AI-based platform network sales commodity information processing method, system and medium

Abstract

The present application provides a method, system and medium for processing information of online sales products on a platform based on AI, and belongs to the field of artificial intelligence and big data technology. The method includes: obtaining web platform information within a preset time period, extracting sales product crawling information, and then extracting product price information, product sales information, product inventory information and product evaluation information respectively, and processing them separately to obtain the product value preservation ability index, product sales ability index, product inventory guarantee ability index and product evaluation index, and finally processing them through a preset evaluation model to obtain the product competitiveness index, and compare the product competitiveness index with the preset competitiveness index threshold to determine whether the competitiveness index meets the requirements. The present application can automatically capture sales product information from the platform through AI combined with crawler technology, and quickly process and analyze the captured data, which greatly reduces the time and energy of manual collection and provides the platform with more accurate product competitiveness.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence and big data technology, and more specifically, to an AI-based platform network sales product information processing method, system and medium. Background Art

[0002] Although the traditional platform network sales product processing method has met the needs of product information release, display, update and information interaction with customers to a certain extent, it also has some obvious shortcomings. The cumbersome manual operation and slow response speed result in low efficiency of information update. It relies on data manually input by merchants and the basic data collection function of e-commerce platforms, and is unable to comprehensively collect and analyze sales product information. As a result, it often relies on experience and intuition in formulating marketing strategies and optimizing product information, making it difficult to make accurate and effective decisions.

[0003] The current platform network sales product processing technology still has problems such as low efficiency in obtaining product information, and insufficient analysis and processing of collected data. It is unable to accurately reflect the comprehensive performance of the product in terms of value preservation, sales, inventory guarantee, and overall competitiveness. There is a lack of targeted technology that can automatically crawl product information and conduct overall competitiveness assessment.

[0004] In view of the above problems, effective technical solutions are urgently needed. Summary of the invention

[0005] The purpose of this application is to provide an AI-based platform network sales commodity information processing method, system and medium, which can obtain the web platform information within a preset time period, extract the sales commodity crawling information, and then extract the commodity price information, commodity sales information, commodity inventory information and commodity evaluation information respectively, and process them separately to obtain the commodity value preservation ability index, commodity sales ability index, commodity inventory guarantee ability index and commodity evaluation index, and finally process them through a preset evaluation model to obtain the commodity competitiveness index, compare the commodity competitiveness index with the preset competitiveness index threshold, and judge whether the competitiveness index meets the requirements. This application can automatically capture sales commodity information from the platform through AI combined with crawler technology, and quickly process and analyze the captured data, which greatly reduces the time and energy of manual collection and provides the platform with more accurate commodity competitiveness.

[0006] This application provides an AI-based platform network sales product information processing method, including the following steps:

[0007] Obtain web platform information within a preset time period and extract sales product crawling information;

[0008] Extracting product price information, product sales information, product inventory information and product evaluation information based on the crawled information of the sold products;

[0009] Processing the commodity price information through a preset commodity value preservation ability evaluation model to obtain a commodity value preservation ability index;

[0010] Processing the commodity sales information through a preset commodity sales capability evaluation model to obtain a commodity sales capability index;

[0011] Processing the commodity inventory information through a preset inventory guarantee capability evaluation model to obtain a commodity inventory guarantee capability index;

[0012] Processing the product evaluation information through a preset product evaluation model to obtain a product evaluation index;

[0013] Obtaining a commodity competitiveness index by processing the commodity value preservation ability index, commodity sales ability index, commodity inventory guarantee ability index and commodity evaluation index;

[0014] The commodity competitiveness index is compared with a preset competitiveness index threshold to obtain a competitiveness index deviation rate, and the situation of the competitiveness index deviation rate and the preset index deviation rate threshold is determined.

[0015] Among them, in the AI-based platform network sales commodity information processing method described in the present application, it is characterized in that the commodity price information is processed through a preset commodity value preservation ability evaluation model to obtain a commodity value preservation ability index, specifically:

[0016] Extracting original value data, discount rate data and promotion frequency data based on the commodity price information;

[0017] The original value data, discount rate data and promotion frequency data are processed through a preset commodity value preservation ability evaluation model to obtain a commodity value preservation ability index.

[0018] Among them, in the AI-based platform network sales commodity information processing method described in the present application, it is characterized in that the commodity sales information is processed through a preset commodity sales ability evaluation model to obtain a commodity sales ability index, specifically:

[0019] Extracting sales quantity data, sales amount data and sales growth rate data based on the commodity sales information;

[0020] The sales quantity data, sales amount data and sales growth rate data are processed through a preset commodity sales ability evaluation model to obtain a commodity sales ability index.

[0021] Among them, in the AI-based platform network sales commodity information processing method described in the present application, it is characterized in that the commodity inventory information is processed through a preset inventory guarantee capability evaluation model to obtain a commodity inventory guarantee capability index, specifically:

[0022] Extracting inventory quantity data, inventory turnover rate data and zero inventory frequency data according to the commodity inventory information;

[0023] The inventory quantity data, inventory turnover rate data and zero inventory frequency data are processed through a preset inventory guarantee capability evaluation model to obtain a commodity inventory guarantee capability index.

[0024] Among them, in the AI-based platform network sales product information processing method described in the present application, it is characterized in that the product evaluation information is processed through a preset product evaluation evaluation model to obtain a product evaluation index, specifically:

[0025] Extracting return quantity data and customer rating data based on the product evaluation information;

[0026] The return quantity data and customer rating data are processed through a preset product evaluation and assessment model to obtain a product evaluation index.

[0027] Among them, in the AI-based platform network sales commodity information processing method described in the present application, it is characterized in that the commodity competitiveness index is obtained by processing according to the commodity value preservation ability index, commodity sales ability index, commodity inventory guarantee ability index and commodity evaluation index, specifically:

[0028] The commodity competitiveness index is obtained by processing the commodity value preservation ability index, commodity sales ability index, commodity inventory guarantee ability index and commodity evaluation index through a preset commodity competitiveness evaluation model;

[0029] The calculation formula of the commodity competitiveness evaluation model is:

[0030]

[0031] Among them, G ω is the commodity competitiveness index, H e 、M a , S t 、E v They are commodity value preservation ability index, commodity sales ability index, commodity inventory guarantee ability index and commodity evaluation index, θ 1 ,θ 2 , κ, λ are preset characteristic coefficients.

[0032] Among them, in the AI-based platform network sales commodity information processing method described in the present application, it is characterized in that the commodity competitiveness index is compared with a preset competitiveness index threshold to obtain a competitiveness index deviation rate, and the competitiveness index deviation rate is judged to be different from the preset index deviation rate threshold, specifically:

[0033] Comparing the commodity competitiveness index with a preset competitiveness index threshold to obtain a competitiveness index deviation rate;

[0034] Determining whether the competitiveness index deviation rate is greater than a preset index deviation rate threshold;

[0035] If the competitiveness index deviation rate is greater than or equal to the index deviation rate threshold, the product does not have sufficient competitiveness;

[0036] If the competitiveness index deviation rate is less than the index deviation rate threshold, the product competitiveness meets the requirements.

[0037] In a second aspect, the present application provides an AI-based platform network sales commodity information processing system, the system comprising: a memory and a processor, the memory comprising a program of an AI-based platform network sales commodity information processing method, and the program of the AI-based platform network sales commodity information processing method is executed by the processor to implement the following steps:

[0038] Obtain web platform information within a preset time period and extract sales product crawling information;

[0039] Extracting commodity price information, commodity sales information, commodity inventory information and commodity evaluation information according to the sales commodity information;

[0040] Processing the commodity price information through a preset commodity value preservation ability evaluation model to obtain a commodity value preservation ability index;

[0041] Processing the commodity sales information through a preset commodity sales capability evaluation model to obtain a commodity sales capability index;

[0042] Processing the commodity inventory information through a preset inventory guarantee capability evaluation model to obtain a commodity inventory guarantee capability index;

[0043] Processing the product evaluation information through a preset product evaluation model to obtain a product evaluation index;

[0044] Obtaining a commodity competitiveness index by processing the commodity value preservation ability index, commodity sales ability index, commodity inventory guarantee ability index and commodity evaluation index;

[0045] The commodity competitiveness index is compared with a preset competitiveness index threshold to obtain a competitiveness index deviation rate, and the situation of the competitiveness index deviation rate and the preset index deviation rate threshold is determined.

[0046] Among them, in the AI-based platform network sales commodity information processing system described in the present application, it is characterized in that the commodity price information is processed through a preset commodity value preservation ability evaluation model to obtain a commodity value preservation ability index, specifically:

[0047] Extracting original value data, discount rate data and promotion frequency data based on the commodity price information;

[0048] The original value data, discount rate data and promotion frequency data are processed through a preset commodity value preservation ability evaluation model to obtain a commodity value preservation ability index.

[0049] In a third aspect, the present application also provides a readable storage medium, which includes an AI-based platform network sales product information processing method program. When the AI-based platform network sales product information processing method program is executed by a processor, the steps of the AI-based platform network sales product information processing method as described in any one of the above items are implemented.

[0050] From the above, it can be seen that the AI-based platform network sales product information processing method, system and medium provided in this application obtains the web platform information within a preset time period, extracts the sales product crawling information, and then extracts the product price information, product sales information, product inventory information and product evaluation information respectively. The product value preservation ability index, product sales ability index, product inventory guarantee ability index and product evaluation index can be obtained by processing them respectively. Finally, the product competitiveness index is obtained by processing through a preset evaluation model, and the product competitiveness index is compared with the preset competitiveness index threshold to determine whether the competitiveness index meets the requirements. This application can automatically capture sales product information from the platform through AI combined with crawler technology, and quickly process and analyze the captured data, which greatly reduces the time and energy of manual collection and provides the platform with more accurate product competitiveness.

[0051] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 A flowchart of a method for processing information of commodity sold on a platform network based on AI provided in an embodiment of the present application;

[0054] Figure 2 A flowchart of obtaining a commodity value preservation ability index of a method for processing commodity information on a platform network sold based on AI provided in an embodiment of the present application;

[0055] Figure 3 A flowchart of obtaining a commodity sales capability index of a method for processing commodity information on a platform network sold on an AI-based basis provided in an embodiment of the present application;

[0056] Figure 4 A flowchart of obtaining a commodity inventory guarantee capability index of a method for processing commodity information on a platform network sold based on AI provided in an embodiment of the present application;

[0057] Figure 5 A flowchart of obtaining a product evaluation index for the AI-based platform network sales product information processing method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0059] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0060] Please refer to Figure 1 , Figure 1 The flowchart of the method for processing information of commodity sales on a platform network based on AI in some embodiments of the present application. The method for processing information of commodity sales on a platform network based on AI is used in a terminal device, such as a computer, a mobile phone terminal, etc. The method for processing information of commodity sales on a platform network based on AI comprises the following steps:

[0061] S101, obtaining web page platform information within a preset time period, and extracting sales product crawling information;

[0062] S102, extracting commodity price information, commodity sales information, commodity inventory information and commodity evaluation information according to the crawled information of the sold commodities;

[0063] S103, processing the commodity price information through a preset commodity value preservation ability evaluation model to obtain a commodity value preservation ability index;

[0064] S104, processing the commodity sales information through a preset commodity sales capability evaluation model to obtain a commodity sales capability index;

[0065] S105, processing the commodity inventory information through a preset inventory guarantee capability evaluation model to obtain a commodity inventory guarantee capability index;

[0066] S106, processing the product evaluation information through a preset product evaluation model to obtain a product evaluation index;

[0067] S107, obtaining a commodity competitiveness index by processing the commodity value preservation ability index, the commodity sales ability index, the commodity inventory guarantee ability index, and the commodity evaluation index;

[0068] S108, comparing the commodity competitiveness index with a preset competitiveness index threshold, obtaining a competitiveness index deviation rate, and determining whether the competitiveness index deviation rate is equal to the preset index deviation rate threshold.

[0069] Among them, this application first automatically obtains web platform information within a preset time period through crawler technology. The data captured from the web page often contains a lot of useless or redundant information, which needs to be cleaned and sorted. AI technology can be used to automatically identify and remove these data to improve data quality. Combined with AI technology, sales product crawling information is extracted from the acquired web platform information, and then product price information, product sales information, product inventory information and product evaluation information are extracted respectively. The product value preservation ability index, product sales ability index, product inventory guarantee ability index and product evaluation index can be obtained by processing them separately. Finally, the product competitiveness index is obtained by processing through the preset evaluation model, and the product competitiveness index is compared with the preset competitiveness index threshold to determine whether the competitiveness index meets the requirements. This application uses AI combined with crawler technology to automatically capture sales product information from the platform and quickly process and analyze the captured data, greatly reducing the time and effort of manual collection. It only needs to set the crawler rules and parameters to achieve automatic data capture and update. Through AI technology, the crawler can more accurately identify key information in the web page, such as product name, price, specifications, inventory, etc., reduce data capture errors, and even if the target website is updated or revised, the crawler can adjust the crawling strategy in time to ensure the continuity and accuracy of the data, providing the platform with more accurate product competitiveness.

[0070] Please refer to Figure 2 , Figure 2 The flowchart of the method for processing the information of platform network sales products based on AI in some embodiments of the present application is to obtain the value preservation index of the product. According to the embodiment of the present invention, the product price information is processed by a preset product value preservation evaluation model to obtain the value preservation index of the product, specifically:

[0071] S201, extracting original value data, discount rate data and promotion frequency data according to the commodity price information;

[0072] S202: Process the original value data, discount rate data and promotion frequency data through a preset commodity value preservation ability evaluation model to obtain a commodity value preservation ability index.

[0073] Among them, in order to grasp the price trend and value preservation ability of commodities, the original value data, discount rate data and promotion frequency data are extracted according to the commodity price information. The original value data indicates the initial price of the commodity and represents the standard value of the commodity put on the market. The discount rate data reflects the important indicators of commodity market demand, competition situation, price elasticity, product life cycle stage, brand image and positioning, and merchant sales strategy. The promotion frequency data is an important indicator in commercial operations that reflects market demand, competition situation, inventory management, sales strategy and brand strategy, consumer behavior and loyalty, etc. The original value data, discount rate data and promotion frequency data are processed through the preset commodity value preservation ability evaluation model to obtain the commodity value preservation ability index. A high commodity value preservation ability index means that the market demand for the commodity is relatively stable and is not easily affected by external factors.

[0074] The calculation formula of the commodity value preservation ability evaluation model is:

[0075]

[0076] Among them, H e is the commodity value preservation index, y p ,d r 、p r They are original value data, discount rate data and promotion frequency data. τ、υ、 It is a preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset commodity sales database).

[0077] Please refer to Figure 3 , Figure 3 The flowchart of the method for processing the commodity sales information of the platform network based on AI in some embodiments of the present application is to obtain the commodity sales ability index. According to the embodiment of the present invention, the commodity sales information is processed by a preset commodity sales ability evaluation model to obtain the commodity sales ability index, specifically:

[0078] S301, extracting sales quantity data, sales amount data and sales growth rate data according to the commodity sales information;

[0079] S302: Process the sales quantity data, sales amount data and sales growth rate data through a preset commodity sales ability evaluation model to obtain a commodity sales ability index.

[0080] Among them, in order to understand and improve the sales ability of goods, sales quantity data, sales amount data and sales growth rate data are extracted based on the sales information of goods. The sales quantity data directly reflects the specific number of products or services sold by the enterprise in a certain period. The enterprise can understand the popularity of its own products in the market and the effectiveness of its sales strategy. The sales amount data refers to the total amount of money obtained by the enterprise through the sale of products or services in a certain period, which can more comprehensively reflect the sales results and profitability of the enterprise. The sales growth rate data is an indicator used to measure the speed and magnitude of the growth or decline of the enterprise's sales in a certain period, which can help the enterprise understand its development trend and competitiveness level in the market. The sales quantity data, sales amount data and sales growth rate data are processed through the preset commodity sales ability evaluation model to obtain the commodity sales ability index. The commodity sales ability index comprehensively reflects the sales ability of the enterprise's goods from three aspects: sales quantity, sales amount and sales growth rate;

[0081] The calculation formula of the commodity sales ability evaluation model is:

[0082]

[0083] Among them, M a is the commodity sales ability index, s m 、s p 、a z are the sales quantity data, sales amount data and sales growth rate data, ε, ζ, It is a preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset commodity sales database).

[0084] Please refer to Figure 4 , Figure 4 The flowchart of the method for processing the information of commodity sold on the platform network based on AI in some embodiments of the present application is to obtain the commodity inventory guarantee capability index. According to the embodiment of the present invention, the commodity inventory information is processed by a preset inventory guarantee capability evaluation model to obtain the commodity inventory guarantee capability index, specifically:

[0085] S401, extracting inventory quantity data, inventory turnover rate data and zero inventory frequency data according to the commodity inventory information;

[0086] S402: Process the inventory quantity data, inventory turnover rate data and zero inventory frequency data through a preset inventory guarantee capability evaluation model to obtain a commodity inventory guarantee capability index.

[0087] Among them, in order to ensure that there is enough inventory for the goods sold, the inventory quantity data, inventory turnover rate data and zero inventory frequency data are extracted according to the inventory information of the goods. The inventory quantity data directly reflects the total inventory held by the enterprise at a certain moment or in a certain period of time, helping the enterprise to understand the actual situation of the current inventory and provide a basis for subsequent inventory decisions. The inventory turnover rate data reflects the speed and efficiency of the enterprise's inventory turnover, that is, the number of times the inventory is sold or used in a certain period of time. The higher the inventory turnover rate, the faster the inventory turnover speed of the enterprise and the higher the operating efficiency, which helps to reduce inventory backlogs and reduce inventory costs. The zero inventory frequency data reflects the frequency of the enterprise achieving zero inventory status or close to zero inventory status. Zero inventory refers to the state that the enterprise does not hold inventory or has extremely low inventory. According to the inventory quantity data, inventory turnover rate data and zero inventory frequency data, the preset inventory guarantee capacity evaluation model is used to process and obtain the commodity inventory guarantee capacity index. The commodity inventory guarantee capacity index needs to consider the balance relationship between factors such as inventory cost, capital occupation, and market demand forecast accuracy. Too high inventory guarantee capacity may increase inventory cost and capital occupation pressure, while too low inventory guarantee capacity may fail to meet market demand and lead to sales losses. Therefore, enterprises need to find a reasonable balance between ensuring inventory adequacy and reducing inventory costs;

[0088] The calculation formula of the inventory guarantee capability evaluation model is:

[0089]

[0090] Among them, S t is the commodity inventory guarantee capability index, k m ,t r 、b e are inventory quantity data, inventory turnover rate data and zero inventory frequency data, μ, ν 1 , ν 2 , π are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset commodity sales database).

[0091] Please refer to Figure 5 , Figure 5 The flowchart of the method for processing the information of platform network sales products based on AI in some embodiments of the present application is to obtain the product evaluation index. According to the embodiment of the present invention, the product evaluation information is processed by a preset product evaluation evaluation model to obtain the product evaluation index, specifically:

[0092] S501, extracting return quantity data and customer rating data according to the product evaluation information;

[0093] S502: Process the return quantity data and customer rating data through a preset product evaluation model to obtain a product evaluation index.

[0094] Among them, in order to grasp the user's feedback on the product, the return quantity data and customer rating data are extracted based on the product evaluation information. The number of returns is often directly related to the quality of the product. A high return rate may mean that there are defects in the product design, lax production quality control, or improper packaging. The company needs to pay attention and improve in time. Customer rating is one of the most direct indicators of customer satisfaction. A high score indicates that the customer is satisfied with the product or service, while a low score may reflect customer dissatisfaction or problems. The return quantity data and customer rating data are processed through a preset product evaluation and assessment model to obtain a product evaluation index. The product evaluation index comprehensively reflects the user needs and expectations after the product is sold. By comprehensively analyzing these data, companies can have a more comprehensive understanding of their position, advantages and disadvantages in market competition, thereby formulating more accurate and effective market strategies and product improvement plans;

[0095] The calculation formula of the product evaluation model is:

[0096]

[0097] Among them, E v is the product evaluation index, g r 、c e are the return quantity data and customer rating data, ξ, α is a preset characteristic coefficient (the characteristic coefficient is obtained by querying a preset commodity sales database).

[0098] According to an embodiment of the present invention, the commodity competitiveness index is obtained by processing the commodity value preservation ability index, the commodity sales ability index, the commodity inventory guarantee ability index and the commodity evaluation index, specifically:

[0099] The commodity competitiveness index is obtained by processing the commodity value preservation ability index, commodity sales ability index, commodity inventory guarantee ability index and commodity evaluation index through a preset commodity competitiveness evaluation model;

[0100] The calculation formula of the commodity competitiveness evaluation model is:

[0101]

[0102] Among them, G ω is the commodity competitiveness index, H e 、M a , S t 、E v They are commodity value preservation ability index, commodity sales ability index, commodity inventory guarantee ability index and commodity evaluation index, θ 1 ,θ 2, κ, λ are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset commodity sales database).

[0103] Among them, in order to comprehensively reflect the competitiveness of sales commodities, the commodity competitiveness index is obtained by processing the commodity value preservation ability index, commodity sales ability index, commodity inventory guarantee ability index and commodity evaluation index through the preset commodity competitiveness evaluation model. A high commodity value preservation ability index means that the market demand for the commodity is relatively stable and is not easily affected by external factors. The commodity sales ability index comprehensively reflects the sales ability of the enterprise's commodities from three aspects: sales volume, sales amount and sales growth rate. Excessive inventory guarantee ability may increase inventory costs and capital occupation pressure, while too low inventory guarantee ability may not be able to meet market demand and cause sales losses. The commodity evaluation index comprehensively reflects the user needs and expectations after the sale of the commodity. The commodity competitiveness index reflects the comprehensive competitiveness and relative advantage of the commodity in the market. Enterprises can pay attention to and analyze the changing trends and influencing factors of the commodity competitiveness index to formulate more accurate and effective market strategies and product improvement plans to enhance the competitiveness and market share of the commodities.

[0104] According to an embodiment of the present invention, the product competitiveness index is compared with a preset competitiveness index threshold to obtain a competitiveness index deviation rate, and the competitiveness index deviation rate is judged to be different from the preset index deviation rate threshold, specifically:

[0105] Comparing the commodity competitiveness index with a preset competitiveness index threshold to obtain a competitiveness index deviation rate;

[0106] Determining whether the competitiveness index deviation rate is greater than a preset index deviation rate threshold;

[0107] If the competitiveness index deviation rate is greater than or equal to the index deviation rate threshold, the product does not have sufficient competitiveness;

[0108] If the competitiveness index deviation rate is less than the index deviation rate threshold, the product competitiveness meets the requirements.

[0109] Among them, in order to improve the commodity competitiveness index, the commodity competitiveness index is compared with the preset competitiveness index threshold to obtain the competitiveness index deviation rate, and it is determined whether the competitiveness index deviation rate is greater than the preset index deviation rate threshold. If the competitiveness index deviation rate is greater than or equal to the index deviation rate threshold, the commodity does not have sufficient competitiveness. For example, the competitiveness index deviation rate is 5%, and the index deviation rate threshold is 2.5%. If the competitiveness index deviation rate is less than the index deviation rate threshold, the commodity competitiveness meets the requirements. For example, the competitiveness index deviation rate is 1.6%, and the index deviation rate threshold is 2.5%.

[0110] According to an embodiment of the present invention, it also includes:

[0111] Get web platform server information and extract server load data;

[0112] Comparing the server load data with a preset first load threshold and a second load threshold;

[0113] The first load threshold is less than the second load threshold;

[0114] If the server load data is less than the first load threshold, a high-speed crawling mode setting is obtained;

[0115] If the server load data is greater than or equal to the first load threshold and less than or equal to the second load threshold, a balanced crawling mode setting is obtained;

[0116] If the server load data is greater than the second load threshold, a low-speed crawling mode setting is obtained.

[0117] Among them, in order to improve the crawling efficiency and achieve more friendly data crawling, the web platform server information is obtained, the server load data is extracted, and the server load data is compared with the preset first load threshold and the second load threshold. The first load threshold is less than the second load threshold, for example, the first load threshold is 35%, and the second load threshold is 75%. If the server load data is less than the first load threshold, a high-speed crawling mode setting is obtained, for example, the server load data is 23%. If the server load data is greater than or equal to the first load threshold and less than or equal to the second load threshold, a balanced crawling mode setting is obtained, for example, the server load data is 55%. If the server load data is greater than the second load threshold, a low-speed crawling mode setting is obtained, for example, the server load data is 79%. Through the combination of AI and crawler technology, intelligent scheduling can be performed according to server load factors, resources can be reasonably allocated, and crawling efficiency can be improved. This can not only reduce the waste of resources during the crawling process, but also reduce the pressure on the target website and achieve more friendly crawling.

[0118] The present invention also discloses an AI-based platform network sales commodity information processing system, comprising a memory and a processor, wherein the memory comprises an AI-based platform network sales commodity information processing method program, and when the AI-based platform network sales commodity information processing method program is executed by the processor, the following steps are implemented:

[0119] Obtain web platform information within a preset time period and extract sales product crawling information;

[0120] Extracting product price information, product sales information, product inventory information and product evaluation information based on the crawled information of the sold products;

[0121] Processing the commodity price information through a preset commodity value preservation ability evaluation model to obtain a commodity value preservation ability index;

[0122] Processing the commodity sales information through a preset commodity sales capability evaluation model to obtain a commodity sales capability index;

[0123] Processing the commodity inventory information through a preset inventory guarantee capability evaluation model to obtain a commodity inventory guarantee capability index;

[0124] Processing the product evaluation information through a preset product evaluation model to obtain a product evaluation index;

[0125] Obtaining a commodity competitiveness index by processing the commodity value preservation ability index, commodity sales ability index, commodity inventory guarantee ability index and commodity evaluation index;

[0126] The commodity competitiveness index is compared with a preset competitiveness index threshold to obtain a competitiveness index deviation rate, and the situation of the competitiveness index deviation rate and the preset index deviation rate threshold is determined.

[0127] Among them, this application first automatically obtains web platform information within a preset time period through crawler technology. The data captured from the web page often contains a lot of useless or redundant information, which needs to be cleaned and sorted. AI technology can be used to automatically identify and remove these data to improve data quality. Combined with AI technology, sales product crawling information is extracted from the acquired web platform information, and then product price information, product sales information, product inventory information and product evaluation information are extracted respectively. The product value preservation ability index, product sales ability index, product inventory guarantee ability index and product evaluation index can be obtained by processing them separately. Finally, the product competitiveness index is obtained by processing through the preset evaluation model, and the product competitiveness index is compared with the preset competitiveness index threshold to determine whether the competitiveness index meets the requirements. This application uses AI combined with crawler technology to automatically capture sales product information from the platform and quickly process and analyze the captured data, greatly reducing the time and effort of manual collection. It only needs to set the crawler rules and parameters to achieve automatic data capture and update. Through AI technology, the crawler can more accurately identify key information in the web page, such as product name, price, specifications, inventory, etc., reduce data capture errors, and even if the target website is updated or revised, the crawler can adjust the crawling strategy in time to ensure the continuity and accuracy of the data, providing the platform with more accurate product competitiveness.

[0128] According to an embodiment of the present invention, the commodity price information is processed by a preset commodity value preservation ability evaluation model to obtain a commodity value preservation ability index, specifically:

[0129] Extracting original value data, discount rate data and promotion frequency data based on the commodity price information;

[0130] The original value data, discount rate data and promotion frequency data are processed through a preset commodity value preservation ability evaluation model to obtain a commodity value preservation ability index.

[0131] Among them, in order to grasp the price trend and value preservation ability of commodities, the original value data, discount rate data and promotion frequency data are extracted according to the commodity price information. The original value data indicates the initial price of the commodity and represents the standard value of the commodity put on the market. The discount rate data reflects the important indicators of commodity market demand, competition situation, price elasticity, product life cycle stage, brand image and positioning, and merchant sales strategy. The promotion frequency data is an important indicator in commercial operations that reflects market demand, competition situation, inventory management, sales strategy and brand strategy, consumer behavior and loyalty, etc. The original value data, discount rate data and promotion frequency data are processed through the preset commodity value preservation ability evaluation model to obtain the commodity value preservation ability index. A high commodity value preservation ability index means that the market demand for the commodity is relatively stable and is not easily affected by external factors.

[0132] The calculation formula of the commodity value preservation ability evaluation model is:

[0133]

[0134] Among them, H e is the commodity value preservation index, y p d r 、p r They are original value data, discount rate data and promotion frequency data. τ、υ、 It is a preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset commodity sales database).

[0135] According to an embodiment of the present invention, the commodity sales information is processed by a preset commodity sales capability evaluation model to obtain a commodity sales capability index, specifically:

[0136] Extracting sales quantity data, sales amount data and sales growth rate data based on the commodity sales information;

[0137] The sales quantity data, sales amount data and sales growth rate data are processed through a preset commodity sales ability evaluation model to obtain a commodity sales ability index.

[0138] Among them, in order to understand and improve the sales ability of goods, sales quantity data, sales amount data and sales growth rate data are extracted based on the sales information of goods. The sales quantity data directly reflects the specific number of products or services sold by the enterprise in a certain period. The enterprise can understand the popularity of its own products in the market and the effectiveness of its sales strategy. The sales amount data refers to the total amount of money obtained by the enterprise through the sale of products or services in a certain period, which can more comprehensively reflect the sales results and profitability of the enterprise. The sales growth rate data is an indicator used to measure the speed and magnitude of the growth or decline of the enterprise's sales in a certain period, which can help the enterprise understand its development trend and competitiveness level in the market. The sales quantity data, sales amount data and sales growth rate data are processed through the preset commodity sales ability evaluation model to obtain the commodity sales ability index. The commodity sales ability index comprehensively reflects the sales ability of the enterprise's goods from three aspects: sales quantity, sales amount and sales growth rate;

[0139] The calculation formula of the commodity sales ability evaluation model is:

[0140]

[0141] Among them, M a is the commodity sales ability index, s m 、s p 、a z are the sales quantity data, sales amount data and sales growth rate data, ε, ζ, It is a preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset commodity sales database).

[0142] According to an embodiment of the present invention, the commodity inventory information is processed by a preset inventory guarantee capability evaluation model to obtain a commodity inventory guarantee capability index, specifically:

[0143] Extracting inventory quantity data, inventory turnover rate data and zero inventory frequency data according to the commodity inventory information;

[0144] The inventory quantity data, inventory turnover rate data and zero inventory frequency data are processed through a preset inventory guarantee capability evaluation model to obtain a commodity inventory guarantee capability index.

[0145] Among them, in order to ensure that there is enough inventory for the goods sold, the inventory quantity data, inventory turnover rate data and zero inventory frequency data are extracted according to the inventory information of the goods. The inventory quantity data directly reflects the total inventory held by the enterprise at a certain moment or in a certain period of time, helping the enterprise to understand the actual situation of the current inventory and provide a basis for subsequent inventory decisions. The inventory turnover rate data reflects the speed and efficiency of the enterprise's inventory turnover, that is, the number of times the inventory is sold or used in a certain period of time. The higher the inventory turnover rate, the faster the inventory turnover speed of the enterprise and the higher the operating efficiency, which helps to reduce inventory backlogs and reduce inventory costs. The zero inventory frequency data reflects the frequency of the enterprise achieving zero inventory status or close to zero inventory status. Zero inventory refers to the state that the enterprise does not hold inventory or has extremely low inventory. According to the inventory quantity data, inventory turnover rate data and zero inventory frequency data, the preset inventory guarantee capacity evaluation model is used to process and obtain the commodity inventory guarantee capacity index. The commodity inventory guarantee capacity index needs to consider the balance relationship between factors such as inventory cost, capital occupation, and market demand forecast accuracy. Too high inventory guarantee capacity may increase inventory cost and capital occupation pressure, while too low inventory guarantee capacity may fail to meet market demand and lead to sales losses. Therefore, enterprises need to find a reasonable balance between ensuring inventory adequacy and reducing inventory costs;

[0146] The calculation formula of the inventory guarantee capability evaluation model is:

[0147]

[0148] Among them, S t is the commodity inventory guarantee capability index, k m ,t r 、b e are inventory quantity data, inventory turnover rate data and zero inventory frequency data, μ, ν 1 , ν 2 , π are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset commodity sales database).

[0149] According to an embodiment of the present invention, the commodity evaluation information is processed by a preset commodity evaluation evaluation model to obtain a commodity evaluation index, specifically:

[0150] Extracting return quantity data and customer rating data based on the product evaluation information;

[0151] The return quantity data and customer rating data are processed through a preset product evaluation and assessment model to obtain a product evaluation index.

[0152] Among them, in order to grasp the user's feedback on the product, the return quantity data and customer rating data are extracted based on the product evaluation information. The number of returns is often directly related to the quality of the product. A high return rate may mean that there are defects in the product design, lax production quality control, or improper packaging. The company needs to pay attention and improve in time. Customer rating is one of the most direct indicators of customer satisfaction. A high score indicates that the customer is satisfied with the product or service, while a low score may reflect customer dissatisfaction or problems. The return quantity data and customer rating data are processed through a preset product evaluation and assessment model to obtain a product evaluation index. The product evaluation index comprehensively reflects the user needs and expectations after the product is sold. By comprehensively analyzing these data, companies can have a more comprehensive understanding of their position, advantages and disadvantages in market competition, thereby formulating more accurate and effective market strategies and product improvement plans;

[0153] The calculation formula of the product evaluation model is:

[0154]

[0155] Among them, E v is the product evaluation index, g r 、c e are the return quantity data and customer rating data, ξ, α is a preset characteristic coefficient (the characteristic coefficient is obtained by querying a preset commodity sales database).

[0156] According to an embodiment of the present invention, the commodity competitiveness index is obtained by processing the commodity value preservation ability index, the commodity sales ability index, the commodity inventory guarantee ability index and the commodity evaluation index, specifically:

[0157] The commodity competitiveness index is obtained by processing the commodity value preservation ability index, commodity sales ability index, commodity inventory guarantee ability index and commodity evaluation index through a preset commodity competitiveness evaluation model;

[0158] The calculation formula of the commodity competitiveness evaluation model is:

[0159]

[0160] Among them, G ω is the commodity competitiveness index, H e 、M a , S t 、E v They are commodity value preservation ability index, commodity sales ability index, commodity inventory guarantee ability index and commodity evaluation index, θ 1 ,θ 2, κ, λ are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset commodity sales database).

[0161] Among them, in order to comprehensively reflect the competitiveness of sales commodities, the commodity competitiveness index is obtained by processing the commodity value preservation ability index, commodity sales ability index, commodity inventory guarantee ability index and commodity evaluation index through the preset commodity competitiveness evaluation model. A high commodity value preservation ability index means that the market demand for the commodity is relatively stable and is not easily affected by external factors. The commodity sales ability index comprehensively reflects the sales ability of the enterprise's commodities from three aspects: sales volume, sales amount and sales growth rate. Excessive inventory guarantee ability may increase inventory costs and capital occupation pressure, while too low inventory guarantee ability may not be able to meet market demand and cause sales losses. The commodity evaluation index comprehensively reflects the user needs and expectations after the sale of the commodity. The commodity competitiveness index reflects the comprehensive competitiveness and relative advantage of the commodity in the market. Enterprises can pay attention to and analyze the changing trends and influencing factors of the commodity competitiveness index to formulate more accurate and effective market strategies and product improvement plans to enhance the competitiveness and market share of the commodities.

[0162] According to an embodiment of the present invention, the commodity competitiveness index is compared with a preset competitiveness index threshold to obtain a competitiveness index deviation rate, and the competitiveness index deviation rate is judged to be different from the preset index deviation rate threshold, specifically:

[0163] Comparing the commodity competitiveness index with a preset competitiveness index threshold to obtain a competitiveness index deviation rate;

[0164] Determining whether the competitiveness index deviation rate is greater than a preset index deviation rate threshold;

[0165] If the competitiveness index deviation rate is greater than or equal to the index deviation rate threshold, the product does not have sufficient competitiveness;

[0166] If the competitiveness index deviation rate is less than the index deviation rate threshold, the product competitiveness meets the requirements.

[0167] Among them, in order to improve the commodity competitiveness index, the commodity competitiveness index is compared with the preset competitiveness index threshold to obtain the competitiveness index deviation rate, and it is determined whether the competitiveness index deviation rate is greater than the preset index deviation rate threshold. If the competitiveness index deviation rate is greater than or equal to the index deviation rate threshold, the commodity does not have sufficient competitiveness. For example, the competitiveness index deviation rate is 5%, and the index deviation rate threshold is 2.5%. If the competitiveness index deviation rate is less than the index deviation rate threshold, the commodity competitiveness meets the requirements. For example, the competitiveness index deviation rate is 1.6%, and the index deviation rate threshold is 2.5%.

[0168] According to an embodiment of the present invention, it also includes:

[0169] Get web platform server information and extract server load data;

[0170] Comparing the server load data with a preset first load threshold and a second load threshold;

[0171] The first load threshold is less than the second load threshold;

[0172] If the server load data is less than the first load threshold, a high-speed crawling mode setting is obtained;

[0173] If the server load data is greater than or equal to the first load threshold and less than or equal to the second load threshold, a balanced crawling mode setting is obtained;

[0174] If the server load data is greater than the second load threshold, a low-speed crawling mode setting is obtained.

[0175] Among them, in order to improve the crawling efficiency and achieve more friendly data crawling, the web platform server information is obtained, the server load data is extracted, and the server load data is compared with the preset first load threshold and the second load threshold. The first load threshold is less than the second load threshold, for example, the first load threshold is 35%, and the second load threshold is 75%. If the server load data is less than the first load threshold, a high-speed crawling mode setting is obtained, for example, the server load data is 23%. If the server load data is greater than or equal to the first load threshold and less than or equal to the second load threshold, a balanced crawling mode setting is obtained, for example, the server load data is 55%. If the server load data is greater than the second load threshold, a low-speed crawling mode setting is obtained, for example, the server load data is 79%. Through the combination of AI and crawler technology, intelligent scheduling can be performed according to server load factors, resources can be reasonably allocated, and crawling efficiency can be improved. This can not only reduce the waste of resources during the crawling process, but also reduce the pressure on the target website and achieve more friendly crawling.

[0176] The third aspect of the present invention also provides a readable storage medium, which includes an AI-based platform network sales product information processing method program. When the AI-based platform network sales product information processing method program is executed by a processor, the steps of the AI-based platform network sales product information processing method as described in any one of the above items are implemented.

[0177] The AI-based platform network sales product information processing method, system and medium disclosed in the present invention automatically obtain web page platform information within a preset time period through crawler technology. The data captured from the web page often contains a large amount of useless or redundant information, which needs to be cleaned and sorted. AI technology can be used to automatically identify and remove these data to improve data quality. Combined with AI technology, sales product crawling information is extracted from the acquired web page platform information, and then the product price information, product sales information, product inventory information and product evaluation information are extracted respectively. The product value preservation ability index, product sales ability index, product inventory guarantee ability index and product evaluation index can be obtained by processing them respectively. Finally, the product competitiveness index is obtained by processing through a preset evaluation model, and the product competitiveness index is compared with the preset competitiveness index threshold to determine whether the competitiveness index meets the requirements. This application uses AI combined with crawler technology to automatically capture sales product information from the platform and quickly process and analyze the captured data, greatly reducing the time and effort of manual collection. It only needs to set the crawler rules and parameters to achieve automatic data capture and update. Through AI technology, the crawler can more accurately identify key information in the web page, such as product name, price, specifications, inventory, etc., reduce data capture errors, and even if the target website is updated or revised, the crawler can adjust the crawling strategy in time to ensure the continuity and accuracy of the data, providing the platform with more accurate product competitiveness.

[0178] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0179] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0180] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0181] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a readable storage medium, which, when executed, executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories, random access memories, magnetic disks or optical disks, and other media that can store program codes.

[0182] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A method for processing information on platform network sales products based on AI, characterized in that: The following steps are involved: Obtain web platform information within a preset time period and extract sales product crawling information; Extracting product price information, product sales information, product inventory information and product evaluation information based on the crawled information of the sold products; Extracting original value data, discount rate data and promotion frequency data based on the commodity price information; The original value data, discount rate data and promotion frequency data are processed by a preset commodity value preservation ability evaluation model to obtain a commodity value preservation ability index; Extracting sales quantity data, sales amount data and sales growth rate data based on the commodity sales information; The sales quantity data, sales amount data and sales growth rate data are processed by a preset commodity sales ability evaluation model to obtain a commodity sales ability index; Processing the commodity inventory information through a preset inventory guarantee capability evaluation model to obtain a commodity inventory guarantee capability index; Processing the product evaluation information through a preset product evaluation model to obtain a product evaluation index; The commodity competitiveness index is obtained by processing the commodity value preservation ability index, commodity sales ability index, commodity inventory guarantee ability index and commodity evaluation index through a preset commodity competitiveness evaluation model; The calculation formula of the commodity competitiveness evaluation model is: ； in, is the commodity competitiveness index, They are commodity value preservation ability index, commodity sales ability index, commodity inventory guarantee ability index and commodity evaluation index. is the preset characteristic coefficient; The commodity competitiveness index is compared with a preset competitiveness index threshold to obtain a competitiveness index deviation rate, and the situation of the competitiveness index deviation rate and the preset index deviation rate threshold is determined.

2. The method for processing information of commodity sales on a platform network based on AI according to claim 1, characterized in that: The commodity inventory information is processed by a preset inventory guarantee capability evaluation model to obtain a commodity inventory guarantee capability index, which is specifically: Extracting inventory quantity data, inventory turnover rate data and zero inventory frequency data according to the commodity inventory information; The inventory quantity data, inventory turnover rate data and zero inventory frequency data are processed through a preset inventory guarantee capability evaluation model to obtain a commodity inventory guarantee capability index.

3. The method for processing information of commodity sales on a platform network based on AI according to claim 2, characterized in that: The commodity evaluation information is processed by a preset commodity evaluation evaluation model to obtain a commodity evaluation index, specifically: Extracting return quantity data and customer rating data based on the product evaluation information; The return quantity data and customer rating data are processed through a preset product evaluation and assessment model to obtain a product evaluation index.

4. The method for processing information of commodity sales on a platform network based on AI according to claim 1, characterized in that: The step of comparing the commodity competitiveness index with a preset competitiveness index threshold to obtain a competitiveness index deviation rate and determining whether the competitiveness index deviation rate is different from the preset index deviation rate threshold is as follows: Comparing the commodity competitiveness index with a preset competitiveness index threshold to obtain a competitiveness index deviation rate; Determining whether the competitiveness index deviation rate is greater than a preset index deviation rate threshold; If the competitiveness index deviation rate is greater than or equal to the index deviation rate threshold, the product does not have sufficient competitiveness; If the competitiveness index deviation rate is less than the index deviation rate threshold, the product competitiveness meets the requirements.

5. The AI-based platform network sales commodity information processing system is characterized by: It comprises a memory and a processor, wherein the memory comprises an AI-based platform network sales commodity information processing method program, and when the AI-based platform network sales commodity information processing method program is executed by the processor, the steps of the AI-based platform network sales commodity information processing method as described in any one of claims 1 to 4 are implemented.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes an AI-based platform network sales commodity information processing method program. When the AI-based platform network sales commodity information processing method program is executed by a processor, the steps of the AI-based platform network sales commodity information processing method as described in any one of claims 1 to 4 are implemented.

Images