, commenting and sharing.
Optionally, the presenting X pieces of the related works in the target terminal device in a content recommendation manner includes:
determining content dimension information and historical satisfaction scores corresponding to X related works, wherein the content dimension information comprises: author relevance, title relevance, tag relevance, and topic relevance; the historical satisfaction score corresponding to the creator relevance is a, the historical satisfaction score corresponding to the title relevance is b, the historical satisfaction score corresponding to the label relevance is c, and the historical satisfaction score corresponding to the label relevance is d;
presenting, at the target terminal device, the number of related works corresponding to the creator relevance in a content recommendation manner equal to (a × K)/(a + b + c + d), where K is a non-0 positive integer less than or equal to X, and the value of K is a rounded positive integer;
presenting, at the target terminal device, the number of related works corresponding to the title relevance in a recommended content manner is equal to (b × K)/(a + b + c + d);
presenting the number of related works corresponding to the tag relevance in a recommended content manner at the target terminal device is equal to (c x K)/(a + b + c + d);
and presenting the number of the related works corresponding to the topic relevance in a recommended content mode at the target terminal equipment, wherein the number of the related works is equal to (d x K)/(a + b + c + d).
A third aspect of the present application provides a work recommendation apparatus applied to a server, including:
the system comprises a receiving unit, a processing unit and a display unit, wherein the receiving unit is used for receiving a work identity and a user identity of a target user, the work identity corresponds to a work clicked by the target user on a target terminal device, and the target user is a user account which is logged in when the target terminal device accepts the click of the work;
the first determination unit is used for uniquely determining the works in a preset database according to the identity marks of the works;
a second determining unit, configured to determine X related works in the preset database according to content dimensions corresponding to the works, where X is a positive integer greater than or equal to 0;
a third determining unit, configured to determine, according to the user identity, a target terminal device where the target user is located;
and the sending unit is used for sending the X related works to the target terminal equipment of the target user when the target user obtains the target content, so that the target terminal equipment presents the related works in a content recommending mode.
Optionally, the content dimension includes: one or more of a creator relevance, a title relevance, a tag relevance, or a topic relevance;
the second determining unit is specifically configured to determine X related works in a preset database according to the content dimensions corresponding to the works
Determining one or more author-related works related to the author relevance in the preset database; and/or the presence of a gas in the gas,
determining one or more title related works related to the title correlation in the preset database; and/or the presence of a gas in the gas,
determining one or more tag-related works related to the tag correlation in the preset database; and/or the presence of a gas in the gas,
determining one or more topic related works related to the topic relevance in the preset database;
and screening preset weights of the creator related works, the title related works, the label related works and the topic related works to obtain X related works, wherein the preset weights are associated with the target user.
Optionally, the apparatus further comprises:
the receiving unit is further used for receiving operation records of the target user on the X related works, wherein the operation records comprise one or more of clicks, praise, collections and comments;
and the scoring unit is used for scoring the satisfaction degrees of the X related works according to the operation records to obtain X satisfaction degree scores.
Optionally, the apparatus further comprises:
the recording unit is used for recording the target content dimension corresponding to Y related works with higher satisfaction degree values in X satisfaction degree values corresponding to X related works, wherein Y is a positive integer less than or equal to X;
and the adjusting unit is used for increasing the weight of the target content dimension in the preset weight.
The fourth aspect of the present application provides a work recommendation device, which is applied to a target terminal device, and includes:
the determining unit is used for determining the work clicked by the target user on the target terminal equipment;
the reporting unit is used for reporting the work identity of the work and the user identity of the target user to a server;
a receiving unit, configured to receive X related works through a return path, where X is a positive integer greater than or equal to 0, the return path is a communication path determined by the server according to the user identity, and the X related works are works determined by the server according to the work identity;
and the presentation unit is used for presenting the related works in a recommended content mode on the target terminal equipment.
Optionally, the apparatus further comprises:
and the reporting unit is further configured to feed back, to a server, operation records of the target user on the X related works, where the operation records include one or more of click, praise, collection, comment, and share.
Optionally, when the presentation unit presents the X related works in the form of recommended content at the target terminal device, the presentation unit is specifically configured to:
determining content dimension information and historical satisfaction scores corresponding to X related works, wherein the content dimension information comprises: author relevance, title relevance, tag relevance, and topic relevance; the historical satisfaction score corresponding to the creator relevance is a, the historical satisfaction score corresponding to the title relevance is b, the historical satisfaction score corresponding to the label relevance is c, and the historical satisfaction score corresponding to the label relevance is d;
presenting, at the target terminal device, the number of related works corresponding to the creator relevance in a content recommendation manner equal to (a × K)/(a + b + c + d), where K is a non-0 positive integer less than or equal to X, and the value of K is a rounded positive integer;
presenting, at the target terminal device, the number of related works corresponding to the title relevance in a recommended content manner is equal to (b × K)/(a + b + c + d);
presenting the number of related works corresponding to the tag relevance in a recommended content manner at the target terminal device is equal to (c x K)/(a + b + c + d);
and presenting the number of the related works corresponding to the topic relevance in a recommended content mode at the target terminal equipment, wherein the number of the related works is equal to (d x K)/(a + b + c + d).
A fifth aspect of the present application provides a computer device comprising:
the system comprises a processor, a memory, a bus, an input/output interface and a wireless network interface;
the processor is connected with the memory, the input/output interface and the wireless network interface through a bus;
the memory stores a program;
the processor, when executing the program stored in the memory, implements the work recommendation method of any one of the first and/or second aspects.
A sixth aspect of the present application provides a computer-readable storage medium having stored therein instructions which, when executed on a computer, cause the computer to perform the work recommendation method of any one of the first and/or second aspects.
A seventh aspect of the present application provides a computer program product which, when executed on a computer, causes the computer to perform the work recommendation method according to any one of the first and/or second aspects. According to the technical scheme, the embodiment of the application has the following advantages:
when the method for recommending works is applied to a server, the method can be implemented by receiving the identity of the works and the user identity of a target user, wherein the identity of the works corresponds to the works clicked by the target user on a target terminal device, the target user is a user account number logged in when the target terminal device clicks the works, the server uniquely determines the works clicked by the target user in a preset database according to the identity of the works, so that the server can simultaneously know the works clicked by the target user and the target user, and can conjecture the interest tendency of the target user on the basis of the work, the target user and the works clicked by the target user can be determined through small-amount data transmission (the works do not need to be reported, but the work identity is only reported), data congestion can be reduced, and the server determines X related works in the preset database according to the content dimension corresponding to the works, and when the target user acquires the target content, the server can send the X related works to the target terminal equipment of the target user, so that the target terminal equipment presents the related works in a content recommending mode. Therefore, the related works recommended to the target user by the work recommendation method in the embodiment of the application are determined according to the content dimension of the work clicked by the target user, and the probability that the related works are matched with the interest tendency of the target user is higher, so that the purpose of recommending the related works individually for different target users is achieved.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of a work recommendation method of the present application as applied to a server;
FIG. 2 is a schematic flowchart of an embodiment of a work recommendation method applied to a target terminal device;
FIG. 3 is a flowchart illustrating an embodiment of a work recommendation method applied to a server and a target terminal device;
FIG. 4 is a schematic structural diagram of an embodiment of a work recommendation device applied to a server;
FIG. 5 is a schematic diagram of a rational structure of a recommendation device for works of the present application when applied to a target terminal device;
FIG. 6 is a schematic structural diagram of an embodiment of a computer device according to the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application 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 present application and are not intended to limit the present application.
It will be understood that when an element is referred to as being "secured to" or "disposed on" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or intervening elements may also be present.
It should be noted that the terms of orientation such as left, right, up, down, etc. in the present embodiment are only relative concepts or reference to the normal use state of the product, and should not be considered as limiting.
The network architecture in the embodiment of the present application may be composed of one or more servers and one or more target terminal devices, where the target terminal devices may be connected to the servers, the target terminal devices, and the servers through wireless networks, or through wired networks, and if the target terminal devices are connected through wireless networks, the specific connection mode may be a cellular wireless network, or a WiFi network, or other types of wireless networks; if the connection is made through a wired network, a common connection method is a fiber network. In the embodiment of the application, the server is integrated with the access function, and each target terminal device can be directly connected to the server without passing through the access network device. The server mainly functions to process services, manage communications, and the like, and communication services to be performed between the target terminal devices need to be processed by the server.
Referring to fig. 1, an embodiment of a recommendation method for works of the present application when applied to a server includes:
101. receiving a work identity and a user identity of a target user, wherein the work identity corresponds to a work clicked by the target user on a target terminal device, and the target user is a user account logged in when the target terminal device accepts the clicked work.
The target user in this embodiment is a user who has completed registration in the server, wherein the target user should have a unique user identity in the server; in this embodiment, the works are works stored in a preset database in the server, each work in the preset database has a unique work identity, and the works can be one or a mixture of multiple types of pictures, characters, videos, audios and the like. The method is mainly used for receiving the work identity and the user identity of the target user, wherein the work identity is corresponding to the work clicked by the target user on the target terminal device, and the target user is a user account which is logged in when the target terminal device receives the clicked work, so that the interest tendency of the target user can be presumed in the subsequent steps according to the work identity and the user identity of the target user. The step only receives the identity identification of the work, but not the work, so that the congestion of data transmission is reduced, and the server resource is saved.
102. And uniquely determining the works in a preset database according to the identity of the works.
According to the identity of the work obtained in step 101, the work can be uniquely determined in the preset database of the server in this step, and the work is the work clicked by the target user at the target terminal device.
103. Determining X related works in a preset database according to the content dimension corresponding to the works, wherein X is a positive integer greater than or equal to 0.
After determining the work clicked by the target user at the target terminal device in step 102, in this embodiment, the target user may be considered to be interested in the work, and based on such understanding, in this step, X relevant works are determined in the preset database according to the content dimension corresponding to the work, where the content dimension may include: the dimensions of author relevance, title relevance, tag relevance, topic relevance, etc., and the dimension information specifically included in the content dimension is not limited herein. The X relevant works determined in the step are all obtained by searching the content dimensions of the works which are interested by the target user, and can be regarded as the works which are interested by the target user with high probability.
104. And determining the target terminal equipment where the target user is located according to the user identity.
Finding a corresponding user account in the server according to the user identity obtained in the step 101, querying a register of the server to obtain a target terminal device currently logged in by the user account, and determining a communication path between the server and the target terminal device, thereby avoiding a problem that a target user replaces the terminal device to log in to cause a failure in tracking recommended works on the terminal device.
105. When the target user acquires the target content, the X related works are sent to the target terminal of the target user, so that the target terminal presents the related works in a content recommending mode.
After the X related works are determined in step 103 and the communication path between the server and the target terminal device is determined in step 104, in this step, when the target user acquires the target content of the server again through the target terminal device, the X related works are sent to the target terminal of the target user, so that the target terminal presents the related works in a content recommendation manner, the purpose of recommending the works with higher probability that the interest tendency fits to the target user is achieved, and when the method of the embodiment is applied to different target users, the purpose of individually recommending the related works to different target users is achieved. The target content in this step may be any content, and the target terminal device in this step may not be the same as the target terminal device in step 101.
Referring to fig. 2, an embodiment of the method for recommending works of the present application when applied to a target terminal device includes:
201. and determining the work clicked by the target user on the target terminal equipment.
The target user of this embodiment is a user account currently logged in the target terminal device, and the works displayed by the target terminal device are the same works existing in the preset database in the server, and at this time, the works clicked by the target user at the target terminal device can be determined according to the clicking behavior of the target user on the works displayed by the target terminal device, and the works can be one or a mixture of multiple types of pictures, characters, videos, audios, and the like.
202. And reporting the work identity of the work and the user identity of the target user to a server.
After determining the works clicked by the target user at the target terminal device in step 101, the step reports the work identity of the works and the user identity of the target user to the server. It should be noted that the work identification reported in this step has an association relationship with the user identification, so that the server can learn that the target user has a tendency of interest in the work represented by the work identification.
203. And receiving X related works through a return path, wherein the return path is a communication path inquired by the server according to the user identity, and the X related works are inquired by the server according to the work identity.
After the step 202 reports the work identity of the work and the user identity of the target user to the server, the server may obtain the corresponding work according to the work identity query, and may know that the content dimension corresponding to the work is queried to obtain X related works, where X is a positive integer greater than or equal to 0; the server can also position the target terminal equipment currently logged in by the user account of the target user according to the user identity, further determine a communication path between the target terminal equipment and the server, and return X related works to the target terminal equipment by taking the communication path as a return path. The target terminal device in this step can receive X relevant works through a return path, and the X relevant works received in this step are all found from the content dimensions of the works interested by the target user, and can be regarded as the works interested by the target user with a high probability.
204. And presenting the related works in a recommended content mode on the target terminal equipment.
After receiving X related works through a return path in step 203, this step selects to present Y related works in a recommended content manner in the target terminal device, where Y is a positive integer less than or equal to X. For example, on the premise that the target terminal device logs in the user account of the target user, when target content (the target content may be any content) is presented in the target terminal device, the related work is presented in a recommended frame position preset in the target content.
Therefore, when the method for recommending works is applied to the target terminal device, the target terminal device needs to report the user identity of the target user and the work identity of the work clicked by the target user to the server in time, receive the X related works returned by the server according to the user identity and the work identity, and then present the related works to the target user in the target terminal device in a content recommending mode, so that the purpose of recommending the works with higher probability of fitting the interest tendency to the target user is achieved.
Referring to fig. 3, the work recommendation method of the present application is applied to an interactive embodiment of a server and a target terminal device, and includes:
301. and determining the work clicked by the target user on the target terminal equipment.
The execution of this step is similar to step 201 in the embodiment of fig. 2, and repeated descriptions are omitted here.
302. And the target terminal equipment reports the identity of the work and the user identity of the target user to the server.
The execution of this step is similar to step 202 in the embodiment of fig. 2, and the repeated description is omitted here.
Specifically, in this step, the target terminal device may report information such as a work identifier of a work clicked by a target user, a content dimension corresponding to a current display state of the work, a user identity identifier of the target user, and a number of recommended works that can be presented on a next refresh page to the server in the form of an HTTP request, package and send the information to the message queue, and then perform preemption by a background distributed machine until all the information is reported to the server.
303. The server uniquely determines the works in a preset database according to the identity of the works.
The execution of this step is similar to step 102 in the embodiment of fig. 1, and repeated descriptions are omitted here.
304. And the server determines X related works in a preset database according to the content dimension corresponding to the works.
The execution of this step is similar to step 103 in the embodiment of fig. 1, and the repeated description is omitted here.
It should be noted that, when the report information received by the server in step 302 includes a content dimension corresponding to the state shown when the work is clicked, it may be considered that the target user is more interested in the content dimension, and then the recommended number of related works of the content dimension may be appropriately increased in this step; when a preference weight formula corresponding to the target user is prestored in the server, X related works can be screened from a preset database according to the preference weight formula, the preset weight of the target user to each content dimension of the works is recorded in the preference weight formula, and the preference degree of the target user to the content dimension is reflected by the size of the preset weight; when the report information received in step 302 includes the number of recommended works that can be presented on the next refresh page of the target terminal device, the server may return the corresponding number of related works according to the number of recommended works that can be presented on the next refresh page of the target terminal device.
For example, the number of related works is exactly X. Then, in this step, works corresponding to a certain number of different content dimensions may be recalled from a preset database according to the preference weight formula of the target user for the works. If the number of the related works of the creator actually needing to show the author relevance is A obtained by multiplying the author relevance preference weight configured in the background by the total number of X, the A related works of the creator related to the creator of the work are recalled from the preset database, and the record source of the A related works of the creator is 'relevantAuthor'; for example, the number B of title related works actually showing title correlation is obtained by multiplying the title correlation preference weight configured in the background by the total number X, then the B title related works related to the title of the work are recalled from the preset database, and the record source of the B title related works is "titleSearch"; for example, the number C of the label-related works actually to be displayed with the label correlation is obtained by multiplying the label correlation preference weight configured in the background by the total number X, then the number C of the label-related works related to the label of the work is recalled from the preset database, and the record source of the C label-related works is "relevantTag"; then, for example, the number D of topic-related works actually showing topic relevance is obtained by multiplying the background-configured topic-relevance preference weight by the total number X, then the D topic-related works related to the topic of the work are recalled from a preset database, and the recording source of the D topic-related works is 'topic', etc.; the above-mentioned a + B + C + D + … … is X, and both A, B, C, D and … … are non-zero positive integers, then X relevant works screened from the preset database are packed and integrated together, and the user id of the target user is stored in the cache database as a cached key value, so that the subsequent steps are sent to the target user.
305. And the server determines the target terminal equipment where the target user is located according to the user identity.
The execution of this step is similar to the step 104 in the embodiment of fig. 1, and repeated descriptions are omitted here.
306. And the server sends the X related works, the content dimensions corresponding to the X related works and the historical satisfaction degree scores to the target terminal equipment.
The server transmits the X related works determined in step 304 to the target terminal device determined in step 305. It should be noted that, in this step, the content dimensions (creator relevance, title relevance, tag relevance, topic relevance, and the like) corresponding to the X relevant works and the historical satisfaction scores corresponding to the X relevant works respectively may be further sent to the target user of the target terminal, where the historical satisfaction score is a score evaluated by the server according to a preset rule after each relevant work is recommended to the user.
307. And the target terminal device presents the related works in a manner of recommending the content.
The execution of this step is similar to step 204 in the embodiment of fig. 2, and the repeated parts are not described again here.
Specifically, determining content dimensions and historical satisfaction scores corresponding to the X related works, wherein the content dimensions comprise: author relevance, title relevance, tag relevance, and topic relevance; assuming that the historical satisfaction score corresponding to the relevance of the creator is a, the historical satisfaction score corresponding to the relevance of the title is b, the historical satisfaction score corresponding to the relevance of the label is c, and the historical satisfaction score corresponding to the relevance of the label is d; presenting the number of related works corresponding to the correlation of the creator in a recommended content mode on a target terminal device, wherein the number of the related works is equal to (a X K)/(a + b + c + d), K is a non-0 positive integer smaller than or equal to X, and the value of K is a rounded positive integer; the number of the related works corresponding to the title relevance is presented in a recommended content mode at the target terminal device and is equal to (b x K)/(a + b + c + d); presenting the number of related works corresponding to the tag relevance in a recommended content manner at the target terminal device to be equal to (c x K)/(a + b + c + d); the number of the related works corresponding to the topic relevance is equal to (d × K)/(a + b + c + d) when the target terminal device presents the topic relevance in a recommended content mode, and the works can be sorted according to the types of the works and the producers of the works in a scattered mode, so that the works of the same type or the same producer are prevented from being piled up at the position of the recommended content.
308. And the target terminal equipment reports the operation record of the target user on the X related works to the server.
After the target terminal device presents the related work in the form of the recommended content in step 307, the target terminal device may accept an operation record of the target user on the related work, where the operation record includes one or more of clicking, praise, collecting, commenting, sharing, and coin inserting, and an expression form of the operation record is not limited herein. In this step, the target terminal device reports the operation record of the related works to the server.
309. And the server carries out satisfaction degree scoring on the X related works respectively according to the operation records to obtain X satisfaction degree scores.
After the server obtains the operation records of the target user on the X related works in the step 308, the server performs satisfaction scoring on the X related works according to the operation records. Specifically, each related work is subjected to satisfaction scoring according to the operation record of each related work, for example, the satisfaction score of the related work is click score × click score weight + like score × like score + like score × favorite score weight + like score × comment score weight + like score × share score weight + like score × coin score + … …; the type and number of operation records to be considered for the satisfaction score of a specific related work can be determined according to actual conditions, and are not further limited herein.
310. And recording the target content dimension corresponding to the Y related works with higher satisfaction degree values in the X satisfaction degree values corresponding to the X related works.
Sorting the X satisfaction scores corresponding to the X related works in the step 309 from high to low, and selecting and recording the target content dimension corresponding to the Y related works with higher satisfaction scores, wherein Y is a positive integer less than or equal to X. That is, the Y related works may be considered as recommended works that are more satisfactory for the target user, and when recommending works to the target user later, the source of the Y related works should be referred to and the weight of the Y related works should be correspondingly increased, so that the related works recommended to the target user later are more suitable for the interest of the target user.
311. And increasing the weight of the target content dimension in the preset weight.
And adjusting the weight of the target content dimension in the preference weight formula corresponding to the target user in the server to ensure that the weight of the target user to the target content dimension is higher, so that the related works recommended to the target user later are more in accordance with the interest of the target user.
According to the method and the device, the content which is possibly interested at present is recommended to the target user in real time from the work clicked by the user at present, and the cost for the target user to obtain information which is useful for the target user from mass work data can be greatly reduced. Meanwhile, according to the work recommendation method, related works are retrieved from multiple content dimensions of the work clicked by the target user, the problem of continuous exposure of the head work (high-heat work) in the prior art is reduced to a certain extent, the exposure probability of the bottom work (low-heat work) is increased, and the ecological prosperity of a work distribution platform is facilitated. According to the embodiment of the application, the conversion efficiency of the recommendation data with different content dimensions can be analyzed and summarized in the background by recording the source form of the recommendation data, so that the recommendation weights with different content dimensions can be adjusted in real time, and a decision maker can conveniently predict the interest and preference of a target user.
The above embodiment describes a method for recommending a work of an application, and the following describes a device for recommending a work of an application, referring to fig. 4, an embodiment of a device for recommending a work applied to a server includes:
a receiving unit 401, configured to receive a work identity corresponding to a work clicked by a target user and a user identity of the target user, where the target user has a unique user identity in the server;
a first determining unit 402, configured to uniquely determine the work in a preset database according to the identity of the work;
a second determining unit 403, configured to determine X related works in the preset database according to content dimensions corresponding to the works, where X is a positive integer greater than or equal to 0;
a third determining unit 404, configured to determine, according to the user identity, a target terminal device where the target user is located;
a sending unit 405, configured to send X pieces of the related works to the target terminal device of the target user when the target user acquires target content, so that the target terminal device presents the related works in a content recommendation manner.
Optionally, the content dimension includes: one or more of a creator relevance, a title relevance, a tag relevance, or a topic relevance;
when the second determining unit 403 determines X relevant works in a preset database according to the content dimension information corresponding to the works, the method specifically includes:
determining one or more author-related works related to the author relevance in the preset database; and/or the presence of a gas in the gas,
determining one or more title related works related to the title correlation in the preset database; and/or the presence of a gas in the gas,
determining one or more tag-related works related to the tag correlation in the preset database; and/or the presence of a gas in the gas,
determining one or more topic related works related to the topic relevance in the preset database;
and screening preset weights of the creator related works, the title related works, the label related works and the topic related works to obtain X related works, wherein the preset weights are associated with the target user.
Optionally, the apparatus further comprises:
the receiving unit 401 is further configured to receive operation records of the target user on the X related works, where the operation records include one or more of clicks, praise, favorites, and comments;
and the scoring unit 406 is used for scoring the satisfaction degrees of the X related works according to the operation records to obtain X satisfaction degree scores.
Optionally, the apparatus further comprises:
a recording unit 407, configured to record, in X satisfaction scores corresponding to X relevant works, a target content dimension corresponding to Y relevant works with a higher satisfaction score, where Y is a positive integer less than or equal to X;
an adjusting unit 408, configured to increase the weight of the target content dimension in the preset weight.
The operation performed by the work recommendation device in the embodiment of the application is similar to the operation performed by the server in the embodiments of fig. 1 and fig. 3, and is not repeated here.
The related works recommended to the target user by the work recommending device are determined according to the content dimensions of the works clicked by the target user, the probability that the related works are matched with the interest tendency of the target user is higher, and therefore personalized recommendation of the related works for different target users is achieved.
Referring to fig. 5, an embodiment of a work recommendation apparatus applied to a target terminal device includes:
an obtaining unit 501, configured to obtain a click behavior of a work displayed in the target terminal device by a target user;
a reporting unit 502, configured to report, to a server, the work identity of the work and the user identity of the target user according to the click behavior;
a receiving unit 503, configured to receive X related works through a return path, where X is a positive integer greater than or equal to 0, the return path is a communication path queried by the server according to the user identity, and the X related works are queried by the server according to the work identity;
a presenting unit 504, configured to present the X related works in a manner of recommending content on the target terminal device.
Optionally, the apparatus further comprises:
the reporting unit 502 is further configured to feed back, to the server, operation records of the target user on the X related works, where the operation records include one or more of clicks, praise, collections, and comments.
Optionally, when the presenting unit 504 presents the X related works in the target terminal device in a manner of recommending content, the method specifically includes:
determining content dimension information and historical satisfaction scores corresponding to X related works, wherein the content dimension information comprises: author relevance, title relevance, tag relevance, and topic relevance; the historical satisfaction score corresponding to the creator relevance is a, the historical satisfaction score corresponding to the title relevance is b, the historical satisfaction score corresponding to the label relevance is c, and the historical satisfaction score corresponding to the label relevance is d;
presenting, at the target terminal device, the number of related works corresponding to the creator relevance in a content recommendation manner equal to (a × K)/(a + b + c + d), where K is a non-0 positive integer less than or equal to X, and the value of K is a rounded positive integer;
presenting, at the target terminal device, the number of related works corresponding to the title relevance in a recommended content manner is equal to (b × K)/(a + b + c + d);
presenting the number of related works corresponding to the tag relevance in a recommended content manner at the target terminal device is equal to (c x K)/(a + b + c + d);
and presenting the number of the related works corresponding to the topic relevance in a recommended content mode at the target terminal equipment, wherein the number of the related works is equal to (d x K)/(a + b + c + d).
The operation performed by the work recommendation apparatus in the embodiment of the application is similar to the operation performed by the target terminal device in the foregoing embodiments of fig. 2 and fig. 3, and is not repeated here.
Therefore, when the work recommendation device of the embodiment of the application is applied to the target terminal device, the target terminal device needs to report the user identity of the target user and the work identity of the work clicked by the target user to the server in time, receive the X related works returned by the server according to the user identity and the work identity, and then present the related works to the target user in the target terminal device in a content recommendation manner, so that the works with higher probability of fitting the interest tendency are recommended to the target user, and the related weights can be intelligently adjusted according to the operation records of the target user on the related works, so that the related works subsequently recommended to the target user are more fitted with the interest of the target user. When the method of the embodiment is applied to different target users, the personalized recommendation of the related works for the different target users is realized.
Referring to fig. 6, a computer device in an embodiment of the present application is described below, where an embodiment of the computer device in the embodiment of the present application includes:
the computer device 600 may include one or more processors (CPUs) 601 and a memory 602, where one or more applications or data are stored in the memory 602. Wherein the memory 602 is volatile storage or persistent storage. The program stored in the memory 602 may include one or more modules, each of which may include a sequence of instructions operating on a computer device. Still further, the processor 601 may be arranged in communication with the memory 602 to execute a series of instruction operations in the memory 602 on the computer device 600. The computer device 600 may also include one or more wireless network interfaces 603, one or more input-output interfaces 604, and/or one or more operating systems, such as Windows Server, Mac OS, Unix, Linux, FreeBSD, etc. The processor 601 may perform the operations performed in the embodiments shown in fig. 1 to fig. 3, which are not described herein again.
In the several embodiments provided in the embodiments of the present application, it should be understood by those skilled in the art that the disclosed system, apparatus and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the unit is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit. The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. A method for recommending works, which is applied to a server, comprises the following steps:
receiving a work identity and a user identity of a target user, wherein the work identity corresponds to a work clicked by the target user on a target terminal device, and the target user is a user account logged in when the target terminal device accepts the click of the work;
uniquely determining the works in a preset database according to the identity marks of the works;
determining X related works in the preset database according to the content dimension corresponding to the works, wherein X is a positive integer greater than or equal to 0;
determining the target terminal equipment where the target user is located according to the user identity;
when the target user acquires target content, X pieces of the related works are sent to the target terminal equipment of the target user, so that the target terminal equipment presents the related works in a content recommending mode.
2. The work recommendation method of claim 1, wherein said content dimensions comprise: one or more of a creator relevance, a title relevance, a tag relevance, or a topic relevance;
the determining X related works in a preset database according to the content dimensions corresponding to the works comprises:
determining one or more author-related works related to the author relevance in the preset database; and/or the presence of a gas in the gas,
determining one or more title related works related to the title correlation in the preset database; and/or the presence of a gas in the gas,
determining one or more tag-related works related to the tag correlation in the preset database; and/or the presence of a gas in the gas,
determining one or more topic related works related to the topic relevance in the preset database;
and screening preset weights of the creator related works, the title related works, the label related works and the topic related works to obtain X related works, wherein the preset weights are associated with the target user.
3. The work recommendation method of claim 2, wherein after X of said related works are obtained, said method further comprises:
receiving operation records of the target user on the X related works, wherein the operation records comprise one or more of clicks, praise, collections and comments;
and respectively carrying out satisfaction degree scoring on the X related works according to the operation records to obtain X satisfaction degree scores.
4. The work recommendation method according to claim 3, wherein after transmitting the X related works to a target terminal of the target user, the method further comprises:
recording target content dimensions corresponding to Y related works with higher satisfaction degree values in X satisfaction degree values corresponding to X related works, wherein Y is a positive integer smaller than or equal to X;
and increasing the weight of the target content dimension in the preset weight.
5. A work recommendation method is applied to a target terminal device and comprises the following steps:
determining the work clicked by the target user on the target terminal equipment;
reporting the work identity of the work and the user identity of the target user to a server;
receiving X related works through a return path, wherein X is a positive integer greater than or equal to 0, the return path is a communication path determined by the server according to the user identity, and the X related works are determined by the server according to the work identity;
and presenting the related works in a recommended content mode on the target terminal equipment.
6. The work recommendation method according to claim 5, wherein after X of said related works are presented in a recommended content manner at said target terminal device, said method further comprises:
and feeding back operation records of the target user on the X related works to a server, wherein the operation records comprise one or more of clicking, praise, collecting, commenting and sharing.
7. The work recommendation method according to claim 6, wherein said presenting X of said related works in a manner of recommending contents at said target terminal device comprises:
determining content dimension information and historical satisfaction scores corresponding to X related works, wherein the content dimension information comprises: author relevance, title relevance, tag relevance, and topic relevance; the historical satisfaction score corresponding to the creator relevance is a, the historical satisfaction score corresponding to the title relevance is b, the historical satisfaction score corresponding to the label relevance is c, and the historical satisfaction score corresponding to the label relevance is d;
presenting, at the target terminal device, the number of related works corresponding to the creator relevance in a content recommendation manner equal to (a × K)/(a + b + c + d), where K is a non-0 positive integer less than or equal to X, and the value of K is a rounded positive integer;
presenting, at the target terminal device, the number of related works corresponding to the title relevance in a recommended content manner is equal to (b × K)/(a + b + c + d);
presenting the number of related works corresponding to the tag relevance in a recommended content manner at the target terminal device is equal to (c x K)/(a + b + c + d);
and presenting the number of the related works corresponding to the topic relevance in a recommended content mode at the target terminal equipment, wherein the number of the related works is equal to (d x K)/(a + b + c + d).
8. A work recommendation device, applied to a server, comprising:
the system comprises a receiving unit, a processing unit and a display unit, wherein the receiving unit is used for receiving a work identity and a user identity of a target user, the work identity corresponds to a work clicked by the target user on a target terminal device, and the target user is a user account which is logged in when the target terminal device accepts the click of the work;
the first determination unit is used for uniquely determining the works in a preset database according to the identity marks of the works;
a second determining unit, configured to determine X related works in the preset database according to content dimensions corresponding to the works, where X is a positive integer greater than or equal to 0;
a third determining unit, configured to determine, according to the user identity, a target terminal device where the target user is located;
and the sending unit is used for sending the X related works to the target terminal equipment of the target user when the target user obtains the target content, so that the target terminal equipment presents the related works in a content recommending mode.
9. A work recommendation device is characterized in that the work recommendation device is applied to a target terminal device and comprises the following components:
the determining unit is used for determining the work clicked by the target user on the target terminal equipment;
the reporting unit is used for reporting the work identity of the work and the user identity of the target user to a server;
a receiving unit, configured to receive X related works through a return path, where X is a positive integer greater than or equal to 0, the return path is a communication path determined by the server according to the user identity, and the X related works are works determined by the server according to the work identity;
and the presentation unit is used for presenting the related works in a recommended content mode on the target terminal equipment.
10. A computer device, comprising:
the system comprises a processor, a memory, a bus, an input/output interface and a wireless network interface;
the processor is connected with the memory, the input/output interface and the wireless network interface through a bus;
the memory stores a program;
the processor, when executing the program stored in the memory, implements the work recommendation method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111141783.1A CN113836421A (en) | 2021-09-28 | 2021-09-28 | Work recommendation method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111141783.1A CN113836421A (en) | 2021-09-28 | 2021-09-28 | Work recommendation method and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113836421A true CN113836421A (en) | 2021-12-24 |
Family
ID=78970877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111141783.1A Pending CN113836421A (en) | 2021-09-28 | 2021-09-28 | Work recommendation method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113836421A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170310771A1 (en) * | 2013-12-20 | 2017-10-26 | Google Inc. | Application programming interface for rendering personalized related content to third party applications |
| CN109740068A (en) * | 2019-01-29 | 2019-05-10 | 腾讯科技（北京）有限公司 | Media data recommended method, device and storage medium |
| CN111859020A (en) * | 2019-04-26 | 2020-10-30 | 北京达佳互联信息技术有限公司 | Recommendation method and device, electronic equipment and computer-readable storage medium |
| CN111970528A (en) * | 2020-08-20 | 2020-11-20 | 广州华多网络科技有限公司 | Live broadcast recommendation method and device, computer equipment and readable storage medium |
-
2021
- 2021-09-28 CN CN202111141783.1A patent/CN113836421A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170310771A1 (en) * | 2013-12-20 | 2017-10-26 | Google Inc. | Application programming interface for rendering personalized related content to third party applications |
| CN109740068A (en) * | 2019-01-29 | 2019-05-10 | 腾讯科技（北京）有限公司 | Media data recommended method, device and storage medium |
| CN111859020A (en) * | 2019-04-26 | 2020-10-30 | 北京达佳互联信息技术有限公司 | Recommendation method and device, electronic equipment and computer-readable storage medium |
| CN111970528A (en) * | 2020-08-20 | 2020-11-20 | 广州华多网络科技有限公司 | Live broadcast recommendation method and device, computer equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2018201459B2 (en) | System and method for improving access to search results | |
| US10762049B1 (en) | Extracting machine data generated by an isolated execution environment from a chunk of data generated by an isolated execution environment manager | |
| US9047614B2 (en) | Adaptive gathering of structured and unstructured data system and method | |
| US20200372007A1 (en) | Trace and span sampling and analysis for instrumented software | |
| US20110040733A1 (en) | Systems and methods for generating statistics from search engine query logs | |
| WO2007071143A1 (en) | Method and apparatus for issuing network information | |
| US11755531B1 (en) | System and method for storage of data utilizing a persistent queue | |
| CN101477527B (en) | Multimedia resource retrieval method and apparatus | |
| WO2009031759A1 (en) | Method and system for generating search collection of query | |
| US11663172B2 (en) | Cascading payload replication | |
| US20170078361A1 (en) | Method and System for Collecting Digital Media Data and Metadata and Audience Data | |
| US11423096B2 (en) | Method and apparatus for outputting information | |
| CN105871585A (en) | Terminal association method and device | |
| CN100561477C (en) | Based on key word and shared searching method and the system of classification | |
| CN107545039B (en) | Keyword index acquisition method and device, computer equipment and storage medium | |
| CN105574037A (en) | Information processing method and device | |
| CN113836421A (en) | Work recommendation method and related device | |
| CN103365858A (en) | Method and device for acquiring searching results from multiple source devices and based on one inquiry sequence | |
| CN111695031A (en) | Label-based searching method, device, server and storage medium | |
| CN112035760A (en) | Task allocation method and computer equipment | |
| CN113377831B (en) | Resource data query method and device, electronic equipment and storage medium | |
| CN116938999B (en) | GRPC-based multiparty information transmission and state synchronization method, system and medium | |
| CN110020101B (en) | Method, device and system for restoring real-time search scene | |
| CN117788003A (en) | Chat robot application service quality evaluation method, computer equipment and medium | |
| CN115879494A (en) | Server and method for preventing repeated generation of permanent two-dimensional code |
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 |