WO2020093289A1

WO2020093289A1 - Resource recommendation method and apparatus, electronic device and storage medium

Info

Publication number: WO2020093289A1
Application number: PCT/CN2018/114441
Authority: WO
Inventors: 罗月
Original assignee: 深圳市欢太科技有限公司; Oppo广东移动通信有限公司
Priority date: 2018-11-07
Filing date: 2018-11-07
Publication date: 2020-05-14
Also published as: CN112868004B; CN112868004A

Abstract

Disclosed are a resource recommendation method and apparatus, an electronic device and a storage medium. The resource recommendation method comprises: acquiring a search request sent by a user terminal, wherein the search request comprises at least one keyword; in response to the search request, acquiring a target resource corresponding to the keyword, wherein resource information of the target resource matches the keyword and network query information of the keyword, and the network query information comprises information acquired from a network platform that matches the keyword; and generating resource recommendation information according to the target resource, and sending the resource recommendation information to the user terminal. This method can improve the accuracy of resource recommendation.

Description

Resource recommendation method, device, electronic equipment and storage medium

Technical field

This application relates to the field of Internet technology, and more specifically, to a resource recommendation method, device, electronic device, and storage medium.

Background technique

With the rapid development of Internet technology, more and more service functions can be provided by network products. When network products provide services to users, they can provide services such as applications, pictures, songs, videos and other forms of resources. Usually the server that provides the resource will provide the resource recommendation service, but the accuracy of the current resource recommendation method is insufficient.

Summary of the invention

In view of the above problems, the present application proposes a resource recommendation method, device, electronic device, and computer-readable storage medium to improve the accuracy of resource recommendation.

In a first aspect, an embodiment of the present application provides a resource recommendation method. The method includes: acquiring a search request sent by a user terminal, where the search request includes at least one keyword; in response to the search request, acquiring the keyword Corresponding target resource, the resource information of the target resource matches the keyword and the network query information of the keyword, and the network query information includes information matching the keyword obtained from a network platform; The target resource generates resource recommendation information, and sends the resource recommendation information to the user terminal.

In a second aspect, an embodiment of the present application provides a resource recommendation apparatus. The apparatus includes a request acquisition module, a request response module, and an information generation module, where the request acquisition module is used to acquire a search request sent by a user terminal, The search request includes at least one keyword; the request response module is used to obtain a target resource corresponding to the keyword, resource information of the target resource, the keyword, and the keyword in response to the search request Matching network query information, the network query information includes information obtained from a network platform that matches the keyword; the information generation module is used to generate resource recommendation information based on the target resource, and the resource recommendation information Sent to the user terminal.

In a third aspect, an embodiment of the present application provides an electronic device, including: one or more processors; a memory; one or more application programs, wherein the one or more application programs are stored in the memory and Is configured to be executed by the one or more processors, and the one or more programs are configured to execute the resource recommendation method provided in the first aspect described above.

According to a fourth aspect, an embodiment of the present application provides a computer-readable storage medium in which program code is stored, and the program code can be called by a processor to execute the resources provided in the first aspect Recommended method.

The solution provided by this application receives the search request sent by the user terminal, responds to the search request, obtains the target resource corresponding to the keyword in the search request, and finally generates resource recommendation information according to the target resource, and sends the resource recommendation information to the user terminal. Since the resource information of the target resource matches the keyword and the network query information of the keyword, and the network query information includes the information matched with the keyword obtained from the network platform, the target resource obtained above is highly correlated with the keyword To improve the accuracy of resource recommendations.

BRIEF DESCRIPTION

In order to more clearly explain the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application For those skilled in the art, without paying any creative work, other drawings can be obtained based on these drawings.

FIG. 1 shows a schematic diagram of an application scenario according to an embodiment of the present application.

FIG. 2 shows a flowchart of a resource recommendation method according to an embodiment of the present application.

FIG. 3 shows a flowchart of a resource recommendation method according to another embodiment of the present application.

FIG. 4 shows a flowchart of step S220 in the resource recommendation method according to an embodiment of the present application.

FIG. 5 shows a flowchart of step S230 in the resource recommendation method according to an embodiment of the present application.

6 shows a flowchart of step S260 in the resource recommendation method according to an embodiment of the present application

7 shows a block diagram of a resource recommendation apparatus according to an embodiment of the present application.

FIG. 8 shows a block diagram of a request response module in the resource recommendation device according to an embodiment of the present application.

9 shows a block diagram of a first resource acquisition unit in a resource recommendation device according to an embodiment of the present application.

10 shows a block diagram of an information generation module in a resource recommendation device according to an embodiment of the present application.

11 is a block diagram of an electronic device for performing a resource recommendation method according to an embodiment of the present application.

12 is a storage unit for storing or carrying program code for implementing the resource recommendation method according to an embodiment of the present application.

detailed description

In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings in the embodiments of the present application.

With the rapid development of Internet technology, the functions of network products are becoming more and more abundant, and the services that network products can provide are also increasing. When providing services to users, network products can provide services of various resources, such as online or offline services of various forms of network resources such as applications, pictures, songs, and videos.

For users, the amount of data provided by the network resource server is too large. To find the network resources of interest from this massive data will consume a lot of time and traffic. Therefore, at present, many servers that provide resources will provide resources. Recommended features. Generally, when a user needs to obtain a desired resource, they can search through some keywords, and the server that provides the resource can recommend the resource to the user terminal according to the keyword. However, this method of resource recommendation usually requires accurate keywords to match. When the obtained keywords are not accurate, the accuracy of resource recommendation will be low.

In response to the above problems, the inventor has made a long-term research and proposed the resource recommendation method, device, electronic device, and computer-readable storage medium provided by the embodiments of the present application. By acquiring the target resources corresponding to the keywords, the acquired target resources The resource information matches the keyword and the network query information of the keyword, and the network query information includes information obtained from the network platform that matches the keyword, so that the keyword is highly related to the target resource, thereby improving the accuracy of resource recommendation .

The application scenarios of the resource recommendation method in the embodiments of the present application are introduced below.

Please refer to FIG. 1, which illustrates a schematic diagram of an application scenario of the resource recommendation method provided by an embodiment of the present application. The application scenario includes an interaction system 10. The interactive system 10 includes: an electronic device 100 and a user terminal 200. Among them, there is a communication connection between the electronic device 100 and the user terminal 200 to implement data or instruction interaction, and the number of the user terminal 200 is at least one.

In the embodiment of the present application, the electronic device 100 is used to provide or recommend resources and other information. The electronic device 100 may be a server, and the server may be a cloud server or a traditional server. The specific server type is not in this embodiment of the present application. As a limitation. The user terminal 200 is used to obtain resource information from the server in response to user operations. The user terminal 200 may be a device capable of running an application program such as a smart phone, tablet computer, e-book, etc. The specific type of user terminal is not used in the embodiment of the present application limited.

The resource recommendation method of the embodiment of the present application is described in detail below.

Referring to FIG. 2, an embodiment of the present application provides a resource recommendation method, which can be applied to electronic devices. The resource recommendation method may include:

Step S110: Acquire a search request sent by the user terminal, where the search request includes at least one keyword.

In the embodiment of the present application, when the user needs to obtain the required resource, the user terminal may send a search request to the electronic device to obtain the resource from the electronic device. The search request sent by the user terminal includes at least one keyword. Among them, the keywords are the words submitted by the user through the user terminal for obtaining the required resources. The number of keywords in the search request may not be limited, and may be one or more. The way for the user terminal to obtain keywords can be for the user to enter the keyword through the input interface of the user terminal, or for converting the voice input by the user through the microphone into a keyword through voice recognition technology. The application examples are not intended to be limiting.

Correspondingly, the electronic device may receive the search request including at least one keyword sent by the user terminal, so that the search request sent by the user terminal for acquiring resources may be obtained.

Step S120: In response to the search request, obtain a target resource corresponding to the keyword, the resource information of the target resource matches the keyword and the network query information of the keyword, and the network query information includes the slave network Information obtained by the platform that matches the keyword.

After acquiring the search request of the user terminal, the electronic device may respond to the search request to obtain related resources according to the search request, and return resource recommendation information to the user terminal.

In the embodiment of the present application, the electronic device may obtain the target resource corresponding to the keyword in the search request according to the search request sent by the user terminal. Specifically, the electronic device may obtain resources matching the keywords and the network query information of the keywords according to the keywords to obtain the target resources corresponding to the keywords. Among them, the network query information of the keyword is the information obtained from the network platform that matches the keyword. For example, when the keyword is the video name A, the corresponding network query information may be "A exclusive broadcast on application a", and For example, when the keyword is music B, the corresponding network query information may be "the application c exists in music B". Of course, the above network query information is only an example, and does not represent the limitation of the network query information in the embodiments of the present application. The online query information can be determined by the network platform and keywords. The resource information represents the basic information of the resource, and may include information such as the title, introduction, type, classification, label, description, and comment of the resource. Of course, the specific basic information may not be limited in the embodiments of the present application. The above resources may include application resources, picture resources, text resources, video resources, and music resources. Specific resources may not be limited in the embodiments of the present application.

As a way, the electronic device can determine the resources that match the keywords and the network query information of the keywords according to the matching degree of the resource information of the resources and the keywords, and the matching degree of the resource information of the resources and the network query information of the keywords To get the target resource corresponding to the keyword. The resource and resource information of the resource can be stored in the electronic device, and the electronic device can read the resource information of the resource to perform the above matching to obtain the target resource. Of course, the resource and the resource information of the resource can also be stored in other devices, and the electronic device can obtain the resource information of the resource from the other device to perform the above matching to obtain the target resource. Specifically, according to the matching degree of the resource information of the resource and the keyword, and the matching degree of the resource information of the resource and the network query information, a method of determining a resource matching the keyword and the network query information of the keyword may be used in the embodiment of the present application Not limited, for example, when the matching degree of the resource information of the resource and the keyword, and the matching degree of the resource information of the resource and the network query information are greater than the set matching degree, the network with the keyword and the keyword can be determined Query information matching resources.

In the embodiment of the present application, the method of acquiring resources matching the keywords and the network query information of the keywords may not be limited, and may also be other methods. For example, you can also obtain resource information that matches the keyword, and then from the resource information that matches the keyword, obtain the resource information that matches the keyword's network query information, and determine the resource that matches the keyword's network query information. Resources corresponding to the information, thereby obtaining resources matching the keywords and the network query information of the keywords.

In the embodiment of the present application, since the target resource corresponding to the keyword is obtained, not only the resource information of the resource is matched with the keyword, but also the resource information of the resource is matched with the network query information of the keyword obtained from the network platform to match The obtained target resource introduces the reference of the network query information, thereby improving the relevance of the keyword and the target resource, that is, obtaining the target resource with high relevance to the keyword.

Step S130: Generate resource recommendation information according to the target resource, and send the resource recommendation information to the user terminal.

In the embodiment of the present application, after acquiring the target resource corresponding to the keyword, the recommendation information may be generated according to the target resource, and the generated resource recommendation information may be sent to the user terminal to recommend the target resource to the user terminal. As a way, the resource recommendation information including at least the link of the target resource may be generated according to the target resource. The link of the target resource is used by the user to obtain the target resource, that is, after the resource recommendation information is recommended to the user terminal, the user terminal enters the target resource page according to the link to obtain the target resource. As another way, it is also possible to generate resource recommendation information including at least the target resource according to the target resource, that is, after recommending the above resource recommendation information to the user terminal, the user terminal can obtain the target resource to realize the keyword The corresponding target resource is recommended to the user. Of course, the specific method for generating the resource recommendation information is not limited in the embodiments of the present application. For example, the resource recommendation information generated according to the target resource may also include an introduction text of the target resource, and the introduction text of the target resource may include the target resource The name, resource description, resource type, resource classification information, and resource label information. The introduction text is used to introduce the target resource so that users can understand the target resource.

The resource recommendation method provided in the embodiment of the present application obtains target resources matching the network query information of the keywords and the keywords obtained from the network platform according to the keywords in the request sent by the user terminal, and then generates resource recommendation information according to the target resources. And send the resource recommendation information to the user terminal to complete the resource recommendation to the user. As the acquired target resources, not only the resource information matches the keywords, but also the resource information matches the keyword's network query information, which improves the relevance of the keywords and the target resources, thereby making the resource recommendation more accurate.

Referring to FIG. 3, another embodiment of the present application provides a resource recommendation method, which can be applied to electronic devices. The resource recommendation method may include:

Step S210: Acquire a search request sent by the user terminal, where the search request includes at least one keyword.

In the embodiment of the present application, step S210 may refer to the content in the foregoing embodiment, and details are not described herein again.

Step S220: In response to the search request, obtain a first resource whose resource information matches the keyword from the resource library.

In the embodiment of the present application, when acquiring the target resource corresponding to the keyword in response to the search request of the user terminal, the first resource whose resource information matches the keyword may be acquired from the resource library. Wherein, the resource library is a database for storing resources, and the resource library may be stored in the above electronic device or other devices. In addition to storing resources, the resource library can also store resource-related information, for example, resource information of resources, etc. Of course, the information specifically stored in the resource library may not be limited in the embodiments of the present application.

Further, referring to FIG. 4, obtaining the first resource whose resource information matches the keyword from the resource library may include:

Step S221: Match the resource information of each resource in the resource library with the keyword to obtain a first degree of matching between the resource information of each resource and the keyword. The resource information includes: a resource title At least one of information, resource introduction information, update description information, comment information, resource classification information, and resource label information.

In the embodiment of the present application, resource information of each resource in the above resource library may be obtained. The resource information may include at least one of resource title information, resource introduction information, update description information, comment information, resource classification information, and resource label information. Of course, specific resource information may not be used in this embodiment of the present application limited. The above resource title information can be the text information composed of the resource title or name; the resource introduction information can be the text information introducing the resource; the update description information can be the text information used to explain the updated content after the resource update; Comment text on resources; resource classification information can represent resource category information, which can include multi-level classifications, such as first-level classification, second-level classification, etc .; resource label information can include resource labels.

Further, the resource information of each resource in the above resource library can be matched with the keyword in the search request to obtain the first matching degree of the resource information of each resource and the keyword. Specifically, the resource information can be matched with the keywords to obtain a matching degree between the resource information and the keywords.

Step S222: Acquire the first resource whose first matching degree is greater than a first preset threshold from the resource library according to the first matching degree of the resource information of each resource and the keyword.

After obtaining the first matching degree of the resource information of each resource in the resource library and the keyword, the first matching degree can be selected from the resource library according to the first matching degree of the resource information of each resource and the keyword The first resource greater than the first preset threshold, that is, the filtered first resource, the first matching degree of the resource information and the keyword is greater than the first preset threshold. As a way, according to the first matching degree of the resource information of each resource and the keyword, the first matching degree greater than the first preset threshold can be filtered out, and then the first matching degree greater than the first preset threshold can be obtained Corresponding resources to obtain the above-mentioned first resources. The specific first preset threshold may not be limited in the embodiment of the present application, for example, the first preset threshold may be 80% to 90%, or 90% to 95%, depending on the actual situation and user needs. set up.

Therefore, the first resource can be obtained, and the matching degree of the resource information of the first resource and the keyword is greater than the first preset threshold, that is, the first resource whose resource information matches the keyword is obtained.

Step S230: Obtain the network query information of the keyword from a network platform. The network platform includes: at least one of an online social platform, an online search platform, an online public platform, and a knowledge service platform.

In the embodiment of the present application, network query information matching keywords can be obtained from a network platform for screening resources. Among them, the network platform may include an online social platform, an online search platform, an online public platform, and a knowledge service platform. The network social platform is a network platform for users to socialize. The web search platform is a web platform for users to search for content or information. The online public platform provides information distribution services for enterprises or users, and can achieve interactions in the form of text, pictures, audio, video, location, and mixed text and picture messages. The knowledge service platform is a platform that concentrates knowledge of various industries, and users can obtain relevant knowledge or submit relevant knowledge from the knowledge scope platform. Of course, the specific network platform may not be limited in the embodiments of the present application.

In the embodiment of the present application, please refer to FIG. 5, obtaining network query information of keywords from a network platform may include:

Step S231: Obtain the first network query information matching the keyword from the network platform.

In the embodiment of the present application, the first network query information matching the keyword can be obtained from the above-mentioned network platform through the keyword, so as to obtain the network query information of the keyword. As a way, obtaining the first network query information matching the keyword from the network platform may include:

Obtaining a preset number of network platforms from the plurality of network platforms as a network platform to be crawled, the second popularity value of the network platform to be crawled is greater than that of other network platforms in the plurality of network platforms A second heat value, the second heat value includes: at least one of accessing heat value, evaluating heat value, and downloading heat value; using an information crawling tool, crawling the web platform according to the keyword, and obtaining the The first network query information with keyword matching.

In the embodiment of the present application, the network platform to be obtained network query information can be determined from the above network platform. In an optional embodiment, the second heat value of each network platform in the plurality of network platforms may be obtained from, wherein the second heat value may include: accessing the heat value, evaluating the heat value, and downloading the heat value At least one. Among them, the access heat value may be a heat value generated based on the user's visits to the network platform, the evaluation heat value may be a heat value generated based on the user's comments on the network platform, and the download heat value may be based on the user's application on the network platform The heat value generated by the downloads of. After the second heat value of each network platform is obtained, the second heat values of all network platforms may be sorted from high to low to obtain a ranking result of the second heat value. According to the ranking result of the second heat value, the network platform corresponding to the preset number of second heat values can be obtained, that is, the determined second heat value of the network platform is greater than the second heat value of other network platforms . The preset number of network platforms obtained above may be used as the network platform to be crawled, that is, the network platform to obtain network query information. It can be understood that, since the determined second hotness value of the network platform to be obtained the network query information is greater than the second hotness value of other network platforms, the credibility of the network query information acquired subsequently can be made higher.

After obtaining the network platform to be crawled, an information crawling tool may be used to crawl the network platform to be crawled according to the keywords in the search request to obtain first network query information that matches the keywords. Among them, the information crawling tool is a web crawler tool that realizes network data extraction. Network data extraction refers to obtaining data from the Internet and converting the obtained unstructured data into structured data.

Thus, the first network query information matching the keywords and obtained from the above network platform can be obtained.

Step S232: Obtain the second network query information from the first network query information to obtain the network query information of the keyword. The first popularity value of the second network query information is greater than that of other network query information. Heat value, the other network query information is network query information other than the second network query information in the first network query information, and the first heat value includes at least: an evaluation heat value.

In the embodiment of the present application, after obtaining the first network query information matching the keyword from the above network platform, the second network query information may be filtered out from the first network query information to obtain the network query of the keyword information.

As an optional manner, the first popularity value of each first network query information in all first network query information may be obtained. The first heat value includes at least an evaluation heat value. Of course, the specific first heat value may not be limited in the embodiments of the present application, and may also include other heat values, such as access heat values. Sort the first popularity values of all the first network query information to obtain a sorting result. According to the sorting result of the first popularity value, the first network query information corresponding to the first target number of the first popularity value may be obtained to obtain the second network query information, that is, the determined second network query information The first popularity value is greater than the first popularity value of other network query information, and the other network query information is all the first network query information except the second network query information. The second network query information obtained above may be used as the network query information of the keyword to obtain subsequent network query information for matching resources. It can be understood that the network query information with the higher first popularity value is acquired as the network query information for matching resources. It can improve the credibility of keyword query information on the Internet for subsequent acquisition.

In the embodiment of the present application, after the second network query information is obtained, the second network query information may be filtered according to the time of the network query information. Therefore, acquiring the second network query information from the first network query information to obtain the keyword network query information may include: acquiring the second network query information from the first network query information, and the second network query information The first heat value is greater than the first heat value of other network query information. The other network query information is the network query information in the first network query information except the second network query information. The first heat value includes at least: the evaluation heat value; The second network query information within a preset time range in the second network query information is used as the keyword network query information.

It can be understood that, after obtaining the above-mentioned second network query information, the second network query information within a preset time range can be acquired according to the time stamp of the network query information as the network query information as a keyword. Optionally, the preset time range may be a time range within a preset time period before the current time, so that newer network query information may be obtained in order to improve the accuracy of subsequent matching resources. Of course, the specific preset time range may not be limited in the embodiments of the present application.

In the embodiment of the present application, the execution order of the above steps S220 and S230 is in the embodiment of the present application, and may not be limited.

Step S240: Acquire a second resource in the first resource whose resource information matches the network query information as a target resource.

After obtaining the network query information of the keywords in the search request, the resource information of the first resource and the network query information can be matched to obtain the second resource that matches the resource information and the network query information.

As a way, obtaining the second resource in the first resource that matches the resource information with the network query information may include:

Acquiring resources present in the network query information; acquiring second resources identical to those present in the network query information from the first resources.

It can be understood that, in the acquired network query information, there may be resources. For example, if the acquired network query information is “A exclusively broadcasted by application a”, then the resource present in the network query information is application a. Therefore, the existing resource can be obtained from the network query information. If the resource also exists in the first resource, it indicates that the resource information of the resource also matches the network query information, and the resource can be used as the target resource. Optionally, it can be judged whether the resource present in the network query information exists in the first resource, and if the resource present in the network query information exists, the second resource is obtained. After comparing all the resources present in the network query information with the first resources, all the second resources can be obtained.

As another way, acquiring the second resource of the first resource that matches the resource information with the network query information may include:

Acquiring resource information existing in the network query information; acquiring a second degree of matching between the existing resource information and resource information of each resource in the first resource; acquiring the second from the first resource The second resource whose matching degree is greater than the second preset threshold.

In the embodiment of the present application, obtaining the second resource that matches the above-mentioned resource information existing in the first resource with the network query information may also be a resource that matches the resource information existing in the network query information with each resource in the first resource The information is matched to obtain a second matching degree between the resource information present in the network query information and the resource information of each resource. According to all the second matching degrees, the second resources whose second matching degree is greater than the first preset threshold can be obtained from the first resources, that is, the second resources in which the resource information matches the network query information in the first resources are obtained. It can be understood that there may be resource information in the network query information, therefore, the resource information in the network query information and the resource information of the resource in the first resource may be matched to obtain the resource information and the resource information in the network query information Matching resources, thereby obtaining a second resource.

In the above embodiment, since the resource information includes resource title information, resource introduction information, update description information, comment information, resource classification information, and resource tag information, etc., there may be various types of information in the existing resource information, for example, There may be resource title information and resource introduction information at the same time. When obtaining the matching degree between the existing resource information and the resource information of each resource, matching may be performed according to different information in the resource information. As a way, obtaining the second degree of matching between the existing resource information and the resource information of each resource in the first resource may include:

Acquiring a plurality of third matching degrees between the plurality of types of information in the existing resource information and the plurality of types of information in the resource information of each resource in the first resource, the plurality of information in the existing resource information and the There is a one-to-one correspondence between various information in the resource information of each resource; according to preset weights, the multiple third matching degrees are weighted and summed to obtain the existing resource information and each resource in the first resource The second matching degree of resource information.

It can be understood that, each type of information in the existing resource information may be matched with each type of information in each resource in the first resource to obtain a third matching degree corresponding to each type of information. According to the importance of different information, different weights are set to improve the accuracy of the second matching degree between the existing resource information and the resource information of each resource in the first resource. The specific preset weight may not be limited in the embodiments of the present application, and may be set according to actual conditions and needs. For example, when the resource information includes resource title information, resource introduction information, update description information, comment information, resource classification information, and resource label information, the third matching degree corresponding to the resource title information is a1, and the third matching corresponding to the resource introduction information The degree is a2, the third matching degree corresponding to the update description information is a2, the third matching degree corresponding to the update description information is a3, the third matching degree corresponding to the comment information is a4, and the third matching degree corresponding to the resource classification information is a5 , The third matching degree corresponding to the resource tag information is a6, and the weights corresponding to the above resource information can be set to 0.4, 0.2, 0.1, 0.1, 0.1, and 0.1 respectively, then the third matching degree can be (0.4 * a1 + 0.2 * a2 + 0.1 * a3 + 0.1 * a4 + 0.1 * a5 + 0.1 * a6), so that the second matching degree between the existing resource information and the resource information of the first resource can be obtained.

By setting the weight of the third matching degree corresponding to different information and obtaining the second matching degree, the demand for the importance of different information can be satisfied, so as to obtain the target resource that meets the demand.

In the embodiment of the present application, the above two implementation manners can also be combined to obtain the second resource. For example, when the resource exists in the network query information, the second implementation method can be used to acquire the second resource, which does not exist in the network query information In the case of resources, the latter implementation mode is used to obtain the second resource.

Step S250: Generate a recommended sentence of the target resource according to the network query information corresponding to the target resource and the keyword.

After acquiring the target resource according to the keywords of the search request, resource recommendation information can be generated according to the target resource to recommend the target resource to the user.

In the embodiment of the present application, the recommended sentence of the target resource may be generated according to the network query information and the keyword corresponding to the target resource, so as to subsequently recommend the related recommended sentence to the user. Among them, the recommended sentence is a sentence used to show the relevance of resources and keywords to the user. Understandably, the network query information corresponding to the target resource is the information obtained from the network platform corresponding to the above keyword. The correlation of keywords has a better explanatory. Therefore, generating recommendation sentences based on network query information and keywords can make the resource recommendation information recommended to the user more convincing. As a way, the sentence containing the keyword and the name of the target resource can be obtained from the network query information of the keyword, and the sentence containing the keyword and the name of the target resource is used as the recommended sentence of the target resource. As another way, you can obtain the web query information with the highest first popularity value from the web query information of keywords, and then obtain the sentences in the web query information with the highest first popularity value, and finally use semantic generation rules to Words and keywords to generate recommended sentences for target resources.

Step S260: Generate resource recommendation information according to the target resource and the recommendation sentence.

In the embodiment of the present application, after the recommendation sentence is generated according to the network query information and keywords of the target resource, the resource recommendation information may be generated according to the target resource and the recommendation sentence. When there are multiple target resources, there are also multiple recommended sentences, and the target resources correspond to the recommended sentences one-to-one. Understandably, the resource recommendation information including at least the link of the target resource and the recommended sentence can be generated according to the target resource and the recommended sentence, or the resource recommendation information including at least the target resource and the recommended sentence can be generated so that subsequent users can view the resource recommendation information Based on the recommended sentence, you can choose the target resource you need and increase the convincing power of the target resource.

In the embodiment of the present application, when the resource recommendation information is generated according to the target resource and the recommended sentence, the target resource may also be sorted accordingly to generate the resource recommendation information. Therefore, referring to FIG. 6, step S260 may include:

Step S261: Sort the target resources according to a third heat value to obtain a sorting result, where the third heat value includes: downloading the heat value, evaluating the heat value, or accessing the heat value.

It is understandable that when there are multiple target resources, the target resources can be sorted according to the third heat value of the target resources, for example, the target resources are sorted in the order of the third heat value from high to low for subsequent generation In the resource recommendation information of the user, the user can see the target resources sorted by the third popularity value. The third heating value may include: downloading the heating value, evaluating the heating value, or accessing the heating value. Of course, the specific third heating value may not be limited in the embodiments of the present application.

Step S262: Generate resource recommendation information based on the sorting result and the recommendation sentence.

In the embodiment of the present application, after obtaining the sorting result of the target resources sorted according to the third popularity value, the resource recommendation information may be generated based on the sorting result and the recommendation sentence, that is, the content of the target resource in the generated resource recommendation information and its content The sorting of the recommended sentences corresponds to the sorting result described above, so that the user can see the results sorted by the third popularity value.

In the embodiment of the present application, when the resource recommendation information is generated based on the sorting result and the recommended sentence, the relevant target resource may be marked after the sorting result is obtained. Therefore, the resource recommendation method may further include: acquiring the historically downloaded resources of the user; and marking the same resources in the sorting result as the historically downloaded resources.

It can be understood that, in the above sorting result, the same resource in the sorting result as the historical downloaded resource can be marked according to the historical data of the resource downloaded by the user, that is, the resource downloaded by the user. After marking the sorting result as described above, the resource recommendation information is generated according to the recommended sentence and the marked sorting result, so that when the user views the resource recommendation information generated according to the sorting result and the recommended sentence, the user learns the resources that have been downloaded.

In the embodiment of the present application, before the resource recommendation information is generated according to the target resource and the recommended sentence, the target resource corresponding to the acquired keyword may also be filtered. Therefore, before generating resource recommendation information, the resource recommendation method may further include: acquiring the historical download amount of each target resource in the target resource; and removing the target resource according to the historical download amount of each target resource The target resource whose download volume in the history is lower than the preset download volume.

It is understandable that when there are multiple target resources, the historical download data of each target resource can be rooted to filter the target resources. Specifically, a target resource whose historical download volume is lower than the preset download volume may be obtained, and then the target resource whose historical download volume is lower than the preset download volume is removed from a plurality of target resources. The preset download amount may not be limited in the embodiment of the present application, for example, it may be 100 times or 1000 times, and the specific value may be set according to requirements. Then, resource recommendation information is generated according to the target resource after removing the resource whose historical download volume is lower than the preset download volume, and the recommendation sentence, which can avoid recommending resources with low download volume to the user.

Step S270: Send the resource recommendation information to the user terminal.

After the resource recommendation information is generated, the resource recommendation information generated according to the target resource and the recommended sentence may be sent to the user terminal for the user terminal to display the resource recommendation letter information.

In the embodiment of the present application, the correspondence relationship between the resource recommendation information and the keywords generated above may also be stored for subsequent use. Therefore, the resource recommendation method may further include:

Store the correspondence between the resource recommendation information and the keyword; when a search request including the keyword is obtained within a preset time range, according to the correspondence, the resource recommendation corresponding to the keyword is obtained Information, and send the resource recommendation information to the user terminal.

It can be understood that, after the correspondence relationship between the above resource recommendation information and keywords is stored, when a search request including the same keyword is received within a subsequent preset time range, the stored correspondence relationship can be used to obtain directly The resource recommendation information corresponding to the keyword, and send the resource recommendation information to the user terminal. The specific preset time range may not be limited in the embodiments of the present application. For example, the preset time range may be within a day or a month, and the specific preset time range may be based on actual needs. set up. In this way, the calculation amount of the electronic device can be reduced, and the feedback time of resource recommendation information can be reduced.

The resource recommendation method provided in this embodiment of the present application obtains a target resource whose resource information matches the keyword and the network query information of the keyword from the resource library according to the keyword in the search request sent by the user terminal, and then corresponds to the target resource The network query information and keywords are used to generate the recommended sentence of the target resource, and finally, the resource recommendation information is generated according to the target resource and the recommended sentence, and the resource recommendation information is sent to the user terminal. As the acquired target resources, not only the resource information matches the keywords, but also the resource information matches the keyword's network query information, which improves the relevance of the keywords and the target resources, thereby making the resource recommendation more accurate. In addition, the generated resource recommendation information includes recommended sentences generated based on network query information and keywords, which can increase the convincing power of the target resource recommended to the user.

Please refer to FIG. 7, which shows a structural block diagram of a resource recommendation device provided by an embodiment of the present application. The resource recommendation device 400 includes a request acquisition module 410, a request response module 420, and an information generation module 430. Wherein, the request obtaining module 410 is used to obtain the search request sent by the user terminal, the search request includes at least one keyword; the request response module 420 is used to obtain the target corresponding to the keyword in response to the search request Resource, the resource information of the target resource matches the keyword and the network query information of the keyword, the network query information includes information obtained from a network platform that matches the keyword; the information generation module 430 is used to generate resource recommendation information according to the target resource, and send the resource recommendation information to the user terminal.

In an embodiment of the present application, referring to FIG. 8, the request response module 420 may include: a first resource acquisition unit 421, a network query information acquisition unit 422, and a second resource acquisition unit 423. The first resource acquisition unit 421 is used to acquire the first resource whose resource information matches the keyword from the resource library; the network query information acquisition unit 422 is used to acquire the network of the keyword from a network platform For querying information, the network platform includes: at least one of a network social platform, a network search platform, a network public platform, and a knowledge service platform; the second resource obtaining unit 423 is configured to obtain resource information and The second resource matching the network query information is used as the target resource.

In the embodiment of the present application, referring to FIG. 9, the first resource acquisition unit 421 includes: a matching degree acquisition subunit 4211 and a resource screening subunit 4212. Wherein, the matching degree obtaining subunit 4211 is used to match the resource information of each resource in the resource library with the keyword to obtain the first matching degree of the resource information of each resource and the keyword , The resource information includes: at least one of resource title information, resource introduction information, update description information, comment information, resource classification information, and resource label information; the resource screening subunit 4212 is configured to The first matching degree of the resource information of the keyword and the keyword, and obtaining the first resource whose first matching degree is greater than a first preset threshold from the resource library.

As a way, the second resource acquisition unit 423 may be specifically configured to: acquire resources present in the network query information; acquire second resources identical to those present in the network query information from the first resources .

As another way, the second resource acquisition unit 423 may be specifically configured to: acquire resource information existing in the network query information; acquire the resource information existing and the resource information of each resource in the first resource A second matching degree; obtaining a second resource whose second matching degree is greater than a second preset threshold from the first resources.

Further, the second resource acquiring unit 423 acquiring the second matching degree between the existing resource information and the resource information of each resource in the first resource may include: acquiring multiple types of information in the existing resource information and Multiple third matching degrees of multiple information in resource information of each resource in the first resource, multiple information in the existing resource information corresponds to multiple information in resource information of each resource ; Weighting and summing the plurality of third matching degrees according to preset weights to obtain a second matching degree of the existing resource information and the resource information of each resource in the first resource.

In the embodiment of the present application, the network query information acquiring unit 422 may be specifically configured to: acquire the first network query information matching the keyword from the network platform; and acquire the second network query from the first network query information Information, the network query information of the keyword is obtained, the first popularity value of the second network query information is greater than the first popularity value of other network query information, and the other network query information is included in the first network query information In addition to the network query information other than the second network query information, the first heat value includes at least: an evaluation heat value.

Further, the network query information acquiring unit 422 acquires second network query information from the first network query information to obtain the network query information of the keyword, which may include: acquiring from the first network query information Second network query information, the first popularity value of the second network query information is greater than the first popularity value of other network query information, the other network query information is the first network query information except the second network For network query information other than query information, the first popularity value includes at least: an evaluation fever value; using the second network query information within a preset time range in the second network query information as the network query for the keyword information.

In the embodiment of the present application, the network query information acquiring unit 422 acquiring the first network query information matching the keyword from the network platform may include: using an information crawling tool to crawl the network platform according to the keyword to obtain The first network query information matching the keyword.

In the embodiment of the present application, the resource recommendation device 400 may further include: a network platform acquisition module. The network platform obtaining module is used to obtain a preset number of network platforms from the plurality of network platforms as a network platform to be crawled, and the second heat value of the network platform to be crawled is greater than the plurality of networks Second heat values of other network platforms in the platform, the second heat values include: at least one of access heat values, evaluation heat values, and download heat values.

In the embodiment of the present application, referring to FIG. 10, the information generation module 430 may include: a recommendation sentence generation unit 431 and a recommendation information generation unit 432. The recommended sentence generating unit 431 is used to generate a recommended sentence of the target resource based on the network query information corresponding to the target resource and the keyword; the recommended information generating unit is used 432 to generate the recommended sentence based on the target resource and the recommended sentence Generate resource recommendation information.

Further, the recommendation information generating unit 432 may be specifically configured to sort the target resources according to a third heat value to obtain a sorting result. The third heat value includes: download heat value, evaluation heat value, or access heat value ; Generate resource recommendation information based on the sorting result and the recommended sentence.

In the embodiment of the present application, the resource recommendation device 400 may further include: a historical resource acquisition module and a resource marking module. The historical resource obtaining module is used to obtain the historical downloaded resources of the user; the resource marking module is used to mark the same resources in the sorting result as the historical downloaded resources.

In the embodiment of the present application, the resource recommendation device 400 may further include: a download quantity acquisition module and a resource removal module. The download amount obtaining module is used to obtain the historical download amount of each target resource in the target resource; the resource removal module is used to remove the historical download amount of the target resource from the target resource according to the historical download amount of each target resource Set download target resources.

In the embodiment of the present application, the resource recommendation device 400 may further include: a correspondence storage module and a recommendation information sending module. The correspondence storage module is used to store the correspondence between the resource recommendation information and the keyword; the recommendation information sending module is used to obtain a search request including the keyword within a preset time range, according to the For the correspondence, obtain resource recommendation information corresponding to the keyword, and send the resource recommendation information to the user terminal.

Those skilled in the art can clearly understand that for the convenience and conciseness of the description, the specific working processes of the above-described device and module can be referred to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

In the several embodiments provided in this application, the coupling between the modules may be electrical, mechanical, or other forms of coupling.

In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module. The above integrated modules may be implemented in the form of hardware or software function modules.

In summary, the solution provided by this application receives the search request sent by the user terminal, responds to the search request, obtains the target resource corresponding to the keyword in the search request, and finally generates resource recommendation information based on the target resource Send to user terminal. Since the resource information of the target resource matches the keyword and the network query information of the keyword, and the network query information includes the information matched with the keyword obtained from the network platform, the target resource obtained above is highly correlated with the keyword To improve the accuracy of resource recommendations.

Please refer to FIG. 11, which shows a structural block diagram of an electronic device provided by an embodiment of the present application. The electronic device 100 in this application may include one or more of the following components: a processor 110, a memory 120, a Bluetooth module 130, and one or more application programs, where one or more application programs may be stored in the memory 120 and be It is configured to be executed by one or more processors 110, and one or more programs are configured to perform the method as described in the foregoing method embodiments.

The processor 110 may include one or more processing cores. The processor 110 connects various parts of the entire electronic device 100 by using various interfaces and lines, executes or executes instructions, programs, code sets or instruction sets stored in the memory 120, and calls data stored in the memory 120 to execute Various functions and processing data of the electronic device 100. Alternatively, the processor 110 may use at least one of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). Various hardware forms. The processor 110 may integrate one or a combination of a central processing unit (Central Processing Unit, CPU), an image processing unit (Graphics Processing Unit, GPU), and a modem. Among them, CPU mainly deals with operating system, user interface and application program, etc .; GPU is used for rendering and rendering of display content; modem is used for handling wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 110, and may be implemented by a communication chip alone.

The memory 120 may include random access memory (RAM) or read-only memory (Read-Only Memory). The memory 120 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 120 may include a storage program area and a storage data area, where the storage program area may store instructions for implementing an operating system and instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.) , Instructions for implementing the following method embodiments. The storage data area may also store data created by the terminal 100 in use (such as a phone book, audio and video data, and chat history data).

The Bluetooth module 130 is used to realize the Bluetooth connection between the electronic device and the two Bluetooth headsets, and the data interaction between the two Bluetooth headsets. Among them, the number of the Bluetooth module 130 may be one or multiple integrated together , Not limited here. Specifically, it can communicate with Bluetooth devices via Bluetooth protocol 5.0 / 4.2 / 4.1 / 2.1 / 2.0, Bluetooth low energy technology (Bluetooh Low Energy, BLE), Bluetooth enhanced rate technology (Enhanced Data Rate, EDR) or Bluetooth basic rate (Base, Rate, BR) etc. The basic circuit configuration is similar to the WiFi module, and can also be composed of a power amplifier, a wireless transceiver, a transceiver switch, a low-noise amplifier and an antenna. The Bluetooth module 130 may use a first communication frequency band, where the first communication frequency band may be 2.4 GHz.

Please refer to FIG. 12, which shows a structural block diagram of a computer-readable storage medium provided by an embodiment of the present application. The computer readable medium 800 stores program codes, and the program codes can be called by a processor to execute the method described in the above method embodiments.

The computer-readable storage medium 800 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium 800 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 800 has a storage space for the program code 810 that performs any of the method steps described above. These program codes can be read from or written into one or more computer program products. The program code 810 may be compressed in an appropriate form, for example.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still Modifications to the technical solutions described in the foregoing embodiments, or equivalent replacements to some of the technical features therein; and these modifications or replacements do not drive the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

A resource recommendation method, characterized in that the method includes:

Obtain a search request sent by a user terminal, where the search request includes at least one keyword;

In response to the search request, acquiring a target resource corresponding to the keyword, the resource information of the target resource matches the keyword and the network query information of the keyword, the network query information includes the Information matching the keywords;

Generate resource recommendation information according to the target resource, and send the resource recommendation information to the user terminal.
The method according to claim 1, wherein the acquiring the target resource corresponding to the keyword comprises:

Obtaining a first resource whose resource information matches the keyword from the resource library;

Acquiring network query information of the keyword from a network platform, the network platform includes: at least one of an online social platform, an online search platform, an online public platform, and a knowledge service platform;

Acquire a second resource in the first resource whose resource information matches the network query information as a target resource.
The method according to claim 2, wherein the acquiring the first resource whose resource information matches the keyword includes:

Matching the resource information of each resource in the resource library with the keyword to obtain a first degree of matching between the resource information of each resource and the keyword, the resource information includes: resource title information, resources At least one of introduction information, update description information, comment information, resource classification information, and resource label information;

According to the first matching degree of the resource information of each resource and the keyword, a first resource whose first matching degree is greater than a first preset threshold is obtained from the resource library.
The method according to claim 2, wherein the acquiring a second resource in which the resource information in the first resource matches the network query information includes:

Obtaining resources present in the network query information;

Acquiring a second resource that is the same as the resource existing in the network query information from the first resource.
The method according to claim 2, wherein the acquiring a second resource in which the resource information in the first resource matches the network query information includes:

Obtaining resource information existing in the network query information;

Acquiring a second matching degree between the existing resource information and the resource information of each resource in the first resource;

Obtain from the first resource a second resource whose second matching degree is greater than a second preset threshold.
The method according to claim 5, wherein the second degree of matching between the existing resource information and the resource information of each resource in the first resource comprises:

Acquiring a plurality of third matching degrees between the plurality of types of information in the existing resource information and the plurality of types of information in the resource information of each resource in the first resource, the plurality of information in the existing resource information and the There is a one-to-one correspondence between various information in the resource information of each resource;

Weighting and summing the plurality of third matching degrees according to preset weights to obtain a second matching degree of the existing resource information and the resource information of each resource in the first resource.
The method according to claim 2, wherein the acquiring network query information of the keyword from a network platform includes:

Obtain the first network query information matching the keyword from the network platform;

Acquiring second network query information from the first network query information to obtain network query information of the keyword, the first popularity value of the second network query information is greater than the first popularity value of other network query information, The other network query information is network query information other than the second network query information in the first network query information, and the first heat value includes at least: an evaluation heat value.
The method according to claim 7, wherein the acquiring second network query information from the first network query information to obtain the network query information of the keyword includes:

Acquiring second network query information from the first network query information, the first popularity value of the second network query information is greater than the first popularity value of other network query information, the other network query information is the first In network query information other than the second network query information, the first heat value includes at least: an evaluation heat value;

Use the second network query information within a preset time range in the second network query information as the network query information of the keyword.
The method according to claim 7, wherein the acquiring first network query information that matches the keyword from the network platform includes:

Use the information crawling tool to crawl the network platform according to the keywords to obtain the first network query information that matches the keywords.
The method according to claim 9, characterized in that the method uses the information crawling tool to crawl the network platform according to the keywords before obtaining the first network query information matching the keywords, the method Also includes:

Obtaining a preset number of network platforms from the plurality of network platforms as a network platform to be crawled, the second popularity value of the network platform to be crawled is greater than that of other network platforms in the plurality of network platforms A second heat value, the second heat value includes at least one of an access heat value, an evaluation heat value, and a download heat value.
The method according to any one of claims 1-10, wherein the generating resource recommendation information according to the target resource includes:

Generate a recommended sentence of the target resource according to the network query information corresponding to the target resource and the keyword;

According to the target resource and the recommendation sentence, resource recommendation information is generated.
The method according to claim 11, wherein the generating resource recommendation information according to the target resource and the recommendation sentence includes:

Sorting the target resources according to a third heat value to obtain a sorting result, where the third heat value includes: downloading the heat value, evaluating the heat value, or accessing the heat value;

Based on the sorting result and the recommendation sentence, resource recommendation information is generated.
The method according to claim 12, wherein after sorting the target resources according to the third popularity value and obtaining a sorting result, the method includes:

Obtain the resource of historical download of the user;

Mark the same resource in the sorting result as the resource downloaded from the history.
The method according to claim 11, wherein before the generating resource recommendation information according to the target resource and the recommendation sentence, the method further comprises:

Obtaining the historical download volume of each target resource in the target resources;

According to the historical download amount of each target resource, the target resource whose historical download amount is lower than the preset download amount in the target resource is removed.
The method according to any one of claims 1-10, wherein after the resource recommendation information is generated according to the target resource and sent to the user terminal of the user, the The method also includes:

Store the correspondence between the resource recommendation information and the keywords;

When a search request including the keyword is acquired within a preset time range, resource recommendation information corresponding to the keyword is acquired according to the correspondence relationship, and the resource recommendation information is sent to the user terminal.
A resource recommendation device, characterized in that the device includes: a request acquisition module, a request response module and an information generation module, wherein,

The request obtaining module is used to obtain a search request sent by a user terminal, where the search request includes at least one keyword;

The request response module is used to obtain the target resource corresponding to the keyword in response to the search request, the resource information of the target resource matches the keyword and the network query information of the keyword, and the network query The information includes information obtained from the network platform that matches the keywords;

The information generating module is configured to generate resource recommendation information according to the target resource, and send the resource recommendation information to the user terminal.
The apparatus according to claim 16, wherein the request response module comprises: a first resource acquisition unit, a network query information acquisition unit, and a second resource acquisition unit, wherein,

The first resource obtaining unit is configured to obtain a first resource whose resource information matches the keyword from a resource library;

The network query information obtaining unit is used to obtain network query information of the keyword from a network platform, the network platform includes: at least one of a network social platform, a network search platform, a network public platform and a knowledge service platform;

The second resource acquisition unit is used to acquire a second resource in the first resource whose resource information matches the network query information as a target resource.
The apparatus according to claim 17, wherein the first resource acquisition unit comprises: a matching degree acquisition subunit and a resource screening subunit, wherein,

The matching degree obtaining subunit is used to match the resource information of each resource in the resource library with the keyword, to obtain the first matching degree of the resource information of each resource and the keyword, the The resource information includes: at least one of resource title information, resource introduction information, update description information, comment information, resource classification information, and resource label information;

The resource screening sub-unit is configured to obtain the first matching degree greater than the first preset threshold from the resource library according to the first matching degree of the resource information of each resource and the keyword Resources.
An electronic device, characterized in that it includes:

One or more processors;

Memory

One or more application programs, wherein the one or more application programs are stored in the memory and are configured to be executed by the one or more processors, the one or more programs are configured to execute as The method of any one of claims 1-15.
A computer readable storage medium, characterized in that the computer readable storage medium stores program code, and the program code can be called by a processor to execute the method according to any one of claims 1-15 .