Unlock instant, AI-driven research and patent intelligence for your innovation.
Data recommendation method, device, equipment and medium based on artificial intelligence
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of data recommendation and artificial intelligence, applied in data processing applications, electronic digital data processing, digital data information retrieval, etc., can solve problems such as lack of historical behavior data, inability to implement targeted data recommendations, and user cold start, etc., to achieve Effects of avoiding limitations, mitigating data non-sharing issues, and improving generalization capabilities
Active Publication Date: 2021-12-17
PING AN TECH (SHENZHEN) CO LTD
View PDF0 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0004] Embodiments of the present invention provide an artificial intelligence-based data recommendation method, device, computer equipment, and storage medium, aiming to solve the problem that some users in the prior art face a user cold start due to lack of historical behavior data, and cannot implement targeted The problem with data recommendation
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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
no. 1 Embodiment
[0060] In an embodiment, as the first specific embodiment of obtaining the corresponding similar user row vector set in the second matrix according to the similar vector set, including:
[0061] Obtaining a user identification set of the similar vector set, acquiring row vectors having user identifications in the user identification set in the second matrix to form a similar user row vector set.
[0062] In this embodiment, for example, the acquired target user corresponds to the first row vector R in the first matrix 1 , R 1 The corresponding row vector is (u 1 , j 1 , W u_1j_1 ). At this time, it is obtained in the first matrix (u 1 , j 1 , W u_1j_1 ) The corresponding similar vector set includes the following row vectors (u 2 , j 2 , W u_2j_2 ), (u 3 , j 4 , W u_3j_4 ), (u 5 , j 6 , W u_5j_6 ) and (u 6 , j 1 , W u_6j_4 ). The set of user identities included in the set of similarity vectors has u 2 , u 3 , u 5 and u 6 . If there are also behavior dat...
no. 2 Embodiment
[0064] In an embodiment, as the second specific embodiment of obtaining a corresponding similar user row vector set in the second matrix according to the similar vector set, including:
[0065] Each similar vector in the similar vector set is used as a similar user row vector to form a similar user row vector set.
[0066] In this embodiment, for example, the acquired target user corresponds to the first row vector R in the first matrix 1 , R 1 The corresponding row vector is (u 1 , j 1 , W u_1j_1 ). At this time, the set of similar vectors obtained in the second matrix includes the following row vectors (U 2 , I 1 , W U_2I_1 ), (U 3 , I 1 , W U_3I_1 ), (U 5 , I 2 , W U_5I_2 ) and (U 6 , I 2 , W U_6I_2 ). At this time, each similar vector in the similar vector set is directly used as a similar user row vector to form a similar user row vector set, that is, the similar user row vector set includes (U 2 , I 1 , W U_2I_1 ), (U 3 , I 1 , W U_3I_1 ), (U 5 , ...
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 present invention relates to artificial intelligence, and provides an artificial intelligence-based data recommendation method, device, device, and medium. First, the first recommended data set of the target user is obtained through transfer learning, and the second recommended data set of the target user is obtained based on federated learning. The default recommended data set is to integrate the first recommended data set, the second recommended data set and the default recommended data set through a preset voting strategy or average strategy to obtain a final recommended data set, and use transfer learning The machine learning paradigm of federated learning alleviates the cold start problem and data non-sharing problem in the recommendation system, and also effectively improves the generalization ability of the recommendation model, and the migration method based on the neighborhood relationship and the method of multi-source data can make full use of And mining the value of existing source data, based on data and model-driven, avoiding the limitations of manually setting rules or expert experience.
Description
technical field [0001] The present invention relates to the field of intelligent decision-making of artificial intelligence, in particular to an artificial intelligence-based data recommendation method, device, computer equipment and storage medium. Background technique [0002] One of the important goals of smart training is to implement differentiated training course recommendations according to the individual needs of users, which can be achieved by designing an excellent recommendation system model. The recommendation model often needs to use a large amount of user historical behavior data as input, and at the same time use other auxiliary information to predict the user's preference for a certain course, so as to achieve accurate push of training courses. [0003] If users are classified into multiple levels according to preset standards, some levels of users may lack historical behavior data, which will lead to the problem of user cold start (User Cold Start), that is,...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More