User intention prediction method based on multi-data fusion
A technology of user intentions and prediction methods, applied in the field of network information, can solve problems such as low computing efficiency, inability to quickly guide users, and high time complexity, achieve data integrity, overcome easy deviations, and improve computing efficiency
Active Publication Date: 2021-08-24
深圳市查策网络信息技术有限公司
View PDF13 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In view of the defects of this method, the existing method is to judge the weight of the effect factor of the visitor behavior index, so as to obtain the accurate judgment result of the website operation, but this method has high time complexity and low calculation efficiency, and cannot Meet the needs of quickly guiding users to use the network platform
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
[0029] The present invention will be further described in detail below in conjunction with the embodiments and the accompanying drawings, but the embodiments of the present invention are not limited thereto.
[0030] The present invention provides a user intention prediction method based on multi-data fusion, comprising the following steps:
[0031] (1) Collect access record data such as the user's access address, arrival time, access frequency, and access duration on the platform, and perform data fusion on the access record data. The specific steps are:
[0032] 1.a. Use a four-byte positive integer to number the access address as N 1 ;
[0033] 1.b. Use the four-byte time cutoff to record the arrival time with an accuracy of N in milliseconds 2 ;
[0034] 1.c. Use a four-byte positive integer to record the visit frequency, and record the number of visits per minute as N3;
[0035] 1.d. Use a four-byte positive integer to record the access time with an accuracy of N seco...
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 relates to a user intention prediction method based on multi-data fusion, and the method comprises the following steps: collecting access record data, such as an access address, arrival time, access frequency and access duration, of a user on a platform, and carrying out the data fusion of the access record data; inputting the fused access record data into a multi-layer neural network for discretization to obtain user target result data and an output vector of the multi-layer neural network; calculating the dimension value of each component in the output vector of the multi-layer neural network, selecting the dimension value larger than a threshold value, and the threshold value is a tightness control factor of the output vector of the multi-layer neural network; and mapping back to access record data corresponding to the target result data according to the selected dimension value, namely a prediction result of the user intention. Through the method, the time complexity of predicting the user intention can be effectively reduced, the calculation efficiency of an algorithm is improved, the data becomes more complete, the accuracy of a data analysis result is improved, and the requirement of quickly guiding a user to use a network platform is met.
Description
technical field [0001] The present invention relates to the technical field of network information, in particular to a user intention prediction method based on multi-data fusion. Background technique [0002] With the development of science and technology, network marketing has become a mature business model. Enterprises obtain users through website construction, provide users with information and business services, and users' seemingly random access to web pages hides a lot of information that is not related to the user's actual situation. There is a strong correlation between the required business services. If the user's access intention can be predicted through access record data such as the user's access address, arrival frequency, access frequency, access duration, and bounce rate, it will help users better use the corporate website, find the business services they need, and better guide them. Users use the enterprise website platform. [0003] In the method of predi...
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): G06Q10/04G06K9/62G06N3/04G06N3/08
CPCG06Q10/04G06N3/08G06N3/045G06F18/25
Inventor 林正春兰林陈功文
Owner 深圳市查策网络信息技术有限公司