A method for personalized recommendation of silk products based on wavelet network
A wavelet network and recommendation method technology, applied in special data processing applications, instruments, business and other directions, can solve the problems of not being able to keep existing customers well, and not be able to implement personalized services well, and achieve good application value, The effect of good recommendation accuracy and diversity
Active Publication Date: 2016-04-13
HANGZHOU WENSLI SILK TECH
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Aiming at the problems existing in silk enterprises, such as not being able to keep existing customers well, digging out potential customers, and not being able to implement personalized services well, a method for personalized recommendation of silk products based on wavelet network is proposed
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
[0019] The present invention will be described in further detail below in conjunction with the accompanying drawings.
[0020] The silk product personalized recommendation method based on wavelet network of the present invention comprises the following steps:
[0021] 1. User behavior feature extraction: A user interest feature based on Hidden Semi-Markov Model (HSMM) is designed for the user’s silk product purchase behavior which changes greatly with seasons, weather and environment. Extraction method, its structural block diagram is as follows figure 1 shown. Firstly, by analyzing the user's interests, the state transition sequence is obtained, and the hidden behavior state is obtained by using the Viterbi algorithm according to this sequence, and then the hidden semi-Markov model is established to extract the user's interest characteristics.
[0022] 2. Data preprocessing: First, compress the user behavior data stream (including user browsing behavior, description evaluat...
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 invention discloses a silk product individualized recommendation method based on a wavelet network. The silk product individualized recommendation method based on the wavelet network is suitable for the development of differentiated services, profit increase and additional value and competitiveness increase of silk enterprises in China. The wavelet network is introduced and used for user behavior data stream compression. In the process of user similarity calculation, user preference and credibility are fully considered, so that a user group most similar to a target user is obtained, a recommendation list is generated according to the evaluation condition of the user group, and products ranking in the top are recommended to the target user. According to the silk product individualized recommendation method based on the wavelet network, the requirements of the user can be scientifically, reasonably and effectively predicted and analyzed, the recommendation accuracy rate and diversity are good, the shortages existing in the silk product individualized recommendation process of traditional silk enterprises are effectively overcome, and application value is good.
Description
technical field [0001] The invention relates to the field of intelligent information processing, in particular to a wavelet network-based personalized recommendation method for silk products. Background technique [0002] At present, most silk enterprises in the world produce silk printed products in large quantities, but the final consumers demand small quantities. This is because traditional silk enterprises cannot meet the individual needs of consumers due to the consideration of economies of scale. . With the birth of digital printing technology, this kind of problem has been gradually solved. Digital printing is not limited by patterns and features of small batches. Consumers can obtain a series of unique silk fabrics at will according to their personal preferences or design ideas. "personalise". [0003] However, this kind of personalized service still depends on the active needs of consumers. In order to enable silk companies to better maintain existing customers an...
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): G06F17/30G06Q30/00
Inventor 马廷方田雪宋瑛张梅飞
Owner HANGZHOU WENSLI SILK TECH