CN111259248B

CN111259248B - Information resource recommendation method and device, readable storage medium and electronic equipment

Info

Publication number: CN111259248B
Application number: CN202010062394.9A
Authority: CN
Inventors: 徐利民; 陈宇飞; 范艳
Original assignee: Beijing Bo Xue Guang Yue Education Technology Co ltd
Current assignee: Beijing Bo Xue Guang Yue Education Technology Co ltd
Priority date: 2020-01-19
Filing date: 2020-01-19
Publication date: 2023-11-03
Anticipated expiration: 2040-01-19
Also published as: CN111259248A

Abstract

The application discloses a recommendation method and device of information resources, a readable storage medium and electronic equipment, and relates to the technical field of data processing. The information resource recommendation method comprises the following steps: obtaining a plurality of groups of information resource groups through various ways, wherein the information resource groups are obtained based on user behaviors, and the user behaviors reflect interests of users; according to the interests of the user, ordering a plurality of information resources in the information resource group from high to low to obtain an information resource sequence; selecting a first preset number of information resources arranged in the front in the information resource sequence to form a recommended information resource group; and transmitting a plurality of groups of recommended information resource groups corresponding to the plurality of groups of information resource groups.

Description

Information resource recommendation method and device, readable storage medium and electronic equipment

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for recommending information resources, a readable storage medium, and an electronic device.

Background

With the development of internet technology, the acquisition of information resources becomes more and more convenient. In such a case, the information resource provision product may recommend information resources of interest to the user, thereby enabling the user to obtain a corresponding sense of satisfaction. However, when the information resource acquired by the user is on a relatively limited topic for a long time, the ability of knowing different things and the opportunity of contacting different things are lost, so that an information cocoon room is formed unknowingly.

Therefore, how to avoid the formation of information cocoons by users is a urgent problem for information resource supply products.

Disclosure of Invention

In view of the above, embodiments of the present application are directed to providing a method and an apparatus for recommending information resources, a readable storage medium, and an electronic device, so as to solve the problem in the prior art that a user easily forms an information cocoon room.

In one aspect, the present application provides a method for recommending information resources, including: obtaining a plurality of groups of information resource groups through various ways, wherein the information resource groups are obtained based on user behaviors, and the user behaviors reflect interests of users; according to the interests of the user, ordering a plurality of information resources in the information resource group from high to low to obtain an information resource sequence; selecting a first preset number of information resources arranged in the front in the information resource sequence to form a recommended information resource group; and transmitting a plurality of groups of recommended information resource groups corresponding to the plurality of groups of information resource groups.

Another aspect of the present application provides a method for recommending information resources, including: receiving a plurality of recommended information resource groups corresponding to a plurality of information resource groups, wherein the acquisition of the information resource groups is based on user behaviors, and the user behaviors reflect the interests of the user; and presenting a plurality of information resources corresponding to the plurality of recommended information resource groups on a user interface.

In still another aspect, the present application provides an information resource recommendation apparatus, including: the acquisition module is used for acquiring a plurality of groups of information resource groups through various ways, wherein the acquisition of the information resource groups is based on user behaviors, and the user behaviors reflect the interests of the user; the ordering module is used for ordering the plurality of information resources in the information resource group from high to low according to the interests of the user to obtain an information resource sequence; the selection module is used for selecting a first preset number of the information resources arranged in the front in the information resource sequence to form a recommended information resource group; and the recommending module is used for sending a plurality of groups of recommended information resource groups corresponding to the plurality of groups of information resource groups.

In still another aspect, the present application provides an information resource recommendation apparatus, including: the receiving module is used for receiving a plurality of recommended information resource groups corresponding to the plurality of information resource groups, wherein the acquisition of the information resource groups is based on user behaviors, and the user behaviors reflect the interests of the user; and the presentation module is used for presenting a plurality of information resources corresponding to the plurality of recommended information resource groups on a user interface. In yet another aspect, the present application provides a computer-readable storage medium storing a computer program for executing the recommendation method of information resources according to any one of the first or second aspects.

In still another aspect, the present application provides an electronic device, including: a processor; a memory for storing the processor-executable instructions; the processor is configured to execute the information resource recommendation method described in any one of the first aspect or the second aspect.

The embodiment of the application takes the user behavior as the basis, and obtains a plurality of groups of information resource groups through various ways, so that the obtained information resource groups can be related to the interests of the user. Because the information resources in the information resource sequence are arranged from high to low according to the interests of the user, and the information resources in the recommended information resource group are the first preset number of information resources arranged in the information resource sequence, the information resources in the recommended information resource group watched by the user can be more in line with the migration interests of the user, and further the formation of information cocoons by the user is effectively avoided.

Drawings

The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.

Fig. 1 is a flow chart illustrating a method for recommending information resources according to an embodiment of the present application.

Fig. 2 is a flowchart of a method for recommending information resources according to another embodiment of the present application.

Fig. 3 is a flowchart illustrating a method for recommending information resources according to still another embodiment of the present application.

Fig. 4 is a flowchart illustrating a method for recommending information resources according to still another embodiment of the present application.

Fig. 5 is a flowchart illustrating a method for recommending information resources according to still another embodiment of the present application.

Fig. 6 is a flowchart illustrating a method for recommending information resources according to still another embodiment of the present application.

Fig. 7 is a schematic structural view of a recommendation method of information resources according to still another embodiment of the present application.

Fig. 8 is a schematic structural view of a recommending apparatus for information resources according to an embodiment of the present application.

Fig. 9 is a schematic structural view of a recommendation method of information resources according to another embodiment of the present application.

Fig. 10 is a schematic block diagram of an electronic device in accordance with one embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

Summary of the application

As described in the background art, the current information resource supply products have a problem in that it is easy for users to form information cocoons. That is, current information resource provision products easily recommend information resources limited to the preference category to the user after determining the preference of the user. After the user continuously views the information resources belonging to the preference category, the information resource supply product can deepen understanding of the preference, so that interests of the user are fixed, and an information cocoon house is formed.

Therefore, if the migration interest of the user can be known and information resources belonging to the migration interest category are recommended to the user, the formation of an information cocoon house by the user can be effectively avoided.

Exemplary method

Fig. 1 is a flowchart of a method for recommending information resources according to an embodiment of the present application, and the recommending method may be applied to a first electronic device. For example, the first electronic device may be a server or a cluster of servers.

Based on the above, the embodiment of the application provides a recommendation method of information resources. As shown in fig. 1, the recommendation method may include the following steps.

Step 110, multiple information resource groups are obtained through multiple approaches. The information resource group is acquired based on user behavior, and the user behavior reflects interests of a user.

In particular, the information resource group may be composed of a plurality of information resources. And acquiring the information resource group, namely acquiring a plurality of information resources corresponding to the information resource group. Here, a set of information resource groups is obtained by one route, and different information resource groups correspond to different acquisition routes.

Because the user behavior can reflect the interests of the user, the information resource group is acquired according to the user behavior, namely, the information resource group is acquired according to the interests of the user.

Step 120, according to the interests of the user, ordering the plurality of information resources in the information resource group from high to low to obtain an information resource sequence.

Specifically, in the information resource sequence, a plurality of information resources are ordered from high to low according to the interests of the user. Here, the more the information resource that is arranged in front can be in line with the current interest of the user. The current interest may be a migration interest.

For the multiple sets of information resource sets obtained in step 110, each set of information resource sets may obtain a corresponding sequence of information resources according to step 120.

In step 130, in the information resource sequence, a first preset number of information resources arranged in front are selected to form a recommended information resource group.

Here, the number of information resources in the information resource sequence may be the same as the first preset number or may be different from the first preset number. When the number of information resources in the information resource sequence is different from the first preset number, after the recommended information resource group is formed, remaining information resources exist in the information resource sequence. This remaining information resource can be used in the next recommendation. In addition, the information resources in the recommended information resource group can be more in line with the migration interests of the user.

Similarly, for the multiple sets of information resource sets obtained in step 110, each set of information resource sets may obtain a corresponding set of recommended information resources per step 130.

Further, among the plurality of recommended information resource groups, the number of information resources in each recommended information resource group may be different. That is, the plurality of first preset numbers corresponding to the plurality of recommended information resource groups may not be identical or may be different.

And 140, recommending a plurality of groups of recommended information resource groups corresponding to the plurality of groups of information resource groups to the user.

Specifically, the number of information resource groups may be the same as the number of recommended information resource groups. That is, a set of information resource groups corresponds to a set of recommended information resource groups.

The embodiment of the application takes the user behavior as the basis, and obtains a plurality of groups of information resource groups through various ways, so that the obtained information resource groups can be related to the interests of the user. Because the information resources in the information resource sequence are arranged from high to low according to the interests of the user, and the information resources in the recommended information resource group are the first preset number of information resources arranged in the information resource sequence in front, the information resources in the recommended information resource group watched by the user can comprise the information resources more in line with the migration interests of the user, and further the formation of information cocoons by the user is effectively avoided.

In one embodiment of the present application, the recommendation method may further include determining whether the information resources in the recommended information resource group have been viewed by the user before performing step 140. And recommending the judged information resource to the user when the judged information resource is not watched by the user, so that the recommended information resource watched by the user can be the information resource which is not watched.

In one embodiment of the application, the recommendation method may further include determining whether the information resources in the recommended information resource group have been marked as uninteresting by the user prior to performing step 140. And recommending the judged information resource to the user when the judged information resource is not marked as uninteresting by the user, so as to ensure that the recommended information resource watched by the user can be the information resource of interest to the user.

In one embodiment of the present application, the difference between the suitable viewing age of an information resource in the information resource group and the age of the user is + -1, so that the recommended information resource viewed by the user can be suitable for the user.

In one embodiment of the application, a plurality of information resources in an information resource group belong to an information resource library, and the information resource library comprises A classifications, wherein A is more than or equal to 1; as shown in fig. 2, step 110 may include the following steps.

Step 210, in the A categories, B hobbies corresponding to the hobbies of the user are combined into an initial user category group. In the initial user classification group, B preference classifications are ranked from high to low according to the preference degree of the user, and B is more than or equal to 1.

In particular, the preference may be set by the user at the time of registering the information resource provision product. The user's preference level for preference categories may be represented by a first score. For example, the user's favorite taste classifications may be a first taste classification, a second taste classification, and a third taste classification, respectively. Here, the first preference category is a category corresponding to the first preference set by the user. The second preference category is a category corresponding to a second preference set by the user. The third preference category is a category corresponding to the third preference set by the user. Accordingly, the first score of the first preference category is higher than the first score of the second category, which is higher than the first score of the third category. That is, in the user initial category group, the ranks of the three taste categories are the first taste category, the second taste category, and the third taste category.

Here, the user initial classification group may belong to attribute information of the user.

Step 220, selecting a second preset number of information resources from the information resources corresponding to each preference category in the Y previous preference categories of the user initial category group, so as to obtain C information resources. Wherein C is equal to the product of Y and a second preset number, and Y is more than or equal to 1.

Step 230, selecting a third preset number of information resources from the information resources corresponding to each preference category in the X following preference categories in the initial user category group, so as to obtain D information resources. Wherein D is equal to the product of X and a third preset number, B is equal to the sum of X and Y, and X is more than or equal to 1.

Here, the second preset number may be the same as or different from the third preset number. When the second preset number is different from the third preset number, the second preset number may be 1 more than the third preset number.

Step 240, the C information resources and the D information resources are grouped into a first information resource group. Wherein the plurality of information resource groups includes a first information resource group.

In this embodiment, the user behavior may be user-set preferences.

Because the information resources in the first information resource group belong to the user's preference classification, and the user's preference classification can reflect the user's interests, the information resources in the first information resource group can be ranked according to the user's interests.

For example, when the number num of information resources corresponding to the plurality of information resource groups is 100, the number z1 of information resources corresponding to the first information resource group may be 45 (z1=num×45%).

In one embodiment of the application, the attribute information of the user comprises user keywords, wherein the user keywords comprise E user keywords, and the E is more than or equal to 1 and is related to the user behavior. As shown in fig. 3, step 110 may include the following steps.

And step 310, F information resources with E user keywords are formed into a second information resource group. Here, F.gtoreq.1.

In particular, the information resource may include a keyword, and the keyword may be a user keyword. Accordingly, for F information resources, each information resource may include at least one of E user keywords. Here, the user keywords may be obtained through user behavior, or may be obtained through adjacent user recommendations. When the user keyword is obtained through a user behavior, the user behavior may be a behavior performed by the user before the recommendation method provided by the embodiment of the present application is executed. For example, the user behavior may include at least one of a user viewing information resources in an information resource library and a user searching information resources in an information resource library. When the user keyword is recommended by a neighboring user, the user behavior may be a behavior of the user inferred from the behavior of the neighboring user.

The attribute information of the user also includes a user viewing keyword group. Specifically, after a user views an information asset in the information asset library, keywords of the viewed information asset will be added to the user view keyword group. It should be appreciated that before the keyword group of the viewed information resource is added to the user viewing keyword group, it may be determined whether the keyword of the viewed information resource has been added to the user viewing keyword group. When the keywords of the viewed information asset have been added to the user viewing keyword group, the second score of the keywords of the viewed information asset will be increased. When the keyword of the watched information resource is not added with the user watching keyword group, the keyword of the watched information resource can be added with the user watching keyword group. In the keyword group watched by the user, the keywords of the information resource are ranked from high to low according to the second score. Among the user viewing keyword groups, the keywords of the preset number of information resources arranged in front may constitute user viewing preference keyword groups. For example, the preset number may be equal to 5. Here, the keywords of the information resource may be preset.

The attribute information of the user also includes a user search keyword group. Specifically, when a user searches for an information resource, a search keyword is input, or a sentence including the search keyword is input. After the user enters, the search keyword will be added to the user search keyword group. It should be appreciated that before the search keyword is added to the user search keyword group, it is determined whether the search keyword has been added to the user search keyword group. When the search keyword has been added to the user search keyword group, the number of searches for the search keyword will be increased by 1. When the search keyword is not added to the user search keyword group, the search keyword is added to the user search keyword group. Among the user search keyword groups, the search keyword groups with the highest search frequency in the preset days form user search preference keyword groups. Here, the search frequency is positively correlated with the number of searches. For example, the preset number of days may be 10 and the preset number may be 5.

The attribute information of the user also includes user preference keyword groups. Here, the user preference keyword group may be a union of the user viewing preference keyword group and the user search preference keyword group.

The attribute information of the user also includes a user classification group. In particular, a plurality of information resources in an information resource group may belong to an information resource library, the information resource library comprising a classifications, and the user classification group comprising the a classifications. The user may select an interest category among the a categories when initially registering the information resource offering product. To reflect the user's preference for the selected interest categories, the selected interest categories may be uniformly scored. Here, the selected interest categories may have the same score. After the information resource provisioning product has been in use for a period of time, the user may select a new interest category among the A categories and score the newly selected interest category. The score for the newly selected interest category may be the same as the score for the selected interest category at the time of initial registration. For example, the scored score may be 50 points. At the same time, the user may cancel the previously selected interest category, and accordingly, the third score of the cancelled interest category may be deducted. For example, the deducted score may be 50 points. The information resource provisioning product may include a channel bar, and the channel bar may include P channels. Here, the channel may correspond to one of a categories. According to the favorite degree, the user can sort the P channels from high to low to obtain a sorted channel column. In the sorting channel column, the corresponding classifications of the preset number of channels that are ranked in front may be scored. For example, the preset number may be 3, i.e., the number of channels to be divided may be 3. Among the three channels that are weighted, the score that each channel is weighted is different. For example, the classification corresponding to the channel arranged in the first place may be increased by 50 points, the classification corresponding to the channel arranged in the second place may be increased by 30 points, and the classification corresponding to the channel arranged in the third place may be increased by 10 points. In the user classification group, the A classifications are ranked from high to low according to a third score. Among the user classification groups, the fifth preset number of classifications arranged in front may constitute a user preference classification group. For example, the fifth preset number may be 5. Here, the third score may represent a preference degree of the user for each of the a categories.

The attribute information of the user also includes a keyword group recommended by the adjacent user. Specifically, user a has a user preference category group a and a user preference keyword group a ', and user B has a user preference category group B and a user preference keyword group B'. Here, the age difference of the user a and the user B may be ±1. Regardless of the ordering of the two preference classification groups and the preference keyword groups, if each element in B can be found in the preference classification group a, and the number of the same elements of B 'and a' reaches a certain degree, then the user B is called as the adjacent user of the user A. Among the user preferred keyword groups B' of the user B, the preset number of keyword groups arranged in front form the adjacent user recommended keyword group. For example, the preset number may be 2.

In an embodiment of the present application, the user keyword group may be a union of the user viewing preference keyword group, the user search preference keyword group, and the neighboring user recommendation keyword group. In the user keyword group, the user behavior corresponding to the keyword belonging to the adjacent user recommended keyword group may be the behavior of the user inferred from the behavior of the adjacent user.

Step 320, in the second information resource group, ordering the F information resources according to a preset rule, so as to obtain a third information resource group.

In one embodiment of the present application, step 320 may include ordering F information resources from high to low according to how well the keywords of the information resources match the user's preferred keyword groups.

Specifically, the preset rule may be a matching degree of the keyword of the information resource and the keyword group preferred by the user. In the third information resource group, the F information resources may be ordered from high to low according to the preset rule. For example, the F information resources may include a first information resource and a second information resource. When the first information resource includes 5 keywords, and 3 keywords in the 5 keywords belong to the user preference keyword group, the matching degree between the keywords of the first information resource and the user preference keyword group may be 3. Similarly, the first information resource may be ranked ahead of the second information resource when the keyword of the second information resource may match the user-preferred keyword group by a degree of 2.

In step 330, in the third information resource group, a fourth preset number of information resources arranged in front are selected to form a fourth information resource group. Wherein the plurality of information resource groups includes a fourth information resource group.

For example, when the number num of information resources corresponding to the plurality of information resource groups is 100, the number z1 of information resources corresponding to the fourth information resource group may be 45 (z1=num×45%). Here, the plurality of information resource groups may include a first information resource group or a fourth information resource group.

In one embodiment of the application, the user comprises H adjacent users, and the plurality of information resources comprise information resources liked by the adjacent users, wherein H is more than or equal to 1; as shown in fig. 4, step 110 may include the following steps.

In step 410, an eighth predetermined number of neighboring users from the H neighboring users are selected to form a neighboring user group. For example, the eighth preset number may be 5.

Step 420, selecting a ninth preset number of information resources with the viewing time point closest to the current time point from the R information resources liked by the adjacent users.

Here, the information resource liked by the adjacent user may refer to an information resource that is praised, collected or annotated as good by the adjacent user.

And step 430, forming Q information resources corresponding to the adjacent user groups into a sixth information resource group. Wherein Q is equal to a product of the eighth preset number and the ninth preset number, and the plurality of information resource groups includes a sixth information resource group.

In this embodiment, user behavior may refer to behavior of a user inferred from behavior of neighboring users.

For example, when the number num of information resources corresponding to the plurality of information resource groups is 100, the number z3 of information resources corresponding to the sixth information resource group may be 10 (z3=num×10%).

In one embodiment of the application, a plurality of information resources in an information resource group belong to an information resource library, and the information resource library comprises A classifications, wherein A is more than or equal to 1; as shown in fig. 5, step 110 may include the following steps.

Step 510, grouping a classifications into user classification groups. In the user classification group, A classifications are ranked from high to low according to the preference degree of the user.

In step 520, a fifth predetermined number of categories, which are arranged in front, are selected to form a user preference category group.

In step 530, in the user preference classification group, a sixth preset number of classifications arranged in front are selected to form a candidate classification group. For example, the sixth preset number may be 2.

Step 540, selecting a seventh preset number of information resources from the G information resources corresponding to the candidate classification group to form a fifth information resource group. Wherein the plurality of information resource groups comprise a fifth information resource group, and G is more than or equal to 1.

In this embodiment, the user behavior may include at least one of selecting an interest category among the a categories, canceling the selected interest category, and ordering the P channels in the channel bar.

For example, when the number num of information resources corresponding to the plurality of information resource groups is 100, the number z2 of information resources corresponding to the fifth information resource group may be a difference between 30 and z5 (z2=num×30% -z 5). The designation of z5 will be specifically explained hereinafter.

In one embodiment of the application, a plurality of information resources in an information resource group belong to an information resource library; as shown in fig. 6, step 110 may include the following steps.

And step 610, sorting all the information resources in the information resource library from high to low according to the heat value to obtain a heat information resource group.

Here, the heat value may include a first sub-value related to the user behavior. But the user behavior may refer to at least one of browsing, praying, annotating, looking up, collecting, sharing, taking notes, annotating uninteresting, annotating disfavored, canceling praying, canceling disfavored information resources in the information resource library by other users. The above operations all correspond to different scores. When other users perform the above operations on an information resource, the information resource may have a score accumulated. The accumulated score of the information resource may be a first sub-value, and the accumulated score may also be referred to as a fourth score. Here, the other user is not a recommendation object of the recommendation method provided by the embodiment of the present application.

Here, the information resource with a high heat value may not be the information resource corresponding to the user classification group of the user. When a user views the information resource with high popularity value, the theme corresponding to the information resource with high popularity value can become the migration interest of the user. Therefore, after the information resource with high heat value is recommended to the user, the formation of the information cocoon house by the user can be effectively avoided.

In step 620, a tenth preset number of information resources arranged in front are selected from the hot information resource groups to form a seventh information resource group. Wherein the plurality of information resource groups includes a seventh information resource group.

For example, when the number num of information resources corresponding to the plurality of information resource groups is 100, the number z4 of information resources corresponding to the seventh information resource group may be 15 (z4=num×15%).

In one embodiment of the application, the heat value further comprises a second sub-value that decays over time.

Specifically, the heat value of each information resource may be changed slowly with the lapse of time, and the portion of the heat value that decays with the lapse of time may be referred to as a second sub-value. For example, the change in the second sub-value may satisfy newton's law of thermal cooling, and the change function may be specified as follows.

Current second sub-value = last period second value ₀ ))

Here, K is a heat attenuation coefficient, and can be set by itself. If it is desired that the heat decays slightly slower, the coefficient K may be set smaller; if it is desired that the heat decays a little faster, the coefficient K may be set to be a little larger. T-T ₀ To start from the release or the putting on shelf of the information resource, the current number of hours. The second sub-value is updated once at 59 minutes and 59 seconds per day 23. In one embodiment of the application, the heat value further comprises an initial heat value.

Specifically, the setting of the initial heat value may be considered from the keywords. For example, to determine an initial heat value for an information resource to be evaluated, keywords for the information resource may be matched with all keywords for the first x information resources having the highest current heat. Specifically, y information resources may include keywords of the information resource to be evaluated currently in the first x information resources with the highest current heat. Of the y information resources, the heat value of each information resource can be H _i (i=1, 2,3 … … y), the number of keywords of each information resource including the information resource to be evaluated may be a, respectively _i (i=1, 2,3 … … y). In this case, the initial heat value H of the information resource to be evaluated ₀ The calculation formula of (c) may be as follows.

H ₀ ＝0(y＝0)

In one embodiment of the application, a plurality of information resources in an information resource group belong to an information resource library, and the information resource library comprises I appointed information resources, wherein I is more than or equal to 1; step 110 may specifically include: and forming the I appointed information resources into an eighth information resource group. Wherein the plurality of information resource groups includes an eighth information resource group.

Specifically, the information resources in the recommended information resource group may be preset manually. For example, when the recommended information resource is an article and the recommended information resource is referred to as a top page, the background of the information resource supply product may manually set what article the top page recommends as a specific article, and may also set the ranking of the articles in the background, and set the validity period of the specific article. For manually selected articles, a weighting factor may be set in the recommendation system and the factor may be background adjustable.

For example, the number of information resources in the eighth information resource group may be denoted by z5, and the value of z5 may be variable.

In one embodiment of the application, a plurality of information resources in an information resource group belong to an information resource library, and the information resource library comprises A classifications, wherein A is more than or equal to 1; in a user classification group comprising A classifications, according to the preference degree of users, the A classifications are ranked from high to low; step 120 may include: and ordering the plurality of information resources according to the ordering of the A classifications in the user classification group.

Specifically, among the plurality of information resources, each information resource corresponds to one of a classifications.

In one embodiment of the application, the user taxonomy includes user preference keyword groups; wherein, according to the sorting of the A classifications in the user classification group, the sorting of the plurality of information resources comprises: when J information resources belong to the same category in the A categories, the J information resources are ranked from high to low according to the matching degree of the keywords of the information resources and the keyword groups preferred by the user, wherein J is more than or equal to 1.

In particular, the plurality of information resources may include J information resources belonging to the same category. The J information resources cannot be ranked in order of the a categories in the user category group. To enable the J information resources to be ranked, the degree of matching of the information resource's keywords to the user's preferred keyword groups may be based on the degree of matching of the information resource's keywords to the user's preferred keyword groups. For example, the J information resources may include a third information resource that may include 5 keywords and a fourth information resource that may include 3 keywords. When 4 keywords in the 5 keywords of the third information resource belong to the user preference keyword group, and 2 keywords in the 3 keywords of the fourth information resource belong to the user preference keyword group, the matching degree of the keywords of the third information resource and the user preference keyword group is higher than that of the keywords of the fourth information resource and the user preference keyword group. In such a case, the third information resource will be ranked before the fourth information resource when the third information resource and the fourth information resource are ranked.

In one embodiment of the application, ordering J information resources from high to low includes: when the J information resources comprise K information resources with the same matching degree, the K information resources are ordered from high to low according to a heat value, wherein the heat value comprises a first sub-value related to user behaviors, and K is more than or equal to 1.

Here, the matching degree may refer to a matching degree of the keyword of the information resource and the keyword group preferred by the user. When the matching degree of the K information resources is the same, the K information resources will not be ranked according to the matching degree. To be able to order, the K information resources may be ordered by a hotness value. For example, when the K information resources include a fifth information resource and a sixth information resource, and the heat value of the fifth information resource is greater than the heat value of the sixth information resource, the fifth information resource may be arranged before the sixth information resource.

In one embodiment of the application, ordering K information resources from high to low includes: when the K information resources comprise L information resources with the same heat value, the L information resources are ordered from high to low according to the score of the information resources, the score is related to the user behavior, and L is more than or equal to 1.

Here, the score of the information resource may refer to the fourth score described above. The user behavior may refer to at least one of browsing, praying, annotating, looking up, collecting, sharing, taking notes, annotating uninteresting, annotating disfavored, canceling praying, canceling looking, canceling collecting, and canceling disfavored information resources in the information resource library by other users.

In one embodiment of the application, the attribute information of the user includes user preference keyword groups; step 120 may specifically include: and ordering the information resources from high to low according to the matching degree of the key words of the information resources and the key word groups preferred by the user.

Specifically, when the information resource library does not include a classifications, the information resources in the information resource library will not be classified by category. In such a case, the plurality of information resources may be ordered according to the degree to which the keywords of the information resources match the user-preferred keyword groups.

In one embodiment of the application, when the information resource library does not include a classifications, ordering the plurality of information resources from high to low may include: when the plurality of information resources comprise M information resources with the same matching degree, the M information resources are ordered from high to low according to a heat value, wherein the heat value comprises a first sub-value related to user behaviors, and M is more than or equal to 1.

In one embodiment of the present application, when the information resource library does not include a classifications, ordering the M information resources from high to low may include: when the M information resources comprise N information resources with the same heat value, the N information resources are ordered from high to low according to the score of the information resources, the score is related to the user behavior, and N is more than or equal to 1. Here, the score of the information resource may be the fourth score described above.

In one embodiment of the application, the user behavior comprises at least one of the following behaviors: setting hobbies by the user; the user views the information resources in the information resource library, wherein a plurality of information resources in the information resource group belong to the information resource library; searching information resources in an information resource library by a user; inferred behavior of the user from behavior of neighboring users; the user selects an interest category from A categories, wherein the information resource library comprises A categories; the user cancels the selected interest classification; the user sorts the P channels in the channel bar; and the other users browse, praise, annotate the good looking, collect, share, make notes, annotate uninteresting, annotate the dislike, cancel praise, cancel the good looking, cancel the collection and cancel the dislike the information resource in the information resource library.

In one embodiment of the application, the information resource includes at least one of an article, video, and audio.

Embodiments of the present application are described in more detail below in conjunction with specific examples.

In one embodiment of the present application, the information resource recommendation method provided in the embodiment of the present application is applied to the recommendation field of the article. Here, the read-suitable ages of all recommended articles are ±1 year old of the age of the user. Articles read by the user and articles not of interest have been manipulated may not be recommended.

Specifically, five information resource groups are obtained in step 110, and the five information resource groups may be the first information resource group, the fifth information resource group, the sixth information resource group, the seventh information resource group, and the eighth information resource group, respectively. Alternatively, the first information resource group may be replaced with a fourth information resource group. In addition, the first information resource group may be replaced with the ninth information resource group. Articles in the ninth information resource group can be randomly obtained by classifying and equivalent amounts of articles in the information resource library.

The number of articles corresponding to the five information resource groups may be represented by num, the number of articles corresponding to the first information resource group may be represented by z1 (z1=num×45%) and the number of articles corresponding to the fifth information resource group may be represented by z2 (z2=num×30% -z 5), the number of articles corresponding to the sixth information resource group may be represented by z3 (z3=num×10%) and the number of articles corresponding to the seventh information resource group may be represented by z4 (z4=num×15%) and the number of articles corresponding to the eighth information resource group may be represented by z5 (the value of z5 may be variable).

When num=100, z1=45, z2=30-z5, z3=10, z4=15, and z5 have various values. Each 20 articles in the first information resource group, the fifth information resource group, the sixth information resource group, the seventh information resource group, and the eighth information resource group is a recommended article batch. When z5=0, a batch of recommended articles may be extracted at 45%, 30%, 10%, 15% before the first information resource group, the fifth information resource group, the sixth information resource group, and the seventh information resource group, respectively. When z5+.0, the articles in the eighth information resource group can be sequentially and evenly distributed in 5 batches of recommended articles. The ratio is unchanged when the other groups are allocated. The number of the articles in the eighth information resource group is subtracted from 30% of the articles in the fifth information resource group.

In another embodiment of the present application, the recommendation method of information resources provided in the embodiment of the present application is applied to a channel bar of an article. Here, the read-suitable ages of all recommended articles are the ages of ±1 year of the user. All the articles are classified articles of the channel, namely, in the channel bar recommendation, the classification problem does not exist, and only the user keywords are needed to search and match. Further, articles read by the user and articles which are not of interest are operated to make no recommendation.

Specifically, two sets of information resource groups are obtained in step 110, and the two sets of information resource groups may be referred to as an eleventh information resource group and a twelfth information resource group, respectively. Alternatively, the eleventh information resource group may be replaced with the thirteenth information resource group, and the articles in the thirteenth information resource group may be randomly acquired in the read-suitable age articles under the channel classification. The retrieval route of the articles in the eleventh information resource group may be the same as the retrieval route of the articles in the fourth information resource group described above. The fourteenth information resource group may be acquired before the twelfth information resource group is acquired. Here, the acquisition path of the article of the fourteenth information resource group may be the same as the acquisition path of the article of the seventh information resource group. After the fourteenth information resource group is obtained, the first z7 articles under the channel classification are screened out from the fourteenth information resource group, and the first z7 articles form a twelfth information resource group.

The number of articles corresponding to the two information resource groups may also be represented by num, the number of articles corresponding to the eleventh information resource group may be represented by z6 (z6=num×70%) and the number of articles corresponding to the twelfth information resource group may be represented by z7 (z7=num×30%).

When num=100, each recommended article is extracted from the articles of the eleventh information resource group and the twelfth information resource group at a ratio of 70% and 30%, respectively.

The information resource recommendation method provided by the embodiment of the application has more efficient utilization of the information resource and lower requirement on the number of the information resource. Because the application marks the information resources by adopting a plurality of dimensions such as classification, keywords, difficulty and the like, the identification of the information resources is more accurate, and the construction of the user portrait model is also suitable for a unique information resource system, the limited information resources can be accurately recommended to a large number of users according to the personalized characteristics of the users, the interests of the users are triggered, and the distribution problem of the limited information resources is mainly solved.

The information resource is strictly controlled, healthy and positive in the production link, so that the method is not only suitable for students in schools and other special scene users, but also has good effect on the positive value of vast national treasures, and helps to solve the problem of the bottom layer in national education of personality culture. The problem that the conventional information resource supply product wastes the time of the user due to the fact that the conventional low-quality information resource is used is solved, and the method is more helpful for the user.

The application can give the user a surprise and pleasure to the reading experience. The triggering of the user's interest is not limited to the features that the user has explicitly fed back to the system, but also includes reasonable inferences made by the system based on the user's characteristics, including concepts and applications that are close to the user, where a significant portion of the content may be of interest to the user.

The application does not depend on an algorithm too much, and focuses on content quality and educational significance, so that the product value of the application is longer, a user can feed back multidimensional user data more seriously, and data acquisition is guaranteed more.

The embodiment of the application also provides another information resource recommending method which can be applied to the second electronic equipment. For example, the second electronic device may be a terminal of the user.

As shown in fig. 7, the recommendation method of the information resource may include the following steps.

Step 710, a plurality of recommended information resource groups corresponding to the plurality of information resource groups are received. The information resource group is acquired based on user behaviors, and the user behaviors reflect the interests of the user.

Specifically, multiple recommended information resource groups corresponding to the multiple information resource groups sent by the first electronic device may be received by the second electronic device.

In step 720, a plurality of information resources corresponding to the plurality of recommended information resource groups are presented on the user interface.

The information resource supply product can be applied to the second electronic device. After the user opens the information resource provisioning product, the second electronic device will send a request to the first electronic device. After the first electronic device receives the request, a recommendation method of the information resource installed on the first electronic device is executed so as to recommend the information resource to the user.

Exemplary embodimentsDevice and method for controlling the same

The information resource recommending method according to the embodiment of the present application is described above, and the information resource recommending apparatus according to the embodiment of the present application is described below with reference to fig. 8.

As shown in fig. 8, the information resource recommending apparatus may include an obtaining module 810 configured to obtain multiple information resource groups through multiple ways, where the obtaining of the information resource groups is based on user behavior, and the user behavior reflects interests of a user; the ordering module 820 is configured to order the plurality of information resources in the information resource group from high to low according to the interests of the user, so as to obtain an information resource sequence; a selecting module 830, configured to select a first preset number of information resources arranged in front in the information resource sequence to form a recommended information resource group; and a recommending module 840, configured to recommend multiple recommended information resource groups corresponding to the multiple information resource groups to the user.

The operations and functions of the obtaining module 810, the sorting module 820, the selecting module 830, and the recommending module 840 of the recommending apparatus for information resources may refer to the methods of 110, 120, 130, and 140 of fig. 1, and are not repeated herein.

In one embodiment of the application, a plurality of information resources in an information resource group belong to an information resource library, and the information resource library comprises A classifications, wherein A is more than or equal to 1; among the a categories, the obtaining module 810 groups B hobbies corresponding to the hobbies of the user into a user initial category group, wherein in the user initial category group, the B hobbies are ranked from high to low according to the hobbies of the user, and B is more than or equal to 1; selecting a second preset number of information resources from the information resources corresponding to each taste classification in the Y taste classifications arranged in the front of the user initial classification group to obtain C information resources, wherein C is equal to the product of Y and the second preset number, and Y is more than or equal to 1; selecting a third preset number of information resources from the information resources corresponding to each taste classification in the X taste classifications arranged at the back of the user initial classification group to obtain D information resources, wherein D is equal to the product of X and the third preset number, B is equal to the sum of X and Y, and X is equal to or greater than 1; the C information resources and the D information resources are grouped into a first information resource group, wherein the plurality of information resource groups includes the first information resource group.

The operation and function of the obtaining module 810 of the information resource recommendation device may refer to the methods 210, 220, 230, and 240 of fig. 2, and in order to avoid repetition, a description thereof will be omitted.

In one embodiment of the application, the attribute information of the user comprises user keyword groups, wherein the user keyword groups comprise E user keywords, and the user keywords are related to user behaviors, and E is more than or equal to 1; wherein, the obtaining module 810 forms F information resources with E user keywords into a second information resource group, F is more than or equal to 1; in the second information resource group, F information resources are ordered according to a preset rule to obtain a third information resource group; and selecting a fourth preset number of information resources arranged in the front from the third information resource group to form a fourth information resource group, wherein the plurality of information resource groups comprise the fourth information resource group.

The operation and function of the obtaining module 810 of the information resource recommendation device may refer to the methods of 310, 320 and 330 in fig. 3, and will not be repeated herein.

In one embodiment of the application, the user key phrase comprises a user preference key phrase; the obtaining module 810 sorts the F information resources from high to low according to the matching degree of the keywords of the information resources and the keyword groups preferred by the user.

In one embodiment of the application, a plurality of information resources in an information resource group belong to an information resource library, and the information resource library comprises A classifications, wherein A is more than or equal to 1; the obtaining module 810 groups a classifications into a user classification group, and in the user classification group, the a classifications are ranked from high to low according to the preference degree of the user; selecting a fifth preset number of classifications arranged in the front from the user classification groups to form a user preference classification group; selecting a sixth preset number of classifications arranged in the front from the user preference classification groups to form candidate classification groups; and selecting a seventh preset number of information resources from the G information resources corresponding to the candidate classification group to form a fifth information resource group, wherein the plurality of information resource groups comprise the fifth information resource group, and G is more than or equal to 1.

The operation and function of the obtaining module 810 of the information resource recommendation device may refer to the methods 510, 520, 530, and 540 of fig. 5, and are not repeated herein.

In one embodiment of the application, the user comprises H adjacent users, and the plurality of information resources comprise information resources liked by the adjacent users, wherein H is more than or equal to 1; the obtaining module 810 selects an eighth preset number of adjacent users from the H adjacent users to form an adjacent user group; selecting a ninth preset number of information resources closest to the current time point from R information resources liked by the adjacent users; and forming Q information resources corresponding to the adjacent user groups into a sixth information resource group, wherein Q is equal to the product of the eighth preset number and the ninth preset number, and the plurality of information resource groups comprise the sixth information resource group.

The operation and function of the obtaining module 810 of the information resource recommendation device may refer to the methods of 410, 420, and 330 of fig. 4, and are not repeated herein.

In one embodiment of the application, a plurality of information resources in an information resource group belong to an information resource library; the obtaining module 810 sorts all information resources in the information resource library from high to low according to the heat value to obtain a heat information resource group; selecting a tenth preset number of information resources arranged in the front from the heat information resource groups to form a seventh information resource group, wherein a plurality of groups of information resource groups comprise the seventh information resource group; wherein the hotness value comprises a first sub-value related to the user behavior.

The operation and function of the obtaining module 810 of the information resource recommendation device may refer to the method of 610 and 620 of fig. 6, and will not be described herein again to avoid repetition.

In one embodiment of the application, a plurality of information resources in an information resource group belong to an information resource library, and the information resource library comprises I appointed information resources, wherein I is more than or equal to 1; wherein the acquisition module 810 groups the I specified information resources into an eighth information resource group, wherein the plurality of information resource groups includes the eighth information resource group.

In one embodiment of the application, a plurality of information resources in an information resource group belong to an information resource library, and the information resource library comprises A classifications, wherein A is more than or equal to 1; in a user classification group comprising A classifications, according to the preference degree of users, the A classifications are ranked from high to low; wherein the ranking module 820 ranks the plurality of information resources according to the ranking of the a categories in the user category group.

In one embodiment of the application, the user classification group includes user preference keyword groups; wherein, the sorting module 820 sorts J information resources from high to low according to the matching degree of the keywords of the information resources and the keyword groups preferred by the user when the J information resources belong to the same category in the A categories, and J is more than or equal to 1.

In one embodiment of the present application, the ranking module 820 ranks the K information resources from high to low according to a hotness value when the J information resources include K information resources with the same matching degree, wherein the hotness value includes a first sub-value related to the user behavior, and K is equal to or greater than 1.

In one embodiment of the application, the ranking module 820 ranks the L information resources from high to low according to the score of the information resources when the K information resources include L information resources having the same popularity value, the score being related to user behavior, and L.gtoreq.1.

In one embodiment of the application, the attribute information of the user comprises user preference keyword groups; the ranking module 820 ranks the plurality of information resources from high to low according to the matching degree of the keywords of the information resources and the keyword groups preferred by the user.

In one embodiment of the present application, when the plurality of information resources includes M information resources with the same matching degree, the ranking module 820 ranks the M information resources from high to low according to a heat value, where the heat value includes a first sub-value related to the user behavior, and M is greater than or equal to 1.

In one embodiment of the present application, when the M information resources include N information resources with the same popularity value, the ranking module 820 ranks the N information resources from high to low according to the score of the information resources, where the score is related to the user behavior, and N is equal to or greater than 1.

The embodiment of the application also provides another information resource recommending device, and the information resource recommending device is described below with reference to fig. 9.

As shown in fig. 9, the information resource recommending apparatus may include a receiving module 910, configured to receive a plurality of recommended information resource groups corresponding to a plurality of information resource groups, where the information resource groups are acquired based on user behavior, and the user behavior reflects interests of a user; and a presenting module 920, configured to present, on the user interface, a plurality of information resources corresponding to the plurality of recommended information resource groups.

The operations and functions of receiving module 910 and presenting module 920 of the information resource referring to the methods of 710 and 720 of fig. 7 may be omitted herein for avoiding repetition.

The embodiment of the application takes the user behavior as the basis, and obtains a plurality of groups of information resource groups through various ways, so that the obtained information resource groups can be related to the interests of the user. Because the information resources in the information resource sequence are arranged from high to low according to the interests of the user, and the information resources in the recommended information resource group are the first preset number of information resources arranged in the information resource sequence, the information resources in the recommended information resource group watched by the user can be more in line with the migration interests of the user, and further the formation of information cocoons by the user is effectively avoided. The embodiments of the information resource recommendation device may refer to the above embodiments of the information resource recommendation method, and in order to avoid repetition, a description thereof will be omitted.

Exemplary electronic device

Fig. 10 is a schematic block diagram of an electronic device 10 in accordance with one embodiment of the present application.

As shown in fig. 10, the electronic device 10 may include a processor 11 and a memory 12 for storing instructions executable by the processor 11. The processor 11 may be configured to perform the recommendation method for information resources according to any one of the embodiments of the present application described in the above "exemplary method". For example, the electronic device 10 may be the first electronic device or the second electronic device described above.

In particular, the electronic device 10 may include one or more processors 11 and memory 12. The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

Memory 12 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM) and/or cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. On which one or more computer program instructions may be stored, which may be executed by the processor 11 to implement the information resource recommendation method according to any one of the embodiments of the present application described in the above-mentioned "exemplary method". Various contents such as an input signal, a signal component, a noise component, and the like may also be stored in the computer-readable storage medium.

In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown).

For example, the input device 13 may include a communication network connector, a keyboard, a mouse, and the like. The output device 14 may include a display, speakers, a printer, and a communication network and remote output apparatus connected thereto, etc.

Of course, only some of the components of the electronic device 10 that are relevant to the present application are shown in fig. 10 for simplicity, components such as buses, input/output interfaces, etc. being omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.

Exemplary computer program product and computer readable storage Medium

Embodiments of the present application provide a computer-readable storage medium. The storage medium stores a computer program for executing the recommendation method of information resources according to any one of the embodiments of the present application described in "exemplary method".

In particular, in addition to the methods and apparatus described above, embodiments of the application may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform the steps in the recommended methods of information resources according to various embodiments of the application described in the "exemplary methods" section of this specification.

The computer program product may write program code for performing operations of embodiments of the present application 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.

Furthermore, embodiments of the present application may also be a computer-readable storage medium, on which computer program instructions are stored, which, when being executed by a processor, cause the processor to perform the steps in the recommendation method of information resources according to various embodiments of the present application described in the above section "exemplary method" of the present specification.

The computer 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 may include, 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 basic principles of the present application have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not intended to be limiting, and these advantages, benefits, effects, etc. are not to be considered as essential to the various embodiments of the present application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not necessarily limited to practice with the above described specific details.

The block diagrams of the devices, apparatuses, devices, systems referred to in the present application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.

It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present application.

The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.

Claims

1. A method for recommending information resources, comprising:

obtaining a plurality of groups of information resource groups through various ways, wherein the information resource groups are obtained based on user behaviors, and the user behaviors reflect interests of users;

According to the interests of the user, ordering a plurality of information resources in the information resource group from high to low to obtain an information resource sequence;

selecting a first preset number of information resources arranged in the front in the information resource sequence to form a recommended information resource group; and

transmitting a plurality of groups of recommended information resource groups corresponding to the plurality of groups of information resource groups;

wherein the plurality of information resources in the information resource group belong to an information resource library, the information resource library comprises A classifications, and A is more than or equal to 1;

the obtaining multiple information resource groups through multiple ways comprises:

b hobbies corresponding to the hobbies of the user are classified into an initial user classification group in the A classifications, wherein in the initial user classification group, the B hobbies are ranked from high to low according to the hobbies of the user, and the B is more than or equal to 1;

selecting a second preset number of information resources from the information resources corresponding to each taste classification in the Y taste classifications arranged in the front of the user initial classification group to obtain C information resources, wherein the C is equal to the product of the Y and the second preset number, and the Y is more than or equal to 1;

Selecting a third preset number of information resources from the information resources corresponding to each of the following X hobby classifications in the initial user classification group to obtain D information resources, wherein D is equal to the product of X and the third preset number, B is equal to the sum of X and Y, and X is more than or equal to 1;

and forming a first information resource group by the C information resources and the D information resources, wherein the plurality of information resource groups comprise the first information resource group.

2. The method according to claim 1, wherein the attribute information of the user comprises a user keyword group comprising E user keywords, wherein the user keywords are related to the user behavior, and wherein E is equal to or greater than 1;

wherein the obtaining multiple groups of information resource groups through multiple ways comprises:

f information resources with the E user keywords form a second information resource group, wherein F is more than or equal to 1;

in the second information resource group, sequencing the F information resources according to a preset rule to obtain a third information resource group; and

And selecting a fourth preset number of information resources arranged in the front from the third information resource group to form a fourth information resource group, wherein the plurality of information resource groups comprise the fourth information resource group.

3. The method of claim 2, wherein the user keyword groups comprise user preference keyword groups;

wherein the ordering the F information resources according to a preset rule includes:

and sequencing the F information resources from high to low according to the matching degree of the keywords of the information resources and the keyword groups preferred by the user.

4. The method of claim 1, wherein the plurality of information resources in the set of information resources belong to an information resource library, the information resource library comprising a classifications, the a being ≡1;

the A classifications form a user classification group, and in the user classification group, the A classifications are ranked from high to low according to the preference degree of the user;

selecting a fifth preset number of the classifications arranged in the front from the user classification groups to form user preference classification groups;

Selecting a sixth preset number of the classifications arranged in the front from the user preference classification groups to form candidate classification groups; and

and selecting a seventh preset number of information resources from G information resources corresponding to the candidate classification group to form a fifth information resource group, wherein the plurality of information resource groups comprise the fifth information resource group, and G is more than or equal to 1.

5. The method of claim 1, wherein the user comprises H adjacent users, the plurality of information resources comprising information resources liked by the adjacent users, the H being ≡1;

selecting an eighth preset number of adjacent users from the H adjacent users to form an adjacent user group;

selecting a ninth preset number of information resources closest to the current time point from R information resources liked by the adjacent user, wherein R is more than or equal to 1; and

and forming Q information resources corresponding to the adjacent user groups into a sixth information resource group, wherein Q is equal to the product of the eighth preset number and the ninth preset number, and the plurality of information resource groups comprise the sixth information resource group.

6. The method of claim 1, wherein the plurality of information resources in the set of information resources belong to an information resource library;

according to the heat value, sequencing all the information resources in the information resource library from high to low to obtain a heat information resource group; and

selecting a tenth preset number of information resources arranged in the front from the heat information resource groups to form a seventh information resource group, wherein the plurality of information resource groups comprise the seventh information resource group;

wherein the hotness value comprises a first sub-value related to the user behavior.

7. The method of claim 6, wherein the heat value further comprises a second sub-value that decays over time.

8. The method of claim 1, wherein the plurality of information resources in the set of information resources belong to an information resource library, the information resource library comprising I specified information resources, the I being ≡1;

and forming the I designated information resources into an eighth information resource group, wherein the plurality of information resource groups comprise the eighth information resource group.

9. The method of claim 1, wherein the plurality of information resources in the set of information resources belong to an information resource library, the information resource library comprising a classifications, the a being ≡1; in the user classification group comprising the A classifications, the A classifications are ranked from high to low according to the preference degree of the user;

wherein said ordering the plurality of information resources in the information resource group from high to low according to the interests of the user comprises:

and ordering the plurality of information resources according to the ordering of the A classifications in the user classification group.

10. The method of claim 9, wherein the user classification group comprises user preference keyword groups;

wherein said ranking said plurality of information resources according to the ranking of said a categories in said user category group comprises:

when J information resources belong to the same category in the A categories, the J information resources are ranked from high to low according to the matching degree of the keywords of the information resources and the keyword groups preferred by the user, and J is more than or equal to 1.

11. The method of claim 10, wherein said ordering said J of said information resources from high to low comprises:

And when the J information resources comprise K information resources with the same matching degree, sequencing the K information resources from high to low according to a heat value, wherein the heat value comprises a first sub-value related to the user behavior, and the K is more than or equal to 1.

12. The method of claim 11, wherein said ordering said K of said information resources from high to low comprises:

and when the K information resources comprise L information resources with the same heat value, sequencing the L information resources from high to low according to the score of the information resources, wherein the score is related to the user behavior, and the L is more than or equal to 1.

13. The method of claim 1, wherein the attribute information of the user comprises user preference key words;

and sequencing the information resources from high to low according to the matching degree of the keywords of the information resources and the keyword groups preferred by the user.

14. The method of claim 13, wherein said ordering said plurality of said information resources from high to low comprises:

When the information resources comprise M information resources with the same matching degree, sequencing the M information resources from high to low according to a heat value, wherein the heat value comprises a first sub-value related to the user behavior, and M is more than or equal to 1.

15. The method of claim 14, wherein said ordering said M of said information resources from high to low comprises:

when the M information resources comprise N information resources with the same heat value, sorting the N information resources from high to low according to the score of the information resources, wherein the score is related to the user behavior, and N is more than or equal to 1.

16. The method according to any one of claims 1 to 15, wherein the user behavior comprises at least one of the following behaviors:

the user sets hobbies;

the user views information resources in an information resource library, wherein the plurality of information resources in the information resource group belong to the information resource library;

the user searches information resources in the information resource library;

inferred behavior of a user from behavior of a neighboring user;

The user selecting an interest category from a categories, wherein the information repository includes the a categories;

the user cancelling the selected interest classification;

the user sorts P channels in the channel bar, wherein P is more than or equal to 1; and

and the other users browse, praise, annotate with good looking, collect, share, make notes, annotate with no interest, annotate with no preference, cancel praise, cancel with good looking, cancel with collection and cancel with no preference the information resources in the information resource library.

17. The method of any one of claims 1 to 15, wherein the information resource comprises at least one of an article, video, and audio.

18. An information resource recommendation device, comprising:

the acquisition module is used for acquiring a plurality of groups of information resource groups through various ways, wherein the acquisition of the information resource groups is based on user behaviors, and the user behaviors reflect the interests of the user;

the ordering module is used for ordering the plurality of information resources in the information resource group from high to low according to the interests of the user to obtain an information resource sequence;

the selection module is used for selecting a first preset number of the information resources arranged in the front in the information resource sequence to form a recommended information resource group; and

The recommending module is used for sending a plurality of groups of recommended information resource groups corresponding to the plurality of groups of information resource groups;

the acquisition module is further configured to group B hobbies corresponding to the hobbies of the user into a user initial classification group in the a classifications, where in the user initial classification group, the B hobbies are ranked from high to low according to the hobbies of the user, and the B is greater than or equal to 1; selecting a second preset number of information resources from the information resources corresponding to each taste classification in the Y taste classifications arranged in the front of the user initial classification group to obtain C information resources, wherein the C is equal to the product of the Y and the second preset number, and the Y is more than or equal to 1; selecting a third preset number of information resources from the information resources corresponding to each of the following X hobby classifications in the initial user classification group to obtain D information resources, wherein D is equal to the product of X and the third preset number, B is equal to the sum of X and Y, and X is more than or equal to 1; and forming a first information resource group by the C information resources and the D information resources, wherein the plurality of information resource groups comprise the first information resource group.

19. A computer readable storage medium storing a computer program for executing the recommendation method of information resources according to any of the preceding claims 1-17.

20. An electronic device, the electronic device comprising:

a processor;

a memory for storing the processor-executable instructions;

the processor is configured to perform the information resource recommendation method according to any one of the preceding claims 1-17.