A Streaming Data Recommendation Method Based on Feature Evolution
A data recommendation and data technology, applied in special data processing applications, electrical digital data processing, digital data information retrieval, etc., can solve the problems of poor recommendation performance and achieve good recommendation results
Active Publication Date: 2020-09-08
GLOBAL TONE COMM TECH
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This method completely ignores the continuity of feature changes, and completely abandons the previously used recommendation model, making the recommendation performance very poor during the model alternation period
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 Construction
[0027] In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments These are some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0028] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a," "the," and "the" as used in the embodiments of the present invention and the appended claims are intended to include the plural fo...
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 provides a feature set evolution problem in a convective data recommendation system. When the recommendation model is alternated, the old recommendation model and the new recommendation model are considered at the same time, so as to achieve the smooth evolution of the recommendation model and avoid the recommendation performance when the model is switched. of sudden drop. The present invention expands model switching from one point to a time period. In the model switching time period, the old and new feature sets and recommendation models exist and function at the same time; the recommendation results obtained by the two models are combined through the weight factor , so as to get the final recommendation result in this time period. This feature and model smooth evolution recommendation system overcomes the problem of sudden drop in recommendation performance caused by direct switching between feature sets and recommendation models in the original streaming data recommendation system.
Description
technical field [0001] The present invention relates to the field of data recommendation, in particular, to the field of stream data recommendation. Background technique [0002] The recommendation technology based on batch data has experienced many years of development. With the popularization of the Internet of Things and social networks, recommendation based on streaming data has become a popular research direction in the field of content recommendation. Different from the general recommendation system, the data is only described by feature vectors. In the recommendation system based on streaming data, the training data is added with a time attribute, and the data input to the recommendation model is also in chronological order. In the streaming data recommendation system, technologies related to real-time processing of big data need to be used, and the construction and training of the recommendation system model will be different. [0003] Since the streaming data recom...
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 Patents(China)
IPC IPC(8): G06F16/9535G06K9/62
CPCG06F18/214
Inventor 程国艮李欣杰
Owner GLOBAL TONE COMM TECH