Unlock instant, AI-driven research and patent intelligence for your innovation.

Rapid data intelligent analysis method for internet mall user behavioral habits

An intelligent analysis and Internet technology, applied in the field of rapid data intelligent analysis, can solve the problems of low learning efficiency and poor learning effect, and achieve the effect of reducing the possibility of cycle prediction, reducing the number of cells, and improving learning efficiency

Pending Publication Date: 2021-02-05
江苏瑞祥科技集团有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved in the present invention is: in order to solve the problem existing in the above-mentioned background technology, provide a kind of improved fast data intelligent analysis method that is used for Internet shopping mall user's behavior habit, solve the low learning efficiency when fast training of HTM (HierarchicalTemporal Memory) and poor learning

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
  • Rapid data intelligent analysis method for internet mall user behavioral habits
  • Rapid data intelligent analysis method for internet mall user behavioral habits
  • Rapid data intelligent analysis method for internet mall user behavioral habits

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0023] figure 1 The shown fast data intelligent analysis method for Internet shopping mall user behavior habits includes Internet shopping mall user behavior pattern sequence, encoding module, space pool module and time module. There are six steps to learn cell set, adjust dendritic branches, adjust active cell set, and make predictions:

[0024] Step 1, use the scene to construct the sequence of commodities, and form different timing patterns of commodity combinations.

[0025] Step 2, for different marketing scenarios, the user behavior combination pattern with time series characteristics is used as the training object of the HTM fast training model;

[0026] Step 3, obtain the set of microcolumns activated by the input can be generated by the spatial pooling algorithm, select some microcolumns from all microcolumns to activate, and activate the microcolumns corresponding to the current input;

[0027] Step 4, generating the learning cell set depends on the predicted cell ...

Embodiment 2

[0049] In this embodiment, take "abab" as an example of the input sequence in the rapid training of the present invention. First, through the learning of the spatial pool, it is assumed that the input a will activate microcolumns 1 and 3, and microcolumn b will activate microcolumns 2 and 4. , and there are 4 cells on each microcolumn, and set the connectivity threshold of dendrites to 0.8. The following describes the process when studying online:

[0050] For the first input a in the sequence, because there is no context, it is assumed that the learning cell that the time pool generates this input is: cell 1，1 and cell 3，1 , representing the first cell of microcolumn No. 1 and the first cell of microcolumn No. 3, respectively, and no dendritic branch needs to be adjusted, and the active cell is also reset to cell 1，1 and cell 3，1 .

[0051] For the second input b in the sequence, the active cell at the previous moment is not predicted to the current input, so there is no ...

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

No PUM Login to View More

Abstract

The invention relates to the technical field of network marketing and artificial intelligence, in particular to a rapid data intelligent analysis method for Internet shopping mall user behavior habits, which comprises an Internet shopping mall user behavior mode sequence, a coding module, a space pool module and a time module. According to the current behavior of the user, more targeted sales recommendation is given; according to the method, input position information can be distinguished by utilizing the advantages of a plurality of cells contained in a micro-column in HTM, and an input active cell set is reset to be a learning cell set, so that learning can be carried out for a current input sequence during HTM online learning, and the learning efficiency is improved; in the repeated sequence learning process, the number of active cell sets is reduced, the number of cells associated with the active cell sets can be effectively reduced, the possibility of cyclic prediction is reduced,and the HTM learning effect is improved; and according to the method, the synaptic value in the newly added dendritic branch is set to be greater than the communication threshold, so that the learning efficiency of HTM is improved.

Description

technical field [0001] The invention relates to the technical fields of network marketing and artificial intelligence, in particular to a fast data intelligent analysis method for Internet shopping mall user behavior habits. Background technique [0002] Internet shopping mall user behavior habits are carried out in specific scenarios, and users also recognize products through scenarios, and have different needs in different scenarios. If the selling point of the product is connected with the needs of the user, and the use of the scene can effectively touch the pain point of the user, arouse the emotional resonance of the consumer, and stimulate the desire to buy, then a good interactive relationship can be established, thereby forming consumer stickiness and loyalty. For initial users or users with little consumption information, due to insufficient user information, it is difficult to dig out the user's consumption habits, and it is difficult to provide users with targeted...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q30/02G06Q30/06G06N3/04G06N3/08
CPCG06Q30/0201G06Q30/0631G06N3/04G06N3/082
Inventor 朱博袁云燕左翌张雨钊蔡文华
Owner 江苏瑞祥科技集团有限公司