WO2020019189A1

WO2020019189A1 - Big data-based web shopping guide system

Info

Publication number: WO2020019189A1
Application number: PCT/CN2018/097016
Authority: WO
Inventors: 陈钦鹏
Original assignee: 深圳齐心集团股份有限公司
Priority date: 2018-07-25
Filing date: 2018-07-25
Publication date: 2020-01-30

Abstract

Disclosed are a big data-based web shopping guide system, the system comprising an e-commerce web service platform, a web shopping guide module, and a web shopping client. The web shopping client receives a product search instruction from a user, gathers a product list viewed by the user, and forwards the same to the e-commerce web service platform. The e-commerce web service platform receives and stores the product search instruction and the product list viewed by the user, and the web shopping guide module establishes a personal information model and performs analysis, so as to acquire personal information of the user comprising an age group, gender, and preference. The web shopping guide module recommends, according to the product search instruction sent by the web client and the personal information of the user, a product list, and sends the same to the e-commerce web service platform. The e-commerce web service platform sends the recommended product list to the web shopping client for the user to select. The present invention accelerates searches, and finds accurate information meeting user demands, thereby providing a superior experience.

Description

Online shopping guide system based on big data

Technical field

The invention relates to a network-based shopping guide system based on big data.

Background technique

With the rapid development of science and technology, society and economy, the era of big data has begun. The value sources of big data have more comprehensive characteristics. From the data dimension, time dimension, spatial dimension, and cross-border data, they all converge. The value of big data is reflected in more accurate and personalized services provided to customers.In addition, big data has great value potential in artificial intelligence such as language, vision, and prediction.For example, behavior analysis based on consumer habits can give Users bring many significant conveniences, which can provide customers with precise and extreme personalized services.

On the other hand, with the continuous progress of society, the degree of a commoditized society has continued to increase, and the consumption capacity of residents has continued to increase, while the continuous progress of the information society has led to the diversity and multi-selection of residents' consumption patterns, which poses a challenge to the commerce and trade industry. Will be more intense. How to judge the consumption habits of end consumers, and then formulate their own product sales strategies to achieve positive online shopping guides has become a top priority.

Summary of the Invention

A brief overview of embodiments of the invention is given below in order to provide a basic understanding of some aspects of the invention. It should be understood that the following summary is not an exhaustive overview of the invention. It is not intended to identify key or important parts of the invention, nor is it intended to limit the scope of the invention. Its purpose is merely to present some concepts in a simplified form as a prelude to the more detailed description that is discussed later.

According to one aspect of the present application, the system is provided including a server and a plurality of mobile terminals connected to the server. The server is provided with an e-commerce network service platform and a network shopping guide module. The mobile terminal is provided with an online shopping client. The online shopping client is used for Log on to the e-commerce network service platform to display the product list; the online shopping guide module is used to provide a product recommendation list for the online shopping client; wherein the process of the network shopping module providing the product recommendation list to the online shopping client is as follows:

The online shopping client receives the user's product search command and collects the product list browsed by the user, and forwards the product search command and the product list browsed by the user to the e-commerce network service platform;

The e-commerce network service platform receives the search product command sent by the online shopping client and the product list browsed by the user and stores it. The online shopping guide module establishes a subjective information model and analyzes the product search command of the online shopping client and the product list browsed by the user to obtain users. Subjective information including age, gender, and preferences;

The online shopping guide module sends the recommended product list to the e-commerce network service platform according to the search product order sent by the online shopping client and the subjective information of the user;

The e-commerce network service platform sends the recommended product list to the online shopping client for users to select.

Further, the process of providing a product recommendation list for the online shopping client by the online shopping guide module further includes: the online shopping client collects the product list information in the recommended product list browsed by the user, and sends the product list information to the e-commerce network service platform; The e-commerce network service platform receives and stores the product list information, and the network shopping guide module performs a comparative analysis on the product list information to modify the subjective information model.

The online shopping guide module also recommends the product list according to the product evaluation, and the online shopping client analyzes the product list information in the recommended product list: comprehensively evaluate the product list information by the quality, price, and user evaluation of similar products, and according to the comprehensive The ranking of the product list information is from high to low.

The online shopping guide module establishes and analyzes the subjective information model of the online shopping client's product search command and the product list browsed by the user, including:

The online shopping guide module establishes a subjective information model according to the product list browsed by the user in advance; the subjective information model is used to describe the weight analysis of the subjective information, and the z subjective information sets are recorded as X = {x1, x2, ..., xz}, and m is selected An evaluation index reflecting subjective factors is denoted as Y = {y1, y2,…, ym}, and the weight vector w of the index is w = (w1, w2,…, wm) ^T , ∑wi = 1,1 <i <m, wi∈ [0,1], the subjective information model is described in a matrix form as: A = (a _ij ) _{z × m} , where a _ij is subjective information, given as a triangular fuzzy number, and then according to a preset weight vector Information calculates optimal indicator weights.

The online shopping guide module correlates the search product commands of the online shopping client within a preset time period to form a related set, and analyzes the related set to obtain a combined combined product command;

The online shopping guide module compares the product list browsed by the user with the subjective information model for a period of time to modify the combined product order to make it more accurately match the user's subjective trademark list.

Compared with the prior art, the present invention has the following advantages:

1. The creative user's search for product commands within a certain period of time are associated and combined to form a combined product command, which can get a closer search list, which greatly reduces the user's search time;

2. This application judges the user ’s age range, gender, and preferences through user operations. On the one hand, it respects the user ’s privacy (the user ’s true information is not obtained). On the other hand, it can provide more information based on the user ’s actual needs rather than the actual age good service;

3. In addition, it can provide accurate and personalized services for customers' data mining. Among them, the user's subjective attribute set S is used to describe the user's preferences and understand the user's psychological needs. The combination of product orders is also modified to further reduce users. Search time, and get a more subjective list of users, giving users a good sense of experience; this application can not only speed up the search, but also accurately retrieve the customized information that users need, which is very humane Experience.

detailed description

Embodiments of the present invention will be described below.

The invention provides a big data-based online shopping guide system. The system includes a server and a plurality of mobile terminals connected to the server. The server is provided with an e-commerce network service platform and a network shopping guide module. The mobile terminal is provided with an online shopping client. The online shopping client is used to log in to the e-commerce network service platform to display the product list; the online shopping guide module is used to provide a product recommendation list for the online shopping client; the process of providing the online shopping client with a product recommendation list is as follows:

The e-commerce network service platform receives the search product command sent by the online shopping client and the product list browsed by the user and stores it in the database;

The online shopping guide module reads the database to obtain the search product command of the online shopping client and the list of products browsed by the user, and analyzes it according to a pre-established subjective information model (the more times the user uses the e-commerce network service platform, the platform models it The more accurate) to obtain the subjective information of the user, the subjective information includes at least the age range, gender, and preference; wherein preference is data that reflects the user ’s personality and preferences, for example, when users browse e-commerce online service platforms, they often pay attention to Current affairs information, or often pay attention to emotional articles or books, or often pay attention to articles or books full of righteousness, etc., from the attention of information and preset big data judgment methods to analyze user preferences; preferences are used to understand the user's psychological needs ;

The e-commerce network service platform sends the recommended product list to the online shopping client for users to select;

The online shopping client collects the product list information in the recommended product list browsed by the user, and sends the product list information to the e-commerce network service platform; the e-commerce network service platform receives and stores the product list information, and the online shopping guide module stores the product list information A comparative analysis is performed to modify the subjective information model.

The online shopping guide module establishes and analyzes a subjective information model of the product search command of the online shopping client and the product list browsed by the user, including:

The online shopping guide module establishes a subjective information model in advance according to the product list browsed by the user; the subjective information model is used to describe the weight analysis of the subjective information. The z subjective information sets are recorded as X = {x1, x2, ..., xz}, and m manifestations are selected The evaluation index of subjective factors is written as Y = {y1, y2,…, ym}, and the weight vector w of the index is w = (w1, w2,…, wm) ^T , ∑wi = 1,1 <i <m, wi∈ [0,1], the subjective information model is described in a matrix form as: A = (a _ij ) _{z × m} , where a _ij is the subjective information, given as a triangular fuzzy number, and then calculated based on the preset weight vector information Optimal index weight; the calculation of the above model is the prior art, which is not described in detail in this application;

The online shopping guide module correlates the search merchandise commands of the online shopping client within a preset time period to form an association set, and analyzes the association set to obtain the combined merchandise command. For example, some users do not know when to search for merchandise. What kind of search is required, so several search product commands are required. However, the platforms in the prior art search for a certain command and do not search for the deep needs of the user. For example, a user needs to search for a piece of clothing, There will be several search product orders: "mature, two-piece, professional wear" "dress" "dress, professional" "dress, heavy industry embroidery" "professional wear, slim fit", the search results of existing platforms are targeted at the above key respectively Words are retrieved one by one to get a list of conclusions to the user. This application is a combination of various search product orders, and the combined product order obtained is "two-piece suit or dress, professional wear, slim fit and embroidery, and price = [100-]". The user search command (mature, Heavy industry embroidery) It can be seen that the user's age has a certain purchasing power, so after the combination of product orders, the price will be automatically omitted below 100, and the search results obtained by the user will be more accurate at this time;

The online shopping guide module compares the product list browsed by the user with the subjective information model for a period of time to modify the combined product order to make it more accurately match the user's subjective trademark list. For example, after calculating the subjective factor evaluation index y1 of the user's subjective information model, that is, the weight vector w1 is the largest, then supplement the combined commodity command and add the interval value of the subjective factor to correct the combined commodity command. . If the subjective factor corresponding to the evaluation index y1 is body type (body data obtained from height value and weight value) is overweight, then add “and weight = [120-140]” to the combined product command, so as to obtain a more accurate user subjective The list of products for the feature.

In addition, the e-commerce network service platform of the present application also sets detailed labels for describing the attributes of the products on each of the products on the e-commerce network service platform, including at least the characteristics for describing the subjective characteristics of the user. For example, the label includes product classification (for example, the major category of the product is clothes, then the small category can be subdivided into business wear, casual wear, student wear, etc.), and product specifications (for example, if the product is clothes, it indicates what body type and weight range are suitable) , Product style (for example, if the product is clothes, it indicates that it is capable, gentle, or neutral, etc.), product evaluation (thinner, thinner), and product rating (such as setting a perfect score of 10 points), which is conducive to the online shopping guide module Recommended. Among them, product style is the characteristic that describes the subjective characteristics of users. It is also possible to set characteristics that are subjective to the user according to the specific broad category of the product.

The invention not only improves the user experience mentioned above, but also improves the intelligent characteristics: when the user does a search when he does not know the specific product style, he no longer needs to explore it step by step. The online shopping guide module of this application is based on its The subjective information model and the combination of product commands to directly give a list of products suitable for the user's subjective information have very good intelligent characteristics.

It should be emphasized that the term "including / comprising" as used herein refers to the presence of a feature, element, step or component, but does not exclude the presence or addition of one or more other features, elements, steps or components.

In addition, the method of the present invention is not limited to being performed in the chronological order described in the specification, but may also be performed in other chronological order, in parallel, or independently. Therefore, the execution order of the methods described in this specification does not limit the technical scope of the present invention.

Although the present invention has been disclosed above by describing specific embodiments of the present invention, it should be understood that all the embodiments and examples described above are illustrative and not restrictive. Those skilled in the art may design various modifications, improvements, or equivalents to the present invention within the spirit and scope of the appended claims. These modifications, improvements or equivalents should also be considered to be included in the protection scope of the present invention.

Claims

A big data-based online shopping guide system is characterized in that the system includes a server and a plurality of mobile terminals connected to the server. The server is provided with an e-commerce network service platform and a network shopping guide module. The mobile terminal is provided with an online shopping client. The online shopping client is used to log in to the e-commerce network service platform to display the list of products; the online shopping guide module is used to provide a recommended list of products for the online shopping client; wherein the process of providing the recommended list of products to the online shopping client by the online shopping module is as follows:

The online shopping client receives the user's product search command and collects the product list browsed by the user, and forwards the product search command and the product list browsed by the user to the e-commerce network service platform;

The e-commerce network service platform receives the search product order sent by the online shopping client and the product list browsed by the user, and stores it;

The online shopping guide module reads the database to obtain the product search command of the online shopping client and the product list browsed by the user, and analyzes according to a pre-established subjective information model to obtain the subjective information of the user. The subjective information includes at least the age group, gender, and preference. ;

The online shopping guide module sends the recommended product list to the e-commerce network service platform according to the search product order sent by the online shopping client and the subjective information of the user;

The e-commerce network service platform sends the recommended product list to the online shopping client for users to select.
The online shopping guide system based on big data according to claim 1, wherein the process of the online shopping guide module providing a product recommendation list for an online shopping client further comprises:

The online shopping client collects the product list information in the recommended product list browsed by the user, and sends the product list information to the e-commerce network service platform; the e-commerce network service platform receives and stores the product list information, and the online shopping guide module stores the product list information A comparative analysis is performed to modify the subjective information model.
The online shopping guide system based on big data according to claim 1 or 2, characterized in that: the online shopping guide module further recommends a product list according to a product evaluation, and the online shopping client analyzes the product list information in the recommended product list: Comprehensively evaluate the product list information based on the quality, price, and user evaluation of similar products, and arrange the product list information according to the comprehensive evaluation from high to low.
The online shopping guide system based on big data according to claim 1 or 2, characterized in that the online shopping guide module establishes and analyzes a subjective information model of the online shopping client's product search command and the product list browsed by the user, and specifically includes:

The online shopping guide module establishes a subjective information model in advance according to the product list browsed by the user;

The online shopping guide module correlates the search product commands of the online shopping client within a preset time period to form a related set, and analyzes the related set to obtain a combined combined product command;

The online shopping guide module compares the product list browsed by the user with the subjective information model for a period of time to modify the combined product order to make it more accurately match the user's subjective trademark list.
The big data-based online shopping guide system according to claim 4, characterized in that:

The subjective information model is used to describe the weight analysis of subjective information. The z sets of subjective information are recorded as X = {x1, x2, ..., xz}, and m evaluation indexes reflecting subjective factors are selected and recorded as Y = {y1, y2,…, ym}, the index's weight vector w = (w1, w2,…, wm) T , ∑wi = 1,1 <i <m, wi∈ [0,1], the subjective information model is described in matrix form It is: A = (a ij ) z × m , where a ij is subjective information and is given in the form of a triangular fuzzy number, and then an optimal index weight is calculated according to preset weight vector information.
The online shopping guide system based on big data according to claim 1, characterized in that the preference is data reflecting the personality and preferences of the user, including categories of information that users often browse when browsing the e-commerce network service platform, for Understand the psychological needs of users.