CN115618109A

CN115618109A - Content recommendation method and device, electronic equipment and computer-readable storage medium

Info

Publication number: CN115618109A
Application number: CN202211309911.3A
Authority: CN
Inventors: 卢建兴
Original assignee: Beijing Zitiao Network Technology Co Ltd
Current assignee: Beijing Zitiao Network Technology Co Ltd
Priority date: 2022-10-25
Filing date: 2022-10-25
Publication date: 2023-01-17

Abstract

The invention relates to the technical field of Internet and discloses a content recommendation method, a content recommendation device, electronic equipment and a computer readable storage medium. Wherein, the method comprises the following steps: receiving search information, wherein the search information comprises key words representing content creators; displaying multimedia content corresponding to the content creator on a search result page; and responding to the fact that the multimedia content contains the living service class content, displaying a living service class content clustering result of a target dimension corresponding to the user who executes the searching operation on the searching result page, wherein the clustering result of the living service class content is obtained by clustering the living service class content issued by the creator in advance according to a plurality of clustering dimensions of different classes and different levels. By implementing the method and the device, when the search information is received, the living service type content clustering result of the target dimension corresponding to the user executing the search operation is directly displayed on the search result page, so that the convenience and the search efficiency of the search operation of the user are improved.

Description

Content recommendation method and device, electronic equipment and computer-readable storage medium

Technical Field

The invention relates to the technical field of internet, in particular to a content recommendation method and device, electronic equipment and a computer readable storage medium.

Background

The related content platform receives and displays the multimedia content released by the content creator, so that the user can find the content in which the user is interested on the content platform, for example, if the content creator can release the food video or the travel video created by the user to the content platform, the user can find the characteristic food information or the interesting scenic spot information on the content platform.

However, as the multimedia contents released by the content creator are increasing, when a user wants to search for a living service type content (such as food, travel, etc.) released by the content creator on a content platform and interested by the user or a more popular living service type content released by the content creator, the user needs to search for all multimedia contents released by the content creator, and the content searching mode is inefficient.

Disclosure of Invention

In view of this, embodiments of the present invention provide a content recommendation method and apparatus, an electronic device, and a computer-readable storage medium, so as to solve the problem that the existing manner for a user to search for multimedia content published by a content creator on a content platform is inefficient.

According to a first aspect, an embodiment of the present invention provides a content recommendation method, including: receiving search information, wherein the search information comprises keywords for representing content creators; displaying the multimedia content corresponding to the content creator on a search result page; and responding to the multimedia content containing the living service type content, and displaying a living service type content clustering result of a target dimension corresponding to the user executing the search operation on the search result page, wherein the clustering result of the living service type content is obtained by clustering the living service type content issued by the creator in advance according to a plurality of clustering dimensions of different types and different grades.

Optionally, the search information further comprises keywords characterizing the search intention; displaying a living service class content clustering result of a target dimension corresponding to a user performing a search operation on the search result page, wherein the method comprises the following steps: determining the target dimension according to the key words representing the search intention; determining the grade of the clustering dimension corresponding to the target dimension; and displaying the clustering result of the target dimension life service type content on the search result page according to the display mode corresponding to the grade.

Optionally, displaying, on the search result page, a living service class content clustering result of a target dimension corresponding to a user performing a search operation, including: obtaining historical interaction data authorized by the user on a content platform; matching the historical interaction data with clustering dimensions of a plurality of categories; determining the target dimension and the grade of the target dimension according to a matching result; and displaying the clustering result of the life service type content of the target dimension on the search result page according to the display mode corresponding to the grade.

Optionally, displaying the clustering result of the target dimension of the lifestyle service type content on the search result page according to a display mode corresponding to the grade, where the method includes: obtaining geographical location information authorized by the user; sequencing the life service type content clustering results of the target dimension to be displayed according to the geographic position information; and displaying the clustering result of the life service type content of the target dimension on the search result page according to the sequence of the distance from near to far.

Optionally, the search result page includes a preset content display area, where the preset content display area includes a plurality of content display sub-areas; the method further comprises the following steps: and when the clustering result of the life service type content of the target dimension comprises a plurality of types, displaying an aggregation result corresponding to one type of the life service type content in each content display sub-area according to a target display sequence.

Optionally, the method further comprises: and responding to the touch operation aiming at any content display subarea, and displaying an introduction page of the corresponding life service type content.

Optionally, a shop POI icon corresponding to the life service category content is displayed on the introduction page.

Optionally, the method further comprises: and displaying recommendation reason label information on each content display subarea, wherein the recommendation reason label information is determined according to at least one of position information of the life service type content, heat information of the life service type content and preference information of commodities contained in the life service type content.

Optionally, the different categories of clustering dimensions include: a geographic location dimension and a content type dimension.

According to a second aspect, an embodiment of the present invention provides a content recommendation apparatus, including: the receiving module is used for receiving search information, and the search information comprises key words representing content creators; the display module is used for displaying the multimedia content corresponding to the content creator on a search result page; and the first display module is used for responding to the fact that the multimedia content contains the living service content, displaying a living service content clustering result of a target dimension corresponding to a user executing the search operation on the search result page, and clustering the living service content issued by the creator according to a plurality of clustering dimensions of different categories and different grades in advance to obtain the clustering result of the living service content.

According to a third aspect, an embodiment of the present invention provides an electronic device, including: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the content recommendation method according to the first aspect or any one of the optional embodiments of the first aspect.

According to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions for causing a computer to execute the content recommendation method according to the first aspect or any one of the optional implementation manners of the first aspect.

According to the content recommendation method provided by the embodiment of the invention, the search information comprising the key words representing the content creators is received, the multimedia content corresponding to the content creators is displayed on the search result page, the living service type content contained in the multimedia content is clustered according to the preset clustering dimensionality, and the living service type content clustering result of the corresponding target dimensionality is displayed for the user, so that the living service type content clustering of the corresponding dimensionality is directly displayed in the displayed search result page in the process that the user searches the favorite content creators, the trouble of searching by the user is avoided, and the convenience and the searching efficiency of the user are improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.

FIG. 1 is a schematic diagram of a display page according to an embodiment of the invention;

FIG. 2 is a flow chart of a method of content recommendation according to an embodiment of the present invention;

FIG. 3 is a flow chart of a method of content recommendation according to an embodiment of the present invention;

FIG. 4 is a flow chart of a method of content recommendation according to an embodiment of the present invention;

FIG. 5 is a flow chart of a method of content recommendation according to an embodiment of the present invention;

fig. 6 is a block diagram of a configuration of a content recommendation apparatus according to an embodiment of the present invention;

fig. 7 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present 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.

The related content platform receives and displays the multimedia content released by the content creator, so that the user can find the content in which the user is interested on the content platform, for example, if the content creator can release the food video or the travel video created by the user to the content platform, the user can find the characteristic food information or the interesting scenic spot information on the content platform. However, as the multimedia contents released by the content creator are increasing, when the user wants to search the content platform for the content of the living service class (such as store exploring class, food class, travel class, etc.) released by the content creator and interested in the user or for the content of the living service class released by the content creator and popular with the user, the user needs to search all the multimedia contents released by the content creator, and the content searching method is inefficient.

Based on this, the technical scheme of the invention displays the result search page for displaying the multimedia content issued by the content creator by responding to the search operation of the user for the content creator, and if the multimedia content contains the living service content, the result search page displays the living service content clustering result of the target dimension to the user, so that the corresponding living service content (such as the living service content interested by the user or the living service content with higher heat degree) is directly displayed in the search result page in the process of searching the favorite content creator by the user, the user can directly see the interested or more heat living service content in the search result page, the trouble of searching by the user is avoided, and the convenience and the efficiency of searching by the user are improved.

In accordance with an embodiment of the present invention, there is provided an embodiment of a content recommendation method, it should be noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.

The embodiment of the present invention provides a content recommendation method, which can be used in an electronic device, such as a mobile phone, a tablet computer, a computer, and the like, capable of running a content platform client program, where the content platform may include, but is not limited to, an image-text platform, a video platform, and the like, and the embodiment of the present invention takes the video platform as an example to describe the scheme described in the embodiment of the present invention. Fig. 2 is a flowchart of a content recommendation method according to an embodiment of the present invention, as shown in fig. 2, the flowchart includes the following steps:

s31, receiving search information, wherein the search information comprises keywords representing content creators.

For example, when the content platform is enabled, a search window may be displayed on a main page or other display page of the content platform, and a user may perform a content search operation through the search window. The keywords input in the embodiment of the present application and characterizing the content creator include, but are not limited to, the ID, name, and other identification information corresponding to the content creator input. When the identification information of the content creator input by the user is received, responding to the operation of searching the content creator in the content platform and displaying the searched search result page for displaying the multimedia content released by the content creator.

And S32, displaying the multimedia content corresponding to the content creator on a search result page.

Exemplarily, the multimedia content corresponding to the content creator may include, but is not limited to, a lifestyle service type video (such as a cate recommendation video, a scenery spot recommendation video, and the like) related to "people use for eating and staying", and a favorite video, a talent skill video, and the like uploaded by the content creator. The content platform can store the received multimedia content and the corresponding identity information of the content creator in a server of the content platform in a correlated manner when receiving the multimedia content uploaded by the content creator, can match the identity with the pre-stored identity information when receiving the search information representing the identity of the content creator, and can display the stored multimedia content corresponding to the identity on a search result page when the matching is successful.

The search result page may present multimedia content in a manner that all multimedia content is displayed in a predetermined area of the search result page; the predetermined area may be a touchable area, so that a user can perform a corresponding type of adjustment operation on the predetermined area, such as sliding up/down or sliding left/right on the predetermined area, to realize a corresponding sliding display of the multimedia content displayed in the predetermined area; or the displayed multimedia contents are played in turn or sequentially switched to be displayed through sliding operation. The type of the adjustment operation is not limited in the embodiments of the present application, and can be determined by those skilled in the art according to actual needs. By adjusting the display mode of the multimedia contents displayed in the preset area, the flexible display of the plurality of multimedia contents can be realized, and the user can browse and check the plurality of multimedia contents conveniently.

And S33, responding to the multimedia content containing the life service type content, and displaying a life service type content clustering result of a target dimension corresponding to the user executing the search operation on the search result page, wherein the clustering result of the life service type content is obtained by clustering the life service type content issued by the creator in advance according to a plurality of clustering dimensions of different types and different grades.

Exemplarily, the multimedia content corresponding to the content creator may include living service content related to "use for clothing and living people", and may also include non-living service content such as favorite, talent exhibition, and the like; for the received search information containing the content creator identity, the type recognition algorithm of the pre-integrated multimedia content type can be used for carrying out the type recognition on the stored multimedia content corresponding to the identity so as to determine whether the multimedia content corresponding to the identity contains the living service content or not; when the multimedia content contains the living service content, the clustering result of the living service content associated with the interest point of the user can be displayed to the user by combining the interest point of the user who performs the search operation.

In the embodiment of the application, when the living service contents contained in the multimedia contents are clustered, the contained living service contents can be clustered in advance; the clustering mode can be that a content platform presets a plurality of clustering dimensions of different types and different grades, and carries out clustering operation on the contained life service contents according to the preset clustering dimensions. In the embodiment of the application, the clustering dimensions of different categories may include geographic location dimensions (e.g., different cities or different areas of the same city, etc.) and content type dimensions, and a plurality of sub-dimensions of different types may be set in the clustering dimension of each category, for example, for a catering dimension for which the content type is catering, the catering dimension may be used as a first-level classification, a corresponding second-level classification may be set according to tastes in the first-level classification, and a corresponding second-level classification may also be set according to a family or a category of dishes, for example, the second-level classification set according to the category of dishes may include, but is not limited to, a hot pot, a chinese meal, a western meal, a dessert, and the like; similarly, the third-level classification can be correspondingly set according to needs under the second-level classification, for example, for the hotpot under the second-level classification, the third-level classification can be set according to the taste of the hotpot, for example, the hotpot can comprise but not limited to a spicy hotpot, a Chaoshan hotpot and the like, and the number of levels which can be set is not limited in the embodiment of the application.

Specifically, the determination method of the interest point of the user performing the search operation may be determined from search information input by the user, and if the search information input by the user is "a hot pot recommended by the content creator a", the interest point of the user may be obtained by parsing as "a hot pot gourmet", and a clustering result of a dimension corresponding to "a hot pot" in the life service type content uploaded by the content creator a is displayed to the user; the method for determining the interest point of the user performing the search operation may also be that when receiving the search information, obtaining user history interactive data authorized by the user performing the search operation from the content platform, determining a target dimension to be displayed to the user performing the search operation after analyzing the user history interactive data, and displaying a life service type content clustering result of the corresponding target dimension on a search result page, and if determining that the user frequently searches or browses 'hot pot' food in the history search process after analyzing the user history interactive data authorized by the user, displaying a food clustering result of the dimension corresponding to 'hot pot' in the life service type content uploaded by the content creator a to the user. By combining with the interest points of the users who execute the searching operation to adaptively display the clustering results of the pre-clustered life service contents, the favorite contents of the users can be recommended in batch in a targeted manner, and the convenience and the searching efficiency of the users for searching the related contents on the content platform are improved.

Before clustering the contained living service contents, the living service contents issued by the content creator can be screened according to preset selection conditions. Specifically, for the content of the living services released by the content creator, technologies such as OCR and/or ASR may be utilized to extract the related content information, and then the content of the living services released by the content creator is screened according to the preset selection condition. Taking a content platform as an example of a video platform, the preset selection condition in this embodiment may include, but is not limited to, video high-heat characterization data (such as video playing amount, praise number, comment data, and the like), video quality (such as whether the video has jittering feeling, video substantial introduction content proportion, and the like), video content type (such as whether the video belongs to a probe store class, a package explanation class, a feature introduction class, and the like), video timeliness (such as a release time length), video relevance (such as whether the video is related to a life service class, and whether the video has an anchor point, and the like. The type and the number of the preset selection conditions are not limited in the embodiment of the application, and can be determined by those skilled in the art according to actual needs.

According to the content recommendation method provided by the embodiment of the invention, the search information comprising the key words representing the content creators is received, the multimedia content corresponding to the content creators is displayed on the search result page, the living service type content contained in the multimedia content is clustered according to the preset clustering dimension, and the living service type content clustering result of the corresponding target dimension is displayed for the user, so that the living service type content clustering of the corresponding dimension is directly displayed in the search result page in the process of searching the favorite content creators by the user, the trouble of searching by the user is avoided, and the convenience and the searching efficiency of the user are improved.

As an optional implementation manner of the embodiment of the present invention, the search information further includes a keyword representing a search intention, that is, a user performing a search operation simultaneously inputs a keyword representing a content creator and a keyword representing a search intention; displaying, on the search result page, a living service class content clustering result of a target dimension corresponding to a user performing a search operation, as shown in fig. 3, including:

s331a, determining the target dimension according to the key words representing the search intention; exemplarily, when a keyword representing a search intention is received, a pre-trained neural network model can be used for performing semantic identification on the input keyword representing the search intention, the identified semantic result is matched with preset clustering dimensions of different categories, and the clustering dimension with the matching degree larger than a certain threshold value is used as a target dimension. If the semantically identified keyword representing the search intention is 'hot pot', matching the keyword with identifiers of a plurality of clustering dimensions of different categories, if similarity matching is firstly carried out on the keyword and 'catering dimensions' and 'tourism dimensions' under the first-level classification, then secondary classification matching is continuously carried out under the matched 'catering dimensions', the secondary classification can be classified according to the dish types, and when the category of 'hot pot food' is included under the secondary classification, the 'hot pot food' clustered in advance can be taken as a target dimension through the similarity matching.

S332a, determining the grade of the clustering dimension corresponding to the target dimension; illustratively, different clustering dimensions define different corresponding grades in advance, so when a target dimension is matched, the grade of the corresponding clustering dimension is determined according to the grade identification associated with the target dimension.

And S333a, displaying the clustering result of the living service class content of the target dimension on the search result page according to the display mode corresponding to the grade. For example, for clustering dimensions of different levels, a display mode corresponding to the clustering dimensions can be preset, for example, catering dimensions and tourism dimensions which are classified as the first level can be directly tiled and displayed on a search result page; for the cuisine classification of the secondary classification under the catering dimensionality, according to the number of cuisine, when the number is small, all cuisine can be flatly laid and displayed on a search result page; when the number is large, the corresponding cuisine categories can be displayed in a preset area in the search result page in a manner of sliding display in response.

As an optional implementation manner of the embodiment of the present invention, displaying, on the search result page, a living service class content clustering result of a target dimension corresponding to a user performing a search operation, as shown in fig. 4, includes:

s331b, obtaining historical interaction data authorized by the user on the content platform; illustratively, the historical interaction data authorized by the user on the content platform may include, but is not limited to, any one or more of search keywords corresponding to search behavior before the user authorized performs the search operation, historical browsing records of the user on the content platform, and user tag data of the user on the content platform.

S332b, matching the historical interactive data with clustering dimensions of multiple categories; illustratively, the pre-trained semantic recognition model may be used to perform semantic recognition on the historical interaction data, and match the semantic recognition result with the preset clustering positions of multiple categories. Taking the historical search behavior of the user as an example, when receiving that any user executes the search operation, the step of extracting and identifying the search keyword corresponding to the search behavior of the user for a certain number of times before executing the search operation includes: the method includes the steps that multiple people gather food, the spicy taste and the good atmosphere, identified historical interaction data can be matched with label information corresponding to multiple clustering dimensions, for example, for a gourmet food clustering dimension of ' hot pot ', the corresponding label information may include ' suitable for gathering food ' and ' Sichuan Yu ' characteristic ', for a gourmet food clustering dimension of ' dessert ', the corresponding label information may include ' moderate sweetness ' and ' suitable for working ', historical search keywords of a user are matched with the label information of each clustering dimension, and a specific matching mode can be that each historical search keyword is compared with labels of the multiple clustering dimensions.

S333b, determining the target dimension and the grade of the target dimension according to the matching result; for example, a clustering dimension with a matching degree greater than a predetermined threshold may be used as a target dimension, and a rank of the clustering dimension with the matching degree greater than the predetermined threshold may be used as a rank of the target dimension. If the historical search keyword ' multi-person dinner party ' is matched with the hot pot label ' suitable dinner party ', the historical search keyword ' spicy and hot ' is matched with the ' hot pot label ' Chongyu characteristic ', and the historical search keyword is not matched with the label of the ' dessert ' food clustering dimension completely, the ' hot pot ' food clustering dimension can be used as the target dimension. Similarly, for the historical browsing records of the user on the content platform or the user tag data of the user on the content platform, after the semantic keywords are extracted, the target dimensions can be determined by matching the tags corresponding to the different types of clustering dimensions, and the details are not repeated here.

And S334b, displaying the clustering result of the life service type content of the target dimension on the search result page according to the display mode corresponding to the grade. Specifically, refer to the description of the corresponding part in step S333a in the above embodiment, which is not described herein again.

As an optional implementation manner of the embodiment of the present invention, displaying, on the search result page, the clustering result of the target dimension of the lifestyle service contents according to the display manner corresponding to the rank, as shown in fig. 5, includes:

s51, obtaining the geographical position information authorized by the user; for example, the content platform may obtain the geographic location information of the user when the user activates the content platform under the authorization of the user.

S52, sorting the clustering results of the life service type contents of the target dimension to be displayed according to the geographic position information;

and S53, displaying the clustering result of the life service type content of the target dimension on the search result page according to the sequence of the distance from near to far. For example, for a to-be-displayed target dimension "hot pot" including 3 hot pot restaurants in the clustering result, the distance from each hot pot restaurant to the geographic position of the user can be calculated according to the acquired geographic position information of the user and the geographic position information of the 3 hot pot restaurants, the calculated distances are sorted from near to far from the user and displayed on the search result page from near to far, and the nearest hot pot restaurant is displayed at the most front position of all the hot pot restaurants or at the position most easily seen by other users. And displaying the clustering result of the living service contents of the target dimension in a near-to-far manner by combining the geographic position information authorized by the user, so that the user can select a destination more favorable for travel requirements in time.

As an optional implementation manner of the embodiment of the present invention, the search result page includes a preset content display area, where the preset content display area includes a plurality of content display sub-areas, specifically, as shown in fig. 1, a search result page 11 includes a search input area 12, a content creator identifier 13, a predetermined area 14 for displaying multimedia content issued by a content creator, a preset content display area 15, and a plurality of content display sub-areas 16; by inputting the name of the content creator in the search input area 12, the user can display the corresponding content creator id 13 on the search result page, display the multimedia content published by the content creator in the preset area 14, and display the result of clustering the life service-like content of the target dimension that may be of interest to the user in the preset content display area 15. In the embodiment of the application, the preset content display area may further include text identification information and graphic information of recommended life service contents, the graphic information may be a touch icon, and when a user is interested in any displayed life service content, the user can know detailed description of the corresponding life service content by touching the icon.

The method further comprises the following steps: and when the clustering result of the life service type content of the target dimension comprises a plurality of types, displaying an aggregation result corresponding to one type of the life service type content in each content display sub-area according to a target display sequence. Illustratively, the target display order may be distance priority, user preference priority or popularity priority corresponding to the life service type content, price priority, sales priority, content introduction detail page quality priority, etc., which may be determined by those skilled in the art according to actual needs. And for the life service type contents containing a plurality of types of target dimensions, sequentially and correspondingly displaying in each content display sub-area according to the target display sequence.

As an optional implementation manner of the embodiment of the present invention, the method further includes: and responding to the touch operation aiming at any content display subarea, and displaying an introduction page of the corresponding life service type content. Illustratively, the introduction page displays introduction video and/or graphic information about the life service content issued by the corresponding content creator, so that the user can more specifically know the life service content in which the user is interested.

As an optional implementation manner of the embodiment of the present invention, a shop POI icon corresponding to the content of the lifestyle service class is displayed on the introduction page. By displaying the shop POI icon corresponding to the life service content on the introduction page, the user can directly enter the self introduction page of the shop by clicking the POI icon, and the user can be further helped to know the shop information in a more specific manner.

As an optional implementation manner of the embodiment of the present invention, the method further includes: and displaying recommendation reason label information on each content display subarea, wherein the recommendation reason label information is determined according to at least one of position information of the life service type content, heat information of the life service type content and preference information of commodities contained in the life service type content. The display position of the recommendation reason label information can be any position in the content display sub-area, as long as the mark of the displayed life service type content is not shielded, and the recommendation reason label information can be selectively arranged at the upper left corner of the content display sub-area in the embodiment of the application. By displaying the corresponding recommendation reason label information on each content display sub-area, the user can conveniently select the corresponding life service type content according to the actual requirement.

In this embodiment, a content recommendation apparatus is further provided, which is used to implement the foregoing embodiments and preferred embodiments, and is not described again after being described. The term "module" as used below may implement a combination of software and/or hardware of predetermined functionality. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.

The present embodiment provides a content recommendation apparatus, as shown in fig. 6, including:

a receiving module 41, configured to receive search information, where the search information includes keywords representing content creators. For a detailed description, reference is made to the corresponding related description of the above method embodiments, which is not repeated herein.

And a display module 42, configured to display the multimedia content corresponding to the content creator on the search result page. For a detailed description, reference is made to the corresponding related description of the above method embodiments, which is not repeated herein.

A first display module 43, configured to, in response to that the multimedia content includes a living service class content, display, on the search result page, a living service class content clustering result of a target dimension corresponding to a user performing a search operation, where the clustering result of the living service class content is obtained by clustering, in advance, the living service class content issued by the creator according to a plurality of different classes and different levels of clustering dimensions. For detailed description, reference is made to the corresponding related description of the above method embodiments, and details are not repeated herein.

The content recommendation device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and a memory executing one or more software or fixed programs, and/or other devices that may provide the above-described functionality.

The content recommendation device provided by this embodiment displays the multimedia content corresponding to the content creator on the search result page by receiving the search information including the keyword representing the content creator, clusters the living service content included in the multimedia content according to the preset clustering dimension, and displays the living service content clustering result of the corresponding target dimension to the user, so that the living service content clustering of the corresponding dimension is directly displayed in the search result page in the process of searching the favorite content creator by the user, the trouble of searching by the user is avoided, and the convenience and the searching efficiency of searching by the user are improved.

As an optional embodiment of the present invention, the search information further includes a keyword representing a search intention; the first display module 43 includes: the first determining submodule is used for determining the target dimension according to the keywords representing the search intention; the second determining sub-module is used for determining the grade of the clustering dimension corresponding to the target dimension; and the first display sub-module is used for displaying the clustering result of the life service type content of the target dimension on the search result page according to the display mode corresponding to the grade.

As an alternative embodiment of the present invention, the first display module 43 includes: the acquisition submodule is used for acquiring historical interactive data authorized by the user on the content platform; the matching submodule is used for matching the historical interactive data with the clustering dimensions of a plurality of categories; the third determining submodule is used for determining the target dimension and the grade of the target dimension according to a matching result; and the second display sub-module is used for displaying the clustering result of the life service type content of the target dimension on the search result page according to the display mode corresponding to the grade.

As an optional embodiment of the present invention, the first display sub-module or the second display sub-module includes: the acquisition unit is used for acquiring the geographical position information authorized by the user; the sorting unit is used for sorting the clustering results of the life service type contents of the target dimension to be displayed according to the geographic position information; and the display unit displays the clustering result of the life service type contents of the target dimension on the search result page according to the sequence of the distances from near to far.

As an optional implementation manner of the present invention, the search result page includes a preset content display area, where the preset content display area includes a plurality of content display sub-areas; the device further comprises: and the second display module is used for displaying the aggregation result corresponding to the life service type content of one type in each content display subarea according to the target display sequence when the life service type content clustering result of the target dimension contains a plurality of types.

As an optional embodiment of the present invention, the second display module is further configured to display an introduction page of the corresponding life service type content in response to a touch operation on any one of the content display sub-areas.

As an optional embodiment of the present invention, a shop POI icon corresponding to the content of the lifestyle service class is displayed on the introduction page.

As an optional implementation manner of the present invention, the second display module is further configured to display recommendation reason tag information on each of the content display sub-regions, where the recommendation reason tag information is determined according to at least one of location information of a lifestyle service type content, popularity information of the lifestyle service type content, and benefit information of a commodity included in the lifestyle service type content.

As an optional embodiment of the present invention, the different classes of clustering dimensions include: a geographic location dimension and a content type dimension.

Further functional descriptions of the modules are the same as those of the corresponding embodiments, and are not repeated herein.

An embodiment of the present invention further provides an electronic device, which has the content recommendation apparatus shown in fig. 6.

Referring to fig. 7, fig. 7 is a schematic structural diagram of an apparatus according to an alternative embodiment of the present invention, and as shown in fig. 7, the apparatus may include: at least one processor 601, such as a Central Processing Unit (CPU), at least one communication interface 603, memory 604, and at least one communication bus 602. Wherein the communication bus 602 is used to enable connection communication between these components. The communication interface 603 may include a Display (Display) and a Keyboard (Keyboard), and the optional communication interface 603 may also include a standard wired interface and a standard wireless interface. The Memory 604 may be a high-speed volatile Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The memory 604 may alternatively be at least one storage device located remotely from the aforementioned processor 601. Wherein the processor 601 may be in connection with the apparatus described in fig. 6, an application program is stored in the memory 604, and the processor 601 calls the program code stored in the memory 604 for performing any of the above-mentioned method steps.

The communication bus 602 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus 602 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 7, but this is not intended to represent only one bus or type of bus.

The memory 604 may include a volatile memory (e.g., a random-access memory (RAM); the memory may also include a non-volatile memory (non-volatile memory), such as a flash memory (flash memory), a hard disk (HDD) or a solid-state drive (SSD); the memory 604 may also comprise a combination of the above types of memory.

The processor 601 may be a Central Processing Unit (CPU), a Network Processor (NP), or a combination of the CPU and the NP.

The processor 601 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof. The PLD may be a Complex Programmable Logic Device (CPLD), a field-programmable gate array (FPGA), a General Array Logic (GAL), or any combination thereof.

Optionally, the memory 604 is also used for storing program instructions. The processor 601 may call program instructions to implement the content recommendation method as shown in the embodiment of fig. 2 of the present application.

The embodiment of the invention also provides a non-transitory computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions can execute the processing method of the content recommendation method in any method embodiment. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk Drive (Hard Disk Drive, abbreviated as HDD), or a Solid State Drive (SSD); the storage medium may also comprise a combination of memories of the kind described above.

Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art will be able to make various edits and modifications without departing from the spirit and scope of the present invention, and such edits and modifications fall within the scope defined by the appended claims.

Claims

1. A content recommendation method, comprising:

receiving search information, wherein the search information comprises key words representing content creators;

displaying the multimedia content corresponding to the content creator on a search result page;

and responding to the multimedia content containing the living service type content, and displaying a living service type content clustering result of a target dimension corresponding to the user executing the search operation on the search result page, wherein the clustering result of the living service type content is obtained by clustering the living service type content issued by the creator in advance according to a plurality of clustering dimensions of different types and different grades.

2. The method of claim 1, wherein the search information further comprises keywords characterizing search intent; displaying the clustering result of the life service type content of the target dimensionality corresponding to the user executing the searching operation on the searching result page, wherein the clustering result comprises the following steps:

determining the target dimension according to the key words representing the search intention;

determining the grade of the clustering dimension corresponding to the target dimension;

and displaying the clustering result of the life service type content of the target dimension on the search result page according to the display mode corresponding to the grade.

3. The method of claim 1, wherein displaying, on the search result page, the clustering results of the lifestyle service-like content of the target dimension corresponding to the user performing the search operation comprises:

obtaining historical interaction data authorized by the user on a content platform;

matching the historical interaction data with clustering dimensions of a plurality of categories;

determining the target dimension and the grade of the target dimension according to a matching result;

4. The method according to claim 2 or 3, wherein the step of displaying the clustering result of the target dimension of the lifestyle service type content on the search result page according to the display mode corresponding to the grade comprises the following steps:

acquiring geographical location information authorized by the user;

sequencing the life service type content clustering results of the target dimension to be displayed according to the geographic position information;

and displaying the clustering result of the life service type content of the target dimension on the search result page according to the sequence of the distance from near to far.

5. The method of claim 1, wherein the search results page includes a preset content display area, the preset content display area including a plurality of content display sub-areas; the method further comprises the following steps:

and when the clustering result of the life service type content of the target dimension comprises a plurality of types, displaying an aggregation result corresponding to one type of the life service type content in each content display sub-area according to a target display sequence.

6. The method of claim 5, further comprising:

and responding to the touch operation aiming at any content display subarea, and displaying an introduction page of the corresponding life service type content.

7. The method according to claim 6, wherein a shop POI icon corresponding to the life service class content is displayed on the introduction page.

8. The method of claim 5, further comprising:

and displaying recommendation reason label information on each content display subarea, wherein the recommendation reason label information is determined according to at least one of position information of the life service type content, heat information of the life service type content and preference information of commodities contained in the life service type content.

9. The method of claim 1, wherein the different classes of clustering dimensions comprise: a geographic location dimension and a content type dimension.

10. A content recommendation apparatus characterized by comprising:

the receiving module is used for receiving search information, and the search information comprises key words representing content creators;

the display module is used for displaying the multimedia content corresponding to the content creator on a search result page;

and the first display module is used for responding to the fact that the multimedia content contains the living service content, displaying a living service content clustering result of a target dimension corresponding to a user executing the search operation on the search result page, and clustering the living service content issued by the creator according to a plurality of clustering dimensions of different categories and different grades in advance to obtain the clustering result of the living service content.

11. An electronic device, comprising:

a memory and a processor, the memory and the processor being communicatively connected to each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the content recommendation method of any one of claims 1-9.

12. A computer-readable storage medium storing computer instructions for causing a computer to execute the content recommendation method according to any one of claims 1 to 9.