CN114780830A - Content recommendation method, device, electronic device and storage medium - Google Patents

Abstract

The application provides a content recommendation method and device, electronic equipment and a storage medium, and relates to the technical field of cloud computing and internet big data. The method comprises the following steps: acquiring characteristic information of a user, and determining the role type of the user according to the characteristic information; and determining first recommended content recommended to the user based on a data recall mode corresponding to the role type. According to the content recommendation method, the data recall mode is determined according to the role type of the user for content recommendation, so that the matching degree of the recommended content and the user is higher, and the recommendation effect is improved.

Description

Content recommendation method, device, electronic device and storage medium

technical field

The present application relates to the technical fields of cloud computing and Internet big data, and in particular, to a content recommendation method, device, electronic device and storage medium.

Background technique

With the development of network technology and mobile communication technology, people are more and more accustomed to obtaining various information through the Internet to meet the needs of daily life. As a result, many content publishing platforms have emerged.

The content publishing platform recommends to users by acquiring information that users may need. At present, the general content publishing platform mainly pushes content through the user's historical operation behavior. However, for the knowledge content platform, there are few historical operation behaviors of users that can be obtained, so that the content recommended to users is not highly matched with the user, which affects the effect of content recommendation.

SUMMARY OF THE INVENTION

The present application provides a content recommendation method, device, electronic device, and storage medium, so as to improve the matching degree between the recommended content and the user, thereby improving the recommendation effect.

On the one hand, the present application provides a content recommendation method, including:

Obtain the user's characteristic information, and determine the user's role type according to the characteristic information;

Based on the data recall method corresponding to the role type, the first recommended content to be recommended to the user is determined.

Optionally, the characteristic information includes the content quantity of the historical operation content in the first time range, and the role type of the user is determined according to the characteristic information, including:

If the quantity of content exceeds the preset quantity threshold, the user is determined as a user of the first role type.

Optionally, based on the data recall method corresponding to the role type, determine the first recommended content recommended to the user, including:

If the user is a user of the first role type, the first recommended content to be recommended to the user is determined based on the historical operation content in the first time range.

Optionally, determining the first recommended content recommended to the user based on the historical operation content in the first time range, including:

determining the content attribute of the historical operation content in the first time range, and the content attribute includes user interests or user needs;

Based on the content attribute, the first recommended content to be recommended to the user is determined.

Optionally, determining the content attribute of the historical operation content of the first time range, including:

If the historical operation content of the first time range satisfies the preset condition, the content attribute is determined to be the user's interest;

The preset conditions include at least one of the following:

The historical operation content of the first time range is the user's subscription content;

The similarity between the historical operation content of the first time range and the user's historical operation content of the second time range exceeds a first similarity threshold; wherein the second time range is determined based on the first time range;

The correlation between the historical operation content in the first time range and the role type corresponding to the user does not exceed the correlation threshold.

Optionally, based on the content attribute, determine the first recommended content recommended to the user, including:

If the content attribute is the user's interest, determining the first recommended content to be recommended to the user based on the user's historical operation content in the third time range;

If the content attribute is the user's requirement, determining the first recommended content to be recommended to the user based on the user's historical operation content in the fourth time range;

Wherein, the third time range is greater than the fourth time range.

Optionally, determine the role type of the user according to the feature information, including:

If the quantity of the content does not exceed the preset quantity threshold, the user is determined as a user of the second role type.

Optionally, based on the data recall method corresponding to the role type, determine the first recommended content recommended to the user, including:

If the user is a user of the second role type, the first recommended content to be recommended to the user is determined based on the user tag of the user.

Optionally, the user label has a corresponding relationship with the knowledge domain to which the user belongs; or the user label includes a user label corresponding to a lower knowledge domain of the knowledge domain to which the user belongs.

Optionally, based on the data recall method corresponding to the role type, determine the first recommended content recommended to the user, including:

Based on the data recall method corresponding to the role type, determine the basic data to be recommended corresponding to the role type;

The multiple contents in the basic data to be recommended are sorted according to at least one of the data category or the data recall priority, and the first recommended content to be recommended to the user is determined from the multiple contents according to the sorting result.

Optionally, the method further includes:

Determine the second recommended content recommended to the user based on the relevant information of the user;

The relevant information includes at least one of the following:

The user's subscription content, the user's similar user's historical operation content, and the user's corresponding industry information; the similar user is a user whose similarity with the user exceeds the second similarity threshold.

On the other hand, the present application provides a content recommendation device, comprising:

The type determination module is used to obtain the characteristic information of the user, and determine the role type of the user according to the characteristic information;

The content recommendation module is configured to determine the first recommended content to be recommended to the user based on the data recall method corresponding to the role type.

On the other hand, the present application provides an electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method in any of the embodiments of the present application.

In another aspect, the present application provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method in any of the embodiments of the present application.

The present application provides a content recommendation method, device, electronic device, and storage medium. The user's role type is determined according to feature information, and the content recommended to the user is determined based on the data recall method corresponding to the role type: for users of the first role type , due to the large number of historical operation content, the recommended content can be determined according to the historical operation content; for users of the second role type, due to the small number of historical operation content, the recommended content is determined according to the user tag, which can avoid the need for historical operation content. In this case, the recommendation effect is poor, so that the matching degree between the recommended content and the user can be improved. Further, when the recommended content is determined according to the historical operation content, since the user's interest is stable for a long time and the user's demand changes rapidly, if the content attribute is the user's interest, the recommended content is determined according to the user's long-term historical operation content; If the content attribute is the user's requirement, the recommended content is determined according to the user's short-term historical operation content. In this way, the matching degree between the recommended content and the user can be further improved, thereby improving the recommendation effect.

It should be understood that the content described in this section is not intended to identify key or critical features of the embodiments of the application, nor is it intended to limit the scope of the application. Other features of the present application will become readily understood from the following description.

Description of drawings

The accompanying drawings are used for better understanding of the present solution, and do not constitute a limitation to the present application. in:

FIG. 1 is a schematic diagram of a system architecture of a content recommendation method in an embodiment of the present application;

FIG. 2 is a flowchart of a content recommendation method in an embodiment of the present application;

3 is a flowchart of a content recommendation method in an embodiment of the present application;

4 is a schematic diagram of a content recommendation method in an embodiment of the present application;

FIG. 5 is a schematic diagram of a content recommendation apparatus in an embodiment of the present application;

FIG. 6 is a block diagram of an electronic device used to implement an embodiment of the present application.

Detailed ways

Exemplary embodiments of the present application are described below with reference to the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.

In order to more clearly demonstrate the content recommendation method provided in the embodiment of the present application, an application scenario of the content recommendation method provided in the embodiment of the present application is first introduced.

The content recommendation method provided in this application can be applied to the content of various content publishing platforms, such as news information content publishing platforms, professional knowledge content publishing platforms, e-commerce platforms, social media platforms, and platforms within the enterprise for employees of various departments to obtain corresponding information. Recommended. The feature information of the platform user can be obtained through the server of the content publishing platform, the user's role type can be determined according to the feature information, and the recommended content can be determined and recommended to the user based on the data recall method corresponding to the role type.

1 is a schematic diagram of a system architecture of a content recommendation method in an embodiment of the application; as shown in FIG. 1 , a server of a content publishing platform acquires feature information of platform users, determines the role type of each user according to the feature information of each user, and determines the role type of each user based on The data recall method corresponding to each role type determines the content recommended to the corresponding user, and sends it to the user terminal of each user.

An embodiment of the present application provides a content recommendation method. FIG. 2 is a flowchart of a content recommendation method according to an embodiment of the present application. The method can be applied to a content recommendation apparatus, and the apparatus can be deployed in a server or other processing device. In some possible implementations, the method may also be implemented by the processor invoking computer-readable instructions stored in the memory. As shown in Figure 2, including:

In step S201, characteristic information of the user is acquired, and the role type of the user is determined according to the characteristic information.

This embodiment of the present application introduces a server as an execution subject. The server obtains the user's feature information, where the feature information may be information that represents the user's unique attributes, including but not limited to the user's basic information, occupation category, job position characteristics, information related to the user's historical operation content, and the like.

The specific method of acquiring the user's feature information may be receiving the feature information sent by the user terminal, or may be the user's feature information queried from a preset database according to the user's identity, or may be statistics based on the user's historical operation behavior. The characteristic information obtained by the analysis and the acquisition method of the characteristic information may be determined according to the specific content of the characteristic information, which is not limited in this application.

A specific implementation manner of determining the user's role type according to the feature information may include: the server establishes an association relationship between the feature information and the role type in advance, and can obtain the user's role type according to the feature information and the association relationship. In addition, the server can also pre-configure multiple role types, and after acquiring the user's feature information, the feature information is matched and calculated with multiple role types respectively, and the character type corresponding to the feature information is determined according to the matching result.

The role type may be a type that is pre-divided according to the characteristic information of multiple users. For example, users can be divided into different role types such as R&D, sales, products, and operations according to their job characteristics.

Step S202: Determine the first recommended content to be recommended to the user based on the data recall method corresponding to the role type.

The relationship between the role type and the data recall method is pre-configured, and after the user's role type is determined, the corresponding data recall method can be obtained according to the role type and the relationship. The recall basis is obtained according to the data recall method, and the data similar to the recall basis is recalled as the first recommended content, or the data similar to the recall basis is screened to obtain the first recommended content and sent to the user terminal.

Among them, the data recall may be to recall data similar to the existing data in the massive data according to the characteristics of the existing data, and recommend these similar data to the user. The data recall method in the embodiment of the present application may be a specific implementation manner of obtaining the recall basis. Different data recall methods can obtain different recall basis, and the recall data is recommended to users according to different recall basis.

In the related art, in a scenario where the recommended content is item information, items of interest to the user are determined based on the user's historical behavior on the items, and the recommendation is performed. However, this algorithm is not applicable in the recommendation scenarios of knowledge content platforms such as documents and videos. First, for users in the knowledge content platform, for example, users related to technology research and development, their historical behaviors may be very small, so the co-occurrence matrix of users and items is very sparse, and subsequent algorithm steps cannot be performed. Secondly, the main purpose of the users who use the knowledge content platform is to consult some product materials and cases of application fields, so it is based on needs. Interests are relatively stable and change slowly, while knowledge content users' demands for data change rapidly, and the accuracy of direct content recommendation based on rapidly changing user behavior is low. Another major class of recommendation algorithms are deep learning algorithms based on user behavior sequences. This type of algorithm obtains a fixed-dimensional vector by embedding the items in the user's historical click sequence into a fixed-dimensional vector space, and then splices it together with other features as a feature, and inputs it into the neural network to optimize the objective function. However, this type of algorithm is also based on user interests and requires more user click behaviors. For knowledge content platforms, the scene is mainly biased towards the needs of users, and users have few click behaviors, which cannot provide enough training data for neural networks. training.

The content recommendation method provided by this application determines the user's role type according to the feature information, and determines the content recommended to the user based on the data recall method corresponding to the role type, which is suitable for a variety of different types of content publishing platforms. The matching degree of users is higher, and the recommendation effect is improved.

In a possible implementation manner, the feature information in step S201 includes the content quantity of the historical operation content in the first time range, and the role type of the user is determined according to the feature information, including:

If the quantity of content exceeds the preset quantity threshold, the user is determined as a user of the first role type.

In practical applications, the user's role type may be determined according to the amount of content in the user's historical operation content in the first time range, and if the amount of content exceeds a preset number threshold, it is a user of the first role type.

The historical operation content may be content corresponding to the user's historical operation behavior, and the operation behavior may include click, search, and the like. The first time range may be a time period before the current time, for example, 1 month, 2 months, etc. before the current time. The quantity of content may be the sum of the quantity of content clicked and searched by the user, or the quantity of content may be determined solely according to the quantity of content clicked or the quantity of content searched for. For example, if the user clicked on 10 articles and searched for 20 contents in 1 month before the current time, the number of contents would be 30; or if the user clicked on 25 articles in 2 months before the current time, the number of contents would be 25. The first time range and quantity threshold can be configured according to specific needs.

In an example, for the knowledge content platform, if a user in a product and sales related role has rich historical operation behaviors such as searching and clicking, the user in the product and sales related role is determined as a user of the first role type.

It should be noted that, in addition to users in product and sales related roles, users of the first role type may also be any users with a large number of historical operation contents, which is not limited in this application.

In the technical solution of the present application, after the role type of the user is determined, different data recall methods are used for content recommendation for different role types, as shown in the following embodiments:

In a possible implementation, in step S202, based on the data recall method corresponding to the role type, determine the first recommended content to be recommended to the user, including:

If the user is a user of the first role type, the first recommended content to be recommended to the user is determined based on the historical operation content in the first time range.

In practical applications, if the user is determined to be a user of the first role type according to the feature information, since the number of historical operation contents of the user of this role type is large, the first recommended content is determined according to the historical operation contents. Optionally, the recall basis is obtained according to the historical operation content in the first time range, and after the content similar to the recall basis is obtained, the content similar to the recall basis can be used as the first recommended content; Select a part of the content, and recommend it to the user as the first recommended content.

Wherein, based on the historical operation content of the first time range, the specific implementation of determining the first recommended content is shown in the following embodiments:

In a possible implementation manner, the first recommended content to be recommended to the user is determined based on the historical operation content of the first time range, including:

determining the content attribute of the historical operation content in the first time range, and the content attribute includes user interests or user needs;

Based on the content attribute, the first recommended content to be recommended to the user is determined.

In practical applications, if it is determined that the user is a user of the first role type, the content attribute of the historical operation content in the first time range is determined, wherein the content attribute is an attribute representing the relationship between the historical operation content and the user, and the historical operation content is an attribute representing the relationship between the historical operation content and the user. The relationship between the operation content and the user may be the user's attention level or frequency of the historical operation content, etc., and the content attributes include user interests and user needs. After judging whether the historical operation content belongs to the user's interest or the user's demand, different methods are adopted to determine the first recommended content according to different content attributes.

Wherein, for how to determine the content attribute of the historical operation content, see the following embodiments:

In a possible implementation manner, the content attribute of the historical operation content of the first time range is determined, including:

If the historical operation content of the first time range satisfies the preset condition, the content attribute is determined to be the user's interest;

The preset conditions include at least one of the following:

The historical operation content of the first time range is the user's subscription content;

The similarity between the historical operation content of the first time range and the user's historical operation content of the second time range exceeds a first similarity threshold; wherein the second time range is determined based on the first time range;

The correlation between the historical operation content in the first time range and the role type corresponding to the user does not exceed the correlation threshold.

In practical applications, it is determined whether the content attribute is user interest or user demand by judging whether the historical operation content in the first time range satisfies the preset conditions. Content belongs to user needs.

Among them, the historical operation content of the first time range is the user's subscription content. For example, the article clicked by the user belongs to the column subscribed by the user, and the column subscribed by the user includes the content of the column that the user has long-term attention needs, such as user attention and user collection. Therefore, It is more biased towards user interests.

The similarity between the historical operation content of the first time range and the user's historical operation content of the second time range exceeds the first similarity threshold. For example, for the historical operation content, in a long time interval, has the user clicked similar content. If the user has clicked on similar content in a long period of time, this stable click behavior can indicate that the historical operation content belongs to the user's interest. Wherein, the second time range is determined based on the first time range, and may be determined based on the click time of the historical click content within the first time range.

The correlation between the historical operation content in the first time range and the role type corresponding to the user does not exceed the correlation threshold. For example, if the user is a user in a product-related role, the historical operation content in the first time range belongs to the organizational culture category or is not related to the product. the public content, the historical operation content belongs to the user's interest.

If the content attributes of the historical operation content in the first time range are different, the methods for determining the first recommended content are different, as shown in the following embodiments:

In a possible implementation manner, the first recommended content to be recommended to the user is determined based on the content attribute, including:

If the content attribute is the user's interest, determining the first recommended content to be recommended to the user based on the user's historical operation content in the third time range;

If the content attribute is the user's requirement, determining the first recommended content to be recommended to the user based on the user's historical operation content in the fourth time range;

Wherein, the third time range is greater than the fourth time range.

In practical applications, after the content attribute is determined, for the historical operation content whose content attribute is the user's demand, since the user's demand changes rapidly, when determining the first recommended content, select the time range that is shorter from the current time. The content of the historical operation is used as the basis for recall. For example, you can choose the content clicked in the last day or two as the basis for the recall. As for the historical operation content whose content attribute is the user's interest, the historical operation content with a longer time range from the current time is selected as the recall basis. After determining the recall basis, recall similar content and add it to the recommended candidate list, and select the content in the candidate list as the first recommended content.

In this embodiment of the present application, the user's historical operation content is further subdivided into user needs and user interests. When determining the recall basis, due to the rapid changes in user needs, only the recent historical operation content is retained as the recall basis; while the user interest is more stable for a long time and will be retained and tracked for a long time as the recall basis. By distinguishing user needs and user interests, it is possible to retain and track user interests for a long time, and at the same time quickly provide feedback on changes in user needs, so as to recommend content with a higher degree of matching to users.

In a possible implementation manner, in step S201, the role type of the user is determined according to the feature information, including:

If the quantity of the content does not exceed the preset quantity threshold, the user is determined as a user of the second role type.

In practical applications, the user's role type can be determined according to the amount of content in the user's historical operation content in the first time range, and if the amount of content does not exceed a preset number threshold, it is a user of the second role type.

In an example, for the knowledge content platform, users related to technology research and development have few records of search and click behaviors, and users in the role related to technology research and development are determined as users of the second role type.

It should be noted that, in addition to the users in the related role of technology research and development, the users of the second role type may also be any users with a small number of historical operation contents, which is not limited in this application.

Wherein, for users of the second role type, the method for determining the first recommended content is shown in the following embodiments:

In a possible implementation manner, in step S202, the first recommended content to be recommended to the user is determined based on the data recall method corresponding to the role type, including:

If the user is a user of the second role type, the first recommended content to be recommended to the user is determined based on the user tag of the user.

In practical applications, if the user is a user of the second role type, due to the small amount of historical operation content in the first time range, if the recommendation is made based on the historical operation content in the first time range, it may not get enough recall Accordingly, the first recommended content is determined based on the user tag. Optionally, according to the keyword in the user tag, content matching the user tag is queried, and all or part of the content is selected as the first recommended content.

In one example, for R&D-related users with few click behaviors, a recall method based on user tags will be mainly relied on. A corresponding user tag is set for the user in advance, and the user tag can be a product tag of a product that the user participates in research and development, whereby the user is associated with the product and recommends product-related content for the user.

Among them, how to configure the user label, see the following examples:

In a possible implementation manner, the user tag of the user has a corresponding relationship with the knowledge domain to which the user belongs.

In practical applications, user tags can be configured according to the knowledge domain to which the user belongs. The knowledge domain may be a domain related to the role type of the user, for example, may be the department to which the user's job position belongs. A corresponding relationship is established between the user tag and the knowledge domain to which the user belongs, and content recommendation is performed based on the user label, which may be content recommendation for the user based on the knowledge domain.

In an example, user labels are configured according to the department to which the user's job position belongs, and users in the same department are configured with the same user label. This processing method can make user tags radiate more users and improve the efficiency of tag configuration.

In a possible implementation manner, the user tag of the user includes a user tag corresponding to a subordinate knowledge field of the knowledge field to which the user belongs.

In practical applications, the user tag may include, in addition to the user tag corresponding to the knowledge field to which the user belongs, a user tag corresponding to a subordinate knowledge field of the knowledge field to which the user belongs. For example, the subordinate knowledge domain of the knowledge domain may be the subordinate department of the current department, and the user label of the superior department includes the user label of the subordinate department. Through such nesting processing, user tags will radiate to more users, one user can correspond to multiple user tags, and content recommendation based on multiple user tags can increase the matching degree between the recommended content and the user.

In a possible implementation manner, in step S202, the first recommended content to be recommended to the user is determined based on the data recall method corresponding to the role type, including:

Based on the data recall method corresponding to the role type, determine the basic data to be recommended corresponding to the role type;

The multiple contents in the basic data to be recommended are sorted according to at least one of the data category or the data recall priority, and the first recommended content to be recommended to the user is determined from the multiple contents according to the sorting result.

In practical applications, the recall basis is obtained based on the data recall method corresponding to the role type, and the content similar to the recall basis is obtained as the basic data to be recommended. The basic data to be recommended can include multiple categories of content. The similarity of each content is divided differently, it may be divided according to different recall methods, or it may be divided according to other features of each content, which is not limited in this application.

Among them, the data recall priority may be the priority corresponding to each recall method. It can be understood that the priority of the recall basis obtained by different recall methods is different, and accordingly, the priority of the content similar to the recall basis is also different. After sorting the multiple contents in the basic data to be recommended, the first recommended content is determined among the multiple contents according to the sorting result, so that the content more in line with the user's needs can be recommended, and the effect of the content recommendation can be improved.

In a possible implementation, the method further includes:

Determine the second recommended content recommended to the user based on the relevant information of the user;

The relevant information includes at least one of the following:

The user's subscription content, the user's similar user's historical operation content, and the user's corresponding industry information; the similar user is a user whose similarity with the user exceeds the second similarity threshold.

In practical applications, in addition to determining the first recommended content to be recommended to the user based on the data recall method corresponding to the role type, the second recommended content can also be determined according to the relevant information of the user, so as to enrich the recommended content and meet the diverse needs of users. demand. Specifically, content similar to the user's subscription content, historical operation content of the user similar to the user, and industry information corresponding to the user are acquired, and at least one of them is recommended to the user as the second recommended content. Among them, the industry information may include: the latest hot information of the industry that has undergone deep processing; the latest headlines including the development trend information of the industry; the latest intelligence information of the industry, and the like.

FIG. 3 is a flowchart of a content recommendation method in an embodiment of the present application. As shown in Figure 3, the method includes:

Step S301, acquiring the content quantity of the historical operation content of the user in the first time range.

Step S302, judging whether the quantity of content exceeds a preset quantity threshold.

Step S303, if the quantity of the content exceeds a preset quantity threshold, the user is determined as a user of the first role type.

Step S304, if the quantity of the content does not exceed a preset quantity threshold, the user is determined as a user of the second role type.

Step S305, if the user is a user of the first role type, determine whether the content attribute of the historical operation content in the first time range is a user requirement or a user interest.

Step S306, if the content attribute is the user's interest, determine the first recommended content to be recommended to the user based on the historical operation content of the user in the third time range.

Step S307, if the content attribute is the user's requirement, determine the first recommended content to be recommended to the user based on the historical operation content of the user in the fourth time range. The third time frame is greater than the fourth time frame.

Step S308, if the user is a user of the second role type, determine the first recommended content to be recommended to the user based on the user tag of the user.

In the content recommendation method provided by the present application, the role type of the user is determined according to the content quantity of the historical operation content in the first time range, and different data recall methods are used for different role types to determine the content recommended to the user, which can make the recommended content The matching degree with users is higher, and the recommendation effect is improved.

FIG. 4 is a schematic diagram of a content recommendation method in an embodiment of the present application. In the embodiment of the present application, the content recommendation method is applied to the knowledge management platform of enterprises and institutions. The knowledge management platform stores a large number of product information, product dynamics, sales cases, organizational culture and other content. In order to allow employees and users to obtain the information they need and are interested in, it provides a content (which can be a feed stream) recommendation function. . At the same time, because users come from different positions such as R&D, sales, products, and operations, they have different needs and access methods. Sales-related users have rich historical behavior records such as searches and clicks. However, because sales-related users, such as pre-sales architects, solution architects, etc., will change the fields and products involved, their demand for content is changing rapidly. For development-related users, there are few historical behavior records such as searches and clicks. However, because these users are responsible for the research and development of certain products, they are associated with these products, and accurate product labels are configured for such users.

As shown in Figure 4, a database of data to be recommended is constructed in advance, and the database includes historical click content of multiple users, user subscription information, user identity information, product information, industry information, industry headlines, industry intelligence and other data. Determine the role type of the user according to the number of the user's historical click content. For sales-related users who have more historical behavior records, classify the historical click records, that is, determine whether the content attribute of the historical click content is user demand or user interest, determine the data recall method according to the content attribute, and recall from the database according to the historical click. , if the content attribute is user interest, the long-term historical click content is used as the recall basis to recall similar content from the database; if the content attribute is user demand, the short-term historical click content is used as the recall basis to recall similar content from the database . For development-related users with fewer historical behavior records, user tags are generated, and similar content is recalled from the database according to the user tags. In addition, whether it is a user related to development or a user related to sales, data can be recalled from the database based on similar users, recall based on user subscription numbers, recall based on the latest popular data, recall based on the latest headlines, and recall based on the latest intelligence. The data recalled in various ways is used as the basic data to be recommended, and the basic data to be recommended is sorted and rearranged according to the document category, or sorted according to the recall priority, and the content is recommended according to the sorting result. When sorting and rearranging, for sales-related users, due to the large number of historical behavior records, the content recalled according to the user's historical behavior will be ranked at the top. For development-related users, due to the lack of historical click behavior, but with more user tags, in the sorting and rearrangement stage, the content recalled based on user tags is ranked in the top position, so that the content is recommended. The recommended content has a higher matching degree with the user, and the recommendation effect is better.

FIG. 5 is a schematic diagram of a content recommendation apparatus according to an embodiment of the present application. As shown in FIG. 5, the content recommendation apparatus may include:

Type determination module 501, used for acquiring the characteristic information of the user, and determining the role type of the user according to the characteristic information;

The content recommendation module 502 is configured to determine the first recommended content to be recommended to the user based on the data recall mode corresponding to the role type.

The content recommendation device provided by the present application determines the user's role type according to the feature information, and determines the recommended content to the user based on the data recall method corresponding to the role type, which can make the recommended content more closely match the user and improve the recommendation effect.

In a possible implementation manner, the feature information includes the content quantity of the historical operation content in the first time range, and the type determination module 501 includes a type determination unit for:

If the quantity of content exceeds the preset quantity threshold, the user is determined as a user of the first role type.

In a possible implementation manner, the content recommendation module 502 is used for:

If the user is a user of the first role type, the first recommended content to be recommended to the user is determined based on the historical operation content in the first time range.

In a possible implementation manner, the content recommendation module 502 includes an attribute determination unit and a content recommendation unit;

an attribute determining unit, configured to determine a content attribute of the historical operation content of the first time range, where the content attribute includes user interests or user needs;

A content recommendation unit, configured to determine the first recommended content to be recommended to the user based on the content attribute.

In one possible implementation, the attribute determines the unit, specifically for:

If the historical operation content of the first time range satisfies the preset condition, the content attribute is determined to be the user's interest;

The preset conditions include at least one of the following:

The historical operation content of the first time range is the user's subscription content;

The similarity between the historical operation content of the first time range and the user's historical operation content of the second time range exceeds a first similarity threshold; wherein the second time range is determined based on the first time range;

The correlation between the historical operation content in the first time range and the role type corresponding to the user does not exceed the correlation threshold.

In a possible implementation manner, the content recommendation unit is specifically used for:

If the content attribute is the user's interest, determining the first recommended content to be recommended to the user based on the user's historical operation content in the third time range;

If the content attribute is the user's requirement, determining the first recommended content to be recommended to the user based on the user's historical operation content in the fourth time range;

Wherein, the third time range is greater than the fourth time range.

In one possible implementation, a type determination unit for:

If the quantity of the content does not exceed the preset quantity threshold, the user is determined as a user of the second role type.

In a possible implementation manner, the content recommendation module 502 is used for:

If the user is a user of the second role type, the first recommended content to be recommended to the user is determined based on the user tag of the user.

In a possible implementation manner, the user tag has a corresponding relationship with the knowledge domain to which the user belongs; or

The user tag includes the user tag corresponding to the lower knowledge field of the knowledge field to which the user belongs.

In a possible implementation manner, the content recommendation module 502 is used for:

Based on the data recall method corresponding to the role type, determine the basic data to be recommended corresponding to the role type;

The multiple contents in the basic data to be recommended are sorted according to at least one of the data category or the data recall priority, and the first recommended content to be recommended to the user is determined from the multiple contents according to the sorting result.

In a possible implementation manner, the content recommendation module 502 is further configured to:

Determine the second recommended content recommended to the user based on the relevant information of the user;

The relevant information includes at least one of the following:

The user's subscription content, the user's similar user's historical operation content, and the user's corresponding industry information; the similar user is a user whose similarity with the user exceeds the second similarity threshold.

For the functions of each unit, module or sub-module in each apparatus in this embodiment of the present application, reference may be made to the corresponding description in the foregoing content recommendation method embodiment, and details are not described herein again.

According to another aspect of the present application, an electronic device is provided, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method in any of the embodiments of the present application.

According to another aspect of the present application, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method in any of the embodiments of the present application.

FIG. 6 is a block diagram of an electronic device used to implement an embodiment of the present application. As shown in FIG. 6 , the electronic device includes: a memory 610 and a processor 620 , and a computer program that can be executed on the processor 620 is stored in the memory 610 . When the processor 620 executes the computer program, the methods in the above-mentioned embodiments are implemented. The number of the memory 610 and the processor 620 may be one or more.

The electronic equipment also includes:

The communication interface 630 is used to communicate with external devices and perform data interactive transmission.

If the memory 610, the processor 620 and the communication interface 630 are independently implemented, the memory 610, the processor 620 and the communication interface 630 may be connected to each other through a bus and complete communication with each other. The bus may be an Industry Standard Architecture (Industry Standard Architecture, ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (Extended Industry Standard Architecture, EISA) bus or the like. The bus can be divided into address bus, data bus, control bus and so on. For ease of presentation, only one thick line is used in FIG. 6, but it does not mean that there is only one bus or one type of bus.

Optionally, in specific implementation, if the memory 610, the processor 620 and the communication interface 630 are integrated on one chip, the memory 610, the processor 620 and the communication interface 630 can communicate with each other through an internal interface.

The embodiments of the present application provide a computer-readable storage medium, which stores a computer program, and when the program is executed by a processor, implements the methods provided in the embodiments of the present application.

An embodiment of the present application further provides a chip, the chip includes a processor, and is configured to call and execute an instruction stored in the memory from a memory, so that a communication device with the chip installed executes the method provided by the embodiment of the present application.

An embodiment of the present application further provides a chip, including: an input interface, an output interface, a processor, and a memory, the input interface, the output interface, the processor, and the memory are connected through an internal connection path, and the processor is used to execute codes in the memory , when the code is executed, the processor is used to execute the method provided by the embodiment of the application.

It should be understood that the above-mentioned processor may be a central processing unit (Central Processing Unit, CPU), and may also be other general-purpose processors, digital signal processors (digital signal processing, DSP), application specific integrated circuits (application specific integrated circuits, ASIC), field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or any conventional processor or the like. It should be noted that the processor may be a processor supporting an advanced RISC machines (ARM) architecture.

Further, optionally, the above-mentioned memory may include read-only memory and random access memory, and may also include non-volatile random access memory. The memory may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Wherein, the non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (erasable PROM, EPROM), electrically erasable memory Except programmable read-only memory (electrically EPROM, EEPROM) or flash memory. Volatile memory may include random access memory (RAM), which acts as an external cache. By way of example and not limitation, many forms of RAM are available. For example, static RAM (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access Memory (double data date SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synchlink DRAM, SLDRAM) and direct memory bus random access memory (direct rambus RAM) , DR RAM).

In the above-mentioned embodiments, it may be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented in software, it can be implemented in whole or in part in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the present application result in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable device. Computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium.

In the description of this specification, description with reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples", etc., mean specific features described in connection with the embodiment or example , structure, material or feature is included in at least one embodiment or example of the present application. Furthermore, the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, those skilled in the art may combine and combine the different embodiments or examples described in this specification, as well as the features of the different embodiments or examples, without conflicting each other.

In addition, the terms "first" and "second" are only used for descriptive purposes, and should not be construed as indicating or implying relative importance or implying the number of indicated technical features. Thus, a feature delimited with "first", "second" may expressly or implicitly include at least one of that feature. In the description of the present application, "plurality" means two or more, unless otherwise expressly and specifically defined.

Any description of a process or method in the flowcharts or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing a specified logical function or step of the process . Also, the scope of the preferred embodiments of the present application includes alternative implementations in which the functions may be performed out of the order shown or discussed, including performing the functions substantially concurrently or in the reverse order depending upon the functions involved.

The logic and/or steps represented in flowcharts or otherwise described herein, for example, may be considered an ordered listing of executable instructions for implementing the logical functions, may be embodied in any computer-readable medium, For use with, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch instructions from and execute instructions from an instruction execution system, apparatus, or apparatus) or equipment.

It should be understood that various parts of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. All or part of the steps of the method in the above-mentioned embodiments can be completed by instructing the relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one of the steps of the method embodiment or its combination.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing module, or each unit may exist physically alone, or two or more units may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules. If the above-mentioned integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium. The storage medium may be a read-only memory, a magnetic disk or an optical disk, and the like.

The above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the technical field disclosed in the present application can easily think of various changes or Replacement, these should be covered within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (12)

1. A method for recommending content, the method comprising:

acquiring characteristic information of a user, and determining the role type of the user according to the characteristic information;

and determining first recommended content recommended to the user based on a data recall mode corresponding to the role type.

2. The method of claim 1, wherein the characteristic information includes a content amount of historical operation content in a first time range, and wherein determining the role type of the user according to the characteristic information includes:

and if the content quantity exceeds a preset quantity threshold value, determining the user as the user of the first character type.

3. The method according to claim 2, wherein the determining of the first recommended content recommended to the user based on the data recall manner corresponding to the role type includes:

and if the user is the user with the first role type, determining first recommended content recommended to the user based on the historical operation content in the first time range.

4. The method of claim 3, wherein the determining the first recommended content recommended to the user based on the historical operating content for the first time range comprises:

determining a content attribute of the historical operation content in the first time range, wherein the content attribute comprises user interest or user requirements;

and determining first recommended content recommended to the user based on the content attribute.

5. The method according to claim 4, wherein the determining the content attribute of the content of the historical operation in the first time range comprises:

if the historical operation content in the first time range meets a preset condition, determining the content attribute as user interest;

wherein the preset condition comprises at least one of the following:

the historical operation content in the first time range is the subscription content of the user;

the similarity between the historical operation content of the first time range and the historical operation content of the second time range of the user exceeds a first similarity threshold; wherein the second time range is determined based on the first time range;

and the correlation degree of the historical operation content in the first time range and the role type corresponding to the user does not exceed a correlation degree threshold value.

6. The method of claim 4, wherein the determining, based on the content attribute, the first recommended content to be recommended to the user comprises:

if the content attribute is the user interest, determining first recommended content recommended to the user based on historical operation content of the user in a third time range;

if the content attribute is the user requirement, determining first recommended content recommended to the user based on historical operation content of a fourth time range of the user;

wherein the third time range is greater than the fourth time range.

7. The method of claim 2, wherein the determining the role type of the user according to the feature information comprises:

and if the content quantity does not exceed a preset quantity threshold value, determining the user as the user of the second role type.

8. The method of claim 7, wherein the determining the first recommended content recommended to the user based on the data recall manner corresponding to the role type comprises:

and if the user is the user with the second role type, determining first recommended content recommended to the user based on the user label of the user.

9. The method according to claim 8, wherein the user tag has a correspondence with a knowledge domain to which the user belongs; or alternatively

The user tags include user tags corresponding to lower knowledge fields of the knowledge fields to which the user belongs.

10. The method of claim 1, wherein the method further comprises:

determining second recommended content recommended to the user based on the relevant information of the user;

wherein the relevant information comprises at least one of:

the subscription content of the user, the historical operation content of similar users of the user and the industry information corresponding to the user; the similar users are users whose similarity with the users exceeds a second similarity threshold.

11. An apparatus for recommending contents, the apparatus comprising:

the type determining module is used for acquiring the characteristic information of a user and determining the role type of the user according to the characteristic information;

and the content recommending module is used for determining first recommended content recommended to the user based on the data recalling mode corresponding to the role type.

12. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-10.

Images