Internet data intelligent acquisition method and system

Abstract

The invention discloses an Internet data intelligent acquisition method and system, and relates to the field of data intelligent acquisition, the system comprises a historical data acquisition module, a data analysis module and an intelligent acquisition module, the Internet historical data set of a user in a website is acquired, and the Internet historical data set of the user in the website is systematically analyzed, so that the Internet historical data set of the user in the website is acquired; according to the method, the Internet data acquisition control set of each commodity type corresponding to the user in the website is obtained, a data basis is provided for subsequent commodity recommendation corresponding to the user, the accuracy and effectiveness of acquisition and acquisition of the Internet recommended commodity data corresponding to the user are indirectly improved, and then the timeliness and accuracy of recommendation decision making are improved.

Description

Technical Field

[0001] This application relates to the field of intelligent data collection, and particularly to an intelligent internet data collection method and system. Background Art

[0002] Intelligent collection technology can widely and deeply collect a large amount of data from the Internet, including areas that are difficult to cover by traditional data collection. This comprehensiveness enables decision-makers to understand various aspects of information such as the market, users, and competitors more comprehensively, providing a more solid data foundation for decision-making. Intelligent collection technology can collect data from the Internet in real time and update the data in a timely manner to ensure that decision-makers can obtain the latest information. This real-time nature enables decision-makers to respond to market changes more quickly, improving the timeliness and accuracy of decision-making. However, the existing technologies have the following deficiencies;

[0003] When the existing technologies are used for product recommendation, they lack intelligent collection and analysis of user needs and user-preferred product data, resulting in ineffective and non-targeted product recommendations, thereby reducing the accuracy of product recommendations, being unfavorable for stimulating users' shopping desires, and reducing product sales. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent internet data collection method and system to solve the problems raised in the above background art.

[0005] To achieve the above purpose, the present invention provides the following technical solution: An intelligent internet data collection system, comprising:

[0006] A historical data acquisition module: used to acquire the historical internet data collection status of a website to obtain the corresponding internet historical data set of the website;

[0007] A data analysis module: used to analyze according to the corresponding internet historical data set of the website to obtain an internet data collection control set;

[0008] An intelligent collection module: used to collect data according to the corresponding internet data collection control set to obtain an internet data collection result.

[0009] In a preferred embodiment of this solution, the specific implementation method of the historical data acquisition module is as follows:

[0010] Acquire the data call log corresponding to the API port, and obtain the corresponding internet historical data set of the website through the data call log, where the internet historical data set includes time node data and user behavior data, and the user behavior data includes browsing behavior data, search behavior data, social behavior data, and purchase behavior data corresponding to each user;

[0011] The time node data refers to the collection time points corresponding to the user behavior data;

[0012] The browsing behavior data includes the various product pages browsed by the user, the start browsing time points of the various product pages, and the browsing durations corresponding to the various product pages;

[0013] The search behavior data includes the keywords input by the user during each search and the search time points of each search;

[0014] The social behavior data includes the number of evaluations read by the user for the corresponding product pages browsed;

[0015] The purchase behavior data includes the various products purchased by the user, the product prices corresponding to the various purchases, the purchase time points corresponding to the various purchases, the product display pictures and product names corresponding to the various purchases.

[0016] In a preferred solution of this solution, the specific execution method of the data analysis module is as follows:

[0017] Establish a data extraction relationship between the data analysis module and the database, and extract the product categories, product display pictures, product names, and product prices corresponding to the various products stored in the database;

[0018] Divide the time period by the user's corresponding two adjacent purchases of products. The time period between the previous purchase time point and the current purchase time point is recorded as the comparison time period for the current purchase of products. Statistically obtain the comparison time periods for the user's corresponding various purchases of products, and obtain the durations of the comparison time periods for the user's corresponding various purchases of products;

[0019] Data-divide the browsing behavior data, search behavior data, and social behavior data corresponding to the target user through the time points of the comparison time periods for the user's corresponding various purchases of products to obtain comparison data sets corresponding to the comparison time periods for the user's corresponding various purchases of products;

[0020] Through information screening of the various product pages browsed by each user, obtain the product display pictures, product names, and product prices corresponding to the various product pages browsed by each user. By matching with the product categories, product display pictures, and product names corresponding to the various products stored in the database, obtain the product categories and product prices corresponding to the various product pages browsed by each user. Combine the comparison time periods and the durations of the comparison time periods for the user's corresponding various purchases of products for data analysis and matching to obtain the number of views, total browsing duration, browsing frequency, proportion of total browsing duration, and browsing price range of each product category within the comparison time periods for the user's corresponding various purchases of products;

[0021] Perform data statistics on the product categories corresponding to each product page browsed by the user and the comparison time periods for each purchase of the user to obtain the total number of evaluation readings for each product category within the comparison time periods for each purchase of the user;

[0022] Extract the product categories corresponding to each keyword stored in the database;

[0023] By performing data matching between the keywords entered by the user during each search and the product categories corresponding to each keyword stored in the database, obtain the product categories corresponding to each search by the user. Combine the comparison time periods for each purchase of the user and the duration of the comparison time periods for data matching to obtain the number of searches and the search ratio for each product category within the comparison time periods for each purchase of the user;

[0024] Record the number of views, total view duration, view frequency, total view duration ratio, view price range, number of searches, search ratio, and total number of evaluation readings for each product category within the comparison time periods for each purchase of the user as the dataset to be analyzed for the comparison time periods for each purchase of the user;

[0025] Perform data matching between the product display pictures and product names for each purchase of each user and the product categories, product display pictures, and product names corresponding to each product stored in the database to obtain the product categories for each purchase of each user;

[0026] Perform data matching on the dataset to be analyzed for the comparison time periods for each purchase of the user through the product categories for each purchase of each user to obtain the valid dataset that matches the product categories for each purchase of the user in the analysis dataset, denoted as the valid dataset corresponding to each purchase of the user;

[0027] Among them, the valid dataset refers to the number of views, total view duration, view frequency, total view duration ratio, view price range, number of searches, search ratio, and total number of evaluation readings for the product categories corresponding to each purchase of the user;

[0028] Calculate the average and standard deviation of the commodity prices for each commodity category corresponding to the user's purchases. Match the data based on the commodity prices, commodity categories, standard deviation of commodity prices, and average commodity price corresponding to each purchase. When the commodity price corresponding to each purchase falls within the standard price range corresponding to the commodity category, it indicates that the purchase is a valid purchase. Count the valid purchases for each commodity category and match the valid data sets for each valid purchase corresponding to each commodity category;

[0029] The standard range refers to the range where the commodity price is less than or equal to the standard deviation of the commodity price + the average commodity price of the commodity category corresponding to the purchased commodity, and greater than or equal to the average commodity price of the commodity category corresponding to the purchased commodity - the standard deviation of the commodity price. Count the standard price ranges corresponding to each commodity category;

[0030] Extract data from the valid data sets for each valid purchase corresponding to each commodity category to obtain the browsing price ranges for each valid purchase corresponding to each commodity category;

[0031] Compare the browsing price ranges for each valid purchase corresponding to each commodity category with the standard price ranges corresponding to each commodity category to obtain the overlap degree between the browsing price ranges for each valid purchase corresponding to each commodity category and the standard price ranges corresponding to each commodity category, denoted as the price overlap degree for each valid purchase corresponding to each commodity category;

[0032] Compare the price overlap degree for each valid purchase corresponding to each commodity category with the preset price overlap degree threshold. If the price overlap degree is less than the preset price overlap degree threshold, it indicates that the browsing price range for the commodity category corresponding to this valid purchase lacks reference significance. If the price overlap degree is greater than or equal to the preset price overlap degree threshold, it indicates that the browsing price range for the commodity category corresponding to this valid purchase has reference significance, and record the valid data set corresponding to this purchase as the reference data set. Count the reference data sets corresponding to each commodity category;

[0033] Perform data statistics and calculations on the reference data sets corresponding to each commodity category to obtain the standard deviation of the browsing times of each commodity category, the standard deviation of the total browsing duration of each commodity category, the standard deviation of the browsing frequency of each commodity category, the standard deviation of the proportion of the total browsing duration of each commodity category, the standard deviation of the browsing price range of each commodity category, the standard deviation of the search times of each commodity category, the standard deviation of the search proportion of each commodity category, and the standard deviation of the total number of evaluation readings of each commodity category;

[0034] Perform data statistics on each reference data set corresponding to each commodity type to obtain the intervals of the browsing times of the commodity types corresponding to each commodity type, the intervals of the total browsing duration of the commodity types, the intervals of the browsing frequencies of the commodity types, the intervals of the proportions of the total browsing duration of the commodity types, the intervals of the search times of the commodity types, the intervals of the search proportions of the commodity types, and the intervals of the total number of evaluated readings of the commodity types;

[0035] Record the standard price intervals corresponding to each commodity type, the intervals of the browsing times of the commodity types corresponding to each commodity type, the intervals of the total browsing duration of the commodity types, the intervals of the browsing frequencies of the commodity types, the intervals of the proportions of the total browsing duration of the commodity types, the intervals of the search times of the commodity types, the intervals of the search proportions of the commodity types, and the intervals of the total number of evaluated readings of the commodity types as the Internet data collection control set.

[0036] In a preferred embodiment of this solution, the specific execution method of the intelligent acquisition module is as follows:

[0037] Extract the recommended values corresponding to the browsing times of the commodity types, the total browsing duration of the commodity types, the browsing frequencies of the commodity types, the proportions of the total browsing duration of the commodity types, the search times of the commodity types, the search proportions of the commodity types, and the total number of evaluated readings of the commodity types stored in the database;

[0038] Obtain the browsing behavior data, search behavior data, and social behavior data after the latest commodity purchase time point, and perform data analysis on the browsing behavior data, search behavior data, and social behavior data after the latest commodity purchase time point to obtain the browsing times of each commodity type, the total browsing duration of each commodity type, the browsing frequencies of each commodity type, the proportions of the total browsing duration of each commodity type, the search times of each commodity type, the search proportions of each commodity type, and the total number of evaluated readings of each commodity type;

[0039] If the browsing times of each commodity type, the total browsing duration of each commodity type, the browsing frequencies of each commodity type, the proportions of the total browsing duration of each commodity type, the search times of each commodity type, the search proportions of each commodity type, and the total number of evaluated readings of each commodity type are within the intervals of the browsing times of the commodity types corresponding to each commodity type, the intervals of the total browsing duration of the commodity types, the intervals of the browsing frequencies of the commodity types, the intervals of the proportions of the total browsing duration of the commodity types, the intervals of the search times of the commodity types, the intervals of the search proportions of the commodity types, and the intervals of the total number of evaluated readings of the commodity types, then obtain the recommended values corresponding to the browsing times of the commodity types, the total browsing duration of the commodity types, the browsing frequencies of the commodity types, the proportions of the total browsing duration of the commodity types, the search times of the commodity types, the search proportions of the commodity types, and the total number of evaluated readings of the commodity types;

[0040] Statistically obtain the total recommended value of each commodity category after the latest commodity purchase time point, compare the total recommended value of each commodity category with the preset total recommended value threshold. If the total recommended value of a certain commodity category is less than or equal to the total recommended value threshold, no recommendation will be made for this commodity category. If the total recommended value of a certain commodity category is greater than the total recommended value threshold, recommend this commodity category. Compare the commodity prices of each commodity corresponding to this commodity category after the latest commodity purchase time point with the standard price range corresponding to each commodity category, screen out the commodities that meet the standard price range corresponding to each commodity category and record them as the recommended commodities corresponding to each commodity category, collect data on the recommended commodities corresponding to each commodity category, and record the recommended commodities corresponding to each commodity category collected as the Internet data collection result.

[0041] To achieve the above object, the present invention also provides the following technical solution: An Internet data intelligent collection method, comprising the following steps:

[0042] S1: Obtain the historical Internet data collection status of the website to obtain the Internet historical data set corresponding to the website;

[0043] S2: Analyze according to the Internet historical data set corresponding to the website to obtain the Internet data collection control set;

[0044] S2: Perform data collection according to the corresponding Internet data collection control set to obtain the Internet data collection result.

[0045] Compared with the prior art, the beneficial effects of the present invention are:

[0046] The present invention collects the Internet historical data set of users in the website and systematically analyzes the Internet historical data set of users in the website to obtain the Internet data collection control set corresponding to each commodity category of users in the website, providing a data basis for subsequent commodity recommendations for users, indirectly improving the accuracy and effectiveness of data collection and acquisition of Internet recommended commodities corresponding to users, and further improving the timeliness and accuracy of recommendation decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The present invention is further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to the following drawings without creative efforts.

[0048] Figure 1 It is a schematic diagram of module connection of an embodiment of the present invention.

[0049] Figure 2 It is a schematic diagram of step connection of an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0050] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0051] Please refer to Figure 1 , the present invention provides an Internet data intelligent acquisition system, which includes a historical data acquisition module, a data analysis module, and an intelligent acquisition module;

[0052] The historical data acquisition module is connected to the data analysis module, and the data analysis module is connected to the intelligent acquisition module;

[0053] Historical data acquisition module: used to obtain the historical Internet data acquisition status of the website to obtain the corresponding Internet historical data set of the website;

[0054] Further, the specific execution method of the historical data acquisition module is as follows:

[0055] Obtain the data call log corresponding to the API port, and obtain the corresponding Internet historical data set of the website through the data call log, where the Internet historical data set includes time node data and user behavior data, and the user behavior data includes browsing behavior data, search behavior data, social behavior data, and purchase behavior data corresponding to each user;

[0056] The time node data refers to the acquisition time point corresponding to the user behavior data;

[0057] The browsing behavior data includes each commodity page browsed by the user, the start browsing time point of each commodity page, and the browsing duration corresponding to each commodity page;

[0058] The search behavior data includes the keywords input by the user during each search and the search time point of each search;

[0059] The social behavior data includes the number of evaluations read by the user for each browsed commodity page;

[0060] The purchase behavior data includes each purchase commodity corresponding to the user, the commodity price corresponding to each purchase commodity, the purchase time point corresponding to each purchase commodity, the commodity display map and commodity name corresponding to each purchase commodity.

[0061] Data analysis module: used to analyze according to the corresponding Internet historical data set of the website to obtain the Internet data acquisition control set;

[0062] Further, the specific execution method of the data analysis module is as follows:

[0063] Establish a data extraction relationship between the data analysis module and the database, and extract the commodity categories, commodity display pictures, commodity names, and commodity prices corresponding to each commodity stored in the database;

[0064] Divide the time period based on the commodities purchased by the user in two adjacent purchases. Denote the time period between the previous purchase time point and the current purchase time point as the comparison time period for the current purchase of commodities. Statistically obtain the comparison time periods for each purchase of commodities by the user, and obtain the duration of the comparison time periods for each purchase of commodities by the user;

[0065] Divide the browsing behavior data, search behavior data, and social behavior data corresponding to the target user according to the time points of the comparison time periods for each purchase of commodities by the user, and obtain the comparison data sets corresponding to the comparison time periods for each purchase of commodities by the user;

[0066] By screening the information of each commodity page browsed by each user, obtain the commodity display pictures, commodity names, and commodity prices corresponding to each commodity page browsed by each user. Match with the commodity categories, commodity display pictures, and commodity names corresponding to each commodity stored in the database to obtain the commodity categories and commodity prices corresponding to each commodity page browsed by each user. Combine the comparison time periods and the duration of the comparison time periods for each purchase of commodities by the user for data analysis and matching, and obtain the browsing times, total browsing duration, browsing frequency, proportion of total browsing duration, and browsing price range of each commodity category within the comparison time periods for each purchase of commodities by the user;

[0067] Statistically obtain the total number of evaluation readings of each commodity category within the comparison time periods for each purchase of commodities by the user through the commodity categories corresponding to each commodity page browsed by the user and the comparison time periods for each purchase of commodities by the user;

[0068] Extract the commodity categories corresponding to each keyword stored in the database;

[0069] Match the keywords entered by the user during each search with the commodity categories corresponding to each keyword stored in the database to obtain the commodity categories corresponding to each search by the user. Combine the comparison time periods and the duration of the comparison time periods for each purchase of commodities by the user for data matching, and obtain the search times and search proportions of each commodity category within the comparison time periods for each purchase of commodities by the user;

[0070] Record the number of views of each commodity category, the total browsing duration of each commodity category, the browsing frequency of each commodity category, the proportion of the total browsing duration of each commodity category, the browsing price range of each commodity category, the number of searches for each commodity category, the search proportion of each commodity category, and the total number of evaluation readings of each commodity category during the comparison period corresponding to each purchase of the user as the dataset to be analyzed during the comparison period corresponding to each purchase of the user for each commodity;

[0071] Match the commodity display pictures and commodity names corresponding to each purchase of each user with the commodity categories, commodity display pictures, and commodity names corresponding to each commodity stored in the database to obtain the commodity categories corresponding to each purchase of each user;

[0072] Match the dataset to be analyzed during the comparison period corresponding to each purchase of each commodity through the commodity categories corresponding to each purchase of each user to obtain the effective dataset that conforms to the commodity categories corresponding to each purchase of each commodity in the analysis dataset, denoted as the effective dataset corresponding to each purchase of each commodity;

[0073] Among them, the effective dataset refers to the number of views of the commodity category, the total browsing duration of the commodity category, the browsing frequency of the commodity category, the proportion of the total browsing duration of the commodity category, the browsing price range of the commodity category, the number of searches for the commodity category, the search proportion of the commodity category, and the total number of evaluation readings of the commodity category corresponding to each purchase of each commodity;

[0074] Calculate and obtain the average commodity price and the standard deviation of the commodity price for each commodity category corresponding to the user through the commodity categories and commodity prices corresponding to each purchase of the user. Match the commodity prices, commodity categories, the standard deviation of the commodity price of each commodity category, and the average commodity price corresponding to each purchase of each commodity. When the commodity price corresponding to each purchase of each commodity is within the standard price range corresponding to the corresponding commodity category, it means that this purchase of the commodity is a valid purchase. Statistically obtain each valid purchase corresponding to each commodity category, and match the effective dataset corresponding to each valid purchase of each commodity category;

[0075] The standard interval refers to the interval where the commodity price is less than or equal to the standard deviation of the commodity price + the average commodity price of the commodity category corresponding to the purchased commodity, and greater than or equal to the average commodity price of the commodity category corresponding to the purchased commodity - the standard deviation of the commodity price. Statistically obtain the standard price range corresponding to each commodity category;

[0076] Extract the data from the effective dataset corresponding to each valid purchase of each commodity category to obtain the browsing price range corresponding to each valid purchase of each commodity category;

[0077] Compare the browsing price ranges corresponding to each valid purchase of each commodity type with the standard price ranges corresponding to each commodity type to obtain the overlap degree between the browsing price ranges corresponding to each valid purchase of each commodity type and the standard price ranges corresponding to each commodity type, which is denoted as the price overlap degree corresponding to each valid purchase of each commodity type;

[0078] Compare the price overlap degree corresponding to each valid purchase of each commodity type with a preset price overlap degree threshold. If the price overlap degree is less than the preset price overlap degree threshold, it means that the browsing price range corresponding to the commodity type of this valid purchase lacks reference significance. If the price overlap degree is greater than or equal to the preset price overlap degree threshold, it means that the browsing price range corresponding to the commodity type of this valid purchase has reference significance, and the valid data set corresponding to this purchase is denoted as the reference data set, and the reference data sets corresponding to each commodity type are statistically obtained;

[0079] Perform data statistics and data calculations on the reference data sets corresponding to each commodity type to obtain the standard deviations of the browsing times of the commodity types corresponding to the purchase of each commodity type, the standard deviations of the total browsing durations of the commodity types, the standard deviations of the browsing frequencies of the commodity types, the standard deviations of the total browsing duration ratios of the commodity types, the standard deviations of the browsing price ranges of the commodity types, the standard deviations of the search times of the commodity types, the standard deviations of the search ratios of the commodity types, and the standard deviations of the total number of evaluation readings of the commodity types;

[0080] Perform data statistics on the reference data sets corresponding to each commodity type to obtain the ranges of the browsing times of the commodity types corresponding to the purchase of each commodity type, the ranges of the total browsing durations of the commodity types, the ranges of the browsing frequencies of the commodity types, the ranges of the total browsing duration ratios of the commodity types, the ranges of the search times of the commodity types, the ranges of the search ratios of the commodity types, and the ranges of the total number of evaluation readings of the commodity types;

[0081] Denote the standard price ranges corresponding to each commodity type, the ranges of the browsing times of the commodity types corresponding to the purchase of each commodity type, the ranges of the total browsing durations of the commodity types, the ranges of the browsing frequencies of the commodity types, the ranges of the total browsing duration ratios of the commodity types, the ranges of the search times of the commodity types, the ranges of the search ratios of the commodity types, and the ranges of the total number of evaluation readings of the commodity types as the Internet data collection control set.

[0082] Intelligent acquisition module: used to collect data according to the corresponding Internet data collection control set to obtain Internet data collection results.

[0083] Furthermore, the specific execution method of the intelligent acquisition module is as follows:

[0084] Extract the recommended values corresponding to the number of views of product categories stored in the database, the total duration of product category views, the frequency of product category views, the proportion of the total duration of product category views, the number of searches for product categories, the search proportion of product categories, and the total number of evaluation readings of product categories;

[0085] Obtain the browsing behavior data, search behavior data, and social behavior data after the latest product purchase time point, and perform data analysis on the browsing behavior data, search behavior data, and social behavior data after the latest product purchase time point to obtain the number of views of each product category, the total duration of each product category view, the frequency of each product category view, the proportion of the total duration of each product category view, the number of searches for each product category, the search proportion of each product category, and the total number of evaluation readings of each product category;

[0086] If the number of views of each product category, the total duration of each product category view, the frequency of each product category view, the proportion of the total duration of each product category view, the number of searches for each product category, the search proportion of each product category, and the total number of evaluation readings of each product category are within the intervals of the number of views of product categories, the total duration of product category views, the frequency of product category views, the proportion of the total duration of product category views, the number of searches for product categories, the search proportion of product categories, and the total number of evaluation readings of each product category, then obtain the recommended values corresponding to the number of views of product categories, the total duration of product category views, the frequency of product category views, the proportion of the total duration of product category views, the number of searches for product categories, the search proportion of product categories, and the total number of evaluation readings of product categories;

[0087] Statistically obtain the total recommended value of each product category after the latest product purchase time point, compare the total recommended value of each product category with the preset total recommended value threshold. If the total recommended value of a certain product category is less than or equal to the total recommended value threshold, then do not recommend this product category. If the total recommended value of a certain product category is greater than the total recommended value threshold, then recommend this product category. Compare the product prices of each product corresponding to this product category after the latest product purchase time point with the standard price interval corresponding to each product category, screen out the products that meet the standard price interval corresponding to each product category and record them as the recommended products corresponding to each product category, collect data on the recommended products corresponding to each product category, and record the collected recommended products corresponding to each product category as the Internet data collection result.

[0088] To achieve the above object, the present invention also provides the following technical solution: An Internet data intelligent collection method, including the following steps:

[0089] S1: Obtain the historical Internet data collection status of the website to obtain the Internet historical data set corresponding to the website;

[0090] S2: Analyze according to the Internet historical data set corresponding to the website to obtain an Internet data collection control set;

[0091] S2: Perform data collection according to the corresponding Internet data collection control set to obtain an Internet data collection result.

[0092] The above are all preferred embodiments of this application. The protection scope of this application is not limited hereby. Therefore, all equivalent changes made according to the structure, shape, and principle of this application shall be covered within the protection scope of this application.

Claims

1. An Internet data intelligent collection system, characterized by: include: Historical data acquisition module: used to acquire the historical Internet data collection status of the website and obtain the Internet historical data set corresponding to the website; Data analysis module: used to analyze the Internet historical data set corresponding to the website to obtain the Internet data collection control set; Intelligent collection module: used to collect data according to the corresponding Internet data collection control set to obtain Internet data collection results.

2. The Internet data intelligent collection system according to claim 1, characterized in that: The specific implementation method of the historical data acquisition module is as follows: Obtain the data call log corresponding to the API port, and obtain the Internet historical data set corresponding to the website through the data call log, where the Internet historical data set includes time node data and user behavior data, and the user behavior data includes browsing behavior data, search behavior data, social behavior data, and purchase behavior data corresponding to each user; The time node data refers to the collection time point corresponding to the user behavior data; The browsing behavior data includes each product page browsed by the user, the start time of browsing each product page, and the corresponding browsing time of each product page; The search behavior data includes the keywords entered by the user during each search and the search time point of each search; The social behavior data includes the number of reviews read by the user for each browsed product page; The purchase behavior data includes each purchase of goods corresponding to the user, the goods price corresponding to each purchase of goods, the purchase time point corresponding to each purchase of goods, and the goods display picture and goods name of each purchase of goods.

3. The Internet data intelligent collection system according to claim 2, characterized in that: The specific implementation method of the data analysis module is as follows: Establish a data extraction relationship between the data analysis module and the database to extract the product category, product display image, product name and product price corresponding to each product stored in the database; Divide the time periods of two consecutive purchases of goods by the user, record the time period between the time point of the last purchase of goods and the time point of the current purchase of goods as the comparison time period of the current purchase of goods, obtain the comparison time periods of each purchase of goods by the user, and obtain the length of each comparison time period of each purchase of goods by the user; The browsing behavior data, search behavior data, and social behavior data corresponding to the target user are divided according to the time points of the comparison time periods corresponding to each purchase of goods by the user, so as to obtain a comparison data set corresponding to the comparison time periods corresponding to each purchase of goods by the user; By screening the information of each product page browsed by each user, the product display image, product name and product price corresponding to each product page browsed by each user are obtained, and the product category and product price corresponding to each product page browsed by each user are obtained by matching with the product category, product display image and product name corresponding to each product stored in the database, and data analysis and matching are performed in combination with the comparison time period and the duration of the comparison time period corresponding to each purchase of the product by the user, so as to obtain the number of times each product category is browsed within the comparison time period corresponding to each purchase of the product by the user, the total browsing time of each product category, the browsing frequency of each product category, the ratio of the total browsing time of each product category and the browsing price range of each product category; Data statistics are collected based on the product categories corresponding to each product page browsed by the user and the comparison time periods of each product purchase by the user, so as to obtain the total number of reviews read for each product category within the comparison time periods of each product purchase by the user; Extract the commodity categories corresponding to each keyword stored in the database; By matching the keywords input by the user in each search with the commodity categories corresponding to each keyword stored in the database, the commodity categories corresponding to each search by the user are obtained. The comparison time period and the length of the comparison time period corresponding to each purchase of the commodity by the user are combined for data matching to obtain the number of searches for each commodity category and the search ratio of each commodity category within the comparison time period corresponding to each purchase of the commodity by the user. The number of times each product category is browsed, the total browsing time of each product category, the browsing frequency of each product category, the ratio of the total browsing time of each product category, the browsing price range of each product category, the number of searches for each product category, the search ratio of each product category and the total number of reviews and readings of each product category in the comparison time period corresponding to each purchase of the product by the user are recorded as the data set to be analyzed for the comparison time period corresponding to each purchase of the product by the user; Data matching is performed between the product display pictures and product names of each user's corresponding purchases and the product categories, product display pictures and product names of each product stored in the database to obtain the product categories of each user's corresponding purchases; Match the data sets to be analyzed in the comparison time period of each purchase of goods by each user according to the product types of each purchase, and obtain the valid data sets in the analysis data sets that match the product types of each purchase of goods, which are recorded as the valid data sets corresponding to each purchase of goods; The valid data set refers to the number of product category browsings, total product category browsing time, product category browsing frequency, product category browsing time ratio, product category browsing price range, product category search times, product category search ratio and total number of product category reviews read corresponding to each purchase; The average price and standard deviation of the prices of the commodities corresponding to the commodities purchased by the user are calculated by the commodity types and prices corresponding to the commodities purchased by the user each time. Data matching is performed according to the commodity prices, commodity types, standard deviations of the prices of the commodities ... The standard price range refers to the range where the commodity price is less than or equal to the commodity price standard deviation + commodity price average of the commodity category of the purchased commodity, and greater than or equal to the commodity price average - commodity price standard deviation of the commodity category of the purchased commodity, and the standard price range corresponding to each commodity category is obtained by statistics; Extract data from valid data sets corresponding to each valid purchase of each commodity category to obtain browsing price ranges corresponding to each valid purchase of each commodity category; Compare the browsing price range of each commodity category corresponding to each valid purchase with the standard price range corresponding to each commodity category to obtain the overlap between the browsing price range of each commodity category corresponding to each valid purchase and the standard price range corresponding to each commodity category, which is recorded as the price overlap between each commodity category and each valid purchase; Compare the price overlap of each valid purchase of each commodity type with the preset price overlap threshold. If the price overlap is less than the preset price overlap threshold, it means that the price range of the commodity type browsed for this valid purchase lacks reference significance. If the price overlap is greater than or equal to the preset price overlap threshold, it means that the price range of the commodity type browsed for this valid purchase has reference significance. The valid data set corresponding to this purchase is recorded as the reference data set, and the reference data sets corresponding to each commodity type are obtained by statistics. Data statistics and data calculations are performed on each reference data set corresponding to each commodity category to obtain the standard deviation of the number of commodity category browsings, the standard deviation of the total browsing time of the commodity category, the standard deviation of the frequency of commodity category browsings, the standard deviation of the proportion of the total browsing time of the commodity category, the standard deviation of the price range of the commodity category browsings, the standard deviation of the number of searches for the commodity category, the standard deviation of the search proportion of the commodity category, and the standard deviation of the total number of reviews read for the commodity category; Performing data statistics on each reference data set corresponding to each commodity category, obtaining the interval of the number of commodity category browsing times, the interval of the total commodity category browsing time, the interval of the commodity category browsing frequency, the interval of the total commodity category browsing time ratio, the interval of the number of commodity category searches, the interval of the commodity category search ratio, and the interval of the total number of commodity category review readings; The standard price range corresponding to each commodity category, the range of the number of commodity category browsing times corresponding to the purchase of each commodity category, the range of the total browsing time of the commodity category, the range of the browsing frequency of the commodity category, the range of the proportion of the total browsing time of the commodity category, the range of the search times of the commodity category, the range of the search proportion of the commodity category and the range of the total number of evaluation readings of the commodity category are recorded as the Internet data collection control set.

4. The Internet data intelligent collection system according to claim 3 is characterized in that: The specific implementation method of the intelligent acquisition module is as follows: Extract the recommended values ​​corresponding to the number of browse times of the product category, the total browsing time of the product category, the browsing frequency of the product category, the ratio of the total browsing time of the product category, the number of searches of the product category, the search ratio of the product category, and the total number of reviews and readings of the product category stored in the database; Obtain browsing behavior data, search behavior data, and social behavior data since the latest product purchase time point, and perform data analysis on the browsing behavior data, search behavior data, and social behavior data since the latest product purchase time point to obtain the number of views of each product category, the total browsing time of each product category, the browsing frequency of each product category, the ratio of the total browsing time of each product category, the number of searches for each product category, the search ratio of each product category, and the total number of reviews read for each product category; If the number of browse times of each product category, the total browse time of each product category, the browse frequency of each product category, the ratio of the total browse time of each product category, the number of searches of each product category, the search ratio of each product category and the total number of reviews and readings of each product category are within the corresponding range of the number of browse times of each product category, the range of the total browse time of each product category, the range of the browse frequency of each product category, the range of the ratio of the total browse time of each product category, the range of the search times of each product category, the range of the search ratio of each product category and the range of the total number of reviews and readings of each product category, then the recommended values ​​corresponding to the number of browse times of each product category, the total browse time of each product category, the browse frequency of each product category, the ratio of the total browse time of each product category, the number of searches of each product category, the search ratio of each product category and the total number of reviews and readings of each product category are obtained; The total recommendation value of each commodity category after the latest commodity purchase time point is obtained statistically, and the total recommendation value of each commodity category is compared with the preset total recommendation value threshold. If the total recommendation value of a commodity category is less than or equal to the total recommendation value threshold, the commodity category is not recommended. If the total recommendation value of a commodity category is greater than the total recommendation value threshold, the commodity category is recommended. The commodity prices of each commodity corresponding to the commodity category after the latest commodity purchase time point are compared with the standard price range corresponding to each commodity category. The commodities that meet the standard price range corresponding to each commodity category are selected and recorded as the recommended commodities corresponding to each commodity category. Data collection is performed on the recommended commodities corresponding to each commodity category, and the collected recommended commodities corresponding to each commodity category are recorded as Internet data collection results.

5. An Internet data intelligent collection method, applied to an Internet data intelligent collection system as described in any one of claims 1 to 4, characterized in that: include: S1: Acquire the historical Internet data collection status of the website to obtain the Internet historical data set corresponding to the website; S2: Analyze the Internet historical data set corresponding to the website to obtain the Internet data collection control set; S2: Perform data collection according to the corresponding Internet data collection control set to obtain Internet data collection results.

Images