CN116842257A - Content recommendation method and device, electronic equipment and storage medium - Google Patents

Abstract

The embodiment of the disclosure provides a content recommendation method, a content recommendation device, electronic equipment and a storage medium. The method may include: acquiring a content recommendation request initiated by a user in a target scene, wherein the content recommendation request comprises information for representing the target scene; determining a target content level matched with the target scene represented by the content recommendation request according to a preset matching relation between the scene and the content level, and acquiring target content from a content pool according to the target content level, wherein the content pool comprises a plurality of items of content for recommendation to the user, and each item of content corresponds to at least two content levels; and based on the corresponding relation between the preset recommended position and the content level, issuing the target content to the recommended position corresponding to the target content level in the target scene. According to the embodiment of the invention, the content of more different items can be recommended to the user in the target scene, and the diversity of the recommended content is effectively improved.

Description

Content recommendation method and device, electronic equipment and storage medium

Technical Field

The embodiment of the disclosure relates to the technical field of communication, and more particularly, to a content recommendation method, a device, an electronic device and a storage medium.

Background

This section is intended to provide a background or context to the embodiments of the disclosure recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.

With the development of internet technology, users widely use search services on a network to obtain web contents of interest. In the process of searching content by using various types of APP or various websites, the content of the page used for forming the home page, the list page or the content page is often issued to the user equipment, that is, the content conforming to the current searching scene/page is recommended to the user. Each item of content being delivered has its own content level, which corresponds to the attributes of the content. For example, the content level of the content a is a free level, the content level of the content B is a paid level, and the content level of the content C is a high quality level.

In the related art, each content corresponds to only one content level, so that each content can only be issued to a fixed scene/page matched with the content level of the content, and cannot be issued to a plurality of different scenes, thereby causing that the number of the recommended content to the user in a certain scene is less and the content is barren.

Disclosure of Invention

In a first aspect of the embodiments of the present disclosure, there is provided a content recommendation method, including:

acquiring a content recommendation request initiated by a user in a target scene, wherein the content recommendation request comprises information for representing the target scene;

determining a target content level matched with the target scene represented by the content recommendation request according to a preset matching relation between the scene and the content level, and acquiring target content from a content pool according to the target content level, wherein the content pool comprises a plurality of items of content for recommendation to the user, and each item of content corresponds to at least two content levels;

and based on the corresponding relation between the preset recommended position and the content level, issuing the target content to the recommended position corresponding to the target content level in the target scene.

Optionally, the method further comprises: acquiring basic information of the user, wherein the basic information comprises at least one of the following steps: the ID of the user, the history browsing record of the user and the history favorites of the user; the obtaining the target content from the content pool according to the target content level comprises the following steps: determining first content corresponding to the target content level according to the target content level; and recalling the target content from the first content according to the basic information.

Optionally, the recall of the target content from the first content according to the basic information includes: generating a target index according to the target content level and the basic information; recall the target content from the first content based on the target index.

Optionally, the method further comprises: scoring the target content based on the basic information, and sorting the target content based on a scoring result; the issuing the target content to the recommended position corresponding to the target content level in the target scene includes: and based on the sorting result and the corresponding relation between the preset recommended position and the content level, the target content is issued to the recommended position corresponding to the target content level in the target scene, wherein the position arrangement sequence of the target content with the same target content level follows the sorting result.

Optionally, the method further comprises: and filtering the browsed contents of the user in the target contents according to the historical browsing record of the user.

Optionally, the method further comprises: weighting the target content level according to a preset rule; and adjusting the quantity of the target content corresponding to the target content level according to the weight.

Optionally, the method further comprises:

acquiring performance indexes of each content in the content pool within a preset duration;

and updating the content with the performance index lower than a preset index threshold value based on the alternative recommended content.

In a second aspect of the embodiments of the present disclosure, there is provided a content recommendation apparatus including:

the system comprises an acquisition unit, a storage unit and a processing unit, wherein the acquisition unit is used for acquiring a content recommendation request initiated by a user in a target scene, and the content recommendation request comprises information for representing the target scene;

the determining unit is used for determining a target content level matched with the target scene represented by the content recommendation request according to a preset matching relation between the scene and the content level, and acquiring target content from a content pool according to the target content level, wherein the content pool comprises a plurality of items of content for recommendation to the user, and each item of content corresponds to at least two content levels;

and the issuing unit is used for issuing the target content to the recommended position corresponding to the target content level in the target scene based on the corresponding relation between the preset recommended position and the content level.

In a third aspect of the embodiments of the present disclosure, there is provided an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method described in the example of the first aspect above when executing the computer program.

In a fourth aspect of the embodiments of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method described in the example of the first aspect above.

The above embodiments of the present disclosure have at least the following beneficial effects:

in one aspect, each item of content may be recommended into a plurality of different scenes matching its own content level by setting at least two content levels for each item of content. In other words, according to the content recommendation request initiated by the user in the target scene, more target contents matched with the target scene can be obtained according to the matching relationship between the scene and the content level, so that the diversity of the contents in the target scene is greatly improved. On the other hand, according to the corresponding relation between the recommended position and the content level, the obtained multiple target contents are respectively issued to the recommended position corresponding to the content level, so that the diversity of the contents is improved by improving the diversity of the content level in the target scene, namely, the condition that the contents corresponding to a plurality of different content levels can be recommended in the target scene is ensured, the condition that the target scene only recommends one content with the same content level is avoided, and the diversity of the recommended contents in the target scene is further improved.

Drawings

The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present disclosure will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. Several embodiments of the present disclosure are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings, in which:

FIG. 1 is a block diagram of a content recommendation system provided in an exemplary embodiment;

FIG. 2 is a flow chart of a content recommendation method provided by an exemplary embodiment;

FIG. 3 is a schematic diagram of a content level provided by an exemplary embodiment;

FIG. 4 is a schematic diagram of recall content according to a target index provided by an exemplary embodiment;

FIG. 5 is a block diagram of a content recommendation device provided by an exemplary embodiment;

FIG. 6 is a schematic diagram of a readable storage medium corresponding to a content recommendation method according to an exemplary embodiment;

fig. 7 is a schematic diagram of an electronic device capable of implementing the method according to an exemplary embodiment.

In the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.

Detailed Description

The principles and spirit of the present disclosure will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are presented merely to enable one skilled in the art to better understand and practice the present disclosure and are not intended to limit the scope of the present disclosure in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

Those skilled in the art will appreciate that embodiments of the present disclosure may be implemented as a system, apparatus, device, method, or computer readable storage medium. Accordingly, the present disclosure may be embodied in the following forms, namely: complete hardware, complete software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.

According to an embodiment of the disclosure, a content recommendation method, a content recommendation device, electronic equipment and a storage medium are provided.

In this document, it should be understood that any number of elements in the drawings is for illustration and not limitation, and that any naming is used only for distinction and not for any limitation. And, the data related to the present disclosure may be data authorized by a user or sufficiently authorized by each party.

The principles and spirit of the present disclosure are explained in detail below with reference to several representative embodiments thereof.

Application scene overview

In the process of searching content by using various types of APP or various websites, the content of the page used for forming the home page, the list page or the content page is often issued to the user equipment, that is, the content conforming to the current searching scene/page is recommended to the user. In the related art, each content corresponds to only one content level, so that each content can only be issued to a fixed scene or a fixed page matched with the content level of the content, and cannot be issued to a plurality of different scenes.

For example, for the user demand recommended by the novice, the content level of the content a is a free level, the content level of the content B is a paid level, and the content level of the content C is a loading level. Then content a can only be recommended into the free novice scenario. In fact, content a is left unfinished and belongs to the legend. However, since the content level of the content a does not exist in the carried level, the content a cannot be issued to the scene of the carried novice recommendation, that is, the user cannot find the content a in the scene of the carried novice recommendation. This tends to result in a scenario with a small number of content contained in the novice recommendation, which may not meet the search needs of the user.

Therefore, how to increase the diversity of the recommended content in the recommended scene to meet the search requirement of the user as much as possible is a problem to be solved.

It should be noted that the above application scenario is only shown for the convenience of understanding the spirit and principles of the present disclosure, and the embodiments of the present disclosure are not limited in any way in this respect. Rather, embodiments of the present disclosure may be applied to any scenario where applicable.

Summary of The Invention

In view of this, the present specification provides a technical solution for content recommendation.

The core concept of the specification is as follows: on the one hand, each content can be recommended to a plurality of different scenes matched with the content level by setting at least two content levels corresponding to each content, so that the diversity of the content in the target scene is greatly improved. On the other hand, in the case where the target scene matches to a plurality of content levels, since recommendation scores of different contents are different, there is a possibility that the plurality of contents contained in the target scene are all contents of the same content level. Therefore, by setting the correspondence between the recommended positions and the content levels, the contents of different content levels can be respectively issued to the recommended positions corresponding to the content levels, so that the target scene is prevented from recommending only one content of the same content level, namely, the recommended content contains the contents of different content levels, in other words, the diversity of the content levels in the target scene can be improved.

Exemplary method

The technical idea of the present specification will be described in detail by specific examples.

[ System architecture ]

Fig. 1 is a block diagram of a content recommendation system according to an exemplary embodiment, and as shown in fig. 1, the content recommendation system may include an electronic device 10 and a server 11. The electronic device 10 is a recommended object in the present specification, and the server 11 may send corresponding content to the electronic device 10 in response to a content recommendation request sent by the electronic device 10.

In an embodiment of the disclosure, the electronic device 10 may specifically include, but is not limited to, an electronic device with a certain computing capability, such as a smart phone, a desktop computer, a tablet computer, a notebook computer, an electronic book reader, a smart watch, a smart bracelet, etc., and the electronic device may run software or websites with categories, such as instant messaging, social networking, game, education, etc., and may be applied to a scenario of multi-person audio/video call.

The server may include a server, a server cluster formed by a plurality of servers, or a cloud server. The server side can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and can also be a cloud server for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network ), basic cloud computing services such as big data and artificial intelligent platforms and the like.

The terminal and the server may be directly or indirectly connected through wired communication or wireless communication, and the disclosure is not limited in particular.

Referring to fig. 2, fig. 2 is a flowchart of a content recommendation method according to an exemplary embodiment. The method may be applied to any electronic device as shown in fig. 1. The method may comprise the steps of:

s201: and acquiring a content recommendation request initiated by a user in a target scene, wherein the content recommendation request comprises information for representing the target scene.

Content recommendation is to push content to a target user for consumption, where consumption does not represent a mere pay-for-purchase, but includes reading, forwarding, collecting, focusing, etc. In order to improve the experience of users when using products, the users need to recommend contents to the users according to the demands of the users so as to improve the recommendation effect of the contents.

In the process of searching information by using various APP or various websites, the recommendation requirement of the user on the target content is related to the scene. For example, a scene where a user searches for a novel is a novel recommended scene, a scene where a video is searched for is a video recommended scene, and a scene where an APP is initially used is a new user guidance scene. Obviously, the content recommendation needs of the user in different scenes are not the same. Therefore, the content recommendation request initiated by the user in the target scene can be acquired, and the content recommendation request comprises the information for representing the target scene, so that the target scene in which the user is positioned is determined according to the acquired content recommendation request.

S202: determining a target content level matched with the target scene represented by the content recommendation request according to a preset matching relation between the scene and the content level, and acquiring target content from a content pool according to the target content level, wherein the content pool comprises a plurality of items of content for recommendation to the user, and each item of content corresponds to at least two content levels.

Each item of content has a corresponding content level. Therefore, the matching relation between the scene and the content level can be preset, so that different contents are recommended to different scenes based on the matching relation, specifically, after the target scene is determined according to the content recommendation request of the user, the target content level matched with the target scene can be determined according to the preset matching relation between the scene and the content level, and then the target content corresponding to the target content level is obtained from the content pool according to the target content level.

A content pool is a system for loading content and making the content organically related. The content pool has three elements: content, content container, and interactions between content. The content can be understood as the raw material of a content pool and can be any form of content such as pictures, words, audios and videos, PPT and the like. The content container is the container for loading the content. Common content containers include various websites and website platforms, which can be PC-end websites or mobile-end websites, such as websites of Internet public classes, internet news and the like. Interactions between content refer to associations between content. Common ways of association are internal links, etc., according to which an internal link of one piece of content can jump to another piece of content. Based on the association between the contents, one piece of content can be found out of the other, thereby forming a scale effect.

Typically, a content pool will include a plurality of items of content available for recommendation to a user. In the embodiments of the present specification, at least two content levels may be set for each item of content according to the attribute of the content. Fig. 3 is a schematic diagram of a content level provided by an exemplary embodiment. As shown in FIG. 3, the content pool comprises three contents of image text 1, image text 2 and FIG. 3. Wherein, the image-text 1 belongs to both high quality image-text and guiding payment image-text, therefore, the image-text 1 can correspond to two content levels, namely a high quality level and a guiding payment level. Similarly, the graph 2 may correspond to a guide payment level and a subscription level, and the graph 3 may correspond to a high quality level and a subscription level.

Recall is an important step in the content recommendation field. Recall is that after the target content is determined, the target content is taken out of the content pool and put into the computer process. Since the content pool contains a large amount of content, the data volume of the content is very large after the corresponding content is determined according to the target content level. In order to reduce the amount of data that needs to be processed in the recall phase, the determined content may be filtered during the recall phase.

In some possible implementations, the user's underlying information may be obtained at the same time as the user-initiated content recommendation request is obtained. In the process that users search information by using various APP or various websites, own basic information of each user can be formed. The base information is used to characterize the personal characteristics of the user. The user basic information may include an ID of the user, a history browsing record of the user, a history preference of the user, and the like. Any of the aforementioned basic information can be used as screening conditions for the recall stage to screen the target content. In this embodiment, the target content is obtained from the content pool according to the target content level, specifically, the first content corresponding to the target content level is determined according to the target content level, and then the target content is recalled from the first content according to the basic information of the user.

Because the basic information of the user reflects the personalized recommendation requirement of the user in the target scene, the first content is screened according to the basic information of the user, the screened first content is used as the target content, the target content is recalled and recommended to the user, the recommended content received by the user can be more in line with the personalized requirement of the user, and therefore the recommendation effect of the target content is improved.

In some possible embodiments, the specific implementation manner of recalling the target content from the first content according to the basic information of the user is as follows: a target index is generated according to the target content level and the basic information, and then the target content is recalled from the first content according to the target index.

Because the content pool contains a large amount of content, in order to quickly find out target content meeting the user content recommendation request from the large amount of content, an index can be constructed for each item of content when the content pool is generated, so that the target content can be searched according to the index later, and the content issuing efficiency is improved. In this embodiment, the index of the content may be composed of the content level and the content tag, may be composed of the content level and the unique user identifier, and may be composed of the content level and the content category. Taking fig. 3 as an example, two content levels corresponding to the graphic 1 may have indexes of multiple dimensions respectively. For the high quality level of the image-text 1, the index of the image-text 1 can be the high quality level+the novel (content level+content classification), the high quality level+the martial arts (content level+content label), and the index of the image-text 1 can also be the high quality level+the user ID (content level and user unique identifier). Similarly, for the guided payment level of the image-text 1, the index can be created as the guided payment level+novel, the guided payment Fei Jibie +martial arts, and the guided payment level+user ID.

By setting a plurality of indexes corresponding to a plurality of dimensions in each content level of each item of content, the content can be recalled to the user based on the corresponding indexes when any content level meets the user recommendation request, and the situation that the content level meets the user recommendation request but cannot be recalled due to lack of the indexes is avoided. For example, if only the index of multiple dimensions is set for the high quality level of the graph 1, no index is set for the lead payment level of the graph 1. Then, in the scenario where the user requests a picture of the leading payment level, the target content level is the leading payment level. And the image-text 1 also accords with the personalized recommendation requirement reflected by the basic information of the user. However, because the image-text 1 lacks an index for guiding the payment level, the image-text 1 is lacking in the target content which is finally recalled, and the recommending effect of the target content is affected.

Since each content level of each item of content has a plurality of indexes corresponding to a plurality of dimensions, when the target content is recalled from the content pool, the target index can be generated first according to the target content level and the basic information of the user. Specifically, if the basic information of the user is a history browsing record or a history preference, the classification or the label of the content preferred by the user can be determined according to the basic information, and then the target index is generated according to the target content level and the classification/label of the content. If the basic information of the user is the user ID, a target index can be generated according to the target content level and the user ID. And then searching the target content from the first content according to the target index, and recalling the target content.

FIG. 4 is a schematic diagram of recall content according to a target index, provided by an example embodiment. As shown in fig. 4, the graphics 1, 2, 3 are the first content obtained from the content pool according to the target content level. Two target indexes are generated according to the basic information and the target content level of the user, namely a high quality level and a martial arts, and a guided payment Fei Jibie and a martial arts. The index of the image-text 1 aiming at the high quality level is high quality level plus swordlike, and the index aiming at the guiding payment level is guiding payment Fei Jibie plus swordlike; the index of the image-text 2 aiming at the guiding payment level is guiding payment level + conscious flow; the index of the picture and text 3 aiming at the high quality level is high quality plus martial arts. Therefore, according to the target index, the target content, namely the image text 1 and the image text 3, can be screened from the first content, and then the image text 1 and the image text 3 are recalled.

In this embodiment, the target content is searched by an index method, which is helpful to improve the searching efficiency of the target content, and further improve the issuing efficiency of the target content. Moreover, the target index is generated according to the target content level and the user basic information, so that the target content recalled according to the target index meets the personalized recommendation requirement of the user, and the recommendation experience of the user is improved.

S203: and based on the corresponding relation between the preset recommended position and the content level, issuing the target content to the recommended position corresponding to the target content level in the target scene.

In the content recommendation field, after recalling content potentially of interest to a user from a content pool, the recalled content needs to be ordered. Because the user's interest level in each item of content is different, the user will typically perform the consumption actions such as clicking, collecting, etc. on the content in front of the recommended content displayed in the scene. Therefore, recalled contents are required to be arranged from high to low according to the interest degree of the user so as to stimulate the consumption of the user and promote the recommendation effect of the target contents.

The same target scene may be matched to multiple target content levels, that is, the final recalled target content may correspond to multiple content levels. Then, after sorting the recalled target content, a situation may occur in which the content located at the first few recommended positions in the target scene all corresponds to the same content level, which is unfavorable for stimulating the user to consume. For example, there are 5 recommended positions in the target scene, 6 of 10 recalled contents are high-quality level contents, and 4 are lead payment level contents. The top 5 recommended positions were found to be high quality level content after ranking the 10 items of content. This results in the user not referring to the lead payment level content.

Therefore, in the embodiment of the present disclosure, by presetting the correspondence between the recommended positions and the content levels, based on the correspondence, the target content is delivered to the recommended position corresponding to the target content level in the target scene, so that each target content level has content that can be delivered to the target scene, for example, assuming that the 1 st, 3 rd and 5 th positions correspond to high quality levels and the 2 nd and 4 th positions correspond to guidance payment levels in 5 recommended positions, 3 rd high quality level content can be optionally delivered to the 1 st, 3 rd and 5 th positions of recommended positions, and simultaneously, two guidance payment level contents are optionally selected and delivered to the 2 nd and 4 th positions of recommended positions.

In the above embodiment, on the one hand, by setting at least two content levels corresponding to each content, each content may be recommended to a plurality of different scenes matching with its own content level, so as to greatly improve the diversity of the content in the target scene. On the other hand, through the corresponding relation between the preset recommended position and the content level, the content with different content levels can be respectively issued to the recommended position corresponding to the content level, so that the diversity of the content level in the target scene is improved, and the diversity of the content in the target scene is improved.

In addition, by setting at least two content levels corresponding to each content, the content corresponding to different content levels can be marked by developers in the process of building the content pool, and the content levels do not need to be marked sequentially, so that the building efficiency of the content pool can be improved. For example, developer a may be responsible for marking only high quality content in the content pool, and developer B may be responsible for marking only guidance payment content in the content pool, improving the efficiency of content pool construction by parallel marking.

In some possible implementations, recalled target content may be scored based on the user's underlying information, and the target content ranked based on the scoring results. And then, according to the ordering result and the corresponding relation between the preset recommended position and the content level, the target content is issued to the recommended position corresponding to the target content level in the target scene, wherein the position arrangement sequence of the target content with the same target content level follows the ordering result.

As the basic information of the user reflects the personalized recommendation requirement of the user, the target content is scored according to the basic information of the user, and the obtained scoring result can reflect the interest degree of the user on the target content. Further, the target content may be ranked from high to low according to the scoring result. In this embodiment, it is assumed that there are 6 recommended positions in the target scene, and the ranking result of 6 item targets according to the score from high to low is: high quality level a, high quality level b, high quality level c, high quality level d, guided payment level e, guided payment level f. The corresponding relation between the preset recommended position and the content level is 1 st, 3 rd and 5 th recommended high-quality level content, 2 nd and 4 th recommended guiding payment level and 6 th recommended content of any content level. Therefore, based on the sorting result and the corresponding relation between the preset recommended position and the content level, the final issuing result of the 6-item target content is shown in table 1:

TABLE 1

As can be seen from table 1, the order of the location of the target contents of the same target content level follows the sorting result. I.e. the positions of the 4 items of high quality level content are a, b, c, d from front to back in sequence, which accords with the sequencing result. The leading payment level e is arranged in front of the leading payment f, and also meets the sorting result.

In this embodiment, by making the position arrangement sequence of the target content of the same target content level follow the sorting result, not only can each target content level have content that can be issued to the target scene, but also each item of content can be arranged according to the interest degree of the user, which is helpful for realizing accurate recommendation according to the recommendation request of the user, improving the accuracy of the recommended content, and further improving the recommendation experience of the user.

In some possible implementations, subsequent sorting processes are not favored because the amount of recalled content data is still large. Therefore, after the target content is recalled, the content which is browsed by the user in the target content can be filtered according to the historical browsing record of the user, so that the content which is not browsed by the user and has potential interest is recommended to the user, the data quantity which needs to be processed in sorting is greatly reduced, and the content issuing efficiency is improved.

In some possible embodiments, the target content level may be weighted according to a preset rule, so as to adjust the number of target contents corresponding to the target content level according to the weight. Although the same target scene may be matched to a plurality of different content levels, the number of content requirements for the same target scene for different content levels is not the same. Such as in a lead new user scenario, although the scenario may be matched to a high quality level and a lead payment level, the new user obviously requires a higher quality level to guide the operation. Accordingly, different target content levels may be weighted according to preset rules. The higher the weight of the target content level, the greater the demand for the amount of content corresponding to the target content level in the target scene. The preset rules can be set according to the demands of websites or APP operators, can be set according to the historical data of users, and can be set according to other demands, and the specification is not limited.

In some possible implementations, the content recommendation needs of the user may change over time, so that the content items contained in the content pool also need to be updated. If the content items contained in the content pool are unchanged, the user has lost interest in the content that is not updated when the user's content recommendation needs change. In this case, the content that is not updated is recommended to the user, and the recommendation effect of the content is reduced.

Specifically, performance indexes of various contents in a preset duration are obtained. The performance metrics may include: click rate, collection rate, favorites rate, forward rate, etc. And under the condition that the performance index of any content is lower than a preset index threshold value, the recommendation effect of any content in a preset time period is poor, and the user is interested in any content to a low degree. Thus, the arbitrary item of content can be updated based on the alternative recommended content.

In this embodiment, the content contained in the content pool is updated at regular time by the performance indexes of each content within the preset duration, so as to help ensure that the target content acquired from the content pool meets the content recommendation request of the user, and promote the recommendation effect of the target content.

Exemplary apparatus

In an exemplary embodiment of the present disclosure, a content recommendation apparatus is also provided.

Referring to fig. 5, fig. 5 is a block diagram of a content recommendation device according to an exemplary embodiment.

As shown in fig. 5, the content recommendation device 500 may include: acquisition unit 501, determination unit 502, and issuing unit 503. Wherein:

the obtaining unit 501 is configured to obtain a content recommendation request initiated by a user in a target scene, where the content recommendation request includes information for characterizing the target scene.

The determining unit 502 is configured to determine, according to a preset matching relationship between a scene and a content level, a target content level that matches the target scene represented by the content recommendation request, and obtain, according to the target content level, target content from a content pool, where the content pool includes a plurality of pieces of content for recommendation to the user, and each piece of content corresponds to at least two content levels.

The issuing unit 503 is configured to issue the target content to a recommended position corresponding to the target content level in the target scene based on a preset correspondence between the recommended position and the content level.

Optionally, the apparatus further includes:

a basic information obtaining unit 504, configured to obtain basic information of the user, where the basic information includes at least one of the following: the ID of the user, the history browsing record of the user and the history favorites of the user;

the determining unit 502 is specifically configured to determine, according to the target content level, first content corresponding to the target content level; and recalling the target content from the first content according to the basic information.

Optionally, the recall of the target content from the first content according to the basic information includes: generating a target index according to the target content level and the basic information; recall the target content from the first content based on the target index.

Optionally, the apparatus further includes:

a scoring unit 505, configured to score the target content based on the basic information, and rank the target content based on a scoring result;

the issuing unit 503 is specifically configured to issue the target content to a recommended position corresponding to the target content level in the target scene based on a ranking result and a correspondence between the preset recommended position and the content level, where a position arrangement order of target contents of the same target content level follows the ranking result.

Optionally, the apparatus further includes:

and a filtering unit 506, configured to filter, according to the historical browsing record of the user, content that has been browsed by the user in the target content.

Optionally, the apparatus further includes:

a weighting unit 507, configured to weight the target content level according to a preset rule; and adjusting the quantity of the target content corresponding to the target content level according to the weight.

Optionally, the apparatus further includes:

an updating unit 508, configured to obtain performance indexes of each content in the content pool within a preset duration; and updating the content with the performance index lower than a preset index threshold value based on the alternative recommended content.

The specific details of the above-mentioned respective modules of the content recommendation device 500 have been described in detail in the foregoing description of the content recommendation method flow, and thus are not described herein.

It should be noted that although several modules or units of the content recommendation device 500 are mentioned in the above detailed description, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.

Exemplary Medium

In an exemplary embodiment of the present disclosure, a computer-readable storage medium having stored thereon a program product capable of implementing the method described above in the present specification is also provided. In some possible embodiments, the various aspects of the present disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the disclosure as described in the "exemplary methods" section of this specification, when the program product is run on the terminal device.

Referring to fig. 6, fig. 6 is a schematic diagram of a readable storage medium corresponding to a content recommendation method according to an exemplary embodiment.

Referring to fig. 6, a readable storage medium 600 for implementing the above-described method according to an embodiment of the present disclosure is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the readable storage medium of the present disclosure is not limited thereto, and in the present disclosure, the readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The computer readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

Exemplary electronic device

In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the content recommendation method is also provided.

Referring to fig. 7, fig. 7 is a schematic diagram of an electronic device capable of implementing the method according to an exemplary embodiment.

An electronic device 700 according to such an embodiment of the present disclosure is described below with reference to fig. 7. The electronic device 700 shown in fig. 7 is merely an example and should not be construed to limit the functionality and scope of use of embodiments of the present disclosure in any way.

As shown in fig. 7, the electronic device 700 is embodied in the form of a general purpose computing device. Components of electronic device 700 may include, but are not limited to: the at least one processing unit 701, the at least one memory unit 702, and a bus 703 that connects the different system components (including the memory unit 702 and the processing unit 701).

Wherein the storage unit stores program code executable by the processing unit 701 such that the processing unit 701 performs the steps of the various embodiments described herein above.

The storage unit 702 may include readable media in the form of volatile storage units, such as Random Access Memory (RAM) 7021 and/or cache memory 7022, and may further include Read Only Memory (ROM) 7023.

The storage unit 702 may also include a program/usage tool 7024 having a set (at least one) of program modules 7025, such program modules 7025 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which may include the reality of a network environment, or some combination thereof.

The bus 703 may be one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 700 may also communicate with one or more external devices 704 (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 700, and/or any device (e.g., router, modem, etc.) that enables the electronic device 700 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 705. Also, the electronic device 700 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through the network adapter 706. As shown, the network adapter 706 communicates with other modules of the electronic device 700 via the bus 703. It should be appreciated that although not shown in fig. 7, other hardware and/or software modules may be used in connection with electronic device 700, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.

From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, a terminal device, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It should be noted that although several units/modules or sub-units/modules of the apparatus are mentioned in the above detailed description, this division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more units/modules described above may be embodied in one unit/module in accordance with embodiments of the present disclosure. Conversely, the features and functions of one unit/module described above may be further divided into ones that are embodied by a plurality of units/modules.

Furthermore, although the operations of the methods of the present disclosure are depicted in the drawings in a particular order, this is not required to or suggested that these operations must be performed in this particular order or that all of the illustrated operations must be performed in order to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform.

While the spirit and principles of the present disclosure have been described with reference to several particular embodiments, it is to be understood that this disclosure is not limited to the particular embodiments disclosed nor does it imply that features in these aspects are not to be combined to benefit from this division, which is done for convenience of description only. The disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims (10)

1. A content recommendation method, the method comprising:

acquiring a content recommendation request initiated by a user in a target scene, wherein the content recommendation request comprises information for representing the target scene;

determining a target content level matched with the target scene represented by the content recommendation request according to a preset matching relation between the scene and the content level, and acquiring target content from a content pool according to the target content level, wherein the content pool comprises a plurality of items of content for recommendation to the user, and each item of content corresponds to at least two content levels;

and based on the corresponding relation between the preset recommended position and the content level, issuing the target content to the recommended position corresponding to the target content level in the target scene.

2. The method of claim 1, wherein the step of determining the position of the substrate comprises,

further comprises: acquiring basic information of the user, wherein the basic information comprises at least one of the following steps: the ID of the user, the history browsing record of the user and the history favorites of the user;

the obtaining the target content from the content pool according to the target content level comprises the following steps: determining first content corresponding to the target content level according to the target content level; and recalling the target content from the first content according to the basic information.

3. The method of claim 2, wherein recalling the target content from the first content according to the base information comprises:

generating a target index according to the target content level and the basic information;

recall the target content from the first content based on the target index.

4. The method of claim 2, wherein the step of determining the position of the substrate comprises,

further comprises: scoring the target content based on the basic information, and sorting the target content based on a scoring result;

the issuing the target content to the recommended position corresponding to the target content level in the target scene includes: and based on the sorting result and the corresponding relation between the preset recommended position and the content level, the target content is issued to the recommended position corresponding to the target content level in the target scene, wherein the position arrangement sequence of the target content with the same target content level follows the sorting result.

5. The method as recited in claim 1, further comprising:

and filtering the browsed contents of the user in the target contents according to the historical browsing record of the user.

6. The method as recited in claim 1, further comprising:

weighting the target content level according to a preset rule;

and adjusting the quantity of the target content corresponding to the target content level according to the weight.

7. The method as recited in claim 1, further comprising:

acquiring performance indexes of each content in the content pool within a preset duration;

and updating the content with the performance index lower than a preset index threshold value based on the alternative recommended content.

8. A content recommendation device, characterized in that the device comprises:

the system comprises an acquisition unit, a storage unit and a processing unit, wherein the acquisition unit is used for acquiring a content recommendation request initiated by a user in a target scene, and the content recommendation request comprises information for representing the target scene;

the determining unit is used for determining a target content level matched with the target scene represented by the content recommendation request according to a preset matching relation between the scene and the content level, and acquiring target content from a content pool according to the target content level, wherein the content pool comprises a plurality of items of content for recommendation to the user, and each item of content corresponds to at least two content levels;

and the issuing unit is used for issuing the target content to the recommended position corresponding to the target content level in the target scene based on the corresponding relation between the preset recommended position and the content level.

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1-7 when executing the computer program.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any of claims 1-7.