CN112653907A - Video recommendation method and device - Google Patents
Video recommendation method and device Download PDFInfo
- Publication number
- CN112653907A CN112653907A CN202011477735.5A CN202011477735A CN112653907A CN 112653907 A CN112653907 A CN 112653907A CN 202011477735 A CN202011477735 A CN 202011477735A CN 112653907 A CN112653907 A CN 112653907A
- Authority
- CN
- China
- Prior art keywords
- video
- user
- target
- feature
- determining
- 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.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
Abstract
The invention provides a video recommendation method, a video recommendation device, computer equipment and a computer readable storage medium, wherein the method comprises the following steps: determining the dominant characteristic and the inferior characteristic of the user; acquiring a video watching record of a user; determining a target video corresponding to the target dominant features; determining a feature tag corresponding to the target dominant feature as a feature tag of the target video; and determining the video to be recommended corresponding to the inferior features of the user to be recommended. According to the method and the device, the advantage characteristics of the user and the history record of watching videos can be utilized to determine the target video which enables the user to have the target advantage characteristics, so that the corresponding relation between the characteristic label corresponding to the target advantage characteristics and the target video is established, namely the video is directly associated with the characteristics of the user, the video to be recommended corresponding to the disadvantage characteristics of the user to be recommended is further determined, the video to be recommended which is recommended to the user to be recommended is ensured to be matched with the disadvantage characteristics of the user to be recommended, and therefore the accuracy of video recommendation is improved.
Description
Technical Field
The invention belongs to the technical field of resource recommendation, and particularly relates to a video recommendation method and device, computer equipment and a computer readable storage medium.
Background
The online education is a teaching mode taking a network as a medium, and students can learn at any time and any place by means of online video resources, so that the time and space limitations are really broken.
At present, in order to improve the level of users through video learning, in the prior art, most of videos are subjected to label classification, and video lists under all labels are provided, so that users can independently select and learn according to the lacking ability of the users. The method for automatically generating the classification label of the video comprises the following steps: 1. based on image feature recognition, analyzing image features of key frames in the video, and determining semantic information of the key frames, so that specific content of the video is determined according to the semantic information of the key frames of the video, and further a video classification label is generated; 2. based on text mining, text information contained in a video is analyzed to generate a video classification label, for example, a keyword extracted from the video through text mining is "company development", and then "company development" can be determined as the classification label of the video.
However, in the existing scheme, the video classification tag determined for the video is only related to the image features of the video itself or the text information included in the video, and is not matched with the lacking capability of the user, for example, the lacking capability of the user is self-management capability, but the video classification tag corresponding to the capability does not exist in the video list, so that the video corresponding to the lacking capability of the user cannot be accurately recommended to the user, and the recommendation accuracy is low.
Disclosure of Invention
In view of this, the invention provides a video recommendation method and apparatus, a computer device, and a computer-readable storage medium, which solve the problems that a video corresponding to the user's lack capability cannot be accurately recommended to a user in the current scheme, and the video recommendation accuracy is low.
According to a first aspect of the present invention, there is provided a video recommendation method, including:
determining a characteristic category table corresponding to a user, wherein the characteristic category table records the dominant characteristic and the inferior characteristic of the user;
acquiring a video watching record of the user, wherein a history record of the video watched by the user is recorded in the video watching record;
determining a target video corresponding to the target dominant feature according to the dominant feature of the user and the history of videos watched by the user;
determining a feature tag corresponding to the target dominant feature as a feature tag of the target video, and establishing a corresponding relation between the feature tag and the target video;
determining a target feature tag corresponding to the disadvantaged feature of a user to be recommended, determining a target video corresponding to the target feature tag as a video to be recommended according to the corresponding relation between the feature tag of the target video and the target video, and recommending the video to be recommended to the user to be recommended.
According to a second aspect of the present invention, there is provided a video recommendation apparatus, which may include:
the system comprises a first determining module, a second determining module and a judging module, wherein the first determining module is used for determining a characteristic category table corresponding to a user, and the characteristic category table records the superiority characteristic and the inferiority characteristic of the user;
the acquisition module is used for acquiring a video watching record of the user, wherein a history record of the video watched by the user is recorded in the video watching record;
the second determination module is used for determining a target video corresponding to the target dominant feature according to the dominant feature of the user and the history record of the video watched by the user;
the establishing module is used for determining the feature tag corresponding to the target dominant feature as the feature tag of the target video and establishing the corresponding relation between the feature tag and the target video;
and the third determining module is used for determining a target feature tag corresponding to the inferior feature of the user to be recommended, determining the target video corresponding to the target feature tag as the video to be recommended according to the corresponding relation between the feature tag of the target video and the target video, and recommending the video to be recommended to the user to be recommended.
In a third aspect, an embodiment of the present invention provides a computer device, where the computer device includes:
a memory for storing program instructions;
and the processor is used for calling the program instructions stored in the memory and executing the steps included in the video recommendation method according to the first aspect according to the obtained program instructions.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when executed by a processor, the computer program implements the steps of the video recommendation method according to the first aspect.
Aiming at the prior art, the invention has the following advantages:
the invention provides a video recommendation method, which comprises the following steps: determining a characteristic category table corresponding to the user, wherein the characteristic category table records the advantage characteristics and the disadvantage characteristics of the user; acquiring a video watching record of a user, wherein the video watching record records the history of watching a video by the user; determining a target video corresponding to the target dominant feature according to the dominant feature of the user and the historical record of the video watched by the user; determining a feature tag corresponding to the target dominant feature as a feature tag of a target video, and establishing a corresponding relation between the feature tag and the target video; determining a target feature tag corresponding to the disadvantaged feature of the user to be recommended, determining a target video corresponding to the target feature tag as a video to be recommended according to the corresponding relation between the feature tag of the target video and the target video, and recommending the video to be recommended to the user to be recommended. According to the method and the device, the advantage characteristics of the user and the historical record of the video watched by the user can be utilized to determine the target video enabling the user to have the target advantage characteristics, so that the characteristic label corresponding to the target advantage characteristics is determined as the characteristic label of the target video, the corresponding relation between the characteristic label and the target video is established, namely the video is directly associated with the characteristics of the user, the video to be recommended corresponding to the disadvantage characteristics of the user to be recommended can be determined according to the corresponding relation, the video to be recommended which is recommended to the user to be recommended is ensured to be matched with the disadvantage characteristics of the user to be recommended, and the accuracy of video recommendation is improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flowchart illustrating steps of a method for recommending a video according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating steps of another video recommendation method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a video recommendation interface according to an embodiment of the present invention;
fig. 4 is a block diagram of a video recommendation apparatus according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Fig. 1 is a flowchart illustrating steps of a method for recommending a video according to an embodiment of the present invention, where as shown in fig. 1, the method may include:
step 101, determining a feature category table corresponding to a user, wherein the feature category table records the advantage features and the disadvantage features of the user.
In this step, a feature category table in which an advantage feature and an disadvantage feature of the user are recorded may be first determined, wherein the advantage feature may be a feature good or possessed by the user and the disadvantage feature may be a feature not good or possessed by the user.
Table 1 describes a feature category table of the dominant feature and the inferior feature of the user A, B, C, where k features 1,2, and 3 … features k that measure the user ability of the user may be predetermined, if a certain feature is the dominant feature of the corresponding user, the identifier of the feature corresponding to the user is denoted as 1, and if a certain feature is the inferior feature of the corresponding user, the identifier of the feature corresponding to the user is denoted as 0, as shown in table 1, feature 1 and feature k are the dominant feature of the user a, and feature 2 and feature 3 are the inferior feature of the user a; the feature 3 is the dominant feature of the user B, and the feature 1, the feature 2 and the feature k are all the inferior features of the user B; feature 2 is the dominant feature of user a and features 1, 3 and k are the disadvantaged features of user C.
| Feature 1 | Feature 2 | Feature 3 | … | Feature k | |
| User A | 1 | 0 | 0 | … | 1 |
| User B | 0 | 0 | 1 | … | 0 |
| User C | 0 | 1 | 0 | … | 0 |
TABLE 1
And 102, acquiring a video watching record of the user, wherein the video watching record records a history record of the video watched by the user.
In this step, a video watching record of the user may be obtained, where the video watching record records a history of watching videos of the user, for example, the video watching record may record the watching times of the plurality of users watching a plurality of learning videos in the video library respectively, or may record information such as watching duration or watching frequency of the plurality of learning videos watched by the plurality of users in the video library within a preset time period.
Table 2 states that the user A, B, C views m videos respectively: the number of times of watching video 1, video 2 …, video m, as shown in table 2, the number of times of watching video 1 by user a is 1, the number of times of watching video 2 is 2, and the number of times of watching video m is 3; the number of times that the user B watches the video 1 is 0, the number of times that the user B watches the video 2 is 4, and the number of times that the user B watches the video m is 1; the number of times that the user C watches the video 1 is 2, the number of times that the user C watches the video 2 is 1, and the number of times that the user C watches the video m is 4.
| Video 1 | Video 2 | … | Video m | |
| User A | 1 | 2 | … | 3 |
| User B | 0 | 4 | … | 1 |
| User C | 2 | 1 | … | 4 |
TABLE 2
And 103, determining a target video corresponding to the target dominant characteristic according to the dominant characteristic of the user and the history of videos watched by the user.
In this step, the dominant feature of each user and the history of the video watched by the user may be determined according to the feature category table and the video watching record, and then the target video corresponding to the target dominant feature in the dominant features may be determined.
Specifically, in general, if it is determined that the frequency or frequency of watching a video by a user is higher or the duration of watching the video is longer according to the history of watching the video by the user with a target advantageous feature, it may be considered that the user has or excels in the target advantageous feature because the frequency or frequency of watching the video is higher or the duration of watching the video is longer, that is, the video has a greater effect of improving the target advantageous feature, so that the video may be determined as the target video corresponding to the target advantageous feature.
Further, the history of videos watched by a plurality of users is comprehensively considered, if the number of times or the frequency of watching a certain video by the user D with the target advantage feature is higher than that of watching the video by the user E with other advantage features, or the duration of watching a certain video by the user D with the target advantage feature is longer than that of watching the target video by the user E with other advantage features, it can be considered that the user D has or excels in the target advantage feature, that is, the video has a larger promotion effect on the target advantage feature, so that the video can be determined as the target video corresponding to the target advantage feature.
For example, if the total number of views of the video 1 is 100, the user with the feature 1 views 40 times, the user with the feature 2 views 5 times, and the user with the feature 3 views 11.
And step 104, determining the feature label corresponding to the target dominant feature as the feature label of the target video, and establishing a corresponding relation between the feature label and the target video.
In the step, after the target video corresponding to the target dominant feature is determined, the feature tag corresponding to the target dominant feature can be determined as the feature tag of the corresponding target video, and the corresponding relationship between the feature tag and the target video is established, so that the association relationship between the video and the features of the user is directly established, the problem that the tags determined for the video through technologies such as image feature recognition or text mining are not matched with the features of the user is avoided, the user can intuitively and accurately select the video matched with the disadvantageous features required to be improved according to the tags of the video, and the learning efficiency is improved.
Table 3 describes the target video and the feature label corresponding to the target video, and as shown in table 3, the identifier of the target dominant feature may be used as the feature label corresponding to the target dominant feature, for example, if the target video is video 1 and the target dominant feature corresponding to video 1 is feature 2 and feature 1, respectively, the identifiers "feature 2" and "feature 1" of the target dominant feature may be used as the feature label of video 1; if the target video is video 2 and the target dominant features corresponding to the video 2 are feature 3 and feature 1, respectively, the identifiers "feature 3" and "feature 1" of the target dominant features can be used as feature labels of the video 2; if the target video is a video m and the target dominant features corresponding to the video m are respectively feature 2 and feature 1, the identifiers "feature 2" and "feature 1" of the target dominant features may be used as feature labels of the video m.
| Characteristic label 1 | Characteristic label 2 | |
| Video 1 | Feature 2 | Feature 1 |
| Video 2 | Feature 3 | Feature 1 |
| … | … | … |
| Video m | Feature 2 | Feature 1 |
TABLE 3
Step 105, determining a target feature tag corresponding to the disadvantaged feature of the user to be recommended, determining a target video corresponding to the target feature tag as a video to be recommended according to the corresponding relation between the feature tag of the target video and the target video, and recommending the video to be recommended to the user to be recommended.
In this step, after the corresponding relationship between the feature tag and the target video is established, the video can be recommended for the user according to the corresponding relationship.
Specifically, after the user to be recommended who needs video recommendation is determined, the disadvantage features of the user to be recommended can be determined according to the feature category table in which the advantage features and the disadvantage features of the user are recorded, so that videos are recommended for the user to be recommended according to the disadvantage features of the user to be recommended.
Further, after determining the disadvantage features of the user to be recommended, the target feature tag corresponding to the disadvantage features may be determined according to the corresponding relationship between the feature tag of the target video and the target video, the target video matched with the target feature tag may be determined, the matched target video may be determined as the video to be recommended for the disadvantage features of the user to be recommended, and then the video to be recommended may be recommended to the user to be recommended, so as to complete the video recommendation process.
In summary, the method for recommending a video provided by the embodiment of the present invention includes: determining a characteristic category table corresponding to the user, wherein the characteristic category table records the advantage characteristics and the disadvantage characteristics of the user; acquiring a video watching record of a user, wherein the video watching record records the history of watching a video by the user; determining a target video corresponding to the target dominant feature according to the dominant feature of the user and the historical record of the video watched by the user; determining a feature tag corresponding to the target dominant feature as a feature tag of a target video, and establishing a corresponding relation between the feature tag and the target video; determining a target feature tag corresponding to the disadvantaged feature of the user to be recommended, determining a target video corresponding to the target feature tag as a video to be recommended according to the corresponding relation between the feature tag of the target video and the target video, and recommending the video to be recommended to the user to be recommended. According to the method and the device, the advantage characteristics of the user and the historical record of the video watched by the user can be utilized to determine the target video enabling the user to have the target advantage characteristics, so that the characteristic label corresponding to the target advantage characteristics is determined as the characteristic label of the target video, the corresponding relation between the characteristic label and the target video is established, namely the video is directly associated with the characteristics of the user, the video to be recommended corresponding to the disadvantage characteristics of the user to be recommended can be determined according to the corresponding relation, the video to be recommended which is recommended to the user to be recommended is ensured to be matched with the disadvantage characteristics of the user to be recommended, and the accuracy of video recommendation is improved.
Fig. 2 is a flowchart illustrating steps of another video recommendation method according to an embodiment of the present invention, and as shown in fig. 2, the method may include:
step 201, obtaining a feature category for evaluating the user.
In this step, the preset feature categories for assessing the user may be obtained, so as to determine the superior features that the user has or is good at and the inferior features that the user does not have or is not good at according to the indexes of the user for the feature categories in daily work or life.
The feature categories for assessing users may be determined according to actual business logic, for example, for insurance agents, the feature categories may include: the system comprises a self-management ability, an employee-increasing ability, a customer-obtaining ability, an order-opening ability, a team management ability and the like, wherein the characteristic categories can influence the business level of the insurance agent, or the characteristic categories are contained in a pre-constructed capacity system for evaluating the business level of the insurance agent.
Step 202, obtaining the index of the user for the feature category.
In this step, after the feature category for examining the user is determined, the index of the user for the feature category may be obtained, where the index for the feature category may be a single index or a composite index, that is, multiple indexes are integrated to characterize the feature category.
For example, if the feature classes include: the self-management ability, the ability to increase members, the ability to obtain customers, the ability to make orders and the ability to manage teams, and the index aiming at the self-management ability can be the number of days of attendance of the user every month; the index for the capacity of the added member may be the number of added members per month; the index for the ability to obtain guests may be the number of guests obtained per month; the indicator for the billing capability may be a monthly new bill quantity; the index aiming at the management capability of the team can be the number of people with standard premium of more than 1000 yuan per month of the team, or the number of people with standard premium of more than 1000 yuan per month of the team, the number of newly added members per month of the team and the number of lost members per month of the team.
Step 203, determining the advantage characteristics and the disadvantage characteristics of the user according to the indexes of the user for the characteristic categories to obtain the characteristic category table.
In this step, the feature category of the user may be evaluated according to the obtained index of the user for the feature category, so as to determine the advantage feature and the disadvantage feature of the user, and further obtain a feature category table in which the advantage feature and the disadvantage feature of the user are recorded.
For example, if the number of attendance days per month of user a is 23 days, the number of increased people per month is 2, and the number of people who receive passengers per month is 1, the number of attendance days per month of user B is 18 days, the number of increased people per month is 6, and the number of people who receive passengers per month is 0, the number of attendance days per month of user C is 17 days, the number of increased people per month is 1, and the number of people who receive passengers per month is 4, the advantage feature of user a is the self-management ability represented by the number of attendance days per month, the disadvantage feature is the increased ability represented by the number of increased people per month, and the obtained ability represented by the number of people who receive passengers per month; the user B has the advantages and the disadvantages of capacity of increasing the number of the increased persons per month, self-management capacity represented by the number of the attendance days per month and capacity of acquiring the number of the acquired persons per month; user C has the advantage characteristics of capacity to acquire as characterized by the number of people to acquire each month, the disadvantage characteristics of self-management as characterized by the number of days to attendance each month, and the disadvantage characteristics of capacity to increase as characterized by the number of people to increase each month.
Optionally, the step of determining the dominant feature and the dominant feature of the user according to the index of the user for the feature category in step 203 may specifically include:
substep 2031 of determining an average value of the indexes of the feature categories based on the indexes of the plurality of users for the feature categories.
In this step, in the process of determining the dominant feature and the dominant feature of the user according to the index of the user for the feature category, an average value of the indexes of the plurality of users for a certain feature category may be used as a criterion for determining whether the feature category of a certain user is the dominant feature or the dominant feature.
Specifically, first, an average value of the indexes of the feature categories may be determined according to the indexes of the plurality of users for the feature categories.
For example, for the self-management capability represented by the number of attendance days per month, the number of attendance days per month of a plurality of users may be acquired, and the average value of the number of attendance days per month of the plurality of users may be calculated, and if the number of attendance days per month of the user a is 23 days, the number of attendance days per month of the user B is 18 days, and the number of attendance days per month of the user C is 19 days, it may be determined that the average value of the index corresponding to the self-management capability as the feature class is 20 days; if the number of added persons per month of the users A is 2, the number of added persons per month of the users B is 6, and the number of added persons per month of the users C is 1, the average value of the indexes corresponding to the feature type of the added person capacity can be determined to be 3.
Substep 2032, determining the dominant feature and the dominant feature of the user according to the index of the user for the feature category and the average value.
In this step, after the average value of the indexes of the feature class is determined, the dominant feature and the inferior feature of the user may be determined according to the indexes and the average value of the user for the feature class.
Specifically, referring to the above example, for the self-management capability represented by the number of attendance days per month, if the number of attendance days per month of the user a is 23 days, which is greater than the average value of 20 days, it may be determined that the self-management capability is the dominant feature of the user a; if the number of attendance days of the user B per month is 18 days and is less than the average value of 20 days, the self-management capability can be determined as the disadvantage characteristic of the user B; the number of attendance days per month of user C is 19 days, less than 20 days on average, then the self-administration capability can be determined as a disadvantageous feature of user C. Aiming at the added member capacity represented by the number of added members per month, if the number of added members per month of the user A is 2 and is less than the average value of 3, the passenger obtaining capacity can be determined as the disadvantage characteristic of the user A; the number of the added persons of the user B per month is 6, and is more than 3 on the average, the passenger obtaining capacity can be determined as the advantage characteristic of the user B; if the number of the added persons of the user C per month is 1 and is less than the average number of 3 persons, the passenger obtaining capacity can be determined as the disadvantage characteristic of the user C.
In addition, indexes of a plurality of users for a plurality of months in the near term can be acquired to evaluate the feature categories, so that the accuracy of the judgment process is improved.
And 204, acquiring a video watching record of the user, wherein the video watching record records the history of the video watched by the user.
This step may specifically refer to step 102, which is not described herein again.
Step 205, determining a promotion value of each video to the target dominant feature according to the dominant feature of the user and the history of videos watched by the user.
In this step, a boost value for the target dominant feature of each video may be determined according to the dominant feature of the user and the history of the videos watched by the user.
Specifically, the history of videos watched by a plurality of users can be considered comprehensively, and if the number of times or frequency of watching a certain video by the user D with the target dominant feature is higher than that of watching the video by the user E with other dominant features, or the time length for the user D with the target dominant characteristic to watch a certain video is longer than the time length for the user E with other dominant characteristics to watch the target video, it can be considered that because the frequency or frequency for watching the video by the user D is higher, or the duration of viewing the video, is longer, user D has or is adept at the target vantage point, that is, the video has a larger lifting effect on the target dominant feature, so that the lifting value of the video on the target dominant feature is larger, and the other videos have smaller promotion effect on the target dominant feature, and the other videos have smaller promotion value on the target dominant feature.
For example, if the total number of views of the video 1 is 100, the user with the feature 1 views 40 times, the user with the feature 2 views 5 times, and the user with the feature 3 views 11.
Optionally, step 205 may include:
substep 2051, determining the user with the target advantage characteristic as a target user, and determining the number of times the target user watches the video.
In this step, the user with the target dominant feature may be determined as the target user according to the feature category table, so as to further determine the number of times that the target user views each video.
Referring to table 1, if the target dominant feature is feature 1, the user a having feature 1 is the target user, and referring to table 2, the number of times that the target user watches video 1 is 1, the number of times that the target user watches video 2 is 2, and the number of times that the target user watches video m is 3.
Sub-step 2052, determining the user with the advantageous characteristics as a base user, and determining the number of times the base user watches the video.
In this step, the user with the dominant feature may be determined as the base user according to the feature category table, so as to further determine the number of times that the base user views each video.
Referring to table 1, user a, user B, and user C all have advantageous characteristics, and thus, user a, user B, and user C are all basic users, referring to table 2, the number of times that user a, user B, and user C view video 1 is 3, the number of times that user a, user B, and user C view video 2 is 7, and the number of times that user a, user B, and user C view video m is 8.
Substep 2053, determining a lifting value of each video for the target dominant feature according to the number of times the target user watches the video and the number of times the base user watches the video.
In this step, the promotion value of each video to the target dominant feature may be determined according to the number of times that the target user watches the video and the number of times that the base user watches the video.
Specifically, the process of determining the lifting value of each video for the target dominant feature may specifically be calculated according to the following formula:
wherein, tfi,jWhen the target dominant feature is the feature i, the lifting value of the video j to the target dominant feature i;
the number of times that the target user watches the video j when cnt (i, j) is the target dominant feature is the feature i;
k is the number of dominant features;
and m is the number of videos.
For example, when the target dominant feature is feature 1, referring to table 1 and table 2, it may be determined that the number of times cnt (1,1) that the target user watches video 1 is 1, the number of times cnt (1,2) that the target user watches video 2 is 2, and the number of times cnt (1, m) that the target user watches video m is 3; number of times video 1 was watched by base user
3 times, the number of times the base user viewed video 2
7 times, the number of times the base user viewed video m
The number of times was 8.
It may be determined that the lifting value of video 1 for the target dominant feature (feature 1) is 1/3, the lifting value of video 2 for the target dominant feature (feature 1) is 2/7, and the lifting value of video m for the target dominant feature (feature 1) is 3/8, so that it is known that the lifting effect of video 3 for feature 1 is the greatest, video 1 times is the smallest, and the lifting effect of video 2 for feature 1 is the smallest, so that video 3 may be determined as the target video corresponding to feature 1, and thus the feature label of feature 1 is determined as the feature label of video 2.
Optionally, if the number of target users with the target advantageous features is greater than the number of users with other advantageous features, for most videos, the number of times that the target users watch a certain video is greater than the number of times that the users with other advantageous features watch a certain video, which results in that the feature tags of many videos are the feature tags of the target advantageous features, so that the watching record proportion of the target users watching the videos in the video watching record can be further considered, thereby improving the accuracy of the judgment process.
Correspondingly, sub-step 2053 may specifically include:
(1) and determining the total times of watching all videos by the target user according to the history of watching videos by the user.
In this step, the total number of times that the target user watches all videos may be determined according to the history of the videos watched by the user.
For example, if the target dominant feature is feature 1, the user a having feature 1 is the target user, and referring to table 2, the total number of times that the target user views all videos is 6.
(2) And determining the total times of watching all videos by the basic user according to the history of watching the videos by the user.
In this step, the total number of times that the base user viewed all videos may be determined based on the history of the videos viewed by the user.
Referring to table 1, user a, user B, and user C all have an advantageous feature, and thus, user a, user B, and user C are all basic users, and referring to table 2, the total number of times that user a, user B, and user C view all videos is 18.
(3) And determining the watching record proportion of the target user watching the video in the video watching record according to the total times of the target user watching all the videos and the total times of the basic user watching all the videos.
In this step, the watching record proportion of the target user watching the video in the video watching record can be determined according to the total number of times of the target user watching all the videos and the total number of times of the base user watching all the videos.
Specifically, the process of determining the watching record proportion of the target user watching the video in the video watching record may specifically be calculated according to the following formula:
wherein idfiWhen the target dominant feature is the feature i, the watching record proportion of the video watched by the target user is increased;
For example, in the case where the target dominant feature is feature 1, referring to tables 1 and 2, it may be determined that the total number of times the target user (user a) views all videos is 6 times, and the total number of times the base user (user a, user B, and user C) views all videos is 18 times, and it may be determined that the viewing record weight of the target user viewing videos is 3.
(4) And determining the promotion value of each video to the target dominant feature according to the number of times that the target user watches the video, the number of times that the base user watches the video and the watching record proportion.
Further, the promotion value of each video to the target dominant features can be determined according to the number of times that the target user watches the video, the number of times that the base user watches the video, and the watching record proportion of the target user watching the video.
Specifically, the process of determining the lifting value of each video for the target dominant feature may specifically be calculated according to the following formula:
weighti,j＝tfi,j×idfi，0<i≤k,0<j≤m
wherein, weighti,jIn order to consider the watching record proportion of the target user watching the video in the video watching record, when the target dominant feature is the feature i, the lifting value of the video j to the target dominant feature i.
For example, when the target dominant feature is feature 1, referring to table 1 and table 2, the number of times cnt (1,1) that the target user views video 1 may be determined to be 1, and the number of times that the base user views video 1 may be determined to be 1
The viewing record specific gravity of the target user viewing the video is 3 for 3 times, and therefore, the promotion value of the video 1 to the target dominant feature (feature 1) can be determined to be 1/9; the number of times cnt (1,2) that the target user watches video 2 is 2, and the number of times that the base user watches video 2
The viewing record specific gravity of the target user viewing the video is 3 for 7 times, and therefore, the promotion value of the video 2 to the target dominant feature (feature 1) can be determined to be 2/21; the number of times cnt (1, m) that the target user watches the video m is 3, and the number of times that the base user watches the video m
The viewing record of the video viewed by the target user is weighted 3 for 8 times, and thus, the dominant feature (feature 1) of the video 3 to the target can be determinedThe lift value was 1/8.
Therefore, the lifting effect of the video 3 on the feature 1 is the largest, the lifting effect of the video 2 on the feature 1 is the smallest after the video 1, so that the video 3 can be determined as the target video corresponding to the feature 1, and the feature label of the feature 1 can be determined as the feature label of the video 2.
Specifically, the lifting value of each video for each feature may be calculated and recorded to obtain a video lifting table as shown in table 4, where the lifting value of each video for each dominant feature is recorded in table 4.
| Feature 1 | Feature 2 | … | Feature k | |
| Video 1 | weight1,1 | weight2,1 | … | weightk,1 |
| Video 2 | weight1,2 | weight2,2 | … | weightk,2 |
| … | … | … | … | … |
| Video m | weight1,m | weight2,m | … | weightk,m |
TABLE 4
And step 206, determining the video with the lifting value being greater than or equal to a first preset value as a target video corresponding to the target dominant feature.
In this step, after determining the lifting value of each video for the target dominant feature, a video with the lifting value greater than or equal to a first preset value may be determined as a target video corresponding to the target dominant feature.
In addition, the lifting values may also be arranged in a descending order, so that the video corresponding to the largest two lifting values is determined as the target video corresponding to the target dominant features.
Step 207, determining the feature label corresponding to the target dominant feature as the feature label of the target video, and establishing a corresponding relationship between the feature label and the target video.
This step may be referred to specifically as step 104 above.
Optionally, the step of determining the feature tag corresponding to the target dominant feature as the feature tag of the target video in step 207 may specifically include:
substep 2071, in case that there are multiple target advantageous features corresponding to the target video, determining, as a feature tag of the target video, a feature tag corresponding to a target advantageous feature of which the boost value is greater than or equal to a second preset value for the target video, and displaying the feature tag.
In this step, after the target video corresponding to the target dominant features is determined, in the case that one target video has a plurality of corresponding target dominant features, for the target video, the feature label corresponding to the target dominant feature whose boost value is greater than or equal to the second preset value may be determined as the feature label of the target video and displayed, so that the user may select a video matching with its own disadvantageous feature for learning or select a video of interest for viewing according to the displayed feature label of the target video.
For example, referring to table 4, if for video 1, of the k features, if weight1,1、weight2,1And weightk,1When the target video is larger than the first preset value, that is, the video 1 is the target video with the feature 1, the feature 2 and the feature k, at this time, a feature with a lifting value larger than or equal to a second preset value may be further selected from the multiple target dominant features, and a feature tag corresponding to the feature may be determined as a feature tag of the video 1.
Step 208, determining a target feature tag corresponding to the disadvantaged feature of the user to be recommended, determining the target video corresponding to the target feature tag as the video to be recommended according to the corresponding relation between the feature tag of the target video and the target video, and recommending the video to be recommended to the user to be recommended.
This step may be referred to specifically as step 105 described above.
Fig. 3 is a schematic diagram of a video recommendation interface provided by an embodiment of the present invention, and as shown in fig. 3, it is determined that inferior features of the user to be recommended are order opening capability, customer obtaining capability, and member adding capability, the videos to be recommended with the feature tag "order opening capability" determined by the method are video 1, video 2, and the like, the videos to be recommended with the feature tag "customer obtaining capability" are video 1, video 2, and the like, and the videos to be recommended with the feature tag "member adding capability" are video 1, video 2, and the like, so that the determined videos to be recommended can be pushed to a client corresponding to the user to be recommended, so that the user can select and open the videos to be recommended on the client for learning.
In addition, the advantage characteristics and the disadvantage characteristics of the user can be updated at one interval and one end through the latest acquired indexes of the user for the characteristic categories, so that the video recommended to the client is ensured to be in accordance with the disadvantage characteristics which need to be improved by the client at present, and the accuracy of the video recommendation process is improved.
In summary, the method for recommending a video provided by the embodiment of the present invention includes: determining a characteristic category table corresponding to the user, wherein the characteristic category table records the advantage characteristics and the disadvantage characteristics of the user; acquiring a video watching record of a user, wherein the video watching record records the history of watching a video by the user; determining a target video corresponding to the target dominant feature according to the dominant feature of the user and the historical record of the video watched by the user; determining a feature tag corresponding to the target dominant feature as a feature tag of a target video, and establishing a corresponding relation between the feature tag and the target video; determining a target feature tag corresponding to the disadvantaged feature of the user to be recommended, determining a target video corresponding to the target feature tag as a video to be recommended according to the corresponding relation between the feature tag of the target video and the target video, and recommending the video to be recommended to the user to be recommended. According to the method and the device, the advantage characteristics of the user and the historical record of the video watched by the user can be utilized to determine the target video enabling the user to have the target advantage characteristics, so that the characteristic label corresponding to the target advantage characteristics is determined as the characteristic label of the target video, the corresponding relation between the characteristic label and the target video is established, namely the video is directly associated with the characteristics of the user, the video to be recommended corresponding to the disadvantage characteristics of the user to be recommended can be determined according to the corresponding relation, the video to be recommended which is recommended to the user to be recommended is ensured to be matched with the disadvantage characteristics of the user to be recommended, and the accuracy of video recommendation is improved.
Fig. 4 is a block diagram of a video recommendation apparatus according to an embodiment of the present invention, and as shown in fig. 4, the apparatus may include:
a first determining module 301, configured to determine a feature category table corresponding to a user, where the feature category table records an advantage feature and a disadvantage feature of the user;
an obtaining module 302, configured to obtain a video watching record of the user, where a history of videos watched by the user is recorded in the video watching record;
a second determining module 303, configured to determine, according to the dominant feature of the user and a history of videos watched by the user, a target video corresponding to the dominant feature of the target;
an establishing module 304, configured to determine a feature tag corresponding to the target dominant feature as a feature tag of the target video, and establish a corresponding relationship between the feature tag and the target video;
a third determining module 305, configured to determine a target feature tag corresponding to a disadvantageous feature of a user to be recommended, determine, according to a correspondence between a feature tag of the target video and a target video, the target video corresponding to the target feature tag as a video to be recommended, and recommend the video to be recommended to the user to be recommended.
Optionally, the second determining module 303 includes:
the first determining submodule is used for determining the lifting value of each video to the target dominant feature according to the dominant feature of the user and the historical record of videos watched by the user;
and the second determining submodule is used for determining the video with the lifting value being greater than or equal to the first preset value as the target video corresponding to the target advantage characteristic.
Optionally, the first determining sub-module includes:
the first determining unit is used for determining the user with the target advantage characteristic as a target user and determining the frequency of watching the video by the target user;
the second determining unit is used for determining the user with the advantage characteristics as a basic user and determining the frequency of watching the video by the basic user;
and the third determining unit is used for determining the promotion value of each video to the target dominant feature according to the times of watching the videos by the target user and the times of watching the videos by the basic user.
Optionally, the third determining unit includes:
the first determining subunit is used for determining the total times of watching all videos by the target user according to the history of watching the videos by the user;
the second determining subunit is used for determining the total times of watching all videos by the basic user according to the history of watching the videos by the user;
a third determining subunit, configured to determine, according to the total number of times that the target user watches all videos and the total number of times that the base user watches all videos, a watching record proportion of the target user watching the videos in the video watching record;
and the fourth determining subunit is configured to determine, according to the number of times that the target user watches the video, the number of times that the base user watches the video, and the watching record proportion, a promotion value of each video for the target dominant feature.
Optionally, the establishing module 304 includes:
and a third determining sub-module, configured to, when there are multiple target dominant features corresponding to the target video, determine, as a feature tag of the target video, a feature tag corresponding to a target dominant feature whose lifting value is greater than or equal to a second preset value for the target video, and display the feature tag.
Optionally, the first determining module 301 includes:
the first obtaining submodule is used for obtaining a characteristic category for examining the user;
the second obtaining submodule is used for obtaining the indexes of the user aiming at the characteristic categories;
and the fourth determining submodule is used for determining the advantage characteristics and the disadvantage characteristics of the user according to the indexes of the user aiming at the characteristic categories to obtain the characteristic category table.
Optionally, the fourth determining sub-module includes:
a fourth determining unit, configured to determine an average value of the indicators of the feature categories according to the indicators of the plurality of users for the feature categories;
and a fifth determining unit, configured to determine the dominant feature and the dominant feature of the user according to the index and the average value of the user for the feature category.
In summary, an apparatus for recommending a video according to an embodiment of the present invention includes: determining a characteristic category table corresponding to the user, wherein the characteristic category table records the advantage characteristics and the disadvantage characteristics of the user; acquiring a video watching record of a user, wherein the video watching record records the history of watching a video by the user; determining a target video corresponding to the target dominant feature according to the dominant feature of the user and the historical record of the video watched by the user; determining a feature tag corresponding to the target dominant feature as a feature tag of a target video, and establishing a corresponding relation between the feature tag and the target video; determining a target feature tag corresponding to the disadvantaged feature of the user to be recommended, determining a target video corresponding to the target feature tag as a video to be recommended according to the corresponding relation between the feature tag of the target video and the target video, and recommending the video to be recommended to the user to be recommended. According to the method and the device, the advantage characteristics of the user and the historical record of the video watched by the user can be utilized to determine the target video enabling the user to have the target advantage characteristics, so that the characteristic label corresponding to the target advantage characteristics is determined as the characteristic label of the target video, the corresponding relation between the characteristic label and the target video is established, namely the video is directly associated with the characteristics of the user, the video to be recommended corresponding to the disadvantage characteristics of the user to be recommended can be determined according to the corresponding relation, the video to be recommended which is recommended to the user to be recommended is ensured to be matched with the disadvantage characteristics of the user to be recommended, and the accuracy of video recommendation is improved.
For the above device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant points, refer to the partial description of the method embodiment.
Preferably, an embodiment of the present invention further provides a computer device, which includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, and when being executed by the processor, the computer program implements each process of the above-mentioned video recommendation method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the video recommendation method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here. The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As is readily imaginable to the person skilled in the art: any combination of the above embodiments is possible, and thus any combination between the above embodiments is an embodiment of the present invention, but the present disclosure is not necessarily detailed herein for reasons of space.
The recommendation methods for videos provided herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The structure required to construct a system incorporating aspects of the present invention will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components of the proposed method of video according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Claims (10)
1. A method for recommending a video, the method comprising:
determining a characteristic category table corresponding to a user, wherein the characteristic category table records the dominant characteristic and the inferior characteristic of the user;
acquiring a video watching record of the user, wherein a history record of the video watched by the user is recorded in the video watching record;
determining a target video corresponding to the target dominant feature according to the dominant feature of the user and the history of videos watched by the user;
determining a feature tag corresponding to the target dominant feature as a feature tag of the target video, and establishing a corresponding relation between the feature tag and the target video;
determining a target feature tag corresponding to the disadvantaged feature of a user to be recommended, determining a target video corresponding to the target feature tag as a video to be recommended according to the corresponding relation between the feature tag of the target video and the target video, and recommending the video to be recommended to the user to be recommended.
2. The method of claim 1, wherein the step of determining the target video corresponding to the target dominant feature according to the dominant feature of the user and the history of videos watched by the user comprises:
determining a promotion value of each video to the target dominant feature according to the dominant feature of the user and the history of videos watched by the user;
and determining the video with the lifting value being greater than or equal to a first preset value as a target video corresponding to the target dominant feature.
3. The method of claim 2, wherein the step of determining the elevated value of each video for the target dominant feature based on the dominant feature of the user and the history of videos watched by the user comprises:
determining the users with the target advantage characteristics as target users, and determining the times of watching the video by the target users;
determining the users with the advantage characteristics as basic users, and determining the times of watching the video by the basic users;
and determining the promotion value of each video to the target dominant feature according to the times of watching the videos by the target user and the times of watching the videos by the basic user.
4. The method of claim 3, wherein the step of determining the promotion value of each video for the target dominant feature according to the number of times the target user viewed the video and the number of times the base user viewed the video comprises:
determining the total times of watching all videos by the target user according to the history of watching videos by the user;
determining the total times of watching all videos by the basic user according to the history of watching the videos by the user;
determining the watching record proportion of the target user watching the video in the video watching record according to the total times of the target user watching all the videos and the total times of the basic user watching all the videos;
and determining the promotion value of each video to the target dominant feature according to the number of times that the target user watches the video, the number of times that the base user watches the video and the watching record proportion.
5. The method according to claim 2, wherein the step of determining the feature label corresponding to the target dominant feature as the feature label of the target video includes:
and under the condition that a plurality of target advantageous features are corresponding to the target video, determining a feature label corresponding to the target advantageous feature with the lifting value being greater than or equal to a second preset value as the feature label of the target video and displaying the feature label.
6. The method of claim 1, wherein the step of determining the user's corresponding feature class table comprises:
acquiring a feature category for assessing the user;
acquiring an index of the user for the characteristic category;
and determining the advantage characteristics and the disadvantage characteristics of the user according to the indexes of the user aiming at the characteristic categories to obtain the characteristic category table.
7. The method according to claim 6, wherein the step of determining the dominant feature and the dominant feature of the user according to the index of the user for the feature category comprises:
determining an average value of the indexes of the feature categories according to the indexes of the plurality of users aiming at the feature categories;
and determining the advantage features and the disadvantage features of the user according to the indexes and the average values of the user aiming at the feature categories.
8. An apparatus for recommending video, said apparatus comprising:
the system comprises a first determining module, a second determining module and a judging module, wherein the first determining module is used for determining a characteristic category table corresponding to a user, and the characteristic category table records the superiority characteristic and the inferiority characteristic of the user;
the acquisition module is used for acquiring a video watching record of the user, wherein a history record of the video watched by the user is recorded in the video watching record;
the second determination module is used for determining a target video corresponding to the target dominant feature according to the dominant feature of the user and the history record of the video watched by the user;
the establishing module is used for determining the feature tag corresponding to the target dominant feature as the feature tag of the target video and establishing the corresponding relation between the feature tag and the target video;
and the third determining module is used for determining a target feature tag corresponding to the inferior feature of the user to be recommended, determining the target video corresponding to the target feature tag as the video to be recommended according to the corresponding relation between the feature tag of the target video and the target video, and recommending the video to be recommended to the user to be recommended.
9. A computer device, characterized in that the computer device comprises:
a memory for storing program instructions;
a processor for calling the program instructions stored in the memory and executing the steps included in the video recommendation method according to any one of claims 1 to 7 according to the obtained program instructions.
10. A computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements a method of recommending a video according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011477735.5A CN112653907B (en) | 2020-12-15 | 2020-12-15 | Video recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011477735.5A CN112653907B (en) | 2020-12-15 | 2020-12-15 | Video recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112653907A true CN112653907A (en) | 2021-04-13 |
| CN112653907B CN112653907B (en) | 2022-11-15 |
Family
ID=75354061
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011477735.5A Active CN112653907B (en) | 2020-12-15 | 2020-12-15 | Video recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112653907B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407241A (en) * | 2016-03-21 | 2017-02-15 | 传线网络科技（上海）有限公司 | Video recommendation method and system |
| US20170068870A1 (en) * | 2015-09-03 | 2017-03-09 | Google Inc. | Using image similarity to deduplicate video suggestions based on thumbnails |
| CN108647293A (en) * | 2018-05-07 | 2018-10-12 | 广州虎牙信息科技有限公司 | Video recommendation method, device, storage medium and server |
| CN110941740A (en) * | 2019-11-08 | 2020-03-31 | 腾讯科技（深圳）有限公司 | Video recommendation method and computer-readable storage medium |
-
2020
- 2020-12-15 CN CN202011477735.5A patent/CN112653907B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170068870A1 (en) * | 2015-09-03 | 2017-03-09 | Google Inc. | Using image similarity to deduplicate video suggestions based on thumbnails |
| CN106407241A (en) * | 2016-03-21 | 2017-02-15 | 传线网络科技（上海）有限公司 | Video recommendation method and system |
| CN108647293A (en) * | 2018-05-07 | 2018-10-12 | 广州虎牙信息科技有限公司 | Video recommendation method, device, storage medium and server |
| CN110941740A (en) * | 2019-11-08 | 2020-03-31 | 腾讯科技（深圳）有限公司 | Video recommendation method and computer-readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112653907B (en) | 2022-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| De Langhe et al. | Navigating by the stars: Investigating the actual and perceived validity of online user ratings | |
| Zhang et al. | Booking now or later: do online peer reviews matter? | |
| US20110196716A1 (en) | Lead qualification based on contact relationships and customer experience | |
| US20130204822A1 (en) | Tools and methods for determining relationship values | |
| Tang et al. | Investigating the routes of communication on destination websites | |
| Iacono et al. | Accessibility dynamics and location premia: Do land values follow accessibility changes? | |
| US20130204823A1 (en) | Tools and methods for determining relationship values | |
| CN113535991B (en) | Multimedia resource recommendation method and device, electronic equipment and storage medium | |
| Grigolon et al. | Facet-based analysis of vacation planning processes: a binary mixed logit panel model | |
| US10817888B2 (en) | System and method for businesses to collect personality information from their customers | |
| JP5237337B2 (en) | Object customization and management system | |
| JP2023507043A (en) | DATA PROCESSING METHOD, DEVICE, DEVICE, STORAGE MEDIUM AND COMPUTER PROGRAM | |
| US8478702B1 (en) | Tools and methods for determining semantic relationship indexes | |
| Xia et al. | Can online rating reflect authentic customer purchase feelings? Understanding how customer dissatisfaction relates to negative reviews | |
| US11210637B2 (en) | System and method for generating skill-centric online resumes with verifiable skills | |
| Pertheban et al. | A systematic literature review: Information accuracy practices in tourism | |
| CN112653907B (en) | Video recommendation method and device | |
| JP6320353B2 (en) | Digital marketing system | |
| Patulny | Exposing the “Wellbeing gap” between American Men and Women: Revelations from the sociology of emotion surveys | |
| CN113822566A (en) | Business assessment processing method and device, computer equipment and storage medium | |
| JP2015062096A (en) | Content distribution system | |
| Uddin et al. | E-Government Development & Digital Economy: Relationship | |
| US10970728B2 (en) | System and method for collecting personality information | |
| WO2013119452A1 (en) | Tools and methods for determining relationship values | |
| CN111353288B (en) | Report processing method, system, device and computer readable storage medium |
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 |