Product recommendation method and device, equipment, storage medium and product
By multi-dimensional screening of customer and product information and generating report templates, the problem of inefficient corporate product recommendations caused by insufficient experience of offline account managers has been solved, achieving highly accurate and efficient product recommendations.
Patent Information
- Application Number
- CN202511238812.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-01
- Publication Date
- 2025-10-17
AI Technical Summary
In the existing technology, corporate product recommendations rely on the experience of offline account managers, resulting in low recommendation efficiency and poor accuracy.
Through multi-dimensional screening of customer information and known products, including industry demand screening, expert rule screening and model screening, target products are determined and a recommendation report is generated based on the report template.
It improves the accuracy and efficiency of product recommendations, ensures that new account managers can also quickly and accurately recommend suitable products, and increases the probability of successful recommendations.
Smart Images
Figure CN120807107A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of data analysis, and in particular to a product recommendation method and device, equipment, a storage medium and a product. BACKGROUND
[0002] In the financial field, banks or financial institutions provide diversified public product services such as fund management, financing, settlement, investment, etc. for various types of enterprises and other non-personal customers, and often need customer managers to recommend appropriate products to customers.
[0003] At present, public product marketing mainly relies on the offline sales channels of customer managers. In order to improve the visitor success rate, customer managers usually make product configuration combination reports and other digital tools before the visitor to assist in efficient customer insight. However, when customer managers analyze marketing to customers, they mainly rely on their understanding of the business and past successful experience, making it difficult for new customer managers to quickly replicate, and the existing algorithm has poor accuracy in recommending products, thus leading to low efficiency of public product recommendation.
[0004] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY
[0005] The main purpose of the present application is to provide a product recommendation method, device, equipment, storage medium and product, aiming to solve the technical problem of low efficiency of public product recommendation.
[0006] To achieve the above purpose, the present application provides a product recommendation method, which comprises:
[0007] obtaining customer information of a customer and product information of a known product;
[0008] based on the customer information and the product information, performing multi-dimensional screening on the known product to determine a target product that needs to be recommended to the customer, the screening including industry demand screening, expert rule screening and model screening;
[0009] After obtaining a report template corresponding to the target product, a recommendation report of the target product is obtained based on the report template, so that a user can recommend the target product to the customer based on the recommendation report.
[0010] In an embodiment, the step of performing multi-dimensional screening on the known product based on the customer information and the product information to determine a target product that needs to be recommended to the customer comprises:
[0011] screen the known products based on industry information and company information in the customer information to determine first recommended products and corresponding first recommendation scores;
[0012] screen the known products based on customer behavior information in the customer information to determine second recommended products and corresponding second recommendation scores;
[0013] screen the known products based on customer behavior information in the customer information and the product information to determine third recommended products and corresponding third recommendation scores by using a product recommendation model;
[0014] determine target products to be recommended to the customer from the first recommended products, the second recommended products and the third recommended products based on the first recommendation scores, the second recommendation scores and the third recommendation scores.
[0015] In an embodiment, the step of screening the known products based on industry information and company information in the customer information to determine first recommended products and corresponding first recommendation scores comprises:
[0016] analyze the customer based on the industry information in the customer information to determine an industry to which the customer belongs;
[0017] retrieve historical product marketing data related to the industry to which the customer belongs;
[0018] identify demand product information from the known products based on the historical product marketing data, the demand product information meeting a preset marketing requirement in the industry to which the customer belongs;
[0019] screen first recommended products from the demand products based on the company information and the demand product information, and determine first recommendation scores of the first recommended products.
[0020] In an embodiment, the step of determining target products to be recommended to the customer further comprises:
[0021] identify whether there is a necessary basic product related to the industry to which the customer belongs from the known products, the necessary basic product not belonging to any of the first recommended products, the second recommended products and the third recommended products;
[0022] if there is, determine the necessary basic product as a target product.
[0023] In an embodiment, after obtaining the report template corresponding to the target product, the step of obtaining the recommended report of the target product based on the report template comprises:
[0024] After obtaining the report template corresponding to the target product, the report template is parsed to obtain component information of a target component in the report template, the target component being a component related to an application scenario of the target product selected by the user from a preset component library through a drag operation;
[0025] Based on the component information, relevant product data is matched from a preset database;
[0026] The product data is field-bound to the target component to obtain the recommended report of the target product.
[0027] In an embodiment, the step of field-binding the product data to the target component to obtain the recommended report of the target product further comprises:
[0028] The binding field identifier of the target component is searched from the product data;
[0029] The binding field identifier is mapped and associated with the product data to obtain an association relationship between the product data and the corresponding target component;
[0030] Based on the association relationship, the product data is filled into the corresponding target component to obtain an initial report;
[0031] The initial report is rendered and required elements are added to obtain the recommended report of the target product.
[0032] In addition, to achieve the above-mentioned purpose, the application further provides a product recommendation device, which comprises:
[0033] An acquisition module is configured to acquire customer information of a customer and product information of a known product;
[0034] A screening module is configured to perform multi-dimensional screening on the known product based on the customer information and the product information to determine a target product to be recommended to the customer, wherein the screening comprises industry demand screening, expert rule screening, and model screening;
[0035] A recommendation module is configured to, after obtaining a report template corresponding to the target product, obtain a recommended report of the target product based on the report template, so that the user recommends the target product to the customer based on the recommended report.
[0036] In addition, to achieve the above object, the present application also provides a product recommendation device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the product recommendation method.
[0037] In addition, to achieve the above object, the present application also provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the product recommendation method.
[0038] In addition, to achieve the above object, the present application also provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the product recommendation method.
[0039] The one or more technical solutions provided by the present application have at least the following technical effects:
[0040] According to the customer information of the customer and the product information of the known product, the known product is respectively screened through industry demand, expert rules and model in multiple dimensions, so as to determine the target product to be recommended to the customer, so as to avoid selecting the product to be recommended according to personal experience, and improve the accuracy of the product recommendation algorithm through multi-dimensional screening. When the target product is determined and the report template corresponding to the target product is obtained, the recommendation report of the target product is obtained according to the report template, so that the user can recommend the product to the customer based on the recommendation report, so as to improve the probability of successful recommendation. That is, by multi-dimensional screening of the known product, the influence of personal experience is avoided, so that new users can also determine the target product to be recommended to the customer, and the accuracy of the recommended product is also improved through multi-dimensional screening. Then, the recommendation report of the target product is quickly made through the report template, so as to assist the user to efficiently recommend the product to the customer, so as to improve the efficiency of product recommendation through high accuracy and efficient recommendation. BRIEF DESCRIPTION OF DRAWINGS
[0041] The accompanying drawings incorporated in and forming a part of the specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the application.
[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, for those skilled in the art, other drawings can also be obtained without creative labor.
[0043] Figure 1A flowchart provided for the recommended method embodiment one of the product of the present application;
[0044] Figure 2 A flowchart provided for the recommended method embodiment two of the product of the present application;
[0045] Figure 3 A brief flowchart of product recommendation fusion procedure in the recommended method of the product of the present application;
[0046] Figure 4 A flowchart provided for the recommended method embodiment two of the product of the present application;
[0047] Figure 5 A brief flowchart of report generation in the recommended method of the product of the present application;
[0048] Figure 6 A brief architecture diagram of the recommended system of the product of the present application;
[0049] Figure 7 A module structure diagram of the recommended device of the product of the embodiment of the present application;
[0050] Figure 8 A device structure diagram of the hardware running environment involved in the recommended method of the product in the embodiment of the present application.
[0051] The implementation, functional features and advantages of the present application will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION
[0052] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application, and are not used to limit the present application.
[0053] In order to better understand the technical solutions of the present application, the following will be described in detail in conjunction with the drawings of the specification and specific embodiments.
[0054] The main solution of the embodiment of the present application is that the jig controller obtains customer information of a customer and product information of a known product; based on the customer information and the product information, the known product is screened in multiple dimensions to determine a target product to be recommended to the customer, and the screening includes industry demand screening, expert rule screening and model screening; after obtaining a report template corresponding to the target product, a recommendation report of the target product is obtained based on the report template, so that the user recommends the target product to the customer based on the recommendation report.
[0055] In the present embodiment, for the convenience of description, the jig controller is taken as the execution subject for elaboration.
[0056] Since corporate product marketing currently relies primarily on offline sales channels through account managers, to improve visitor success rates, account managers often create digital tools such as product configuration reports before visiting to assist in effective customer insights. However, these customer marketing analyses rely primarily on their personal understanding of the business and past successes, making it difficult for new account managers to quickly replicate these skills. Furthermore, existing algorithms offer limited accuracy in recommending products, resulting in inefficient corporate product recommendations.
[0057] The present application provides a solution, which performs multi-dimensional screening of known products through industry needs, expert rules and models based on the customer's customer information and product information of known products, so as to determine the target products that need to be recommended to the customer, so as to avoid selecting the products that need to be recommended based on personal experience, and improve the accuracy of the algorithm's product recommendation through multi-dimensional screening. When the target product is determined and the report template corresponding to the target product is obtained, a recommendation report of the target product is obtained according to the report template, so that the user can recommend the product to the customer based on the recommendation report, thereby ensuring that the probability of successful recommendation is increased. That is, the present application avoids the influence of personal experience by performing multi-dimensional screening on known products, so that new users can also determine that the target product needs to be recommended to the customer, and through multi-dimensional screening, the accuracy of the recommended products is also improved, and then a recommendation template for the target product is quickly created through the report template to assist the user in efficiently recommending products to the customer, thereby improving the efficiency of product recommendation through high-precision and efficient recommendations.
[0058] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of implementing the above functions, a fixture controller, etc. The following uses the fixture controller as an example to illustrate this embodiment and the following embodiments.
[0059] Based on this, the present invention provides a method for recommending a product. Figure 1 , Figure 1 This is a flow chart of the first embodiment of the recommended method of the product of this application.
[0060] In this embodiment, the product recommendation method includes steps S10 to S30:
[0061] Step S10, obtaining customer information of the customer and product information of known products;
[0062] It should be noted that customers are companies or enterprises that require business products. Customer information refers to data and characteristics related to the company or enterprise. Known products are all currently available corporate products. Product information includes known product functions, performance, and application scenarios.
[0063] In a specific implementation, the customer information can be obtained through various channels, such as customer registration information, purchase history, online behavior records, customer feedback, etc. The product information can be obtained from product databases, market research reports, etc.
[0064] Step S20, based on the customer information and the product information, multi-dimensional screening of the known products is performed to determine the target products to be recommended to the customer, and the screening includes industry demand screening, expert rule screening and model screening;
[0065] It should be noted that multi-dimensional screening is a process of evaluating and screening known products from multiple different angles, and the screening specifically includes industry demand screening, expert rule screening and model screening, so as to more comprehensively screen products suitable for the customer through comprehensive screening. Among them, the industry demand screening is to screen out demand products strongly related to the industry according to the characteristics and needs of the customer's industry. The expert rule screening is to screen the known products based on the experience and rules of the customer manager. The model screening is to screen the known products by using a data analysis model in combination with customer information and product information. The target product is the final product determined to be suitable for a specific customer after multi-dimensional screening. That is, the target product is the product most likely to meet the current needs of the customer, which is screened from all sellable products according to the customer's industry demand, company size, business scope, historical transaction records and customer behavior, etc.
[0066] It can be understood that by industry demand screening, expert rule screening and model screening, the matching degree of products and customer needs is evaluated from multiple angles, which can more accurately recommend products suitable for the customer, so as to avoid the deviation that may be caused by a single screening method and ensure the accuracy and reliability of the recommendation result.
[0067] It can be understood that the customer information and product information are used for screening to ensure that the target product recommended is determined based on actual data rather than subjective judgment, so as to discover patterns and associations hidden in the data and improve the scientificity and effectiveness of the recommendation.
[0068] It can be understood that according to the customer information, a personalized recommendation report can also be generated, so that the customer feels the pertinence and professionalism of the recommendation, thereby improving the customer's satisfaction and trust, promoting the customer's purchase decision and improving the sales efficiency of the product.
[0069] In a specific implementation, according to industry information and historical product marketing data, products performing well in a specific industry are identified to complete industry characteristic screening; according to the sales experience of experienced customer managers recorded, products suitable for customers are screened from known products to complete expert rule screening; and customer information and product information are input into a machine learning model to determine products strongly related to the customer to complete model screening, and a union is taken from the results of industry characteristic recommendation, expert rule screening and model recommendation, and filtered products are opened to obtain screened products, and the screened products are calculated according to a certain weight to obtain screening scores of different screening methods, and the scores are converted into recommendation star levels to determine target products that need to be recommended to customers. The recommendation star level calculation formula is:
[0070] Score = W1 * S1 + W2 * S2 + W3 * S3;
[0071] Wherein, W1 is the weight of industry demand screening, W2 is the weight of expert rule screening, and W3 is the weight of model screening. It should be noted that W1 + W2 + W3 = 1. S1 is the industry demand screening score, S2 is the expert rule screening score, and S3 is the model screening score.
[0072] Step S30, after obtaining the report template corresponding to the target product, obtaining the recommendation report of the target product based on the report template, so that the user recommends the target product to the customer based on the recommendation report.
[0073] It should be noted that the report template is a preset format and structure for generating a recommendation report, wherein the report template includes a target component. The target component is a specific module in the report template for displaying product information. The component is selected by the user from a preset component library through a drag-and-drop operation, and the report template is laid out through drag-and-drop sorting, alignment, grouping, etc. The recommendation report is generated based on the report template and is a document for recommending target products to customers, wherein the recommendation report includes detailed information of the target product and analysis of the target product suitable for customers to help customers better understand the value and applicability of the target product. The user is a customer manager who sells products.
[0074] It can be understood that the user can select and customize the report template according to the application scenario of the target product, so that the recommendation report is more in line with the needs of the customer, and the customized report template is customized without code, reducing the professionalism of the customized template and improving the efficiency of the target product report production.
[0075] In a specific implementation, after obtaining the report template, the report template is parsed, target components therein are identified for displaying product information, product data related to each target component is matched from a preset database, and the product data is bound to the corresponding target component. Finally, the bound data is filled into the target component to generate an initial report, and the initial report is rendered and formatted to finally generate a recommended report.
[0076] The embodiment provides a product recommendation method. According to customer information of a customer and product information of a known product, the known product is subjected to multi-dimensional screening through industry demand, expert rules and a model, so as to determine a target product to be recommended to the customer, thereby avoiding selection of the product to be recommended according to personal experience, improving the accuracy of product recommendation by the algorithm through the multi-dimensional screening, and obtaining a recommended report of the target product according to a report template when the target product is determined and the report template corresponding to the target product is obtained, so as to enable a user to recommend the product to the customer based on the recommended report, thereby ensuring improvement of the probability of successful recommendation. That is, the application avoids influence of personal experience by multi-dimensional screening of the known product, enables a new user to also determine the target product to be recommended to the customer, and improves the accuracy of the recommended product through the multi-dimensional screening. In addition, the recommended report template of the target product is quickly generated through the report template, so as to assist the user in efficiently recommending the product to the customer, thereby improving the efficiency of product recommendation through high accuracy and efficient recommendation.
[0077] Based on the first embodiment, in the second embodiment, the same or similar contents as the above-mentioned first embodiment can be referred to the above description, and will not be described in detail. On this basis, please refer to Figure 2 , and step S20 further includes steps S01-S04:
[0078] In step S01, the known product is subjected to industry demand screening based on industry information and company information in the customer information, and a first recommended product selected and a corresponding first recommendation score are determined.
[0079] In step S02, the known product is subjected to expert rule screening based on customer behavior information in the customer information, and a second recommended product selected and a corresponding second recommendation score are determined.
[0080] In step S03, a third recommended product selected and a corresponding third recommendation score are determined by using a product recommendation model based on customer behavior information in the customer information and the product information.
[0081] In step S04, based on the first recommendation score, the second recommendation score and the third recommendation score, a target product that needs to be recommended to the customer is determined from the first product to be recommended, the second product to be recommended and the third product to be recommended.
[0082] It should be noted that the industry information is related information of the industry to which the customer belongs, including industry characteristics, industry trends, industry standards and competition situation in the industry, and is used to analyze the demand and preference of the customer in a specific industry, so as to perform industry demand screening. The company information is related information of the company to which the customer belongs, including company size, business scope, financial situation, market positioning and historical transaction records. The customer behavior information is various behavior data of the customer to the known product, including purchase history, browsing behavior, consultation record and feedback opinion.
[0083] It should be noted that the first recommendation score is a score assigned to each selected product according to the matching degree of the product and the industry to which the customer belongs in the industry demand screening process. The second recommendation score is a score assigned to each selected product according to the matching degree of the product and the customer behavior information in the expert rule screening process. The third recommendation score is a score assigned to each selected product according to the comprehensive matching degree of the product and the customer information in the product recommendation model screening process. The first product to be recommended is a product for public screening selected according to the industry information and the company information in the industry demand screening process. The second product to be recommended is a product for public screening selected according to the customer behavior information in the expert rule screening process. The third product to be recommended is a product for public screening selected according to the customer behavior information and the product information in the product recommendation model screening process.
[0084] It can be understood that by using industry demand screening, model screening and expert rule screening, the product to be recommended can be quickly screened from a large number of products for public, so as to save time and labor cost, and also reduce the workload of the customer manager, improve the screening efficiency and accuracy. And by comprehensively evaluating multiple screening results, the target product can be quickly determined, and the efficiency of the recommendation process is improved.
[0085] It can be understood that by comprehensively considering the results of industry demand, expert rule and model screening, a recommendation score is assigned to each product to be recommended, and the recommendation score can also be configured into a report, so as to convert the complex evaluation result into an intuitive numerical value in the form of a recommendation score, so as to facilitate the user and the customer to quickly grasp the key information of the product, so as to help the customer better understand the advantages and adaptability of the target product, thereby improving the sales efficiency of the product.
[0086] In a specific implementation, reference is made to Figure 3According to the industry information and the company information in the customer information, the known products are screened according to the industry demand, and a recommendation result according to the industry screening is obtained; and according to the existing expert rules, a recommendation result for the customer is obtained. For example, the customer browses and clicks product A, a click event occurs, and the customer does not purchase product A, which indicates that the customer may have a related demand for product A, and product A can be recommended for purchase; and based on the customer behavior characteristic information and the product information, a product-specific recommendation list table is generated using a machine learning model, and customers with high percentile rankings are taken as the machine learning model recommendation output result. After obtaining the recommendation results of each dimension, the union of each result is taken, and the products that have been opened are filtered to determine the weight of each product. If there is no union product among the three, all the products that have not been opened in each recommendation result are obtained, and the priority of the union product of the three is higher than the priority of the union product of any two, and the priority of the union product of the three is higher than the priority of the union product of any two. According to the priority from high to low, the weight star level of each product is determined, and finally the product with the highest star level is taken as the target product that meets the customer's demand.
[0087] Further, step S01 further comprises:
[0088] Based on the industry information in the customer information, the customer is analyzed according to the industry, and the industry to which the customer belongs is determined.
[0089] The historical product marketing data related to the industry to which the customer belongs is called.
[0090] Based on the historical product marketing data, demand product information with an opening rate meeting a preset marketing requirement in the industry to which the customer belongs is identified from known products.
[0091] Based on the company information and the demand product information, a first product to be recommended is screened from the demand products, and a first recommendation score of the first product to be recommended is determined.
[0092] It should be noted that the historical product marketing data is a historical record of product marketing activities related to the industry to which the customer belongs, including product sales data, market feedback, customer evaluation, etc. The historical product marketing data is used to analyze which products perform well in the industry to which the customer belongs and which products are more popular in the market. The opening rate is the proportion of a product that is actually used or opened by a customer in a specific industry. The preset marketing requirement is set according to market analysis and industry standards, and is used to evaluate whether a product meets specific standards of market demand. The demand product information is detailed data and characteristics related to the demand product, including the function, performance and application scenario of the product.
[0093] It can be understood that, by screening with historical product marketing data, it is ensured that the recommendation is based on actual data rather than subjective judgment, and by industry analysis, the characteristics and needs of the industry to which the customer belongs are understood in depth, and the recommended products can also be highly matched with the needs of the industry, thereby improving the scientificity and effectiveness of the recommendation.
[0094] In a specific implementation, reference is made to Figure 3 , the industry demand screening of the known products includes: analyzing the industry to which the customer belongs to determine the sub-industry, for example: manufacturing / computer, communication and other electronic equipment manufacturing industry; then identifying the characteristic product information of the industry according to the historical product marketing result data, for example: if the opening rate of product A in industry a to which customer 1 belongs is more than 5 times of the opening rate of product A in all customers, then product A is identified as the characteristic product of industry a; finally, the similarity between the company characteristic array and the demand product characteristic array is calculated to determine the recommendation score.
[0095] Further, step S04 further includes:
[0096] From the known products, it is identified whether there is a necessary basic product related to the industry to which the customer belongs, the necessary basic product does not belong to any one of the first to be recommended product, the second to be recommended product and the third to be recommended product;
[0097] If there is, the necessary basic product is determined as the target product.
[0098] It should be noted that the necessary basic product refers to a product that is indispensable for the normal operation of an enterprise or a specific business process in the industry to which the customer belongs.
[0099] It can be understood that, by identifying the necessary basic product, it is ensured that the recommended product meets the industry standard and the basic business needs of the customer, so as to improve the trust of the customer in the recommendation system.
[0100] In a specific implementation, according to the company's product configuration, the unconfigured basic essential product is identified, the product that meets this rule is recommended with the highest priority, and then the large language model is used to further process the recommendation reason, input the recommendation rule + customer related recommendation product behavior characteristics and other knowledge, and reorganize the recommendation reason to enhance its readability and understandability.
[0101] Based on the first and second embodiments of the present application, in the third embodiment of the present application, the same or similar contents as the above embodiment one can refer to the above introduction, and the following will not be repeated. On this basis, please refer to Figure 4 , step S30 further includes steps S1-S3:
[0102] Step S1, after obtaining the report template corresponding to the target product, the report template is parsed to obtain the component information of the target component in the report template, the target component is a component related to the application scenario of the target product selected by the user from the preset component library through the drag operation;
[0103] Step S2, based on the component information, matching related product data from a preset database;
[0104] Step S3, field binding the product data to the target component, obtaining the recommended report of the target product.
[0105] It should be noted that the component information is a detailed description and configuration information of the target component, including the type, function and layout position of the component. The preset component library is a set of selectable components defined in advance, and the user can select appropriate components from it according to the application scenario of the target product, including but not limited to product overview, functional characteristics, application scenario, customer case, and price information. The preset database is a database that stores product data, including product functions, performance, application scenarios, prices, and historical sales data. Field binding is a process of associating product data with specific fields in the target component.
[0106] It can be understood that the component is selected by the drag operation, which avoids using code to configure the component, reduces the difficulty of configuring the component, thereby enhancing the interactivity between the user and the jig controller, and improving the user experience. And according to the target product, different business scenario product configuration combination reports in this field can be quickly customized, thereby improving the report production efficiency.
[0107] Optionally, the creation process of the report template includes: 1, a report is created by a middle station personnel, and relevant information such as report name is filled in; 2, arranging the report one-two directory structure; 3, retrieving the required report components from the component library; 4, dragging the component to fill in the specified position of the report and adjusting the order; 5, customizing and editing the component display properties, such as displaying products, styles, etc.; 6, saving the report, and the report creation is successful.
[0108] In a specific implementation, reference is made to Figure 5After obtaining the report template, the authority of the customer manager who makes the report is checked and the data is isolated. After the authority of the customer manager is passed, the design template loader is called to load the corresponding report template file (usually in a structured format such as JSON, describing component layout, properties and data binding relationship), the components in the report are parsed and loaded, and the unified data query interface supporting connection with multiple heterogeneous data sources is used to query the required data from the data source. Then the data retrieval logic is developed, the component configuration content is parsed, the target data is located and obtained from the preset source data table. After obtaining the target data, the target data is cleaned, including null / missing value processing, outlier detection and filtering, data format standardization (such as uniform date format, numerical precision, etc.). After the component binding field identifier in the report template is parsed, it is mapped and associated with the actual field in the data source after cleaning, to obtain the recommended report of the target product.
[0109] Further, step S3 further comprises:
[0110] finding the binding field identifier of the target component from the product data;
[0111] mapping and associating the binding field identifier with the product data to obtain the association relationship between the product data and the corresponding target component;
[0112] based on the association relationship, filling the product data into the corresponding target component to obtain an initial report;
[0113] rendering the initial report and adding required elements to obtain the recommended report of the target product.
[0114] It should be noted that the binding field identifier is a specific field identifier in the target component used for association with the product data. Mapping and association is a process of matching the binding field identifier with the product data. Through mapping and association, the corresponding relationship between the product data and the target component can be established to ensure that the data can be correctly displayed in the report. The association relationship is the corresponding relationship between the product data and the target component. The initial report is a report generated after completing the field binding of the product data and the target component. The required elements are additional contents added to the report in the rendering process, such as title, chart, picture and annotation, etc.
[0115] In specific implementation, reference is made to Figure 5According to the template definition, the chart type, the style and the mapped data, a visual chart component is dynamically generated, a placeholder replacement mechanism is realized, the content of a text component is scanned, and a predefined placeholder (such as {company_name}) is replaced by a corresponding actual data value, so as to obtain an initial report. Different preset styles can be adjusted, and user watermarks, system logos and other fixed elements can be automatically embedded in the report during report generation.
[0116] The application also provides a product recommendation system, please refer to Figure 6 The product recommendation device comprises:
[0117] WEB service module: the system supports PC and APP access to the product configuration combination report of the customer.
[0118] Component management module: the system provides a large number of product analysis components, and controls the front-end display style, size, display content and other data of the components through configuration.
[0119] Report development module: by dragging and arranging the components, a corresponding report template can be generated. The report supports self-defined first-level and second-level directories, and the properties of the components in the report can be modified to customize the display of the required content.
[0120] System report template and user report template are provided in the system. The system report template is arranged based on the experience of business experts and is suitable for beginners. The user report template needs to be personalized by the user according to the user's own use habit and is suitable for users with certain marketing experience.
[0121] Report rendering module: through the configuration of the report template, the components in the report template are filled with data in combination with the product holding and recommendation data of the customer. The customer information is combined with the template configuration information to generate the report corresponding to the template.
[0122] Monitoring and alarm module: the system provides alarm services such as main link error log, data job exception and data quality monitoring. In combination with the notification service, the system alarm message is sent in real time to realize the rapid definition and positioning of the exception, so as to ensure the stability of the system.
[0123] Job processing engine: used for generating customer data required for generating a report. In combination with the underlying data table, the data is processed through spark, hive and other big data components to generate underlying report data, which is convenient for the upper-layer application system to process and render.
[0124] The product recommendation engine combines the industry characteristics, the expert rules and the AI model to recommend products, and scores the products according to a certain weight ratio, so as to obtain the recommended product configuration of the customer. A large language model is used to reorganize the product recommendation reasons, and the intelligibility of the product recommendation is enhanced.
[0125] The application also provides a product recommendation device, which refers to Figure 7 , and the product recommendation device comprises:
[0126] The acquisition module 10 is configured to acquire customer information of a customer and product information of known products.
[0127] The screening module 20 is configured to perform multi-dimensional screening on the known products based on the customer information and the product information, to determine a target product to be recommended to the customer. The screening includes industry demand screening, expert rule screening and model screening.
[0128] The recommendation module 30 is configured to obtain a recommendation report of the target product based on a report template corresponding to the target product, so that a user recommends the target product to the customer based on the recommendation report.
[0129] Optionally, the screening module 20 is further configured to perform industry demand screening on the known products based on industry information and company information in the customer information, to determine a first recommended product and a first recommendation score corresponding to the first recommended product. The industry information is information of an industry to which the customer belongs, and the company information is information of a company to which the customer belongs. The screening module 20 is further configured to perform expert rule screening on the known products based on customer behavior information in the customer information, to determine a second recommended product and a second recommendation score corresponding to the second recommended product. The screening module 20 is further configured to determine a third recommended product and a third recommendation score corresponding to the third recommended product by using a product recommendation model based on the customer behavior information in the customer information and the product information. The screening module 20 is further configured to determine the target product to be recommended to the customer from the first recommended product, the second recommended product and the third recommended product based on the first recommendation score, the second recommendation score and the third recommendation score.
[0130] Optionally, the screening module 20 is further configured to perform industry analysis on the customer based on industry information in the customer information, to determine an industry to which the customer belongs. The screening module 20 is further configured to call historical product marketing data related to the industry. The screening module 20 is further configured to identify demand product information that meets a preset marketing requirement in the industry from the known products based on the historical product marketing data. The screening module 20 is further configured to screen a first recommended product from the demand products based on the company information and the demand product information, and to determine a first recommendation score of the first recommended product.
[0131] Optionally, the screening module 20 is further configured to identify, from the known products, whether there is a necessary basic product related to the industry to which the product belongs, the necessary basic product not belonging to any of the first product to be recommended, the second product to be recommended and the third product to be recommended; and if the necessary basic product exists, determine the necessary basic product as the target product.
[0132] Optionally, the recommendation module 30 is configured to, after obtaining the report template corresponding to the target product, parse the report template to obtain component information of a target component in the report template, the target component being a component related to an application scenario of the target product and selected by a user from a preset component library through a drag operation; match related product data from a preset database based on the component information; perform field binding on the product data and the target component to obtain a recommendation report of the target product.
[0133] Optionally, the recommendation module 30 is further configured to find a binding field identifier of the target component from the product data; map and associate the binding field identifier with the product data to obtain an association relationship between the product data and the corresponding target component; fill the product data into the corresponding target component based on the association relationship to obtain an initial report; render the initial report and add required elements to obtain the recommendation report of the target product.
[0134] The product recommendation device provided in the present application adopts the product recommendation method in the above embodiments, and can solve the technical problem of low efficiency of recommending public products. Compared with the prior art, the product recommendation device provided in the present application has the same beneficial effects as the product recommendation method provided in the above embodiments, and other technical features in the product recommendation device are the same as the features disclosed in the above embodiments, which will not be repeated here.
[0135] The present application provides a product recommendation device, which comprises at least one processor and a memory in communication connection with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the product recommendation method in the above embodiment one.
[0136] The following refers to Figure 8, which shows a schematic diagram of the structure of a recommended device suitable for implementing the product of the embodiments of the present application. The recommended device of the product in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 8 The recommended devices of the products shown are merely examples and should not limit the functions and scope of use of the embodiments of the present application.
[0137] like Figure 8 As shown, the product recommendation device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the product recommendation device. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003 including, for example, a magnetic tape, hard disk, etc.; and communication device 1009. The communication device 1009 can allow the recommended device of the product to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows the recommended device of the product with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have instead.
[0138] In particular, according to the embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, the embodiments of the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the methods of the embodiments of the present application are executed.
[0139] The product recommendation device provided by the present application adopts the product recommendation method in the above-mentioned embodiments, and can solve the technical problem of low efficiency of public product recommendation. Compared with the prior art, the product recommendation device provided by the present application has the same beneficial effects as the product recommendation method provided by the above-mentioned embodiments, and other technical features in the product recommendation device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.
[0140] It should be understood that parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the description of the above-mentioned embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0141] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.
[0142] The present application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e. computer program) for executing the product recommendation method in the above-mentioned embodiments.
[0143] The computer readable storage medium provided in the application may, for example, be a U disk, but is not limited to an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination of the above. More specific examples of the computer readable storage medium may include, but are not limited to, an electric connection with one or more conductive wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the embodiment, the computer readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system, or device. The program code contained on the computer readable storage medium can be transmitted by any suitable medium, including but not limited to an electric wire, an optical cable, an RF (Radio Frequency), and the like, or any suitable combination of the above.
[0144] The above computer readable storage medium may be included in a recommended device of a product, or may exist separately without being assembled into the recommended device of the product.
[0145] The above computer readable storage medium carries one or more programs, when the one or more programs are executed by the recommended device of the product, the recommended device of the product: obtains customer information of a customer and product information of a known product; based on the customer information and the product information, multi-dimensionally filters the known product to determine a target product to be recommended to the customer, the filtering including industry demand filtering, expert rule filtering, and model filtering; after obtaining a report template corresponding to the target product, obtains a recommendation report of the target product based on the report template, so that a user recommends the target product to the customer based on the recommendation report.
[0146] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).
[0147] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may
[0148] The modules involved in the embodiments of the present application can be implemented in the form of software or in the form of hardware. In some cases, the name of the module does not constitute a limitation on the module itself.
[0149] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e., a computer program) for executing the product recommendation method described above, and can solve the technical problem of low efficiency of product recommendation. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the product recommendation method provided by the above-mentioned embodiments, and will not be described here.
[0150] The application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the product recommendation method as described above.
[0151] The computer program product provided by the application can solve the technical problem of low efficiency of public product recommendation. Compared with the prior art, the beneficial effects of the computer program product provided by the application are the same as those of the product recommendation method provided by the above-mentioned embodiments, which will not be repeated here.
[0152] The above only describes some embodiments of the application, and does not limit the protection scope of the application. Any equivalent structure transformation made by using the content of the application specification and drawings, or direct / indirect application in other related technical fields is included in the protection scope of the application.
Claims
1. A product recommendation method, characterized in that: The method includes: Obtain customer information of clients and product information of known products; Based on the customer information and the product information, the known products are screened in multiple dimensions to determine target products that need to be recommended to the customer. The screening includes industry demand screening, expert rule screening, and model screening. After obtaining the report template corresponding to the target product, a recommendation report for the target product is obtained based on the report template, so that the user can recommend the target product to the customer based on the recommendation report.
2. The method according to claim 1, wherein The step of screening the known products in multiple dimensions based on the customer information and the product information to determine the target product to be recommended to the customer includes: Based on the industry information and company information in the customer information, screen the known products for industry needs and determine a first recommended product and a corresponding first recommendation score; the industry information is information about the industry to which the customer belongs, and the company information is information about the company to which the customer belongs; Based on the customer behavior information in the customer information, the known products are screened by expert rules to determine a second product to be recommended and a corresponding second recommendation score; Based on the customer behavior information in the customer information and the product information, using a product recommendation model, determining a selected third product to be recommended and a corresponding third recommendation score; Based on the first recommendation score, the second recommendation score and the third recommendation score, a target product that needs to be recommended to the customer is determined from the first product to be recommended, the second product to be recommended and the third product to be recommended.
3. The method according to claim 2, wherein The step of screening known products for industry demand based on the industry information and company information in the customer information and determining a selected first product to be recommended and a corresponding first recommendation score includes: Based on the industry information in the customer information, perform industry analysis on the customer to determine the industry to which the customer belongs; Retrieve historical product marketing data related to the industry; Based on the historical product marketing data, identifying demand product information from known products whose activation rate in the industry meets preset marketing requirements; Based on the company information and the demand product information, a first product to be recommended is screened out from the demand products, and a first recommendation score of the first product to be recommended is determined.
4. The method according to claim 3, wherein The step of determining the target product to be recommended to the customer further includes: Identify, from the known products, whether there is a necessary basic product related to the industry, wherein the necessary basic product does not belong to any of the first product to be recommended, the second product to be recommended, and the third product to be recommended; If so, the necessary basic product is determined as the target product.
5. The method according to claim 1, wherein After obtaining the report template corresponding to the target product, the step of obtaining a recommendation report for the target product based on the report template includes: After obtaining a report template corresponding to the target product, parsing the report template to obtain component information of a target component in the report template, where the target component is a component related to an application scenario of the target product selected by the user from a preset component library through a drag operation; Based on the component information, matching relevant product data from a preset database; The product data and the target component are bound to fields to obtain a recommendation report for the target product.
6. The method according to claim 5, wherein The step of binding the product data to the target component to obtain a recommendation report for the target product further includes: Searching for a binding field identifier of the target component from the product data; Mapping and associating the binding field identifier with the product data to obtain an association relationship between the product data and the corresponding target component; Based on the association relationship, the product data is filled into the corresponding target component to obtain an initial report; The initial report is rendered and required elements are added to obtain a recommendation report for the target product.
7. A product recommendation device, characterized in that: The device comprises: The acquisition module is used to obtain the customer information of the customer and the product information of the known products; A screening module is used to perform multi-dimensional screening of the known products based on the customer information and the product information to determine the target products that need to be recommended to the customer. The screening includes industry demand screening, expert rule screening, and model screening; The recommendation module is used to obtain a report template corresponding to the target product and, based on the report template, obtain a recommendation report for the target product, so that the user can recommend the target product to the customer based on the recommendation report.
8. A recommended device for a product, characterized in that, The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the product recommendation method according to any one of claims 1 to 6.
9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the product recommendation method according to any one of claims 1 to 6 are implemented.
10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the product recommendation method according to any one of claims 1 to 6 are implemented.