Information recall method and device, electronic equipment and storage medium
A technology of preset models and behaviors, applied in the field of information search, it can solve the problems of poor diversity and low overall quality, and achieve the effect of high accuracy, strong diversity and overall quality improvement.
Pending Publication Date: 2021-11-19
BEIJING IQIYI TECH CO LTD
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Since only one feature vector is used for recall, the recall information usually only hits one point of interest of the user, the diversity is poor, and the overall quality of recall is not high
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment approach
[0136] As an implementation manner of the embodiment of the present invention, the above-mentioned device may also include:
[0137] The historical behavior sequence acquisition module is used to obtain the historical behavior sequences of multiple sample users;
[0138] Wherein, any one of the historical behavior sequences is used to describe the search behavior information input by the sample user in the historical time interval.
[0139] The vector dictionary construction module is used to determine the vector dictionary by using a pre-trained preset model.
[0140] As an implementation manner of the embodiment of the present invention, the above preset model may include the first model or the second model;
[0141] The vector dictionary building blocks described above can include:
[0142] A first construction unit, configured to use the first model to process each historical behavior sequence to obtain a clustering feature vector corresponding to each search behavior in...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The embodiment of the invention provides an information recall method and device, electronic equipment and a storage medium, and the method comprises the steps: acquiring a search behavior sequence of a target user, wherein the search behavior sequence is used for describing search behavior information input by the target user in a target time interval; acquiring a clustering feature vector corresponding to the search behavior sequence; taking the clustering feature vector as an index, and determining the target behavior information corresponding to the clustering feature vector in a pre-established vector dictionary, wherein the vector dictionary is used for correspondingly storing the search behavior information and the clustering feature vector. The search behavior sequence of the target user is adopted as a recall basis, the receptive field is wide, and the clustering feature vectors are obtained by clustering the feature vectors corresponding to the search behavior information, so the interest points of the user represented by multiple pieces of search behavior information with the same vector category can be identified, the target behavior information can hit a plurality of interest points of the user, and the diversity is strong.
Description
technical field [0001] The invention relates to the technical field of information search, in particular to an information recall method, device, electronic equipment and storage medium. Background technique [0002] For a website with a search function, accurate search information recommendations for different users can attract users to click on the recommended search information to search, which can effectively achieve the purpose of traffic drainage. The recommendation method for searching information in the related art can be divided into two stages: recall and sorting. Among them, the sorting stage is to sort the recall information, and finally determine the search information to be recommended to the user according to the sorting result. [0003] The current recall methods are mainly divided into i2i (item to item, search behavior information-search behavior information) method at the granularity of search behavior, and u2i (user to item, user-search behavior informat...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/951G06F16/9535G06K9/62
CPCG06F16/951G06F16/9535G06F18/23
Inventor 黄腾玉
Owner BEIJING IQIYI TECH CO LTD