Service information management system based on AI analysis

Abstract

The invention relates to the technical field of service information management, in particular to an AI analysis-based service information management system, which comprises the following steps of: generating a questionnaire according to a keyword of a required product provided by a customer, and recommending a product to the user according to the content of the questionnaire. Then comparing the product actually selected by the user with the recommended product, analyzing whether the product recommendation is qualified or not according to a comparison result, and analyzing an unqualified reason when the product recommendation is judged to be unqualified, so as to realize targeted recommendation for a single customer, improve the matching degree of the recommended product and the product required by the customer, and if the product recommendation is qualified, recommend the recommended product to the customer. If yes, the product selected by the user is located at the front position in the product recommendation table, whether product recommendation is qualified or not is analyzed according to the distribution condition of the positions of the products in the product recommendation table selected by the user, and the control precision of the customer in the product selection process is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of service information management, and in particular to a service information management system based on AI analysis. Background Art

[0002] Intelligent management of service information can effectively improve service efficiency. The existing technology establishes a corresponding purchase model by matching customer characteristics, and classifies products according to the purchase model and pushes them to the e-commerce marketing platform to provide customers with highly similar products. However, it does not provide personalized recommendations for individual users, resulting in a large deviation between the product recommendations for users and their actual needs.

[0003] Chinese Patent Publication No.: CN117726387A discloses an e-commerce marketing system based on big data analysis, including an e-commerce marketing platform, a client terminal and a cloud service platform; the e-commerce marketing platform includes a product display module, a personalized recommendation module, a product transaction module, a product search module and a user information management module; the client terminal is used to carry the e-commerce marketing platform, including a mobile phone and a tablet computer; the cloud service platform includes a terminal server and a cloud server, and the terminal server includes a big data storage module, a weight adjustment module, a big data analysis module and a big data extraction module; the big data analysis module establishes a user purchase model by matching customer characteristics, and classifies the products in the product display module and the products in the personalized recommendation module according to the user purchase model; the personalized recommendation module combines and arranges products of different levels to form a product data combination package, and pushes it to the e-commerce marketing platform; it is used to solve the problem of providing products with high similarity to customers.

[0004] However, the prior art still has the following problems:

[0005] Failure to provide personalized recommendations for individual users results in a large deviation between product recommendations and users’ actual needs. Summary of the invention

[0006] To this end, the present invention provides a service information management system based on AI analysis to overcome the problem in the prior art that no personalized recommendations are made to individual users, resulting in a large deviation between the product recommendations for users and the actual needs of users.

[0007] To achieve the above objectives, the present invention provides a service information management system based on AI analysis. It includes:

[0008] A cloud platform for obtaining information to be screened;

[0009] A questionnaire generating unit, which is connected to the cloud platform and is used to generate a questionnaire according to the information to be screened obtained by the cloud platform;

[0010] a reply receiving unit, connected to the questionnaire generating unit, for extracting keywords based on the questionnaire;

[0011] A product recommendation unit, connected to the reply receiving unit, configured to select corresponding products according to the keywords and generate a product recommendation table;

[0012] an analysis unit connected to the product recommendation unit, for determining the actual acquired products of the target after a predetermined time has passed since the product recommendation table was generated, generating a list of actually acquired products, calculating a recommendation matching degree between the list of actually acquired products and the product recommendation table, analyzing whether the product recommendation for the current target is qualified based on the recommendation matching degree, performing a secondary analysis on whether the product recommendation for the current target is qualified based on the distribution of matching products in the product recommendation table, analyzing reasons why the product recommendation for the current target is unqualified based on keywords of the products in the list of actually acquired products, and performing a secondary analysis on reasons why the product recommendation for the current target is unqualified based on the distribution of brands of the products in the list of actually acquired products.

[0013] Furthermore, the product recommendation unit selects corresponding products according to the keywords, including:

[0014] Determine the demand keywords in the questionnaire,

[0015] Determine the product's symptom keywords and effect keywords,

[0016] If the demand keyword matches the effect keyword or the demand keyword, the corresponding product will be determined as an alternative product.

[0017] The ranking of the products in the product recommendation table is determined based on the matching degree between the demand keyword and each keyword of the product.

[0018] Furthermore, the product recommendation unit determines the matching degree between the demand keyword and each keyword of the product, including:

[0019] Count the number of keywords that are the same as the keywords of the candidate products.

[0020] Calculate the ratio of the number of identical keywords to the total number of required keywords to get the matching degree.

[0021] Furthermore, the analyzing unit analyzes whether the product recommendation for the current target is qualified based on the recommendation matching degree, including:

[0022] Determine the actual number of products in the product list and obtain the first feature quantity.

[0023] Determine the number of products in the actual product list that are the same as the product recommendation table to obtain a second feature number.

[0024] Calculate the ratio of the second feature quantity to the first feature quantity to obtain the recommended matching degree,

[0025] If the recommended matching degree is greater than or equal to the first preset recommended matching degree, the product recommendation for the current target is determined to be qualified;

[0026] If the recommendation matching degree is less than the first preset recommendation matching degree and greater than or equal to the second preset recommendation matching degree, determining whether the product recommendation for the current target is qualified by secondary analysis based on the distribution of the matching products in the product recommendation table;

[0027] If the recommendation matching degree is less than the second preset recommendation matching degree, it is determined that the product recommendation for the current target is unqualified, and the reason why the product recommendation for the current target is unqualified is analyzed based on the keywords of the products in the actually obtained product list.

[0028] Furthermore, the analysis unit secondary analyzes whether the product recommendation for the current target is qualified based on the distribution of the matched products in the product recommendation table, including:

[0029] If the matching products are ranked high and concentrated in the product recommendation table, the product recommendation for the current target is determined to be qualified, and the number of products in the product recommendation table is increased based on the recommendation matching degree;

[0030] If the matching product is ranked low in the product recommendation table, it is determined that the product recommendation for the current target is unqualified, and the reason why the product recommendation for the current target is unqualified is analyzed based on the keywords of the products in the actually obtained product list.

[0031] Furthermore, the analyzing unit increases the number of products in the product recommendation table based on the recommendation matching degree, including:

[0032] Select the products related to the products in the product recommendation table.

[0033] Add related products to the product recommendation table based on the recommended matching degree, where:

[0034] The increase in related products is positively correlated with the recommendation matching degree.

[0035] Furthermore, the analyzing unit analyzes the reasons why the product recommendation for the current target is unqualified based on the keywords of the products in the actually acquired product list, including:

[0036] Extract the actual demand keywords for each product in the actual product list.

[0037] Determine the frequency of occurrence of a single actual demand keyword,

[0038] Calculate the ratio of the frequency of occurrence to the total number of actual demand keywords to obtain the product recommendation eligibility characterization parameters.

[0039] If the product recommendation eligibility characterization parameter is greater than or equal to the preset product recommendation eligibility characterization parameter standard threshold, then the reason why the product recommendation for the current target is unqualified is determined to be a change in the target's demand keywords, and the subsequent product recommendation priority for the target is determined and optimized;

[0040] If the product recommendation eligibility characterization parameter is less than the preset product recommendation eligibility characterization parameter standard threshold, a secondary analysis is performed based on the distribution of brands of products in the actual obtained product list to determine the reason why the product recommendation for the current target is unqualified.

[0041] The analysis unit optimizes the subsequent product recommendation priority for the target, including:

[0042] Whether the products are exhausted is determined according to the usage cycles of the products in the actually obtained product list, and when it is determined that a single product is exhausted, the product is updated to the product recommendation table.

[0043] The analyzing unit secondary analyzes the reasons why the product recommendation for the current target is unqualified based on the distribution of each brand of the products in the actually obtained product list, including:

[0044] The brand with the highest frequency of appearance is identified as the target brand.

[0045] If the distribution of a single target brand is concentrated, the target brand is recorded and the priority of the brand is increased in the subsequent product recommendation process;

[0046] If the distribution of a single target brand is dispersed, the priority of the product in the subsequent product recommendation process is updated based on the actual number of products obtained in the product list, wherein the more the number of products obtained, the higher the priority.

[0047] Compared with the prior art, the beneficial effect of the present invention lies in that, in the present invention, a questionnaire is first generated according to the keywords of the required products provided by the customer, and then product recommendations are made to the user according to the content of the questionnaire. The products actually selected by the user are then compared with the recommended products, and whether the product recommendation is qualified is analyzed according to the comparison results. When the product recommendation is judged to be unqualified, the reasons for its unqualifiedness are analyzed, so as to achieve targeted recommendations for individual customers and improve the matching degree between the recommended products and the products required by the customer.

[0048] Furthermore, the present invention takes into account that if the product recommendation is qualified, the product selected by the user is located at the front position in the product recommendation table. If the selected product is located at the back of the product recommendation table, it is considered that there is a possibility that the user has not finished reading the recommendation table and has searched and selected the product on his own. The qualification of the product recommendation is analyzed according to the distribution of the positions of the products in the product recommendation table selected by the user, thereby improving the control accuracy for customers in the product selection process.

[0049] Furthermore, the present invention takes into account that in the actual product selection process, users select products that are not mentioned in the initial questionnaire. Therefore, when determining that the recommended products match the products actually selected by the customer, products associated with the products in the product recommendation table are added to the product recommendation table to further optimize the control accuracy of user needs, thereby enabling users to select the required products as soon as possible according to the product recommendation table, thereby improving service efficiency.

[0050] Furthermore, the present invention takes into account the brand preference of users. If so, the distribution of a single brand in the products selected by the user will be more concentrated. Therefore, the user's demand product tendency is analyzed according to the distribution of each brand in the products selected by the user, so as to optimize subsequent product recommendations, thereby further improving the accuracy of product recommendations and improving service efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a structural diagram of the service information management system based on AI analysis of the present invention;

[0052] Figure 2 A flow chart for determining whether the product recommendation for the current target is qualified;

[0053] Figure 3 A flow chart for determining whether the product recommendation for the current target is qualified for secondary analysis;

[0054] Figure 4 A decision flow chart for analyzing reasons why product recommendations for the current target are not up to standard. DETAILED DESCRIPTION

[0055] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0056] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0057] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0058] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0059] See also Figure 1 As shown, it is a structural block diagram of the service information management system based on AI analysis of the present invention.

[0060] The embodiment of the present invention proposes a service information management system based on AI analysis, including:

[0061] A cloud platform for obtaining information to be screened;

[0062] A questionnaire generating unit, which is connected to the cloud platform and is used to generate a questionnaire according to the information to be screened obtained by the cloud platform;

[0063] a reply receiving unit, connected to the questionnaire generating unit, for extracting keywords based on the questionnaire;

[0064] A product recommendation unit, connected to the reply receiving unit, configured to select corresponding products according to the keywords and generate a product recommendation table;

[0065] an analysis unit connected to the product recommendation unit, for determining the actual acquired products of the target after a predetermined time has passed since the product recommendation table was generated, generating a list of actually acquired products, calculating a recommendation matching degree between the list of actually acquired products and the product recommendation table, analyzing whether the product recommendation for the current target is qualified based on the recommendation matching degree, performing a secondary analysis on whether the product recommendation for the current target is qualified based on the distribution of matching products in the product recommendation table, analyzing reasons why the product recommendation for the current target is unqualified based on keywords of the products in the list of actually acquired products, and performing a secondary analysis on reasons why the product recommendation for the current target is unqualified based on the distribution of brands of the products in the list of actually acquired products.

[0066] Specifically, in this embodiment, there is no specific limitation on the structures of the cloud platform, questionnaire generation unit, reply receiving unit, product recommendation unit and analysis unit, which can be composed of logical components, including a field editable processor, a computer and a microprocessor in the computer.

[0067] Specifically, the product recommendation unit selects corresponding products according to the keywords, including:

[0068] Determine the demand keywords in the questionnaire,

[0069] Determine the product's symptom keywords and effect keywords,

[0070] If the demand keyword matches the effect keyword or the demand keyword, the corresponding product will be determined as an alternative product.

[0071] The ranking of the products in the product recommendation table is determined based on the matching degree between the demand keyword and each keyword of the product.

[0072] Specifically, the product recommendation unit determines the matching degree between the demand keyword and each keyword of the product, including:

[0073] Count the number of keywords that are the same as the keywords of the candidate products.

[0074] Calculate the ratio of the number of identical keywords to the total number of required keywords to get the matching degree.

[0075] See also Figure 2 As shown, it is a flow chart for determining whether the product recommendation for the current target is qualified.

[0076] Specifically, the analyzing unit analyzes whether the product recommendation for the current target is qualified based on the recommendation matching degree, including:

[0077] Determine the actual number of products in the product list and obtain the first feature quantity.

[0078] Determine the number of products in the actual product list that are the same as the product recommendation table to obtain a second feature number.

[0079] Calculate the ratio of the second feature quantity to the first feature quantity to obtain the recommended matching degree,

[0080] If the recommended matching degree is greater than or equal to the first preset recommended matching degree, the product recommendation for the current target is determined to be qualified;

[0081] If the recommendation matching degree is less than the first preset recommendation matching degree and greater than or equal to the second preset recommendation matching degree, determining whether the product recommendation for the current target is qualified by secondary analysis based on the distribution of the matching products in the product recommendation table;

[0082] If the recommendation matching degree is less than the second preset recommendation matching degree, it is determined that the product recommendation for the current target is unqualified, and the reason why the product recommendation for the current target is unqualified is analyzed based on the keywords of the products in the actually obtained product list.

[0083] Specifically, in this embodiment, the first preset recommendation matching degree D1 and the second preset recommendation matching degree D2 are obtained by pre-measurement, and product recommendation tests are performed on several targets. The information of the products in the product recommendation table and the information of the products in the actual product list obtained when the target places an order are recorded, and the recommendation matching degree D of each single recommendation test is calculated respectively, and the mean value of the recommendation matching degree △D is solved. It is set that D1=α×ΔD, α represents the first accuracy coefficient, 0.85<α<0.9, and D2=β×ΔD, β represents the second accuracy coefficient, 0.75<β<0.8.

[0084] See also Figure 3 As shown, it is a flow chart for determining whether the product recommendation for the current target is qualified by secondary analysis.

[0085] Specifically, the analysis unit performs a secondary analysis based on the distribution of the matched products in the product recommendation table to determine whether the product recommendation for the current target is qualified, including:

[0086] If the matching products are ranked high and concentrated in the product recommendation table, the product recommendation for the current target is determined to be qualified, and the number of products in the product recommendation table is increased based on the recommendation matching degree;

[0087] If the matching product is ranked low in the product recommendation table, it is determined that the product recommendation for the current target is unqualified, and the reason why the product recommendation for the current target is unqualified is analyzed based on the keywords of the products in the actually obtained product list.

[0088] Specifically, in this embodiment, the products in the product recommendation table are divided into two areas according to the number of products, which are the first area and the second area in order. The number of matching products in each area is recorded, and the distribution of products is determined according to the proportion of the number of matching products in each area. If the number of matching products in the first area is greater than the number of matching products in the second area, the distribution of the matching products is determined to be at the front.

[0089] Specifically, the analyzing unit increases the number of products in the product recommendation table based on the recommendation matching degree, including:

[0090] Select the products related to the products in the product recommendation table.

[0091] Add related products to the product recommendation table based on the recommended matching degree, where:

[0092] The increase in related products is positively correlated with the recommendation matching degree.

[0093] In this embodiment, optionally,

[0094] The recommended matching degree D is compared with the preset first preset recommended matching degree standard threshold D10 and the second preset recommended matching degree standard threshold D20.

[0095] If D≤D10, increase the number of first related products L1, and set L1=0.2×L0;

[0096] If D10<D≤D20, then increase the number of second related products L2, and set L2=0.25×L0;

[0097] If D20<D, then increase the number of third related products L3, setting L3=0.3×L0;

[0098] Where L0 is the initial number of associated products, D1 = 1.1 × ΔD, D2 = 1.3 × ΔD.

[0099] See also Figure 4 As shown, it is a decision flow chart for analyzing the reasons why the product recommendation for the current target is unqualified.

[0100] Specifically, the analyzing unit analyzes the reasons why the product recommendation for the current target is unqualified based on the keywords of the products in the actually acquired product list, including:

[0101] Extract the actual demand keywords for each product in the actual product list.

[0102] Determine the frequency of occurrence of a single actual demand keyword,

[0103] Calculate the ratio of the frequency of occurrence to the total number of actual demand keywords to obtain the product recommendation eligibility characterization parameters.

[0104] If the product recommendation eligibility characterization parameter is greater than or equal to the preset product recommendation eligibility characterization parameter standard threshold, then the reason why the product recommendation for the current target is unqualified is determined to be a change in the target's demand keywords, and the subsequent product recommendation priority for the target is determined and optimized;

[0105] If the product recommendation eligibility characterization parameter is less than the preset product recommendation eligibility characterization parameter standard threshold, a secondary analysis is performed based on the distribution of brands of products in the actual obtained product list to determine the reason why the product recommendation for the current target is unqualified.

[0106] Specifically, in this embodiment, the preset product recommendation qualification characterization parameter standard threshold value F0 is obtained in advance, product recommendation tests are carried out on several targets, the product recommendation qualification characterization parameters of each single recommendation test are calculated respectively, and the mean product recommendation qualification characterization parameter ΔF is solved, and F0=γ×ΔF is set, γ represents the recommendation qualification characterization accuracy coefficient, 0.75<γ<0.85.

[0107] Specifically, the analysis unit optimizes the subsequent product recommendation priority for the target, including:

[0108] Whether the products are exhausted is determined according to the usage cycles of the products in the actually obtained product list, and when it is determined that a single product is exhausted, the product is updated to the product recommendation table.

[0109] Specifically, the analysis unit secondary analyzes the reasons why the product recommendation for the current target is unqualified based on the distribution of each brand of the products in the actually obtained product list, including:

[0110] The brand with the highest frequency of appearance is identified as the target brand.

[0111] If the distribution of a single target brand is concentrated, the target brand is recorded and the priority of the brand is increased in the subsequent product recommendation process;

[0112] If the distribution of a single target brand is dispersed, the priority of the product in the subsequent product recommendation process is updated based on the actual number of products obtained in the product list, wherein the more the number of products obtained, the higher the priority.

[0113] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0114] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A service information management system based on AI analysis, characterized in that: include: A cloud platform for obtaining information to be screened; A questionnaire generating unit, which is connected to the cloud platform and is used to generate a questionnaire according to the information to be screened obtained by the cloud platform; a reply receiving unit, connected to the questionnaire generating unit, for extracting keywords based on the questionnaire; A product recommendation unit, connected to the reply receiving unit, configured to select corresponding products according to the keywords and generate a product recommendation table; an analysis unit connected to the product recommendation unit, for determining the actual acquired products of the target after a predetermined time has passed since the product recommendation table was generated, generating a list of actually acquired products, calculating a recommendation matching degree between the list of actually acquired products and the product recommendation table, analyzing whether the product recommendation for the current target is qualified based on the recommendation matching degree, performing a secondary analysis on whether the product recommendation for the current target is qualified based on the distribution of matching products in the product recommendation table, analyzing reasons why the product recommendation for the current target is unqualified based on keywords of the products in the list of actually acquired products, and performing a secondary analysis on reasons why the product recommendation for the current target is unqualified based on the distribution of brands of the products in the list of actually acquired products.

2. The service information management system based on AI analysis according to claim 1, characterized in that: The product recommendation unit selects corresponding products according to the keywords, including: Determine the demand keywords in the questionnaire, Determine the product's symptom keywords and effect keywords, If the demand keyword matches the effect keyword or the demand keyword, the corresponding product will be determined as an alternative product. The ranking of the products in the product recommendation table is determined based on the matching degree between the demand keyword and each keyword of the product.

3. The service information management system based on AI analysis according to claim 2, characterized in that: The product recommendation unit determines the matching degree between the demand keyword and each keyword of the product, including: Count the number of keywords that are the same as the keywords of the candidate products. Calculate the ratio of the number of identical keywords to the total number of required keywords to get the matching degree.

4. The service information management system based on AI analysis according to claim 1, characterized in that: The analyzing unit analyzes whether the product recommendation for the current target is qualified based on the recommendation matching degree, including: Determine the actual number of products in the product list and obtain the first feature quantity. Determine the number of products in the actual product list that are the same as the product recommendation table to obtain a second feature number. Calculate the ratio of the second feature quantity to the first feature quantity to obtain the recommended matching degree, If the recommended matching degree is greater than or equal to the first preset recommended matching degree, the product recommendation for the current target is determined to be qualified; If the recommendation matching degree is less than the first preset recommendation matching degree and greater than or equal to the second preset recommendation matching degree, determining whether the product recommendation for the current target is qualified by secondary analysis based on the distribution of the matching products in the product recommendation table; If the recommendation matching degree is less than the second preset recommendation matching degree, it is determined that the product recommendation for the current target is unqualified, and the reason why the product recommendation for the current target is unqualified is analyzed based on the keywords of the products in the actually obtained product list.

5. The service information management system based on AI analysis according to claim 4 is characterized in that: The analyzing unit secondary analyzes whether the product recommendation for the current target is qualified based on the distribution of the matched products in the product recommendation table, including: If the matching products are ranked high and concentrated in the product recommendation table, the product recommendation for the current target is determined to be qualified, and the number of products in the product recommendation table is increased based on the recommendation matching degree; If the matching product is ranked low in the product recommendation table, it is determined that the product recommendation for the current target is unqualified, and the reason why the product recommendation for the current target is unqualified is analyzed based on the keywords of the products in the actually obtained product list.

6. The service information management system based on AI analysis according to claim 5, characterized in that: The analyzing unit increases the number of products in the product recommendation table based on the recommendation matching degree, including: Select the products related to the products in the product recommendation table. Add related products to the product recommendation table based on the recommended matching degree, where: The increase in related products is positively correlated with the recommendation matching degree.

7. The service information management system based on AI analysis according to claim 1, characterized in that: The analyzing unit analyzes the reasons why the product recommendation for the current target is unqualified based on the keywords of the products in the actually obtained product list, including: Extract the actual demand keywords for each product in the actual product list. Determine the frequency of occurrence of a single actual demand keyword, Calculate the ratio of the frequency of occurrence to the total number of actual demand keywords to obtain the product recommendation eligibility characterization parameters. If the product recommendation eligibility characterization parameter is greater than or equal to the preset product recommendation eligibility characterization parameter standard threshold, then the reason why the product recommendation for the current target is unqualified is determined to be a change in the target's demand keywords, and the subsequent product recommendation priority for the target is determined and optimized; If the product recommendation eligibility characterization parameter is less than the preset product recommendation eligibility characterization parameter standard threshold, a secondary analysis is performed based on the distribution of brands of products in the actual obtained product list to determine the reason why the product recommendation for the current target is unqualified.

8. The service information management system based on AI analysis according to claim 7, characterized in that: The analysis unit optimizes the subsequent product recommendation priority for the target, including: Whether the products are exhausted is determined according to the usage cycles of the products in the actually obtained product list, and when it is determined that a single product is exhausted, the product is updated to the product recommendation table.

9. The service information management system based on AI analysis according to claim 1, characterized in that: The analyzing unit secondary analyzes the reasons why the product recommendation for the current target is unqualified based on the distribution of each brand of the products in the actually obtained product list, including: The brand with the highest frequency of appearance is identified as the target brand. If the distribution of a single target brand is concentrated, the target brand is recorded and the priority of the brand is increased in the subsequent product recommendation process; If the distribution of a single target brand is dispersed, the priority of the product in the subsequent product recommendation process is updated based on the actual number of products obtained in the product list, wherein the more the number of products obtained, the higher the priority.

Images