CN108415992B - Resource recommendation method and device and computer equipment - Google Patents
Resource recommendation method and device and computer equipment Download PDFInfo
- Publication number
- CN108415992B CN108415992B CN201810145643.3A CN201810145643A CN108415992B CN 108415992 B CN108415992 B CN 108415992B CN 201810145643 A CN201810145643 A CN 201810145643A CN 108415992 B CN108415992 B CN 108415992B
- Authority
- CN
- China
- Prior art keywords
- user
- recommended
- resource
- resources
- quality
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The application provides a resource recommendation method, a device and computer equipment, wherein the resource recommendation method comprises the following steps: acquiring resources to be recommended; acquiring a user model of a user, and determining a user classification to which the user belongs; determining the correlation between the user and the resource to be recommended according to the matching degree of the user model and the resource to be recommended; and recommending resources to the user according to the user classification to which the user belongs and the correlation between the user and the resources to be recommended. According to the resource recommendation method and device, resource recommendation can be performed by adopting different modes aiming at different types of users, the overall experience of the users is improved, and the quality of the resources recommended to the users is improved on the premise that the relevance of the recommended resources and the users is guaranteed.
Description
Technical Field
The present application relates to the field of internet technologies, and in particular, to a resource recommendation method and apparatus, and a computer device.
Background
In the prior art, an atlas recommendation system is composed of three major parts, namely an individualized queue, a collaborative recommendation queue and a new hot queue. The personalized queue is matched with the interest points and the classification of the articles according to the interest points and the classification of the user model; the collaborative recommendation queue recommends the reading history of similar users to the current user; the new hot queue recommends the on-line click new atlas resource with high presentation rate and timeliness to all users. Only the personalized queue belongs to personalized recommendation in a strict sense, and although the collaborative recommendation queue and the new hot queue are used as interests of users, the collaborative recommendation queue and the new hot queue have no relation with the personalization, so that the atlas recommended by the whole system has a large difference with the expectation of the users.
In addition, the existing atlas recommendation system does not control the quality of the atlas, that is, the quality of the resource recommended by the system cannot be guaranteed. Because the source of the new hot queue is a resource with high on-line click presentation rate, and the quality of the atlas resource is not controlled by the existing atlas recommendation system, the atlas resource recommended by the new hot queue is easy to have low-quality resources, and if the current user is a high-end user, the experience of the currently recommended content is obviously poor. In addition, since the reading history of the user may have some poor resources more or less, the poor resources are also easily brought out in the collaborative recommendation queue, thereby affecting the user experience.
Disclosure of Invention
The present application is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, a first objective of the present application is to provide a resource recommendation method, so as to implement resource recommendation in different ways for different types of users, improve the overall experience of the users, and improve the quality of resources recommended to the users on the premise of ensuring the relevance between the recommended resources and the users.
A second object of the present application is to provide a resource recommendation apparatus.
A third object of the present application is to propose a computer device.
A fourth object of the present application is to propose a non-transitory computer-readable storage medium.
To achieve the above object, an embodiment of a first aspect of the present application provides a resource recommendation method, including: acquiring resources to be recommended; acquiring a user model of a user, and determining a user classification to which the user belongs; determining the correlation between the user and the resource to be recommended according to the matching degree of the user model and the resource to be recommended; and recommending resources to the user according to the user classification to which the user belongs and the correlation between the user and the resources to be recommended.
According to the resource recommendation method, after the resources to be recommended are obtained, the user model of the user is obtained, the user classification to which the user belongs is determined, the correlation between the user and the resources to be recommended is determined according to the matching degree of the user model and the resources to be recommended, and then the resources are recommended to the user according to the user classification to which the user belongs and the correlation between the user and the resources to be recommended, so that resource recommendation can be performed by different modes for different types of users, the overall experience of the user is improved, and the quality of the resources recommended to the user can be improved on the premise that the correlation between the recommended resources and the user is guaranteed.
To achieve the above object, a second aspect of the present application provides a resource recommendation apparatus, including: the acquisition module is used for acquiring resources to be recommended; acquiring a user model of a user, and determining a user classification to which the user belongs; the determining module is used for determining the correlation between the user and the resource to be recommended according to the matching degree between the user model and the resource to be recommended; and the recommending module is used for recommending the resources to the user according to the user classification to which the user belongs and the correlation between the user and the resources to be recommended.
In the resource recommending device in the embodiment of the application, after the obtaining module obtains the resource to be recommended, the user model of the user is obtained, the user classification to which the user belongs is determined, the determining module determines the correlation between the user and the resource to be recommended according to the matching degree between the user model and the resource to be recommended, and then the recommending module recommends the resource to the user according to the user classification to which the user belongs and the correlation between the user and the resource to be recommended, so that resource recommendation can be performed by adopting different modes for different types of users, the overall experience of the user is improved, and the quality of the resource recommended to the user can be improved on the premise of ensuring the correlation between the recommended resource and the user.
To achieve the above object, an embodiment of a third aspect of the present application provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the method as described above when executing the computer program.
In order to achieve the above object, a fourth aspect of the present application provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implementing the method as described above.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flowchart of an embodiment of a resource recommendation method of the present application;
FIG. 2 is a flowchart of another embodiment of a resource recommendation method of the present application;
FIG. 3 is a flowchart of a resource recommendation method according to another embodiment of the present application;
FIG. 4 is a flowchart of a resource recommendation method according to another embodiment of the present application;
FIG. 5 is a flowchart of a resource recommendation method according to another embodiment of the present application;
FIG. 6 is a schematic structural diagram of an embodiment of a resource recommendation device according to the present application;
FIG. 7 is a schematic structural diagram of another embodiment of a resource recommendation device according to the present application;
FIG. 8 is a schematic structural diagram of an embodiment of a computer apparatus according to the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
From the analysis of user behavior, no matter what user, the interested resources are not rejected, and the user can tolerate the resources with low correlation or even irrelevant resources as long as the quality is good. For resources that are not of good quality, the system will also recommend them to users who are interested in such resources, but need to prevent the proliferation of such resources to other users. Therefore, in general, good resources can be recommended to all users, while relatively bad resources need to be recommended to users according to user classification and relevance of resources to users.
Fig. 1 is a flowchart of an embodiment of a resource recommendation method of the present application, and as shown in fig. 1, the resource recommendation method may include:
Specifically, the server may obtain the resource to be recommended after receiving the operation request sent by the user. The operation request may be a page drop-down operation performed by the user when browsing a page, a page click operation performed by the user, or a page long-press operation performed by the user.
The method for acquiring the resource to be recommended comprises the following steps: and screening the resources in the resource library through the personalized queue, the collaborative recommendation queue and the new hot queue to obtain the resources to be recommended.
The obtaining of the user model of the user and the determining of the user classification to which the user belongs may be: and determining whether the user belongs to a high-end user or a common user according to the user model of the user. In this embodiment, the high-end users include users with high requirements on the quality and relevance of the recommended resources, and the common users include users with no particularly high requirements on the quality of the recommended resources, have a certain tolerance on the resources with low quality, and often pay more attention to the relevant users.
In a specific implementation, the user classification to which the user belongs may be determined according to the user model of the user and by combining historical behaviors of the user (e.g., historical browsing and clicking behaviors of the user).
And 103, determining the correlation between the user and the resource to be recommended according to the matching degree of the user model and the resource to be recommended.
And 104, recommending resources to the user according to the user classification to which the user belongs and the correlation between the user and the resources to be recommended.
In this embodiment, the resource to be recommended may include a picture resource, a text resource, and/or a voice resource, and the specific form of the resource to be recommended is not limited in this embodiment.
According to the resource recommendation method, after the resources to be recommended are obtained, a user model of the user is obtained, the user classification to which the user belongs is determined, the correlation between the user and the resources to be recommended is determined according to the matching degree of the user model and the resources to be recommended, and then the resources are recommended to the user according to the user classification to which the user belongs and the correlation between the user and the resources to be recommended, so that resource recommendation can be performed by different modes for different types of users, the overall experience of the user is improved, and the quality of the resources recommended to the user can be improved on the premise that the correlation between the recommended resources and the user is guaranteed.
Fig. 2 is a flowchart of another embodiment of the resource recommendation method of the present application, as shown in fig. 2, in the embodiment shown in fig. 1 of the present application, step 103 may include:
Specifically, in this embodiment, according to the strength of the correlation degree, the correlation may be divided into strong correlation and weak correlation:
1) strong correlation: when the interest point of the resource to be recommended is matched with the interest point of the user model, and the matched interest point is the interest point with high click presentation rate and enough confidence in the user model, it is determined that the resource to be recommended has strong correlation with the user, and the matched interest point may be called a strong interest point. When the more strong interest points are matched, the stronger the relevance of the resource to be recommended to the user is considered.
2) Weak correlation: when the interest point of the resource to be recommended is matched with the interest point of the user model, or the category to which the resource to be recommended belongs is matched with the interest category of the user model, but the click showing rate of the matched interest point in the user model is not particularly high, or the confidence coefficient of the matched interest point is not particularly high, the matched interest point is considered as the weak interest point of the user, and the fact that the resource to be recommended has weak correlation with the user is determined under the condition.
Fig. 3 is a flowchart of a further embodiment of the resource recommendation method of the present application, as shown in fig. 3, in the embodiment shown in fig. 1 of the present application, step 104 may include:
The predetermined threshold may be set according to system performance and/or implementation requirements, and the size of the predetermined threshold is not limited in this embodiment.
Specifically, the high-end users have high requirements on the quality of resources, so for the recommendation of such users, not only the correlation between the recommended resources and the high-end users but also the quality of the resources are guaranteed, and for the high-end users, resources which are related to the above users and have a quality higher than a predetermined threshold need to be mined for recommendation.
In specific implementation, for a high-end user, after searching for a resource which is related to the user and has a quality higher than a predetermined threshold value in the resource to be recommended, when performing fusion sequencing on the searched resource, the weight of a resource which is strongly related to the user in the searched resource can be increased, so that the resource which is strongly related to the high-end user and has a quality higher than the predetermined threshold value can be preferentially displayed.
Fig. 4 is a flowchart of a further embodiment of the resource recommendation method of the present application, as shown in fig. 4, in the embodiment shown in fig. 1 of the present application, step 104 may include:
And 403, performing fusion sequencing on the searched resources, and increasing the weight of the resources which are related to the user and have the quality higher than a preset threshold value in the searched resources when performing fusion sequencing on the searched resources.
In this embodiment, the quality requirement of the recommended resources by the general user is not particularly high, and the general user often pays more attention to the interest correlation, so that for the recommendation of such users, the recommendation mode should be determined according to the correlation between the user and the resources to be recommended. When the resource to be recommended is judged to be relevant to the user, the user generally has an interest in clicking, and can be used as a recommendation candidate set as long as the resource does not belong to illegal contents, and when the resource to be recommended belongs to high-quality resources, the resource can be properly weighted to ensure the preferential display; when the content irrelevant to the user appears, the quality of the resource to be recommended needs to be ensured, so that the user does not have a sense of disagreement on the resource, and the user can be more objectively mined and diffused with the interest of the user through the behavior of the user on the resource.
In a specific implementation, when performing fusion sorting on the searched resources, the weight of the resource, which is related to the user and has a quality higher than a predetermined threshold, in the searched resources may be increased, and further, the weight of the resource, which is strongly related to the user and has a quality higher than a predetermined threshold, may be set to be greater than the weight of the resource, which is weakly related to the user and has a quality higher than a predetermined threshold, so as to ensure that the resource, which is strongly related to the user and has a quality higher than a predetermined threshold, is preferentially displayed.
And step 404, recommending the sorted resources to the user.
In the embodiments shown in fig. 3 and 4 of the present application, determining the quality of the resource to be recommended may be: and determining the quality of the resources to be recommended according to the quality scores of the resources to be recommended, the plagiarism degree of the resources to be recommended and/or the vulgar degree of the resources to be recommended.
Specifically, according to the quality score of the resource to be recommended, the plagiarism degree of the resource to be recommended, and/or the vulgar degree of the resource to be recommended, determining that the quality of the resource to be recommended may be: and when the quality score of the resource to be recommended is higher than a first threshold, the score of the plagiarism degree of the resource to be recommended is lower than a second threshold and/or the score of the vulgar degree of the resource to be recommended is lower than a third threshold, determining that the quality of the resource to be recommended is higher than a preset threshold.
The first threshold, the second threshold, and the third threshold may be set according to system performance and/or implementation requirements during specific implementation, and the size of the first threshold, the size of the second threshold, and the size of the third threshold are not limited in this embodiment.
In this embodiment, the quality of the resource to be recommended may be determined from the following dimensions:
a) the quality fraction of the resource itself: the resource can obtain a corresponding quality score through an auditing and scoring mechanism on the data stream, the higher the score is, the better the quality of the resource is, which is the most basic condition for identifying the quality of the resource, and once the score of the resource is not met and is lower than the qualified score, the resource can be filtered;
b) the plagiarism degree of the resource: judging the plagiarism degree of the resource on the data stream, wherein the lower the score is, the lower the plagiarism degree is, namely the more novel the resource is;
c) the degree of popularity of the resource: the popularity of a resource is judged on the data stream, and a higher score indicates that the resource is popular and that the resource is filtered when above a certain threshold.
Due to the filtering mechanism on the data stream, the poor quality and the high quality of the resources are only relative, the poor quality resources do not mean unqualified resources, and the resources should not be discarded, otherwise waste is easily caused. For the mining of high-quality resources, the three dimensions are integrated, when the resources meet certain quality scores, novelty and non-trivial conditions, the resources are judged to be high-quality resources, namely resources with the quality higher than a preset threshold value, and the other resources are poor-quality resources.
Fig. 5 is a schematic diagram of a further embodiment of the resource recommendation method of the present application, and as shown in fig. 5, a recommendation system usually wants to recommend a good resource to a user. As a personalized recommendation system, the content which is interested by the user is expected to be shown to the user as much as possible, and meanwhile, the interest of the user is expected to be diffused and mined. Based on the quality and the related two dimensions, the user behavior is analyzed, the interest is a main factor influencing the user click, and it can be considered that most of common users have certain tolerance on the quality of a certain type of resource when the common users are interested in the resource, and have higher requirements on the quality of the resource which is not interested in the resource; in addition, for a small number of high-end users, they have high quality requirements on resources under any condition. Therefore, in general, good resources can be recommended to all users, while relatively bad resources need to be recommended to users according to user classification and relevance of resources to users.
The resource recommendation method provided by the embodiment of the application can improve the quality of recommended resources, can recommend the resources according to different types of users in different modes, can improve the overall experience of the users, has high display weight of the resources with high relevance to the users, and can integrally improve the relevance of the recommended resources to the users. In addition, the resource recommendation method provided by the embodiment of the application still reserves part of non-personalized recommendation modes, so that the recommended data has certain diversity and diffusivity.
Fig. 6 is a schematic structural diagram of an embodiment of the resource recommendation device in the present application, where the resource recommendation device in the embodiment of the present application can implement the resource recommendation method provided in the embodiment of the present application. As shown in fig. 6, the resource recommendation apparatus may include: an acquisition module 61, a determination module 62 and a recommendation module 63;
the acquiring module 61 is configured to acquire a resource to be recommended; acquiring a user model of a user, and determining a user classification to which the user belongs;
specifically, the obtaining module 61 may obtain the resource to be recommended after receiving an operation request sent by a user; the operation request may be a page drop-down operation performed by the user when browsing a page, a page click operation performed by the user, or a page long-press operation performed by the user.
The obtaining module 61 may specifically screen the resources in the resource library through the personalized queue, the collaborative recommendation queue, and the new hot queue, so as to obtain the resources to be recommended.
The obtaining module 61 obtains a user model of a user, and determining a user classification to which the user belongs may be: and determining whether the user belongs to a high-end user or a common user according to the user model of the user. In this embodiment, the high-end users include users with high requirements on the quality and relevance of the recommended resources, and the common users include users with no particularly high requirements on the quality of the recommended resources, have a certain tolerance on the resources with low quality, and often pay more attention to the relevant users.
In a specific implementation, the obtaining module 61 may determine, according to the user model of the user, a user category to which the user belongs, in combination with the historical behavior of the user (for example, the historical browsing and clicking behavior of the user).
And a determining module 62, configured to determine, according to a matching degree between the user model and the resource to be recommended, a correlation between the user and the resource to be recommended.
And the recommending module 63 is configured to recommend resources to the user according to the user classification to which the user belongs and the correlation between the user and the resource to be recommended.
In this embodiment, the resource to be recommended may include a picture resource, a text resource, and/or a voice resource, and the specific form of the resource to be recommended is not limited in this embodiment.
In the resource recommending device, after the obtaining module 61 obtains the resource to be recommended, the user model of the user is obtained, the user classification to which the user belongs is determined, the determining module 62 determines the correlation between the user and the resource to be recommended according to the matching degree between the user model and the resource to be recommended, and then the recommending module 63 recommends the resource to the user according to the user classification to which the user belongs and the correlation between the user and the resource to be recommended, so that resource recommendation can be performed by adopting different modes for different types of users, the overall experience of the user is improved, and the quality of the resource recommended to the user can be improved on the premise of ensuring the correlation between the recommended resource and the user.
Fig. 7 is a schematic structural diagram of another embodiment of the resource recommendation device, in this embodiment, the determining module 62 is specifically configured to obtain an interest point of the resource to be recommended and/or a category to which the resource to be recommended belongs, and determine that the user is related to the resource to be recommended when the interest point of the resource to be recommended is matched with the interest point of the user model and/or the category to which the resource to be recommended belongs is matched with the interest category of the user model; and when the interest point of the resource to be recommended is not matched with the interest point of the user model and the category to which the resource to be recommended belongs is not matched with the interest category of the user model, determining that the user is not related to the resource to be recommended.
Specifically, in this embodiment, according to the strength of the correlation degree, the correlation may be divided into strong correlation and weak correlation:
1) strong correlation: when the interest point of the resource to be recommended is matched with the interest point of the user model, and the matched interest point is the interest point with high click presentation rate and enough confidence in the user model, it is determined that the resource to be recommended has strong correlation with the user, and the matched interest point may be called a strong interest point. When the more strong interest points are matched, the stronger the relevance of the resource to be recommended to the user is considered.
2) Weak correlation: when the interest point of the resource to be recommended is matched with the interest point of the user model, or the category to which the resource to be recommended belongs is matched with the interest category of the user model, but the click showing rate of the matched interest point in the user model is not particularly high, or the confidence coefficient of the matched interest point is not particularly high, the matched interest point is considered as the weak interest point of the user, and the fact that the resource to be recommended has weak correlation with the user is determined under the condition.
Compared with the resource recommendation device shown in fig. 6, the difference is that in the resource recommendation device shown in fig. 7, the recommendation module 63 may include: a quality determination sub-module 631, a lookup sub-module 632, a ranking sub-module 633, and a resource recommendation sub-module 634;
in an implementation manner of this embodiment, the quality determining sub-module 631 is configured to determine the quality of the resource to be recommended;
a searching sub-module 632, configured to search, when the user belongs to a high-end user, resources that are related to the user and have a quality higher than a predetermined threshold value from among the resources to be recommended;
the sorting submodule 633 is used for performing fusion sorting on the resources searched by the searching submodule 632;
and the resource recommending submodule 634 is configured to fuse the sorted resources by the sorting submodule 633 and recommend the resources to the user.
The predetermined threshold may be set according to system performance and/or implementation requirements, and the size of the predetermined threshold is not limited in this embodiment.
Specifically, the high-end users have high requirements on the quality of resources, so for the recommendation of such users, not only the correlation between the recommended resources and the high-end users but also the quality of the resources are guaranteed, and for the high-end users, resources which are related to the above users and have a quality higher than a predetermined threshold need to be mined for recommendation.
In specific implementation, for a high-end user, after the searching sub-module 632 searches for a resource, which is related to the user and has a quality higher than a predetermined threshold, in the resource to be recommended, and when the sorting sub-module 633 performs fusion sorting on the searched resource, the weight of a resource, which is strongly related to the user, in the searched resource can be increased, so that the resource, which is strongly related to the high-end user and has a quality higher than the predetermined threshold, can be preferentially displayed.
In another implementation manner of this embodiment, the quality determining sub-module 631 is configured to determine the quality of the resource to be recommended;
a searching submodule 632, configured to search, when the user belongs to a common user, resources related to the user from among the resources to be recommended, and search, from among the resources to be recommended, resources that are not related to the user but have a quality higher than a predetermined threshold;
the sorting submodule 633 is configured to perform fusion sorting on the resources found by the finding submodule 632, and when performing fusion sorting on the found resources, increase the weight of a resource, which is related to the user and has a quality higher than a predetermined threshold, in the found resources;
the resource recommending sub-module 634 is configured to recommend the resources ranked by the ranking sub-module 633 to the user.
In this embodiment, the quality requirement of the recommended resources by the general user is not particularly high, and the general user often pays more attention to the interest correlation, so that for the recommendation of such users, the recommendation mode should be determined according to the correlation between the user and the resources to be recommended. When the resource to be recommended is judged to be relevant to the user, the user generally has an interest in clicking, and can be used as a recommendation candidate set as long as the resource does not belong to illegal contents, and when the resource to be recommended belongs to high-quality resources, the resource can be properly weighted to ensure the preferential display; when the content irrelevant to the user appears, the quality of the resource to be recommended needs to be ensured, so that the user does not have a sense of disagreement on the resource, and the user can be more objectively mined and diffused with the interest of the user through the behavior of the user on the resource.
In a specific implementation, when performing fusion sorting on the searched resources, the sorting sub-module 633 may increase the weight of the resource, which is related to the user and has a quality higher than a predetermined threshold, in the searched resources, and further may set the weight of the resource, which is strongly related to the user and has a quality higher than the predetermined threshold, to be greater than the weight of the resource, which is weakly related to the user and has a quality higher than the predetermined threshold, so as to ensure that the resource, which is strongly related to the user and has a quality higher than the predetermined threshold, is preferentially displayed.
The quality determining sub-module 631 is specifically configured to determine the quality of the resource to be recommended according to the quality score of the resource to be recommended, the plagiarism degree of the resource to be recommended, and/or the vulgar degree of the resource to be recommended.
The quality determining sub-module 631 is specifically configured to determine that the quality of the resource to be recommended is higher than a predetermined threshold when the quality score of the resource to be recommended is higher than a first threshold, the score of the plagiarism degree of the resource to be recommended is lower than a second threshold, and/or the score of the vulgar degree of the resource to be recommended is lower than a third threshold.
The first threshold, the second threshold, and the third threshold may be set according to system performance and/or implementation requirements during specific implementation, and the size of the first threshold, the size of the second threshold, and the size of the third threshold are not limited in this embodiment.
In this embodiment, the quality of the resource to be recommended may be determined from the following dimensions:
a) the quality fraction of the resource itself: the resource can obtain a corresponding quality score through an auditing and scoring mechanism on the data stream, the higher the score is, the better the quality of the resource is, which is the most basic condition for identifying the quality of the resource, and once the score of the resource is not met and is lower than the qualified score, the resource can be filtered;
b) the plagiarism degree of the resource: judging the plagiarism degree of the resource on the data stream, wherein the lower the score is, the lower the plagiarism degree is, namely the more novel the resource is;
c) the degree of popularity of the resource: the popularity of a resource is judged on the data stream, and a higher score indicates that the resource is popular and that the resource is filtered when above a certain threshold.
Due to the filtering mechanism on the data stream, the poor quality and the high quality of the resources are only relative, the poor quality resources do not mean unqualified resources, and the resources should not be discarded, otherwise waste is easily caused. For the mining of high-quality resources, the above three dimensions are integrated, and when the resources meet a certain quality score, novelty and non-trivial property, the quality determination sub-module 631 may determine that the resources are high-quality resources, that is, resources whose quality is higher than a predetermined threshold, and relatively, the remaining resources are poor-quality resources.
Fig. 8 is a schematic structural diagram of an embodiment of a computer device according to the present application, where the computer device may include a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the resource recommendation method according to the present application may be implemented.
The computer device may be a server or a terminal device, and the specific form of the computer device is not limited in this embodiment.
FIG. 8 illustrates a block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present application. The computer device 12 shown in fig. 8 is only an example, and should not bring any limitation to the function and the scope of use of the embodiments of the present application.
As shown in FIG. 8, computer device 12 is in the form of a general purpose computing device. The components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
Computer device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by computer device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system Memory 28 may include computer system readable media in the form of volatile Memory, such as Random Access Memory (RAM) 30 and/or cache Memory 32. Computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 8, and commonly referred to as a "hard drive"). Although not shown in FIG. 8, a disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a Compact disk Read Only Memory (CD-ROM), a Digital versatile disk Read Only Memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the application.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally perform the functions and/or methodologies of the embodiments described herein.
Computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with computer device 12, and/or with any devices (e.g., network card, modem, etc.) that enable computer device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Moreover, computer device 12 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public Network such as the Internet) via Network adapter 20. As shown in FIG. 8, the network adapter 20 communicates with the other modules of the computer device 12 via the bus 18. It should be appreciated that although not shown in FIG. 8, other hardware and/or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 16 executes various functional applications and data processing by executing programs stored in the system memory 28, for example, to implement the resource recommendation method provided in the embodiment of the present application.
The embodiment of the present application further provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the resource recommendation method provided in the embodiment of the present application can be implemented.
The non-transitory computer readable storage medium described above may take any combination of one or more computer readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read Only Memory (ROM), an Erasable Programmable Read Only Memory (EPROM), a flash Memory, an optical fiber, a portable compact disc Read Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, 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 computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of Network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. 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, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection portion (electronic device) having one or more wires, a portable computer cartridge (magnetic device), a Random Access Memory (RAM), a Read Only Memory (ROM), an Erasable Programmable Read Only Memory (EPROM) or a flash Memory, an optical fiber device, and a portable Compact Disc Read Only Memory (CD-ROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic Gate circuit for implementing a logic function on a data signal, an asic having an appropriate combinational logic Gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), and the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (11)
1. A resource recommendation method, comprising:
acquiring resources to be recommended;
obtaining a user model of a user, and determining a user classification to which the user belongs, wherein the user classification comprises: high-end users and ordinary users;
determining the correlation between the user and the resource to be recommended according to the matching degree of the user model and the resource to be recommended;
recommending resources to the user according to the user classification to which the user belongs and the correlation between the user and the resources to be recommended;
wherein recommending resources to the user according to the user classification to which the user belongs and the correlation between the user and the resources to be recommended comprises:
determining the quality of the resource to be recommended;
when the user belongs to a common user, searching resources related to the user in the resources to be recommended, and searching resources which are not related to the user but have quality higher than a preset threshold value in the resources to be recommended;
performing fusion sequencing on the searched resources, and increasing the weight of the resources which are related to the user and have the quality higher than a preset threshold value in the searched resources when performing fusion sequencing on the searched resources;
recommending the sorted resources to the user;
the determining the quality of the resource to be recommended comprises:
and determining the quality of the resources to be recommended according to the quality scores of the resources to be recommended, the plagiarism degree of the resources to be recommended and/or the vulgar degree of the resources to be recommended.
2. The method according to claim 1, wherein the determining the relevance of the user to the resource to be recommended according to the matching degree of the user model and the resource to be recommended comprises:
obtaining interest points of the resources to be recommended and/or classifications to which the resources to be recommended belong;
if the interest point of the resource to be recommended is matched with the interest point of the user model, and/or the category to which the resource to be recommended belongs is matched with the interest category of the user model, determining that the user is related to the resource to be recommended;
and if the interest point of the resource to be recommended is not matched with the interest point of the user model, and the classification to which the resource to be recommended belongs is not matched with the interest classification of the user model, determining that the user is not related to the resource to be recommended.
3. The method according to claim 1, wherein the recommending resources to the user according to the user classification to which the user belongs and the relevance of the user to the resources to be recommended comprises:
determining the quality of the resource to be recommended;
and when the user belongs to a high-end user, searching resources which are related to the user and have the quality higher than a preset threshold value in the resources to be recommended, fusing and sequencing the searched resources, and recommending the resources to the user.
4. The method according to claim 1, wherein the determining the quality of the resource to be recommended according to the quality score of the resource to be recommended, the plagiarism degree of the resource to be recommended and/or the vulgar degree of the resource to be recommended comprises:
when the quality score of the resource to be recommended is higher than a first threshold, the score of the plagiarism degree of the resource to be recommended is lower than a second threshold and/or the score of the vulgar degree of the resource to be recommended is lower than a third threshold, determining that the quality of the resource to be recommended is higher than a preset threshold.
5. The method according to any one of claims 1 to 3, wherein the obtaining the resource to be recommended comprises:
and screening the resources in the resource library through the personalized queue, the collaborative recommendation queue and the new hot queue to obtain the resources to be recommended.
6. A resource recommendation device, comprising:
the acquisition module is used for acquiring resources to be recommended; and acquiring a user model of a user, and determining a user classification to which the user belongs, wherein the user classification comprises: high-end users and ordinary users;
the determining module is used for determining the correlation between the user and the resource to be recommended according to the matching degree between the user model and the resource to be recommended;
the recommending module is used for recommending resources to the user according to the user classification to which the user belongs and the correlation between the user and the resources to be recommended;
the quality determination submodule is used for determining the quality of the resource to be recommended;
the searching sub-module is used for searching resources related to the user in the resources to be recommended and searching resources which are not related to the user but have quality higher than a preset threshold value in the resources to be recommended when the user belongs to a common user;
the sorting submodule is used for performing fusion sorting on the resources searched by the searching submodule, and increasing the weight of the resources which are related to the user and have the quality higher than a preset threshold value in the searched resources when performing fusion sorting on the searched resources;
the resource recommending submodule is used for recommending the resources sequenced by the sequencing submodule to the user;
the quality determination submodule is specifically configured to determine the quality of the resource to be recommended according to the quality score of the resource to be recommended, the plagiarism degree of the resource to be recommended, and/or the vulgar degree of the resource to be recommended.
7. The apparatus of claim 6,
the determining module is specifically configured to obtain an interest point of the resource to be recommended and/or a category to which the resource to be recommended belongs; when the interest point of the resource in the resource library is matched with the interest point of the user model and/or the category to which the resource belongs is matched with the interest category of the user model, determining that the user is related to the resource; determining that the user is not related to the resource when the point of interest of the resource in the resource pool does not match the point of interest of the user model and the category to which the resource belongs does not match the category of interest of the user model.
8. The apparatus of claim 6, wherein the recommendation module comprises:
the quality determination submodule is used for determining the quality of the resource to be recommended;
the searching sub-module is used for searching resources which are related to the user and have the quality higher than a preset threshold value in the resources to be recommended when the user belongs to a high-end user;
the sorting submodule is used for performing fusion sorting on the resources searched by the searching submodule;
and the resource recommendation submodule is used for fusing the sequenced resources by the sequencing submodule and recommending the resources to the user.
9. The apparatus of claim 6,
the quality determination submodule is specifically configured to determine that the quality of the resource to be recommended is higher than a predetermined threshold when the quality score of the resource to be recommended is higher than a first threshold, the score of the plagiarism degree of the resource to be recommended is lower than a second threshold, and/or the score of the vulgar degree of the resource to be recommended is lower than a third threshold.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of claims 1-5 when executing the computer program.
11. A non-transitory computer-readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810145643.3A CN108415992B (en) | 2018-02-12 | 2018-02-12 | Resource recommendation method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810145643.3A CN108415992B (en) | 2018-02-12 | 2018-02-12 | Resource recommendation method and device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108415992A CN108415992A (en) | 2018-08-17 |
| CN108415992B true CN108415992B (en) | 2022-03-04 |
Family
ID=63128509
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810145643.3A Active CN108415992B (en) | 2018-02-12 | 2018-02-12 | Resource recommendation method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108415992B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109711875B (en) * | 2018-12-19 | 2021-04-20 | 口碑(上海)信息技术有限公司 | Content recommendation method and device |
| CN112784142A (en) * | 2019-10-24 | 2021-05-11 | 北京搜狗科技发展有限公司 | Information recommendation method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004094384A (en) * | 2002-08-29 | 2004-03-25 | Ntt Comware Corp | Recommendation device and method for setting taste information |
| CN102651033A (en) * | 2012-04-09 | 2012-08-29 | 百度在线网络技术（北京）有限公司 | Method and device for recommending online resource |
| CN103108049A (en) * | 2013-02-20 | 2013-05-15 | 杭州东信北邮信息技术有限公司 | Method for providing personalized page for mobile terminal user |
| CN106802915A (en) * | 2016-12-09 | 2017-06-06 | 宁波大学 | A kind of academic resources based on user behavior recommend method |
| CN106815216A (en) * | 2015-11-30 | 2017-06-09 | 北京云莱坞文化传媒有限公司 | A kind of story screening and the method and apparatus for precisely representing |
| CN107609060A (en) * | 2017-08-28 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | Resource recommendation method and device |
-
2018
- 2018-02-12 CN CN201810145643.3A patent/CN108415992B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004094384A (en) * | 2002-08-29 | 2004-03-25 | Ntt Comware Corp | Recommendation device and method for setting taste information |
| CN102651033A (en) * | 2012-04-09 | 2012-08-29 | 百度在线网络技术（北京）有限公司 | Method and device for recommending online resource |
| CN103108049A (en) * | 2013-02-20 | 2013-05-15 | 杭州东信北邮信息技术有限公司 | Method for providing personalized page for mobile terminal user |
| CN106815216A (en) * | 2015-11-30 | 2017-06-09 | 北京云莱坞文化传媒有限公司 | A kind of story screening and the method and apparatus for precisely representing |
| CN106802915A (en) * | 2016-12-09 | 2017-06-06 | 宁波大学 | A kind of academic resources based on user behavior recommend method |
| CN107609060A (en) * | 2017-08-28 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | Resource recommendation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108415992A (en) | 2018-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109087135B (en) | Mining method and device for user intention, computer equipment and readable medium | |
| CN108319723B (en) | Picture sharing method and device, terminal and storage medium | |
| US20170293419A1 (en) | Method and system for context based tab management | |
| US10977317B2 (en) | Search result displaying method and apparatus | |
| US11062086B2 (en) | Personalized book-to-movie adaptation recommendation | |
| CN107656787B (en) | Method for generating topics based on electronic book, computing device and computer storage medium | |
| US20130132851A1 (en) | Sentiment estimation of web browsing user | |
| CN109511015B (en) | Multimedia resource recommendation method, device, storage medium and equipment | |
| US11182447B2 (en) | Customized display of emotionally filtered social media content | |
| CN113486252A (en) | Search result display method, device, equipment and medium | |
| US9223455B2 (en) | User preference analysis method and device | |
| US20140143224A1 (en) | Method and system for generating search results from a user-selected area | |
| CN103902670A (en) | Search recommendation method and device | |
| CN106021449A (en) | Searching method and device for mobile terminal and mobile terminal | |
| US11250468B2 (en) | Prompting web-based user interaction | |
| CN113486253A (en) | Search result display method, device, equipment and medium | |
| CN108415992B (en) | Resource recommendation method and device and computer equipment | |
| CN108334626B (en) | News column generation method and device and computer equipment | |
| CN111770376A (en) | Information display method, device, system, electronic equipment and storage medium | |
| CN111753114A (en) | Image pre-labeling method and device and electronic equipment | |
| CN111738316A (en) | Image classification method and device for zero sample learning and electronic equipment | |
| CN110309414B (en) | Content recommendation method, content recommendation device and electronic equipment | |
| WO2020026012A1 (en) | Method, apparatus, device/terminal/server and storage medium for content interest collection and content data recommendation | |
| CN117171406A (en) | Application program function recommendation method, device, equipment and storage medium | |
| US20200242178A1 (en) | Search processing method and apparatus based on clipboard data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |