Search

CN-122019876-A - Recommendation method, recommendation device, electronic equipment and computer readable storage medium

CN122019876ACN 122019876 ACN122019876 ACN 122019876ACN-122019876-A

Abstract

The embodiment of the application discloses a recommendation method, a recommendation device, electronic equipment and a computer-readable storage medium, and relates to the technical field of recommendation; the method comprises the steps of obtaining a behavior sequence of a user, determining a media asset preference vector and an operation preference vector of the user according to the behavior sequence, predicting recommended media assets according to the behavior sequence and the media asset preference vector, determining a display page of the recommended media assets, determining a current page, determining a shortest preference path from the current page to the display page according to the operation preference vector, the current page and the display page, and recommending the shortest preference path. Therefore, the scheme can help the user to quickly acquire the recommended media resources, so that the recommendation effect is improved.

Inventors

  • LIU LI

Assignees

  • 深圳市雷鸟网络传媒有限公司

Dates

Publication Date
20260512
Application Date
20260129

Claims (10)

  1. 1. A recommendation method, comprising: Acquiring a behavior sequence of a user, and determining a media asset preference vector and an operation preference vector of the user according to the behavior sequence; Predicting recommended media assets according to the behavior sequence and the media asset preference vector, and determining a display page of the recommended media assets; determining a current page; Determining a shortest preference path from the current page to the presentation page according to the operation preference vector, the current page and the presentation page; the shortest preference path is recommended.
  2. 2. The method of claim 1, wherein the determining a shortest preference path from the current page to the presentation page based on the operational preference vector, the current page, and the presentation page comprises: Obtaining graph structure data of a plurality of pages, wherein nodes of the graph structure data are page states of the pages, the page states represent the pages, tag pages in the pages and row-column coordinates in the tag pages, and edges among the nodes represent operation behaviors and operation cost among the page states; determining the weight of each edge according to the operation preference vector; Determining weighted costs of a plurality of paths from the current page to the display page according to the nodes corresponding to the current page, the nodes corresponding to the display page and the weights of all sides; and determining the shortest preference path according to the weighted costs of the paths, and determining an operation behavior sequence corresponding to the shortest preference path.
  3. 3. The method of claim 1, wherein the operational preference vector comprises familiarity and search dependency; Determining an operational preference vector of the user from the sequence of actions, comprising: determining the operation efficiency of the behavior sequence according to the total time consumption and the operation times corresponding to the behavior sequence of the user; Determining familiarity of a user to the behavior sequence according to the operation efficiency of the behavior sequence; and determining the search dependency according to the search operation times and the total operation times corresponding to the behavior sequence.
  4. 4. The method of claim 1, wherein said determining a media preference vector for the user from the sequence of actions comprises: determining the operation times of the user on various media assets according to the behavior sequence; Determining the attention degree of the user to the various media assets according to the proportion of the operation times of the user to the various media assets to the total operation times; determining the scarcity degree of various media assets; determining the weight of each type of the media assets according to the attention degree and the scarcity degree of each type of the media assets; And determining the media asset preference vector of the user according to the weights of the media assets of various types.
  5. 5. The method of claim 1, wherein predicting recommended assets based on the behavior sequence and the asset preference vector comprises: determining a reference user with a first similarity greater than a similarity threshold value with the user's media preference vector according to the user's media preference vector; predicting first media assets and first scores of the first media assets according to the first similarity, the preference media assets of the reference user and the preference degree of the reference user on the preference media assets; Predicting a user intention vector according to the behavior sequence and the media preference vector; Acquiring the media asset characteristics of each media asset, and calculating the second similarity between the user intention vector and the media asset characteristics of each media asset; determining second media assets and second scores of the second media assets according to the second similarity corresponding to the media assets; Acquiring the heat of each first media asset and the heat of each second media asset; And determining the recommended media assets according to the heat degree and the first score of each first media asset and the heat degree and the second score of each second media asset.
  6. 6. The method of claim 1, wherein the obtaining a sequence of behavior of the user comprises: acquiring a time stamp, a page identifier, an element identifier, an action type, duration and/or a next page identifier corresponding to each operation behavior; and generating a behavior sequence of the user according to each operation behavior.
  7. 7. The method of claim 1, wherein the recommending the shortest preference path comprises: And displaying the shortest preference path on the current page.
  8. 8. A recommendation device, comprising: the vector determining module is used for acquiring a behavior sequence of a user and determining a media asset preference vector and an operation preference vector of the user according to the behavior sequence; The media asset prediction module is used for predicting recommended media assets according to the behavior sequence and the media asset preference vector and determining a display page of the recommended media assets; The page determining module is used for determining a current page; The path determining module is used for determining the shortest preference path from the current page to the display page according to the operation preference vector, the current page and the display page; and the path recommending module is used for recommending the shortest preference path.
  9. 9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the recommended method according to any of claims 1 to 7 when the computer program is executed.
  10. 10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the recommendation method according to any of claims 1 to 7.

Description

Recommendation method, recommendation device, electronic equipment and computer readable storage medium Technical Field The embodiment of the application relates to the technical field of recommendation, in particular to a recommendation method, a recommendation device, electronic equipment and a computer readable storage medium. Background In internet products such as content platforms, e-commerce platforms and the like, a display page of recommended media assets (such as video, audio, news and the like) is used as a core module for realizing user conversion and retention, and the rationality of an access path directly determines a recommendation effect. In the product architecture of the related technology, the problem of long jump paths often exists when a user arrives at a display page of recommended content from a current page, and the user can reach a target page only by passing through a plurality of intermediate pages such as a first page, a classification page, a search result page and the like, and the user abandoning rate can be obviously improved when the jump is increased once, so that the reach rate and the conversion efficiency of recommended media resources are low. Disclosure of Invention The embodiment of the application provides a recommendation method, a recommendation device, electronic equipment and a computer readable storage medium, which can help a user to quickly acquire recommended media resources, thereby improving the recommendation effect. In a first aspect, an embodiment of the present application provides a recommendation method, including: Acquiring a behavior sequence of a user, and determining a media asset preference vector and an operation preference vector of the user according to the behavior sequence; Predicting recommended media assets according to the behavior sequence and the media asset preference vector, and determining a display page of the recommended media assets; determining a current page; Determining a shortest preference path from the current page to the presentation page according to the operation preference vector, the current page and the presentation page; the shortest preference path is recommended. In a second aspect, an embodiment of the present application provides a recommendation apparatus, including: the vector determining module is used for acquiring a behavior sequence of a user and determining a media asset preference vector and an operation preference vector of the user according to the behavior sequence; The media asset prediction module is used for predicting recommended media assets according to the behavior sequence and the media asset preference vector and determining a display page of the recommended media assets; The page determining module is used for determining a current page; The path determining module is used for determining the shortest preference path from the current page to the display page according to the operation preference vector, the current page and the display page; and the path recommending module is used for recommending the shortest preference path. In a third aspect, an embodiment of the present application further provides an electronic device, where the electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program when executed by the processor implements the steps in the recommendation method described above. In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, where a computer program is stored, where the computer program when executed by a processor implements the steps in the recommendation method described above. In a fifth aspect, embodiments of the present application also provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions to cause the computer device to perform the methods provided in the various alternative implementations described in the embodiments of the present application. The embodiment of the application has the following beneficial effects: The method comprises the steps of obtaining a behavior sequence of a user, determining a media asset preference vector and an operation preference vector of the user according to the behavior sequence, predicting recommended media assets according to the behavior sequence and the media asset preference vector, predicting the next intention of the user based on the real-time behavior sequence, wherein the media asset preference vector can reflect long-term interest preference of the user to the media assets, so that the recommended media assets predicted based on the behavior sequence and the media asset preference vector have dynamic adaptability and can be accurately matched with