Business opportunity processing method and device, computer equipment and storage medium

Abstract

The embodiment of the invention belongs to the field of artificial intelligence, and relates to a business opportunity processing method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining customer data of each customer, the historical consumption data comprises product information of products purchased by the customer in history and associated salesman identifiers; inputting the customer data into a business opportunity value evaluation model to obtain a business opportunity value score of each customer; inputting the customer data into a business opportunity product recommendation model to obtain a business opportunity product for each customer; obtaining the historical performance of each salesman, and based on the business opportunity value score of each customer and the historical performance of each salesman, matching each customer with each salesman through a business opportunity matching model to obtain a business opportunity matching result; and determining a salesman matched with each customer according to a business opportunity matching result, and recommending a business opportunity product for the customer to the customer through the salesman. The business opportunity conversion rate is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a business opportunity processing method, device, computer equipment and storage medium. Background Art

[0002] In the customer management of the financial insurance field, it is necessary to explore the business opportunity value of customers and recommend products to the discovered business opportunity customers to achieve business opportunity conversion. At present, customer management is mainly carried out by salesmen of financial insurance companies, who mainly rely on subjective consciousness to explore and analyze business opportunity customers, which will affect the accuracy of business opportunity processing and increase the difficulty of business opportunity conversion. At the same time, financial insurance companies often randomly assign salesmen to follow up business opportunity customers, and the business opportunity allocation cannot effectively cover customers and salesmen, further affecting the business opportunity conversion rate. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a business opportunity processing method, apparatus, computer equipment and storage medium to solve the problem of low business opportunity conversion rate.

[0004] In order to solve the above technical problems, the present application embodiment provides a business opportunity processing method, which adopts the following technical solutions:

[0005] Obtain customer data of each customer, including the customer's customer tag and historical consumption data. The historical consumption data includes product information of products purchased by the customer in the past and the associated salesperson ID;

[0006] Inputting the customer data into a business opportunity value assessment model to obtain a business opportunity value score for each customer;

[0007] Inputting the customer data into a business opportunity product recommendation model to obtain business opportunity products for each customer;

[0008] Obtaining the historical performance of each salesperson, and matching each customer with each salesperson through a business opportunity matching model based on the business opportunity value score of each customer and the historical performance of each salesperson, to obtain a business opportunity matching result;

[0009] A salesperson matching each customer is determined according to the business opportunity matching result, and a business opportunity product targeting the customer is recommended to the customer through the salesperson.

[0010] In order to solve the above technical problems, the embodiment of the present application further provides a business opportunity processing device, which adopts the following technical solution:

[0011] The data acquisition module is used to acquire the customer data of each customer, the customer data includes the customer's customer tag and historical consumption data, the historical consumption data includes the product information of the products purchased by the customer in the past and the associated salesperson identification;

[0012] A value scoring module, used to input the customer data into a business opportunity value assessment model to obtain a business opportunity value score for each customer;

[0013] A product determination module, used for inputting the customer data into a business opportunity product recommendation model to obtain business opportunity products for each customer;

[0014] A business opportunity matching module is used to obtain the historical performance of each salesperson, and based on the business opportunity value score of each customer and the historical performance of each salesperson, match each customer with each salesperson through a business opportunity matching model to obtain a business opportunity matching result;

[0015] The product recommendation module is used to determine a salesperson who matches each customer according to the business opportunity matching result, and recommend business opportunity products for the customer to the customer through the salesperson.

[0016] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0017] Obtain customer data of each customer, including the customer's customer tag and historical consumption data. The historical consumption data includes product information of products purchased by the customer in the past and the associated salesperson ID;

[0018] Inputting the customer data into a business opportunity value assessment model to obtain a business opportunity value score for each customer;

[0019] Inputting the customer data into a business opportunity product recommendation model to obtain business opportunity products for each customer;

[0020] Obtaining the historical performance of each salesperson, and matching each customer with each salesperson through a business opportunity matching model based on the business opportunity value score of each customer and the historical performance of each salesperson, to obtain a business opportunity matching result;

[0021] A salesperson matching each customer is determined according to the business opportunity matching result, and a business opportunity product targeting the customer is recommended to the customer through the salesperson.

[0022] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0023] Obtain customer data of each customer, including the customer's customer tag and historical consumption data. The historical consumption data includes product information of products purchased by the customer in the past and the associated salesperson ID;

[0024] Inputting the customer data into a business opportunity value assessment model to obtain a business opportunity value score for each customer;

[0025] Inputting the customer data into a business opportunity product recommendation model to obtain business opportunity products for each customer;

[0026] Obtaining the historical performance of each salesperson, and matching each customer with each salesperson through a business opportunity matching model based on the business opportunity value score of each customer and the historical performance of each salesperson, to obtain a business opportunity matching result;

[0027] A salesperson matching each customer is determined according to the business opportunity matching result, and a business opportunity product targeting the customer is recommended to the customer through the salesperson.

[0028] Compared with the prior art, the embodiments of the present application mainly have the following beneficial effects: obtaining customer data of each customer, the customer data including the customer tag and historical consumption data of the customer, the historical consumption data including the product information of the products purchased by the customer in history and the associated salesperson identification; inputting the customer data into the business opportunity value assessment model, assessing the customer's business opportunity value and obtaining the business opportunity value score of each customer; inputting the customer data into the business opportunity product recommendation model, making personalized product recommendations for the customer, and obtaining the business opportunity product of each customer; the business opportunity matching model combines the salesperson's historical performance and the customer's business opportunity value score for intelligent matching, ensuring that high-value business opportunity customers can be assigned to the most suitable salesperson for follow-up, thereby improving the business opportunity conversion rate and customer satisfaction; the present application uses the business opportunity value assessment model to assess the customer's business opportunity value, and uses the business opportunity product recommendation model to predict business opportunity products for business opportunity customers, thereby improving the accuracy and efficiency of business opportunity processing, and optimizes resource allocation through the business opportunity matching model, thereby further improving the business opportunity conversion rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0030] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0031] Figure 2is a flow chart of an embodiment of a business opportunity processing method according to the present application;

[0032] Figure 3 is a structural schematic diagram of an embodiment of a business opportunity processing device according to the present application;

[0033] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0035] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0036] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0037] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0038] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0039] The terminal devices 101, 102, and 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0040] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0041] It should be noted that the business opportunity processing method provided in the embodiment of the present application is generally executed by a server, and accordingly, the business opportunity processing device is generally set in the server.

[0042] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0043] Continue to refer Figure 2 , shows a flow chart of an embodiment of a business opportunity processing method according to the present application. The business opportunity processing method comprises the following steps:

[0044] Step S201, obtaining customer data of each customer, the customer data including the customer tag and historical consumption data of the customer, the historical consumption data including product information of the products purchased by the customer in the past and the associated salesperson identification.

[0045] In this embodiment, the business opportunity processing method is executed on the electronic device (eg Figure 1 The server shown in the figure can communicate with the terminal device through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G / 5G connection, Wi-Fi connection, Bluetooth connection, Wi MAX connection, Zigbee connection, UWB (Ultra Wi-Fi Band) connection, and other wireless connection methods currently known or to be developed in the future.

[0046] Among them, the customer can be a customer of a financial insurance company, and the customer data is the data related to the customer stored by the financial insurance company. The customer data includes the customer's customer identification (such as customer ID), customer tags, and historical consumption data; the customer tag reflects the customer's basic information, such as age, gender, interests, etc. The historical consumption data is the customer's past consumption record, including the product information of the purchased product and the salesperson identification of the salesperson associated with the purchase behavior.

[0047] Specifically, firstly, the customer data of each customer is obtained, for example, it can be obtained from the customer relationship management system (CRM) within the financial insurance company, for analysis and processing in subsequent steps.

[0048] Step S202: inputting customer data into a business opportunity value assessment model to obtain a business opportunity value score for each customer.

[0049] Specifically, the business opportunity value assessment model can be a rule model, or it can be built based on a neural network model, or it can be a combination of a rule model and a neural network model. The model can use the input customer data to assess the customer's business opportunity value and output each customer's business opportunity value score, which reflects the potential business opportunity value that the customer may bring. Business opportunities refer to opportunities for products or services that customers may purchase in the future, identified by analyzing and predicting customer behavior. The business opportunity value score is a value assessment of these opportunities. The higher the score, the higher the value.

[0050] Step S203: input the customer data into the business opportunity product recommendation model to obtain business opportunity products for each customer.

[0051] Specifically, the customer data is input into the business opportunity product recommendation model, which can be a rule model, a neural network model, or a combination of a rule model and a neural network model. The business opportunity product recommendation model analyzes the customer's consumption preferences based on the customer's historical consumption data and customer tags, and outputs business opportunity products suitable for the customer. The business opportunity product recommendation model can generate a list of business opportunity product recommendations for each customer, which are most likely to attract customers and lead to sales.

[0052] Step S204, obtaining the historical performance of each salesperson, and matching each customer with each salesperson through a business opportunity matching model based on the business opportunity value score of each customer and the historical performance of each salesperson, to obtain a business opportunity matching result.

[0053] Specifically, the historical performance of each salesperson in the financial insurance company is obtained, and the historical performance includes the salesperson's historical sales data and performance records.

[0054] The business opportunity matching model can be a rule model, a neural network model, or a combination of the rule model and the neural network model.

[0055] The business opportunity matching model uses the customer's business opportunity value score and the salesperson's historical performance data to match customers and salespeople. During the matching process, the customer's business opportunity value and the salesperson's performance record are considered to ensure that high-value customers are assigned to high-performance salespeople.

[0056] Step S205, determining a salesperson matching each customer according to the business opportunity matching result, and recommending business opportunity products targeted at the customer to the customer through the salesperson.

[0057] Specifically, based on the business opportunity matching results, the salesperson who matches each customer is determined. The salesperson recommends business opportunity products that meet the customer's needs based on the results of the business opportunity product recommendation model, ensuring that the recommended products are more targeted and improving the customer's purchasing intention and satisfaction.

[0058] In this embodiment, customer data of each customer is obtained, and the customer data includes the customer tag and historical consumption data of the customer, and the historical consumption data includes product information of products purchased by the customer in history and the associated salesperson identification; the customer data is input into a business opportunity value assessment model to assess the customer's business opportunity value and obtain a business opportunity value score for each customer; the customer data is input into a business opportunity product recommendation model to make personalized product recommendations for the customer and obtain business opportunity products for each customer; the business opportunity matching model combines the salesperson's historical performance and the customer's business opportunity value score for intelligent matching to ensure that high-value business opportunity customers can be assigned to the most suitable salesperson for follow-up, thereby improving business opportunity conversion rate and customer satisfaction; this application uses a business opportunity value assessment model to assess the customer's business opportunity value, and uses a business opportunity product recommendation model to predict business opportunity products for business opportunity customers, thereby improving the accuracy and efficiency of business opportunity processing, and optimizes resource allocation through the business opportunity matching model to further improve the business opportunity conversion rate.

[0059] Furthermore, the above-mentioned step of obtaining customer data of each customer may include: obtaining original customer data of each customer, and extracting all customer tags in the original customer data; calculating the coverage rate of each extracted customer tag in the original customer data; according to the obtained coverage rate, dividing each customer tag into a high-coverage tag or a low-coverage tag; for each customer, when there are missing low-coverage tags in the customer's original customer data, inputting the high-coverage tags in the customer's original customer data into the tag prediction model to obtain predicted tags; adding the obtained predicted tags to the customer's original customer data to obtain the customer data of the customer.

[0060] Specifically, the original customer data of each customer is obtained. The original customer data contains the basic information of the customer (such as name, contact information, etc.), customer tags (customer age, gender, geographic location, hobbies, occupation, income level, etc.) and historical consumption records (purchased products, amount, time, etc.). All customer tags in the original customer data are extracted, and the frequency of each customer tag in all original customer data is counted to obtain the coverage of the customer tags. Customer tags can be divided into high coverage tags or low coverage tags according to the preset coverage threshold; it can be considered that high coverage tags are customer tags with a high frequency in all original customer data, and low coverage tags are customer tags with a low frequency in all original customer data. For example, the coverage of the age tag is 95%, the coverage of the gender tag is 90%, and the coverage of the interest tag is 80%, which can be divided into high coverage tags. The coverage of the income level tag is 30%, and the coverage of the marital status tag is 40%, which can be divided into low coverage tags.

[0061] Use machine learning algorithms (such as decision trees, random forests, logistic regression, LightGBM, etc.) in advance to build a label prediction model. For each customer, if there are missing low-coverage labels in the original customer data (for example, there are no labels for income level and marital status), obtain the high-coverage labels in the original customer data of the customer (for example, ① age: 35 years old, ② gender: male, ③ interest: technology), and input them into the label prediction model to obtain the predicted labels (for example, the income level label is "middle income" and the marital status label is "married"). Then add the predicted labels to the original customer data of the customer, complete the missing low-coverage labels, and obtain the customer data. Label prediction can improve customer label coverage and data integrity: provide comprehensive information for subsequent analysis and processing.

[0062] In this embodiment, the original customer data of each customer is obtained, and all customer tags in the original customer data are extracted; the coverage rate of each customer tag in the original customer data is calculated, and the coverage rate represents the frequency of occurrence of the customer tag; according to the coverage rate, each customer tag is divided into a high-coverage tag or a low-coverage tag; for each customer, when there are missing low-coverage tags in the customer's original customer data, the high-coverage tags in the customer's original customer data are input into the tag prediction model to obtain the predicted tags, and the high-coverage tags are added to the customer's original customer data to obtain the customer data of the customer, and the low-coverage tags are filled in, thereby ensuring the comprehensiveness and accuracy of the customer data and ensuring the effectiveness of subsequent business opportunity value evaluation and product recommendation.

[0063] Furthermore, the above step S202 may include: determining a customer tag that has a high correlation with product information in the customer data of each customer as a product preference feature; combining the obtained product preference features to obtain multiple first feature combinations; grouping each customer according to each first feature combination to obtain multiple first customer groups; for each first customer group, calculating the purchase rate of each product in the first customer group; selecting the product corresponding to the highest purchase rate as the business opportunity product for each customer in the first customer group.

[0064] Specifically, from the customer data of each customer, customer tags with high correlation with product information are extracted as product preference features. High correlation tags refer to customer tags that are highly correlated with product information of the products purchased in the customer's historical consumption data.

[0065] The obtained product preference features are combined to form multiple first feature combinations, which represent different customer market segments and can reflect customer preferences for specific products. Customers are grouped according to each first feature combination to obtain multiple first customer groups, and customers in each first customer group have similar product preference features.

[0066] For each first customer group, the purchase rate of each product in the group is counted; the purchase rate refers to the frequency with which a product is purchased in the customer group. In each first customer group, the product with the highest purchase rate is selected as the business opportunity product for each customer in the customer group; this product is the most popular and most likely to be purchased product in the customer group.

[0067] For example, from the customer data of each customer, the customer tags "age group (20-30 years old)", "gender (male)", and "interest tag (interested in technology)" are highly correlated with the product information "electronic products". Then, the age group (20-30 years old) + gender (male) can be used as combination 1, the age group (20-30 years old) + interest tag (interested in technology) can be used as combination 2, and the age group (20-30 years old) + gender (male) + interest tag (interested in technology) can be used as combination 3.

[0068] Assume we have the following customer data:

[0069] Customer 1: 28 years old, male, interested in technology, has purchased electronic products;

[0070] Customer 2: 25 years old, male, not interested in technology, has purchased clothing;

[0071] Customer 3: 32 years old, female, interested in technology, has purchased electronic products;

[0072] Customer 4: 29 years old, male, interested in technology, no purchase history;

[0073] Customer 5: 22 years old, male, interested in sports, and has purchased sporting goods.

[0074] Then customer 1, customer 2, customer 4, and customer 5 all meet combination 1; customer 1, customer 3, and customer 4 meet combination 2; customer 1 and customer 4 meet combination 3. In combinations 1, 2, and 3, the purchase rates of electronic products are 25%, 33.33%, and 50% respectively. The purchase rate of electronic products is the highest in combination 3 (20-30 years old, male, interested in technology), and electronic products are recommended to customers in the customer group corresponding to combination 3.

[0075] In one embodiment, if a customer does not have historical consumption data, the customer can still be divided into customer groups based on customer characteristics, and the recommended products under the customer group are used as business opportunity products for this customer.

[0076] In this embodiment, a customer tag that has a high correlation with product information is determined in the customer data of each customer as a product preference feature; the obtained product preference features are combined to obtain a plurality of first feature combinations; each customer is grouped according to each first feature combination to obtain a plurality of first customer groups; the purchase rate of each product in each first customer group is calculated; and the product corresponding to the highest purchase rate is selected as the business opportunity product for each customer in the first customer group, thereby achieving accurate recommendation of business opportunity products that customers are most likely to be interested in, improving the accuracy of product recommendations and customer satisfaction, enhancing customers' interest in products and willingness to buy, and ensuring an increase in business opportunity conversion rate.

[0077] Furthermore, the above-mentioned step of determining customer tags with a high correlation with product information in the customer data of each customer as product preference features may include: extracting all customer tags and all product information from the customer data of each customer; calculating the correlation between each customer tag and each product information by a preset correlation algorithm; and based on the obtained correlation, extracting customer tags with a high correlation with each product information as product preference features of each customer.

[0078] Specifically, all customer tags (such as age, gender, interests, occupation, income level, etc.) and all product information in the customer's historical consumption data (such as product category, brand, price range, etc.) are extracted from each customer's customer data. These tags and product information reflect the customer's basic attributes and consumption behavior.

[0079] Use a preset correlation algorithm, such as Cramér's V coefficient, to calculate the correlation between each customer tag and each product information. Cramér's V coefficient is a statistic used to measure the strength of the association between two categorical variables. The value ranges from 0 to 1. The larger the value, the higher the correlation.

[0080] According to the calculated relevance, customer tags with a high relevance to the product information are selected (for example, customer tags with a relevance exceeding a relevance threshold can be selected). These highly relevance tags are determined as customer product preference features, which can accurately reflect the customer's purchasing tendency.

[0081] In one embodiment, after calculating the business opportunity products of each customer through the business opportunity product recommendation model, the business opportunity products of each customer are added to the customer data of the customer as new features, thereby ensuring that the mined preference features contain predicted product information.

[0082] In this embodiment, the correlation between each customer tag and each product information is accurately calculated through a correlation algorithm, and customer tags with high correlation are extracted as product preference features to accurately obtain the customer's purchasing tendency, which is conducive to achieving more accurate product recommendations and improving business opportunity conversion rate.

[0083] Furthermore, the above-mentioned step of matching each customer with each salesperson through a business opportunity matching model based on the business opportunity value score of each customer and the historical performance of each salesperson to obtain a business opportunity matching result may include: determining, through a preset correlation algorithm, a customer label with a high correlation with each salesperson identification in the customer data of each customer as a salesperson preference feature of each customer; combining the obtained salesperson preference features to obtain a plurality of second feature combinations; grouping each customer and each salesperson according to each second feature combination to obtain a second customer group and a second salesperson group corresponding to each second feature combination; for the second customer group and the second salesperson group corresponding to each second feature combination, matching each customer in the second customer group with each salesperson in the second salesperson group through a preset sorting matching algorithm based on the business opportunity value score of each customer in the second customer group and the historical performance of each salesperson in the second salesperson group to obtain a business opportunity matching result.

[0084] Specifically, through a preset correlation algorithm, a customer tag with a high correlation with each salesperson identification is determined in the customer data of each customer as the salesperson preference feature of each customer, and these preference features reflect the historical interaction and matching degree between the customer and the salesperson. The correlation algorithm can be the Cramér's V coefficient mentioned above.

[0085] The obtained salesperson preference features are combined to obtain multiple second feature combinations, each of which represents a matching pattern between a customer feature and a salesperson feature. According to each second feature combination, each customer and each salesperson are grouped to obtain a second customer group and a second salesperson group corresponding to each second feature combination, wherein each customer group and salesperson group have similar feature combinations.

[0086] For example, feature combination 3 is: age 30, male, interest is technology; feature combination 4 is: age 25, female, interest is fashion. The following customer data is available:

[0087] Customer A: 30 years old, male, interested in technology;

[0088] Customer B: 25 years old, female, interested in fashion;

[0089] Customer C: 30 years old, male, interested in technology.

[0090] The following salesperson data is available:

[0091] Salesman X: Good at dealing with customers who are "30 years old, male, and interested in technology";

[0092] Salesperson Y: Good at dealing with customers who are "25 years old, female, and interested in fashion."

[0093] Then customers A and C correspond to feature combination 3 and enter one customer group; customer B corresponds to feature combination 4 and enters another customer group. Salesman X enters a salesman group, and this salesman group corresponds to the customer group of customers A and C. Salesman Y enters another salesman group, and this salesman group corresponds to the customer group of customer B.

[0094] For the second customer group and the second salesperson group corresponding to each second feature combination, each customer in the second customer group is matched with each salesperson in the second salesperson group according to the business opportunity value score of each customer in the second customer group and the historical performance of each salesperson in the second salesperson group through a preset sorting and matching algorithm to obtain a business opportunity matching result. The sorting and matching algorithm ensures that high-value customers are matched with high-performance salespersons to optimize resource allocation.

[0095] In one embodiment, customers can be classified / segmented according to their business opportunity value scores to obtain business opportunity value segments, for example, business opportunity values ​​are subdivided into five levels, including extremely high value, high value, medium value, relatively low value, and relatively low value. Then, the second customer group is further subdivided and grouped according to the business opportunity value segments to obtain multiple third customer groups, and customers are matched in each of the third customer groups.

[0096] In this embodiment, through the correlation algorithm, a customer label with a high correlation with each salesperson identification is determined in the customer data of each customer as the salesperson preference feature of each customer; the obtained salesperson preference features are combined to obtain multiple second feature combinations; each customer and each salesperson is grouped according to each second feature combination to obtain a second customer group and a second salesperson group corresponding to each second feature combination, and the second customer group and the corresponding second salesperson group have similar feature combinations, ensuring the matching of customers and salespersons; for each group of corresponding second customer groups and second salesperson groups, based on the business opportunity value score of each customer in the second customer group and the historical performance of each salesperson in the second salesperson group, each customer in the second customer group is matched with each salesperson in the second salesperson group through a sorting matching algorithm to obtain a business opportunity matching result, ensuring that high-value customers are matched with the most suitable salesperson, thereby optimizing resource allocation and improving business opportunity conversion rate.

[0097] Furthermore, the above-mentioned step of matching each customer in the second customer group with each salesperson in the second salesperson group through a preset ranking and matching algorithm based on the business opportunity value score of each customer in the second customer group and the historical performance of each salesperson in the second salesperson group to obtain the business opportunity matching result may include: determining the customer ranking factor of each customer in the second customer group according to the business opportunity value score of each customer in the second customer group, and determining the salesperson ranking factor of each salesperson in the second salesperson group according to the historical performance of each salesperson in the second salesperson group; obtaining the number of customers in the second customer group and the number of salespersons in the second salesperson group; determining the customer matching factor of each customer in the second customer group and the salesperson matching factor of each salesperson in the second salesperson group according to the quantitative relationship between the number of customers and the number of salespersons, and the determined customer ranking factor and salesperson ranking factor; matching each customer in the second customer group with each salesperson in the second salesperson group according to the determined customer matching factor and salesperson matching factor, wherein customers and salespersons having the same values ​​of the customer matching factor and the salesperson matching factor are matched.

[0098] Specifically, according to the business opportunity value score of each customer in the second customer group, each customer is sorted in descending order to obtain the customer ranking factor σ of each customer: M Similarly, according to the historical performance of each salesperson in the second salesperson group, each salesperson is sorted in descending order to obtain the salesperson ranking factor σ of each salesperson N The customer ranking factor indicates the importance of the customer or the value of the potential business opportunity, and the salesperson ranking factor indicates the salesperson’s historical performance.

[0099] The number M of customers of the customers in the second customer group is obtained, and the number N of salesmen of the salesmen in the second salesmen group is obtained.

[0100] According to the quantitative relationship between the number of customers and the number of salesmen (i.e., the size relationship between the numbers), we can determine how to process the customer ranking factor and the salesman ranking factor, thereby obtaining the customer matching factor and the salesman matching factor. In other words, the quantitative relationship determines the matching strategy. The customer matching factor and the salesman matching factor are used to represent the matching relationship between customers and salesmen.

[0101] According to the determined customer matching factor and salesperson matching factor, customers in the second customer group are matched with salespersons in the second salesperson group. The customer matching factor and salesperson matching factor can be numbers with numerical values. The matching principle is that customers and salespersons with the same customer matching factor and salesperson matching factor can be matched.

[0102] In this embodiment, the customer ranking factor of the customer is determined based on the customer's business opportunity value score, and the salesperson ranking factor of the salesperson is determined based on the salesperson's historical performance; the matching strategy is determined based on the quantitative relationship between the number of customers in the second customer group and the number of salespersons in the second salesperson group, so that the customer ranking factor and the salesperson ranking factor are processed to obtain the customer matching factor and the salesperson matching factor; according to the customer matching factor and the salesperson matching factor, each customer and each salesperson are matched, and customers and salespersons with the same customer matching factor and salesperson matching factor are matched, and a sophisticated ranking and matching algorithm is used to ensure that high-value customers are matched with high-performance salespersons first, thereby improving the business opportunity conversion rate and customer satisfaction, and at the same time motivating the salesperson to improve their performance.

[0103] Furthermore, the above-mentioned step of determining the customer matching factor of each customer in the second customer group and the salesperson matching factor of each salesperson in the second salesperson group based on the quantitative relationship between the number of customers and the number of salespersons, as well as the determined customer ranking factor and salesperson ranking factor may include: when the number of customers is greater than or equal to the number of salespersons, calculating the maximum matching number based on the number of customers and the number of salespersons; determining the customer matching factor of each customer based on the maximum matching number and the customer ranking factor of each customer in the second customer group, and determining the salesperson ranking factor of each salesperson in the second salesperson group as the salesperson matching factor of each salesperson; when the number of customers is less than the number of salespersons, determining the customer ranking factor of each customer in the second customer group as the customer matching factor of each customer, and determining the salesperson ranking factor of each salesperson in the second salesperson group as the salesperson matching factor of each salesperson.

[0104] Specifically, when the number of customers is greater than or equal to the number of salesmen, the maximum matching number is calculated based on the number of customers M and the number of salesmen N. The maximum matching number refers to the maximum number of customers that each salesman can match, which is equal to the number of customers M divided by the number of salesmen N and rounded up. For example, if there are 10 customers and 3 salesmen, the maximum matching number is

[0105] At this time, the salesperson ranking factor σ of each salesperson in the second salesperson group is N Determine the salesperson matching factor for each salesperson. According to the maximum matching number and the customer ranking factor σ of each customer in the second customer group M , determine the customer matching factor ceil(σ M / ceil(m / n)); where ceil is the abbreviation of "ceil ing", which is usually used in mathematics and computing to represent the ceiling function.

[0106] When the number of customers is less than the number of salesmen, the customer ranking factor σ of each customer in the second customer group is increased. M Determine the customer matching factor for each customer. Set the salesperson ranking factor σ of each salesperson in the second salesperson group N A salesperson matching factor is determined for each salesperson.

[0107] For example, when the number of customers is greater than the number of salesmen, there are 10 customers and 3 salesmen, and the customer ranking factor σ M They are 1 to 10 respectively. Each salesperson needs to handle customers.

[0108] The customer matching factor is They are 1,1,1,1,2,2,2,2,3,3 respectively.

[0109] The matching is as follows:

[0110] Salesman 1: Customers 1, 2, 3, 4;

[0111] Salesman 2: Customers 5, 6, 7, 8;

[0112] Salesman 3: Customers 9, 10.

[0113] When the number of customers is less than the number of salesmen, there are 5 customers and 8 salesmen, and the customer ranking factor σ M The salesperson ranking factor σ is 1 to 5 respectively. N They are 1 to 8. Each customer is directly assigned a salesperson, and the remaining salespersons have no customers.

[0114] The matching is as follows:

[0115] Customer 1: Salesperson 1;

[0116] Customer 2: Salesperson 2;

[0117] Customer 3: Salesperson 3;

[0118] Customer 4: Salesperson 4;

[0119] Customer 5: Salesperson 5;

[0120] Salesman 6, 7, 8: No customers.

[0121] In this embodiment, the matching strategy is flexibly adjusted according to whether the number of customers is equal to the number of salesmen to ensure the effective use of resources; whether the number of customers is more than the salesmen or the number of salesmen is more than the customers, the setting of the matching factor can optimize the matching effect, improve the business opportunity conversion rate and the work performance of the salesmen.

[0122] It should be emphasized that in order to further ensure the privacy and security of the above customer data, the above customer data can also be stored in a blockchain node.

[0123] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0124] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0125] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0126] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0127] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0128] Further references Figure 3 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a business opportunity processing device, and the device embodiment is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0129] like Figure 3 As shown, the business opportunity processing device 300 described in this embodiment includes: a data acquisition module 301, a value scoring module 302, a product determination module 303, a business opportunity matching module 304 and a product recommendation module 305, wherein:

[0130] The data acquisition module 301 is used to acquire the customer data of each customer. The customer data includes the customer tag and historical consumption data of the customer. The historical consumption data includes the product information of the products purchased by the customer in the past and the associated salesperson identification.

[0131] The value scoring module 302 is used to input customer data into the business opportunity value evaluation model to obtain a business opportunity value score for each customer.

[0132] The product determination module 303 is used to input customer data into the business opportunity product recommendation model to obtain business opportunity products for each customer.

[0133] The business opportunity matching module 304 is used to obtain the historical performance of each salesperson, and based on the business opportunity value score of each customer and the historical performance of each salesperson, match each customer with each salesperson through a business opportunity matching model to obtain a business opportunity matching result.

[0134] The product recommendation module 305 is used to determine a salesperson matching each customer according to the business opportunity matching result, and recommend business opportunity products targeted at the customer to the customer through the salesperson.

[0135] In this embodiment, customer data of each customer is obtained, and the customer data includes the customer tag and historical consumption data of the customer, and the historical consumption data includes product information of products purchased by the customer in history and the associated salesperson identification; the customer data is input into a business opportunity value assessment model to assess the customer's business opportunity value and obtain a business opportunity value score for each customer; the customer data is input into a business opportunity product recommendation model to make personalized product recommendations for the customer and obtain business opportunity products for each customer; the business opportunity matching model combines the salesperson's historical performance and the customer's business opportunity value score for intelligent matching to ensure that high-value business opportunity customers can be assigned to the most suitable salesperson for follow-up, thereby improving business opportunity conversion rate and customer satisfaction; this application uses a business opportunity value assessment model to assess the customer's business opportunity value, and uses a business opportunity product recommendation model to predict business opportunity products for business opportunity customers, thereby improving the accuracy and efficiency of business opportunity processing, and optimizes resource allocation through the business opportunity matching model to further improve the business opportunity conversion rate.

[0136] In some optional implementations of this embodiment, the data acquisition module 301 may include: an original acquisition submodule, a coverage calculation submodule, a label division submodule, a label prediction submodule, and a prediction addition submodule, wherein:

[0137] The original acquisition submodule is used to obtain the original customer data of each customer and extract all customer tags in the original customer data.

[0138] The coverage calculation submodule is used to calculate the coverage of each extracted customer label in the original customer data.

[0139] The label division submodule is used to divide each customer label into a high coverage label or a low coverage label according to the obtained coverage rate.

[0140] The label prediction submodule is used for inputting the high coverage labels in the original customer data of each customer into the label prediction model to obtain the predicted labels when there are missing low coverage labels in the original customer data of the customer.

[0141] The prediction adding submodule is used to add the obtained prediction label to the original customer data of the customer to obtain the customer data of the customer.

[0142] In this embodiment, the original customer data of each customer is obtained, and all customer tags in the original customer data are extracted; the coverage rate of each customer tag in the original customer data is calculated, and the coverage rate represents the frequency of occurrence of the customer tag; according to the coverage rate, each customer tag is divided into a high-coverage tag or a low-coverage tag; for each customer, when there are missing low-coverage tags in the customer's original customer data, the high-coverage tags in the customer's original customer data are input into the tag prediction model to obtain the predicted tags, and the high-coverage tags are added to the customer's original customer data to obtain the customer data of the customer, and the low-coverage tags are filled in, thereby ensuring the comprehensiveness and accuracy of the customer data and ensuring the effectiveness of subsequent business opportunity value evaluation and product recommendation.

[0143] In some optional implementations of this embodiment, the value scoring module 302 may include: a preference determination submodule, a preference combination submodule, a first grouping submodule, a purchase rate calculation submodule, and a product determination submodule, wherein:

[0144] The preference determination submodule is used to determine, in the customer data of each customer, a customer tag that has a high correlation with the product information as a product preference feature.

[0145] The preference combination submodule is used to combine the obtained product preference features to obtain multiple first feature combinations.

[0146] The first grouping submodule is used to group each customer according to each first feature combination to obtain multiple first customer groups.

[0147] The purchase rate calculation submodule is used to calculate the purchase rate of each product in the first customer group for each first customer group.

[0148] The product determination submodule is used to select the product corresponding to the highest purchase rate as the business opportunity product for each customer in the first customer group.

[0149] In this embodiment, a customer tag that has a high correlation with product information is determined in the customer data of each customer as a product preference feature; the obtained product preference features are combined to obtain a plurality of first feature combinations; each customer is grouped according to each first feature combination to obtain a plurality of first customer groups; the purchase rate of each product in each first customer group is calculated; and the product corresponding to the highest purchase rate is selected as the business opportunity product for each customer in the first customer group, thereby achieving accurate recommendation of business opportunity products that customers are most likely to be interested in, improving the accuracy of product recommendations and customer satisfaction, enhancing customers' interest in products and willingness to buy, and ensuring an increase in business opportunity conversion rate.

[0150] In some optional implementations of this embodiment, the preference determination submodule may include: an extraction unit, a relevance calculation unit, and a label determination unit, wherein:

[0151] The extraction unit is used to extract all customer tags and all product information from the customer data of each customer.

[0152] The correlation calculation unit is used to calculate the correlation between each customer tag and each product information by using a preset correlation algorithm.

[0153] The label determination unit is used to extract customer labels with high correlation with each product information as product preference features of each customer according to the obtained correlation.

[0154] In this embodiment, the correlation between each customer tag and each product information is accurately calculated through a correlation algorithm, and customer tags with high correlation are extracted as product preference features to accurately obtain the customer's purchasing tendency, which is conducive to achieving more accurate product recommendations and improving business opportunity conversion rate.

[0155] In some optional implementations of this embodiment, the business opportunity matching module 304 may include: a label determination submodule, a feature combination submodule, a second grouping submodule, and a business opportunity matching submodule, wherein:

[0156] The label determination submodule is used to determine, through a preset correlation algorithm, a customer label with a high correlation with each salesperson identification in the customer data of each customer as the salesperson preference feature of each customer.

[0157] The feature combination submodule is used to combine the obtained salesperson preference features to obtain multiple second feature combinations.

[0158] The second grouping submodule is used to group each customer and each salesperson according to each second feature combination, and obtain a second customer group and a second salesperson group corresponding to each second feature combination.

[0159] The business opportunity matching submodule is used to match each customer in the second customer group with each salesperson in the second salesperson group corresponding to each second feature combination based on the business opportunity value score of each customer in the second customer group and the historical performance of each salesperson in the second salesperson group, through a preset sorting and matching algorithm to obtain business opportunity matching results.

[0160] In this embodiment, through the correlation algorithm, a customer label with a high correlation with each salesperson identification is determined in the customer data of each customer as the salesperson preference feature of each customer; the obtained salesperson preference features are combined to obtain multiple second feature combinations; each customer and each salesperson is grouped according to each second feature combination to obtain a second customer group and a second salesperson group corresponding to each second feature combination, and the second customer group and the corresponding second salesperson group have similar feature combinations, ensuring the matching of customers and salespersons; for each group of corresponding second customer groups and second salesperson groups, based on the business opportunity value score of each customer in the second customer group and the historical performance of each salesperson in the second salesperson group, each customer in the second customer group is matched with each salesperson in the second salesperson group through a sorting matching algorithm to obtain a business opportunity matching result, ensuring that high-value customers are matched with the most suitable salesperson, thereby optimizing resource allocation and improving business opportunity conversion rate.

[0161] In some optional implementations of this embodiment, the business opportunity matching submodule may include: a ranking determination unit, a quantity acquisition unit, a factor determination unit, and a matching unit, wherein:

[0162] The ranking determination unit is used to determine the customer ranking factor of each customer in the second customer group according to the business opportunity value score of each customer in the second customer group, and to determine the salesperson ranking factor of each salesperson in the second salesperson group according to the historical performance of each salesperson in the second salesperson group.

[0163] The quantity acquisition unit is used to acquire the number of customers in the second customer group and the number of salesmen in the second salesmen group.

[0164] The factor determination unit is used to determine the customer matching factor of each customer in the second customer group and the salesperson matching factor of each salesperson in the second salesperson group according to the quantitative relationship between the number of customers and the number of salespersons, as well as the determined customer ranking factor and salesperson ranking factor.

[0165] The matching unit is used to match each customer in the second customer group with each salesperson in the second salesperson group according to the determined customer matching factor and salesperson matching factor, wherein customers and salespersons with the same customer matching factor and salesperson matching factor are matched.

[0166] In this embodiment, the customer ranking factor of the customer is determined based on the customer's business opportunity value score, and the salesperson ranking factor of the salesperson is determined based on the salesperson's historical performance; the matching strategy is determined based on the quantitative relationship between the number of customers in the second customer group and the number of salespersons in the second salesperson group, so that the customer ranking factor and the salesperson ranking factor are processed to obtain the customer matching factor and the salesperson matching factor; according to the customer matching factor and the salesperson matching factor, each customer and each salesperson are matched, and customers and salespersons with the same customer matching factor and salesperson matching factor are matched, and a sophisticated ranking and matching algorithm is used to ensure that high-value customers are matched with high-performance salespersons first, thereby improving the business opportunity conversion rate and customer satisfaction, and at the same time motivating the salesperson to improve their performance.

[0167] In some optional implementations of this embodiment, the factor determination unit may include: a quantity calculation subunit, a first determination subunit, and a second determination subunit, wherein:

[0168] The quantity calculation subunit is used to calculate the maximum matching quantity based on the number of customers and the number of salesmen when the number of customers is greater than or equal to the number of salesmen.

[0169] The first determination subunit is used to determine the customer matching factor of each customer according to the maximum matching number and the customer ranking factor of each customer in the second customer group, and determine the salesperson ranking factor of each salesperson in the second salesperson group as the salesperson matching factor of each salesperson.

[0170] The second determination subunit is used to determine the customer ranking factor of each customer in the second customer group as the customer matching factor of each customer, and to determine the salesperson ranking factor of each salesperson in the second salesperson group as the salesperson matching factor of each salesperson when the number of customers is less than the number of salespersons.

[0171] In this embodiment, the matching strategy is flexibly adjusted according to whether the number of customers is equal to the number of salesmen to ensure the effective use of resources; whether the number of customers is more than the salesmen or the number of salesmen is more than the customers, the setting of the matching factor can optimize the matching effect, improve the business opportunity conversion rate and the work performance of the salesmen.

[0172] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0173] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital processors (DSPs), embedded devices, etc.

[0174] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0175] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the business opportunity processing method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0176] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the business opportunity processing method.

[0177] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0178] The computer device provided in this embodiment can execute the above-mentioned business opportunity processing method. Here, the business opportunity processing method can be the business opportunity processing method of each of the above-mentioned embodiments.

[0179] In this embodiment, customer data of each customer is obtained, and the customer data includes the customer tag and historical consumption data of the customer, and the historical consumption data includes product information of products purchased by the customer in history and the associated salesperson identification; the customer data is input into a business opportunity value assessment model to assess the customer's business opportunity value and obtain a business opportunity value score for each customer; the customer data is input into a business opportunity product recommendation model to make personalized product recommendations for the customer and obtain business opportunity products for each customer; the business opportunity matching model combines the salesperson's historical performance and the customer's business opportunity value score for intelligent matching to ensure that high-value business opportunity customers can be assigned to the most suitable salesperson for follow-up, thereby improving business opportunity conversion rate and customer satisfaction; this application uses a business opportunity value assessment model to assess the customer's business opportunity value, and uses a business opportunity product recommendation model to predict business opportunity products for business opportunity customers, thereby improving the accuracy and efficiency of business opportunity processing, and optimizes resource allocation through the business opportunity matching model to further improve the business opportunity conversion rate.

[0180] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the business opportunity processing method as described above.

[0181] In this embodiment, customer data of each customer is obtained, and the customer data includes the customer tag and historical consumption data of the customer, and the historical consumption data includes product information of products purchased by the customer in history and the associated salesperson identification; the customer data is input into a business opportunity value assessment model to assess the customer's business opportunity value and obtain a business opportunity value score for each customer; the customer data is input into a business opportunity product recommendation model to make personalized product recommendations for the customer and obtain business opportunity products for each customer; the business opportunity matching model combines the salesperson's historical performance and the customer's business opportunity value score for intelligent matching to ensure that high-value business opportunity customers can be assigned to the most suitable salesperson for follow-up, thereby improving business opportunity conversion rate and customer satisfaction; this application uses a business opportunity value assessment model to assess the customer's business opportunity value, and uses a business opportunity product recommendation model to predict business opportunity products for business opportunity customers, thereby improving the accuracy and efficiency of business opportunity processing, and optimizes resource allocation through the business opportunity matching model to further improve the business opportunity conversion rate.

[0182] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0183] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A business opportunity processing method, characterized in that: The steps include: Obtain customer data of each customer, including the customer's customer tag and historical consumption data. The historical consumption data includes product information of products purchased by the customer in the past and the associated salesperson ID; Inputting the customer data into a business opportunity value assessment model to obtain a business opportunity value score for each customer; Inputting the customer data into a business opportunity product recommendation model to obtain business opportunity products for each customer; Obtaining the historical performance of each salesperson, and matching each customer with each salesperson through a business opportunity matching model based on the business opportunity value score of each customer and the historical performance of each salesperson, to obtain a business opportunity matching result; A salesperson matching each customer is determined according to the business opportunity matching result, and a business opportunity product targeting the customer is recommended to the customer through the salesperson.

2. The business opportunity processing method according to claim 1, characterized in that: The step of obtaining the customer data of each customer comprises: Obtaining original customer data of each customer, and extracting all customer tags in the original customer data; Calculating the coverage of each extracted customer tag in the original customer data; According to the obtained coverage rate, each customer tag is classified as a high coverage tag or a low coverage tag; For each customer, when there are missing low-coverage labels in the original customer data of the customer, the high-coverage labels in the original customer data of the customer are input into the label prediction model to obtain a predicted label; The obtained prediction label is added to the original customer data of the customer to obtain the customer data of the customer.

3. The business opportunity processing method according to claim 1, characterized in that: The step of inputting the customer data into the business opportunity product recommendation model to obtain business opportunity products for each customer comprises: determining, in the customer data of each customer, a customer tag having a high correlation with the product information as a product preference feature; Combining the obtained product preference features to obtain multiple first feature combinations; Grouping the customers according to the first feature combinations to obtain a plurality of first customer groups; For each first customer group, calculating the purchase rate of each product in the first customer group; The product corresponding to the highest purchase rate is selected as the business opportunity product for each customer in the first customer group.

4. The business opportunity processing method according to claim 3, characterized in that: The step of determining a customer tag having a high correlation with product information in the customer data of each customer as a product preference feature comprises: Extract all customer tags and all product information from the customer data of each customer; Calculate the correlation between each customer tag and each product information through a preset correlation algorithm; According to the obtained correlation, customer tags having a high correlation with the product information are extracted as product preference features of the customers.

5. The business opportunity processing method according to claim 1, characterized in that: The step of matching each customer with each salesperson through a business opportunity matching model based on the business opportunity value score of each customer and the historical performance of each salesperson to obtain a business opportunity matching result comprises: By using a preset correlation algorithm, determining a customer tag having a high correlation with each salesperson identification in the customer data of each customer as the salesperson preference feature of each customer; Combining the obtained preference features of each salesperson to obtain multiple second feature combinations; The customers and the salesmen are grouped according to the second feature combinations to obtain second customer groups and second salesmen groups corresponding to the second feature combinations; For the second customer group and second salesperson group corresponding to each second feature combination, based on the business opportunity value score of each customer in the second customer group and the historical performance of each salesperson in the second salesperson group, each customer in the second customer group is matched with each salesperson in the second salesperson group through a preset sorting and matching algorithm to obtain a business opportunity matching result.

6. The business opportunity processing method according to claim 5, characterized in that: The step of matching each customer in the second customer group with each salesperson in the second salesperson group by a preset sorting and matching algorithm based on the business opportunity value score of each customer in the second customer group and the historical performance of each salesperson in the second salesperson group to obtain a business opportunity matching result comprises: Determine a customer ranking factor for each customer in the second customer group based on the business opportunity value score of each customer in the second customer group, and determine a salesperson ranking factor for each salesperson in the second salesperson group based on the historical performance of each salesperson in the second salesperson group; Obtain the number of customers in the second customer group, and obtain the number of salesmen in the second salesmen group; Determine a customer matching factor for each customer in the second customer group and a salesperson matching factor for each salesperson in the second salesperson group according to the quantitative relationship between the number of customers and the number of salespersons, and the determined customer ranking factor and salesperson ranking factor; According to the determined customer matching factor and salesperson matching factor, each customer in the second customer group is matched with each salesperson in the second salesperson group, wherein customers and salespersons having the same customer matching factor and salesperson matching factor are matched.

7. The business opportunity processing method according to claim 6, characterized in that: The step of determining the customer matching factor of each customer in the second customer group and the salesperson matching factor of each salesperson in the second salesperson group according to the quantitative relationship between the number of customers and the number of salespersons, and the determined customer ranking factor and salesperson ranking factor comprises: When the number of customers is greater than or equal to the number of salesmen, the maximum matching number is calculated according to the number of customers and the number of salesmen; Determine the customer matching factor of each customer according to the maximum matching number and the customer ranking factor of each customer in the second customer group, and determine the salesperson ranking factor of each salesperson in the second salesperson group as the salesperson matching factor of each salesperson; When the number of customers is less than the number of salesmen, the customer ranking factor of each customer in the second customer group is determined as the customer matching factor of each customer, and the salesman ranking factor of each salesman in the second salesman group is determined as the salesman matching factor of each salesman.

8. A business opportunity processing device, characterized in that: include: The data acquisition module is used to acquire the customer data of each customer, the customer data includes the customer's customer tag and historical consumption data, the historical consumption data includes the product information of the products purchased by the customer in the past and the associated salesperson identification; A value scoring module, used to input the customer data into a business opportunity value assessment model to obtain a business opportunity value score for each customer; A product determination module, used for inputting the customer data into a business opportunity product recommendation model to obtain business opportunity products for each customer; A business opportunity matching module is used to obtain the historical performance of each salesperson, and based on the business opportunity value score of each customer and the historical performance of each salesperson, match each customer with each salesperson through a business opportunity matching model to obtain a business opportunity matching result; The product recommendation module is used to determine a salesperson who matches each customer according to the business opportunity matching result, and recommend business opportunity products for the customer to the customer through the salesperson.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the business opportunity processing method according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the business opportunity processing method according to any one of claims 1 to 7 are implemented.

Images