Data processing method and system based on customer intention analysis

Abstract

The invention discloses a customer intention analysis-based data processing method and system, and a server side method comprises the steps that to-be-analyzed data is collected, the to-be-analyzed data comprises historical sales business data and interaction data of a target customer, and the interaction data is generated by interaction between a salesman and the target customer in a preset time period; performing customer intention analysis on the to-be-analyzed data according to a preset data quantification condition of each customer intention level to obtain a customer intention level corresponding to the target customer; according to the customer intention level, obtaining corresponding sales strategy data from a pre-constructed mapping relation between the customer intention level and sales strategy data; and sending the sales strategy data to a client belonging to a salesman for data display. Therefore, by adopting the embodiment of the invention, automatic generation of the sales strategy data and standardization of sales strategy promotion can be realized, large-scale and online sales management can be realized, and meanwhile, the accuracy of customer intention analysis is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a data processing method and system based on customer intention analysis. Background Art

[0002] In modern business activities, the management and optimization of the sales process is the key to improving corporate competitiveness. Especially in situations involving a large number of potential customers and complex sales processes, such as B2B sales, large equipment sales, or service-oriented product sales, accurately assessing customer purchase intentions and formulating corresponding sales strategies are crucial to improving conversion rates and sales efficiency.

[0003] In related technologies, it is common to rely on the salesperson's personal experience and intuition to evaluate the customer's purchase intention and formulate sales strategy data accordingly. In addition, some companies use customer relationship management (CRM) systems to track customer interactions and sales activities, and assist users in formulating sales strategy data by manually entering and updating customer information. Since the salesperson's evaluation of the customer's purchase intention is often based on personal experience and intuition, the evaluation results are inaccurate. At the same time, although the existing CRM system can collect customer data, it often lacks effective data analysis and processing capabilities and cannot automatically generate sales strategy data. Summary of the invention

[0004] The embodiments of the present application provide a data processing method and system based on customer intention analysis. In order to have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary is not a general review, nor is it intended to identify key / important components or describe the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a preface to the detailed description that follows.

[0005] In a first aspect, an embodiment of the present application provides a data processing method based on customer intention analysis, which is applied to a server, and the method includes: Collect data to be analyzed, including historical sales business data and interaction data of target customers. Interaction data is generated by the interaction between salespersons and target customers within a preset time period. According to the data quantification conditions for the preset intention level of each customer, customer intention analysis is performed on the data to be analyzed to obtain the customer intention level corresponding to the target customer; wherein the data quantification conditions for the preset intention level of each customer are obtained by binding the data quantification conditions for the preset intention level input of each customer, and the preset intention level of each customer is obtained based on the historical communication record text and historical purchase behavior information of each customer, and the historical communication record text and historical purchase behavior information of each customer are obtained based on the collection and pre-processing of historical sales case data; According to the customer intention level, corresponding sales strategy data is obtained from a pre-built mapping relationship between the customer intention level and the sales strategy data; Send the sales strategy data belonging to the target customer to the client belonging to the salesperson for data display.

[0006] Optionally, the data quantification conditions for presetting each customer intention level are generated according to the following steps, including: Collect and pre-process historical sales case data to obtain each customer's historical communication record text and historical purchase behavior information; Generate each customer's historical customer intention level based on each customer's historical communication record text and historical purchase behavior information; The historical customer intention level of each customer is stored as a set; Merging repeated historical customer intention levels in the set to obtain a plurality of preset customer intention levels; The data quantification conditions input for each preset customer intention level are received and bound to obtain the data quantification conditions for each preset customer intention level.

[0007] Optionally, based on each customer's historical communication record text and historical purchase behavior information, generate each customer's historical customer intention level, including: Perform stem extraction or lemmatization on the text of each customer's historical communication records to obtain each customer's standard communication records; The order transaction data contained in the historical purchase behavior information of each customer is sorted to obtain the standard purchase behavior of each customer; Generate text features of keywords and phrases based on standard communication records, and generate numerical features related to purchase frequency, average transaction amount, and last purchase time based on standard purchase behavior, to obtain text features and numerical features for each customer; Based on the text features and numerical features of each customer, calculate the historical customer intention of each customer; From the pre-constructed mapping relationship between historical customer intention degree intervals and customer intention degree levels, the customer intention degree level corresponding to the historical customer intention degree interval containing the historical customer intention degree of each customer is obtained as the historical customer intention degree level of each customer.

[0008] Optionally, the historical customer intention of each customer is calculated based on the text features and numerical features of each customer, including: Count the probability of the preset keywords appearing from the text features of each customer; Extract purchase frequency, average transaction amount, and last purchase time from the numerical features of each customer; According to historical business data, weights are dynamically assigned to the probability of occurrence of preset keywords, purchase frequency, average transaction amount, and last purchase time to obtain probability weight, frequency weight, amount weight, and time weight; The probability of occurrence of the preset keywords, purchase frequency, average transaction amount, and last purchase time are standardized to a range of 0-1 to obtain probability values, frequency values, amount values, and time values; Use probability weight, frequency weight, amount weight and time weight to weight the probability value, frequency value, amount value and time value respectively; Sum the weighted results to get the historical customer intention of each customer;

[0009] in, For each customer's historical customer intention, is the probability weight, is the frequency weight, is the amount weight, is the time weight, is the probability value, is the frequency value, is the amount value, is the time value, + + + =1.

[0010] Optionally, based on historical business data, dynamically assign weights to the probability of occurrence of preset keywords, purchase frequency, average transaction amount, and last purchase time, including: Based on historical business data, obtain quantitative indicators of customer purchase intention as the dependent variable; The probability of occurrence of preset keywords, purchase frequency, average transaction amount, and last purchase time were used as independent variables; Calculate the means of the dependent and independent variables respectively; The Pearson correlation coefficient of each independent variable is calculated using the dependent variable and the independent variable, and the mean of the dependent variable and the independent variable, to determine the correlation between the probability of occurrence of the preset keywords, purchase frequency, average transaction amount, last purchase time and customer purchase intention; According to the size of the Pearson correlation coefficient of each independent variable, the probability of occurrence of the preset keywords, purchase frequency, average transaction amount, and last purchase time are dynamically assigned weights; among them,

[0011] in, is the Pearson correlation coefficient for each independent variable, is the independent variable, is the dependent variable, and are the means of the independent and dependent variables, respectively.

[0012] Optionally, the data quantification conditions for each customer intention level are preset to include a keyword occurrence frequency condition, a purchase frequency condition, an average transaction amount condition, and a last purchase time condition; According to the data quantification conditions for each customer intention level, customer intention analysis is performed on the data to be analyzed to obtain the customer intention level corresponding to the target customer, including: Generate target text features for target customers based on interaction data; Based on historical sales business data, generate numerical features related to purchase frequency, average transaction amount, and last purchase time to obtain target numerical features of target customers; Based on the target text features of target customers, the target probability of the preset keywords appearing is calculated; Based on the target numerical characteristics of target customers, statistics are collected on the target purchase frequency, target average transaction amount, and target last purchase time; Compare the target probability with the keyword occurrence frequency condition to obtain a first comparison result; Compare the target purchase frequency, the target average transaction amount, and the target last purchase time with the purchase frequency condition, the average transaction amount condition, and the last purchase time condition, respectively, to obtain a second comparison result; According to the first comparison result and the second comparison result, the optimal customer intention level is obtained from each preset customer intention level as the customer intention level corresponding to the target customer.

[0013] Optionally, according to the first comparison result and the second comparison result, obtaining the optimal customer intention level from each preset customer intention level as the customer intention level corresponding to the target customer includes: In the case where the preset customer intention level corresponding to the first comparison result and the preset customer intention level corresponding to the second comparison result are the same, the preset customer intention level is used as the customer intention level corresponding to the target customer; or When the preset customer intention level corresponding to the first comparison result is not the same as the preset customer intention level corresponding to the second comparison result, the preset customer intention level that meets the most conditions is determined, and the preset customer intention level that meets the most conditions is used as the customer intention level corresponding to the target customer.

[0014] Optionally, the following steps are performed to generate a pre-built mapping relationship between customer intention levels and sales strategy data, including: Receiving sales strategy data input for each preset customer intention level, and obtaining sales strategy data for each preset customer intention level; the sales strategy data includes strategy information for providing personalized discounts, strategy information for information education and product display, and strategy information for improving brand and product awareness; The mapping relationship between each preset customer intention level and the sales strategy data of each preset customer intention level is stored to obtain the pre-constructed mapping relationship between the customer intention level and the sales strategy data.

[0015] Optionally, after sending the sales strategy data belonging to the target customer to the client of the salesperson for data display, the method further includes: Collecting in real time the first interaction data and the first sales business data generated by the interaction between the salesperson and the target customer within a preset time period; Generate a first text feature of the target customer and a first numerical feature of the target customer according to the first interaction data and the first sales business data; Determining current sales strategy data of the target customer based on the first text feature of the target customer and the first numerical feature of the target customer; Compare the current sales strategy data of the target customer with the sales strategy data displayed by the salesperson's client to see if they are consistent, so as to determine whether the salesperson is advancing according to the displayed sales strategy data and obtain a determination result; The judgment results are sent to the administrator's client for data display.

[0016] In a second aspect, an embodiment of the present application provides a data processing system based on customer intention analysis, the system comprising: A data collection module is used to collect data to be analyzed, which includes historical sales business data and interaction data of target customers. The interaction data is generated by the interaction between the salesperson and the target customer within a preset time period; A customer intention analysis processing module is used to perform customer intention analysis on the data to be analyzed according to the data quantification conditions preset for each customer intention level, and obtain the customer intention level corresponding to the target customer; wherein the data quantification conditions preset for each customer intention level are obtained by binding the data quantification conditions input for each customer intention level, and the preset intention level of each customer is obtained based on the historical communication record text and historical purchase behavior information of each customer, and the historical communication record text and historical purchase behavior information of each customer are obtained based on the collection and pre-processing of historical sales case data; A sales strategy data acquisition module is used to acquire corresponding sales strategy data from a pre-built mapping relationship between customer intention levels and sales strategy data according to the customer intention level; The sales strategy data display module is used to send the sales strategy data belonging to the target customer to the client of the salesperson for data display.

[0017] The technical solution provided by the embodiments of the present application may have the following beneficial effects: In the embodiments of the present application, on the one hand, the present application provides data quantification conditions for pre-setting each customer intention level and a pre-built mapping relationship between customer intention levels and sales strategy data. Therefore, through an automated data analysis process, it is possible to quickly and accurately automatically match customers with corresponding intention levels and automatically generate specific sales strategy data, thereby ensuring that the formulation of all sales strategies is based on unified standards and processes, thereby improving the consistency of strategy execution; on the other hand, historical sales business data and interaction data of target customers are collected, and these data include interaction records between salespeople and target customers within a preset time period, and these data are used to conduct in-depth customer intention analysis. Through precise data analysis, the understanding of customer intentions and the accuracy of prediction are improved.

[0018] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0020] Figure 1 It is a flowchart of a data processing method based on customer intention analysis provided in an embodiment of the present application; Figure 2 This is a data representation intent of historical sales business data provided by this application; Figure 3 It is a data representation intent of interactive data provided by this application; Figure 4 It is a data representation intent of a data quantification condition provided by this application; Figure 5 This is a data representation of the mapping relationship between customer intention level and sales strategy data provided by this application; Figure 6 It is a client interface schematic diagram of sales strategy data displayed by a sales client provided by the present application; Figure 7 It is a structural diagram of a data processing system based on customer intention analysis provided by this application; Figure 8 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] The following description and the accompanying drawings sufficiently illustrate specific embodiments of the present application to enable those skilled in the art to practice them.

[0022] It should be clear that the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0023] When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are only examples of systems and methods consistent with some aspects of the present application as detailed in the attached claims.

[0024] In the description of the present application, it should be understood that the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances. In addition, in the description of the present application, unless otherwise specified, "multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0025] The present application provides a data processing method and system based on customer intention analysis to solve the problems existing in the above-mentioned related technical problems. In the embodiments of the present application, on the one hand, the present application provides data quantification conditions for presetting each customer intention level and a mapping relationship between the pre-built customer intention level and sales strategy data, so that through the automated data analysis process, it is possible to quickly and accurately automatically match the customer to the corresponding intention level and automatically generate specific sales strategy data, thereby ensuring that the formulation of all sales strategies is based on unified standards and processes, and improving the consistency of strategy execution; on the other hand, the historical sales business data and interaction data of the target customers are collected, and these data include the interaction records between the salesperson and the target customer within a preset time period, and use these data to conduct in-depth customer intention analysis. Through precise data analysis, the understanding of customer intentions and the accuracy of prediction are improved. The following uses an exemplary embodiment for detailed description.

[0026] The following will be combined with the attached Figure 1 -Attached Figure 6, a data processing method based on customer intention analysis provided in an embodiment of the present application is introduced in detail. The method can be implemented by a computer program and can be run on a data processing system based on customer intention analysis based on the von Neumann system. The computer program can be integrated into an application or run as an independent tool application.

[0027] See also Figure 1 , which is a flowchart of a data processing method based on customer intention analysis, applied to the server. Figure 1 As shown, the method of the embodiment of the present application may include the following steps: S101, collecting data to be analyzed, where the data to be analyzed includes historical sales business data and interaction data of target customers, where the interaction data is generated by the interaction between the salesperson and the target customer within a preset time period; Among them, the data to be analyzed refers to those data sets that have not yet been analyzed and processed. Target customers refer to specific customer groups or individuals in sales activities who are selected for sales strategy application. Historical sales business data refers to the past sales records, transaction history and related business interaction information involving target customers. Interaction data records the communication and interaction between salespeople and target customers, such as calls, meetings, emails, etc. The preset time period is a specific time range defined in advance during the analysis process, which is used to limit the time limit for collecting interaction data.

[0028] In some embodiments of the present application, for example, a "target customer" is a customer who has a purchase record of a certain brand in the past year, and the preset time period is the past 2 months. The purchase history of the target customer is exported from the company's CRM system, including the order date, the type, quantity and amount of the purchased products, and the communication records with the target customer are extracted from the customer service interaction platform and the email management system. The communication records include the summary of the telephone call between the customer service representative and the customer, the email exchanges, and the online chat content. The collected historical sales business data and interaction data are integrated to form the target customer's data to be analyzed.

[0029] It should be noted that for new customers, the historical sales business data can be null.

[0030] For example, for old customers, historical sales business data such as Figure 2 As shown, interactive data such as Figure 3As shown. The historical sales business data table contains the customer's purchase history, such as customer ID, purchase date, product category, and total amount. This information helps analyze the customer's purchasing behavior and consumption preferences. The interaction data table records the interaction between the salesperson and the customer, including customer ID, interaction date, interaction type (such as phone, email, chat), and description (a brief description of the content or purpose of the interaction). These two tables provide a basic data view to facilitate further analysis of the customer's purchase intention and interaction, thereby providing data support for the formulation of sales strategies.

[0031] S102, performing customer intention analysis on the data to be analyzed according to the data quantification conditions preset for each customer intention level, and obtaining the customer intention level corresponding to the target customer; Among them, data quantification conditions are to convert qualitative data into measurable and comparable numerical conditions. In customer intention analysis, for example, it includes specific numerical ranges or thresholds of indicators such as keyword frequency, purchase frequency, and average transaction amount.

[0032] Among them, customer intention analysis involves evaluating and interpreting customer behavioral data to predict their willingness to purchase products or services. It usually includes analyzing customers' historical transactions, interaction records, and other relevant data points to determine their possible purchase intentions. The purpose of customer intention analysis is to classify customers into different intention levels so that sales strategies can be more customized and effective. Customer intention levels are assigned to different categories or levels based on the results of customer intention analysis. These levels reflect the possibility of customers purchasing products or services, and are usually divided into "high intention", "medium intention" and "low intention". Each level corresponds to a specific sales strategy so that sales staff can conduct sales activities more effectively for different groups.

[0033] In some embodiments of the present application, the specific process of generating data quantification conditions for preset intention levels of each customer includes: collecting and preprocessing historical sales case data to obtain historical communication record text and historical purchase behavior information of each customer; generating each customer's historical customer intention level based on each customer's historical communication record text and historical purchase behavior information; storing each customer's historical customer intention level as a set; merging repeated historical customer intention levels in the set to obtain multiple preset customer intention levels; receiving data quantification conditions input for each preset customer intention level and binding them to obtain data quantification conditions for each preset customer intention level. Data quantification conditions, for example Figure 4 shown.

[0034] Among them, historical communication record text refers to all text records of communication with customers during the sales process, including but not limited to emails, chat records, meeting minutes, etc. These records provide direct evidence of customer inquiries, feedback, and preferences, which helps to analyze customers' purchase intentions. Historical purchase behavior information involves customers' purchase history, such as the types, quantities, frequency, and amounts of goods purchased. By analyzing this information, customers' purchasing patterns and preferences can be revealed, providing an important basis for evaluating their intentions. The historical customer intention level is a level generated for each customer to reflect their purchase intentions based on the customer's historical communication record text and purchase behavior information. These levels are a quantitative representation of the customer's purchase possibility.

[0035] In the embodiment of the present application, by collecting and preprocessing historical sales case data, the enterprise can extract valuable information from each interaction and purchase behavior with the customer. This information is used to generate a historical intention level for each customer, and these levels are stored in a collection. By merging repeated levels in the collection, the enterprise can preset multiple representative and distinguishing customer intention levels. Finally, by setting specific data quantification conditions for each preset level, the enterprise can more accurately evaluate and predict the customer's purchase intention, thereby laying a solid foundation for formulating personalized sales strategies and improving customer relationship management efficiency.

[0036] In some embodiments of the present application, the specific process of generating each customer's historical customer intention level based on each customer's historical communication record text and historical purchasing behavior information includes: performing stem extraction or word form restoration on each customer's historical communication record text to obtain each customer's standard communication record; performing data sorting on the order transaction data contained in each customer's historical purchasing behavior information to obtain each customer's standard purchasing behavior; generating text features of keywords and phrases based on the standard communication records, and generating numerical features related to purchase frequency, average transaction amount, and last purchase time based on the standard purchasing behavior to obtain each customer's text features and numerical features; calculating each customer's historical customer intention based on the text features and numerical features of each customer; and obtaining the customer intention level corresponding to the historical customer intention interval containing each customer's historical customer intention from the pre-constructed mapping relationship between the historical customer intention interval and the customer intention level as the historical customer intention level of each customer.

[0037] Among them, stemming is a text preprocessing technique that returns the stem form of a word by removing common suffixes from the word. For example, simplifying "running" to "run". This helps to classify different forms of the same word into a basic form for effective text analysis. Lemmatization is a process of converting a word into its dictionary form (or original form). For example, converting the past tense of a verb back to its original form. This helps to standardize text data, making it easier to process and analyze. Standard communication records refer to customer communication records that have been processed by stemming or lemmatization to form text data in a unified format. This standardization makes the communication content easier to analyze and compare. Order transaction data refers to the transaction records generated by customers during the purchase process, including order details, payment information, etc. These data are direct evidence of customer purchase behavior and reflect customers' purchase decisions and consumption habits. Standard purchase behavior refers to customer purchase behavior data obtained after sorting and formatting order transaction data. These data are displayed in a unified format for further analysis and calculation. Text features are generated based on standard communication records, reflecting key information of the communication content, such as the frequency and importance of keywords and phrases. These features help understand the customer's communication intentions and concerns. Numerical features are generated based on standard purchase behavior, including quantitative indicators such as purchase frequency, average transaction amount, and last purchase time. These features provide a numerical basis for analyzing customer purchase behavior.

[0038] In an embodiment of the present application, the enterprise can convert the customer's communication records and purchasing behavior into standardized data, and then generate text and numerical features. These features are used to calculate the historical customer intention of each customer, and through a pre-built mapping relationship, the intention value is mapped to a specific intention level. This method not only improves the efficiency and accuracy of customer data analysis, but also enables the sales team to formulate more personalized and effective sales strategies based on the customer's purchase intention level.

[0039] In some embodiments of the present application, the specific process of calculating the historical customer intention of each customer based on the text features and numerical features of each customer includes: from the text features of each customer, counting the probability of occurrence of preset keywords; from the numerical features of each customer, extracting the purchase frequency, average transaction amount, and the last purchase time; according to historical business data, dynamically assigning weights to the probability of occurrence of preset keywords, purchase frequency, average transaction amount, and the last purchase time to obtain probability weights, frequency weights, amount weights, and time weights; standardizing the probability of occurrence of preset keywords, purchase frequency, average transaction amount, and the last purchase time to the range of 0-1 to obtain probability values, frequency values, amount values, and time values; using probability weights, frequency weights, amount weights, and time weights to weight the probability value, frequency value, amount value, and time value, respectively; summing the weighted results to obtain the historical customer intention of each customer.

[0040] Specifically, in, For each customer's historical customer intention, is the probability weight, is the frequency weight, is the amount weight, is the time weight, is the probability value, is the frequency value, is the amount value, is the time value, + + + =1.

[0041] In some embodiments of the present application, the specific process of dynamically allocating weights to the probability of occurrence of preset keywords, purchase frequency, average transaction amount, and last purchase time based on historical business data includes: based on historical business data, obtaining quantitative indicators of customer purchase intention as dependent variables; using the probability of occurrence of preset keywords, purchase frequency, average transaction amount, and last purchase time as independent variables; calculating the means of the dependent variable and the independent variable respectively; using the means of the dependent variable and the independent variable, and the dependent variable and the independent variable, to calculate the Pearson correlation coefficient of each independent variable to determine the correlation between the probability of occurrence of preset keywords, purchase frequency, average transaction amount, and last purchase time and the customer purchase intention; dynamically allocating weights to the probability of occurrence of preset keywords, purchase frequency, average transaction amount, and last purchase time according to the size of the Pearson correlation coefficient of each independent variable; wherein, in, is the Pearson correlation coefficient for each independent variable, is the independent variable, is the dependent variable, and are the means of the independent and dependent variables, respectively.

[0042] The data quantification conditions preset for each customer intention level include keyword occurrence frequency conditions, purchase frequency conditions, average transaction amount conditions, and last purchase time conditions.

[0043] In some embodiments of the present application, according to the data quantification conditions preset for each customer intention level, a customer intention analysis is performed on the data to be analyzed, and the specific process of obtaining the customer intention level corresponding to the target customer includes: generating target text features of the target customer according to the interaction data; generating numerical features related to the purchase frequency, average transaction amount, and the last purchase time according to the historical sales business data, and obtaining the target numerical features of the target customer; based on the target text features of the target customer, counting the target probability of the appearance of preset keywords; based on the target numerical features of the target customer, counting the target purchase frequency, target average transaction amount, and target last purchase time; comparing the target probability with the keyword occurrence frequency condition to obtain a first comparison result; comparing the target purchase frequency, target average transaction amount, and target last purchase time with the purchase frequency condition, the average transaction amount condition, and the last purchase time condition, respectively, to obtain a second comparison result; based on the first comparison result and the second comparison result, obtaining the optimal customer intention level from each preset customer intention level as the customer intention level corresponding to the target customer.

[0044] Specifically, the specific process of obtaining the optimal customer intention level as the customer intention level corresponding to the target customer from each preset customer intention level based on the first comparison result and the second comparison result includes: when the preset customer intention level corresponding to the first comparison result and the preset customer intention level corresponding to the second comparison result are the same, the preset customer intention level is used as the customer intention level corresponding to the target customer; or, when the preset customer intention level corresponding to the first comparison result and the preset customer intention level corresponding to the second comparison result are not the same, determining the preset customer intention level that meets the most conditions, and using the preset customer intention level that meets the most conditions as the customer intention level corresponding to the target customer.

[0045] It should be noted that the generation method of the target text features and target numerical features of the target customers is consistent with the processing method in generating the data quantification conditions for the preset intention level of each customer, and will not be repeated here.

[0046] S103, according to the customer intention level, obtaining corresponding sales strategy data from a pre-constructed mapping relationship between the customer intention level and the sales strategy data; In an embodiment of the present application, a mapping relationship between a pre-built customer intention level and sales strategy data is generated according to the following steps, including: receiving sales strategy data input for each preset customer intention level, and obtaining sales strategy data for each preset customer intention level; the sales strategy data includes strategy information for providing personalized discounts, strategy information for information education and product display, and strategy information for improving brand and product awareness; storing a mapping relationship between each preset customer intention level and the sales strategy data for each preset customer intention level, and obtaining a mapping relationship between a pre-built customer intention level and the sales strategy data.

[0047] Among them, sales strategy data refers to strategy information customized for different customer intention levels, including specific plans for various promotional, communication, education and display activities. These strategy data are designed to adopt the most appropriate sales methods for customers of different levels. Personalized offers refer to customized offers based on the characteristics and purchase history of individual customers, such as discounts on specific products, member-only offers or personalized services, in order to increase the purchase intention of these customers. Information education and product display refer to educating customers about product knowledge, functions and usage methods, as well as demonstrating the characteristics and advantages of products, to enhance customers' purchasing interest and decision-making confidence. Improving brand and product awareness refers to enhancing customers' awareness of brands and products through various marketing activities and communication strategies, thereby building brand image and promoting product sales.

[0048] In an embodiment of the present application, by receiving and processing sales strategy data for different customer intention levels, it is possible to ensure that each preset customer intention level is associated with a most appropriate sales strategy. This includes providing personalized offers to high-intention customers, providing information education and product display to medium-intention customers, and providing strategies to enhance brand and product awareness for low-intention customers. By storing the mapping relationship between these strategy information and intention levels, the enterprise pre-builds a systematic correspondence framework between customer intention levels and sales strategies. This framework not only improves the pertinence and effectiveness of sales strategies, but also optimizes resource allocation.

[0049] Pre-built mappings between customer intention levels and sales strategy data, such as Figure 5As shown in Figure 1, for high-intent customers, sales strategies focus on fast conversion and improving customer satisfaction. For example, offering limited-time discounts can stimulate customers to buy immediately; free upgrade services and VIP-exclusive activities can increase customer loyalty and satisfaction. Customers with medium intention may need more information to facilitate decision-making. Therefore, strategies include product education and demonstrations to help customers better understand the value and usage of the product; providing trial opportunities allows customers to experience the product before purchasing. Low-intent customers may not know enough about the brand or product. Strategies focus on education and brand building, such as sharing brand stories and product information through regular communications, inviting customers to participate in satisfaction surveys to collect feedback and increase engagement, and providing new user offers to entice them to try the product.

[0050] In some embodiments, by Figure 5 The data table of the mapping relationship shown can quickly determine the sales strategy data of the target customers.

[0051] S104, sending the sales strategy data belonging to the target customer to the client of the salesperson for data display.

[0052] In some embodiments, after obtaining the sales strategy data belonging to the target customer, the sales strategy data belonging to the target customer can be sent to the client of the salesperson for data display. The displayed sales strategy data is, for example, Figure 6 shown.

[0053] After the data display, it also specifically includes: real-time collection of first interaction data and first sales business data generated by the interaction between the salesperson and the target customer within a preset time period; generating a first text feature of the target customer and a first numerical feature of the target customer based on the first interaction data and the first sales business data; determining the current sales strategy data of the target customer based on the first text feature of the target customer and the first numerical feature of the target customer; comparing whether the current sales strategy data of the target customer is consistent with the sales strategy data displayed by the salesperson's client to determine whether the salesperson is proceeding in accordance with the displayed sales strategy data, and obtaining a determination result; sending the determination result to the administrator's client for data display.

[0054] Among them, the first interactive data refers to the latest interactive data between the salesperson and the target customer collected within a specific time period. These data may include call records, meeting minutes, email exchanges, etc., which are used to analyze the latest feedback and preferences of customers. The first sales business data refers to the latest sales business information related to the target customer, such as recent order details, purchase history, etc. These data reflect the customer's latest purchasing behavior and business trends. The first text feature and the first numerical feature refer to the text and numerical indicators generated based on the latest interactive data and sales business data to describe the characteristics of the target customer. The first text feature may include keyword frequency, sentiment analysis results, etc., while the first numerical feature may include purchase frequency, average transaction amount, etc.

[0055] It should be noted that the generation method of the first text feature of the target customer and the first numerical feature of the target customer is consistent with the processing method in generating the data quantification conditions for presetting each customer intention level, and will not be repeated here.

[0056] In the embodiment of the present application, by collecting the interaction and business data between the salesperson and the target customer in real time, the system can generate the latest text and numerical features describing the customer characteristics. Using these features, the system can determine and update the current sales strategy for each customer. Subsequently, the system will compare whether the strategy actually implemented by the salesperson is consistent with the preset strategy, thereby evaluating the salesperson's execution ability. Finally, this judgment result is sent to the administrator to help them monitor the performance of the sales team in real time, and adjust the strategy or provide training in a timely manner to ensure the achievement of sales targets.

[0057] In the embodiments of the present application, on the one hand, the present application provides data quantification conditions for pre-setting each customer intention level and a pre-built mapping relationship between customer intention levels and sales strategy data. Therefore, through an automated data analysis process, it is possible to quickly and accurately automatically match customers with corresponding intention levels and automatically generate specific sales strategy data, thereby ensuring that the formulation of all sales strategies is based on unified standards and processes, thereby improving the consistency of strategy execution; on the other hand, historical sales business data and interaction data of target customers are collected, and these data include interaction records between salespeople and target customers within a preset time period, and these data are used to conduct in-depth customer intention analysis. Through precise data analysis, the understanding of customer intentions and the accuracy of prediction are improved.

[0058] The following is a system embodiment of the present application, which can be used to execute the method embodiment of the present application. For details not disclosed in the system embodiment of the present application, please refer to the method embodiment of the present application.

[0059] See also Figure 7, which shows a schematic diagram of the structure of a data processing system based on customer intention analysis provided by an exemplary embodiment of the present application. The data processing system based on customer intention analysis can be implemented as all or part of an electronic device through software, hardware or a combination of both. The system 1 includes a data collection module 10, a customer intention analysis and processing module 20, a sales strategy data acquisition module 30, and a sales strategy data display module 40.

[0060] The data collection module 10 is used to collect data to be analyzed, the data to be analyzed includes historical sales business data and interaction data of target customers, and the interaction data is generated by the interaction between the salesperson and the target customer within a preset time period; The customer intention analysis processing module 20 is used to perform customer intention analysis on the data to be analyzed according to the data quantification conditions preset for each customer intention level, and obtain the customer intention level corresponding to the target customer; The sales strategy data acquisition module 30 is used to acquire corresponding sales strategy data from a pre-built mapping relationship between the customer intention level and the sales strategy data according to the customer intention level; The sales strategy data display module 40 is used to send the sales strategy data belonging to the target customer to the client of the salesperson for data display.

[0061] It should be noted that the data processing system based on customer intention analysis provided in the above embodiment only uses the division of the above functional modules as an example when executing the data processing method based on customer intention analysis. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the data processing system based on customer intention analysis provided in the above embodiment and the data processing method based on customer intention analysis embodiment belong to the same concept. The implementation process is detailed in the method embodiment, which will not be repeated here.

[0062] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0063] In the embodiments of the present application, on the one hand, the present application provides data quantification conditions for pre-setting each customer intention level and a pre-built mapping relationship between customer intention levels and sales strategy data. Therefore, through an automated data analysis process, it is possible to quickly and accurately automatically match customers with corresponding intention levels and automatically generate specific sales strategy data, thereby ensuring that the formulation of all sales strategies is based on unified standards and processes, thereby improving the consistency of strategy execution; on the other hand, historical sales business data and interaction data of target customers are collected, and these data include interaction records between salespeople and target customers within a preset time period, and these data are used to conduct in-depth customer intention analysis. Through precise data analysis, the understanding of customer intentions and the accuracy of prediction are improved.

[0064] The present application also provides a computer-readable medium having program instructions stored thereon, which, when executed by a processor, implement the data processing method based on customer intention analysis provided by the above-mentioned various method embodiments.

[0065] The present application also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the data processing method based on customer intention analysis of the above-mentioned various method embodiments.

[0066] See also Figure 8 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 8 As shown, the electronic device 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .

[0067] The communication bus 1002 is used to realize the connection and communication between these components.

[0068] The user interface 1003 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0069] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0070] Among them, the processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect various parts of the entire electronic device 1000, and executes various functions and processes data of the electronic device 1000 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Optionally, the processor 1001 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 1001 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001, and it can be implemented separately through a chip.

[0071] Among them, the memory 1005 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may also be optionally at least one storage system located away from the aforementioned processor 1001. As Figure 8 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a data processing application based on customer intention analysis.

[0072] exist Figure 8In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 1001 can be used to call the data processing application based on customer intention analysis stored in the memory 1005, and specifically perform the following operations: Collect data to be analyzed, including historical sales business data and interaction data of target customers. Interaction data is generated by the interaction between salespersons and target customers within a preset time period. According to the data quantification conditions of each customer intention level preset, customer intention analysis is performed on the data to be analyzed to obtain the customer intention level corresponding to the target customer; According to the customer intention level, corresponding sales strategy data is obtained from a pre-built mapping relationship between the customer intention level and the sales strategy data; Send the sales strategy data belonging to the target customer to the client belonging to the salesperson for data display.

[0073] In one embodiment, when the processor 1001 generates the data quantification conditions for presetting each customer intention level, the processor 1001 specifically performs the following operations: Collect and pre-process historical sales case data to obtain each customer's historical communication record text and historical purchase behavior information; Generate each customer's historical customer intention level based on each customer's historical communication record text and historical purchase behavior information; The historical customer intention level of each customer is stored as a set; Merging repeated historical customer intention levels in the set to obtain a plurality of preset customer intention levels; The data quantification conditions input for each preset customer intention level are received and bound to obtain the data quantification conditions for each preset customer intention level.

[0074] In one embodiment, when the processor 1001 generates the historical customer intention level of each customer based on the historical communication record text and historical purchase behavior information of each customer, the following operations are specifically performed: Perform stem extraction or lemmatization on the text of each customer's historical communication records to obtain each customer's standard communication records; The order transaction data contained in the historical purchase behavior information of each customer is sorted to obtain the standard purchase behavior of each customer; Generate text features of keywords and phrases based on standard communication records, and generate numerical features related to purchase frequency, average transaction amount, and last purchase time based on standard purchase behavior, to obtain text features and numerical features for each customer; Based on the text features and numerical features of each customer, calculate the historical customer intention of each customer; From the pre-constructed mapping relationship between historical customer intention degree intervals and customer intention degree levels, the customer intention degree level corresponding to the historical customer intention degree interval containing the historical customer intention degree of each customer is obtained as the historical customer intention degree level of each customer.

[0075] In one embodiment, when the processor 1001 calculates the historical customer intention of each customer based on the text features and numerical features of each customer, the processor 1001 specifically performs the following operations: Count the probability of the preset keywords appearing from the text features of each customer; Extract purchase frequency, average transaction amount, and last purchase time from the numerical features of each customer; According to historical business data, weights are dynamically assigned to the probability of occurrence of preset keywords, purchase frequency, average transaction amount, and last purchase time to obtain probability weight, frequency weight, amount weight, and time weight; The probability of occurrence of the preset keywords, purchase frequency, average transaction amount, and last purchase time are standardized to a range of 0-1 to obtain probability values, frequency values, amount values, and time values; Use probability weight, frequency weight, amount weight and time weight to weight the probability value, frequency value, amount value and time value respectively; Sum the weighted results to get the historical customer intention of each customer;

[0076] in, For each customer's historical customer intention, is the probability weight, is the frequency weight, is the amount weight, is the time weight, is the probability value, is the frequency value, is the amount value, is the time value, + + + =1.

[0077] In one embodiment, when the processor 1001 dynamically allocates weights to the probability of occurrence of preset keywords, purchase frequency, average transaction amount, and last purchase time according to historical business data, the following operations are specifically performed: Based on historical business data, obtain quantitative indicators of customer purchase intention as the dependent variable; The probability of occurrence of preset keywords, purchase frequency, average transaction amount, and last purchase time were used as independent variables; Calculate the means of the dependent and independent variables respectively; The Pearson correlation coefficient of each independent variable is calculated using the dependent variable and the independent variable, and the mean of the dependent variable and the independent variable, to determine the correlation between the probability of occurrence of the preset keywords, purchase frequency, average transaction amount, last purchase time and customer purchase intention; According to the size of the Pearson correlation coefficient of each independent variable, the probability of occurrence of the preset keywords, purchase frequency, average transaction amount, and last purchase time are dynamically assigned weights; among them,

[0078] in, is the Pearson correlation coefficient for each independent variable, is the independent variable, is the dependent variable, and are the means of the independent and dependent variables, respectively.

[0079] In one embodiment, when the processor 1001 performs customer intention analysis on the data to be analyzed according to the data quantification condition preset for each customer intention level and obtains the customer intention level corresponding to the target customer, the processor 1001 specifically performs the following operations: Generate target text features for target customers based on interaction data; Based on historical sales business data, generate numerical features related to purchase frequency, average transaction amount, and last purchase time to obtain target numerical features of target customers; Based on the target text features of target customers, the target probability of the preset keywords appearing is calculated; Based on the target numerical characteristics of target customers, statistics are collected on the target purchase frequency, target average transaction amount, and target last purchase time; Compare the target probability with the keyword occurrence frequency condition to obtain a first comparison result; Compare the target purchase frequency, the target average transaction amount, and the target last purchase time with the purchase frequency condition, the average transaction amount condition, and the last purchase time condition, respectively, to obtain a second comparison result; According to the first comparison result and the second comparison result, the optimal customer intention level is obtained from each preset customer intention level as the customer intention level corresponding to the target customer.

[0080] In one embodiment, when the processor 1001 obtains the optimal customer intention level from each preset customer intention level as the customer intention level corresponding to the target customer according to the first comparison result and the second comparison result, the processor 1001 specifically performs the following operations: In the case where the preset customer intention level corresponding to the first comparison result and the preset customer intention level corresponding to the second comparison result are the same, the preset customer intention level is used as the customer intention level corresponding to the target customer; or When the preset customer intention level corresponding to the first comparison result is not the same as the preset customer intention level corresponding to the second comparison result, the preset customer intention level that meets the most conditions is determined, and the preset customer intention level that meets the most conditions is used as the customer intention level corresponding to the target customer.

[0081] In one embodiment, after executing sending the sales strategy data belonging to the target customer to the client of the salesperson for data display, the processor 1001 further performs the following operations: Collecting in real time the first interaction data and the first sales business data generated by the interaction between the salesperson and the target customer within a preset time period; Generate a first text feature of the target customer and a first numerical feature of the target customer according to the first interaction data and the first sales business data; Determining current sales strategy data of the target customer based on the first text feature of the target customer and the first numerical feature of the target customer; Compare the current sales strategy data of the target customer with the sales strategy data displayed by the salesperson's client to see if they are consistent, so as to determine whether the salesperson is advancing according to the displayed sales strategy data and obtain a determination result; The judgment results are sent to the administrator's client for data display.

[0082] In the embodiments of the present application, on the one hand, the present application provides data quantification conditions for pre-setting each customer intention level and a pre-built mapping relationship between customer intention levels and sales strategy data. Therefore, through an automated data analysis process, it is possible to quickly and accurately automatically match customers with corresponding intention levels and automatically generate specific sales strategy data, thereby ensuring that the formulation of all sales strategies is based on unified standards and processes, thereby improving the consistency of strategy execution; on the other hand, historical sales business data and interaction data of target customers are collected, and these data include interaction records between salespeople and target customers within a preset time period, and these data are used to conduct in-depth customer intention analysis. Through precise data analysis, the understanding of customer intentions and the accuracy of prediction are improved.

[0083] 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 a computer program, and the program for data processing based on customer intention analysis can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium of the program for data processing based on customer intention analysis can be a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0084] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A data processing method based on customer intention analysis, It is characterized in that Applied to the server, the method includes: Collecting data to be analyzed, wherein the data to be analyzed includes historical sales business data and interaction data of the target customer, wherein the interaction data is generated by the interaction between the salesperson and the target customer within a preset time period; According to the data quantification conditions for the preset intention level of each customer, the customer intention analysis is performed on the data to be analyzed to obtain the customer intention level corresponding to the target customer; wherein the data quantification conditions for the preset intention level of each customer are obtained by binding the data quantification conditions for the preset intention level input of each customer, and the preset intention level of each customer is obtained based on the historical communication record text and historical purchase behavior information of each customer, and the historical communication record text and historical purchase behavior information of each customer are obtained based on the collection and pre-processing of historical sales case data; According to the customer intention level, obtaining corresponding sales strategy data from a pre-constructed mapping relationship between the customer intention level and the sales strategy data; The sales strategy data belonging to the target customer is sent to the client of the salesperson for data display.

2. The method according to claim 1, It is characterized in that Follow the steps below to generate the data quantification conditions for each customer intention level, including: Collect and pre-process historical sales case data to obtain each customer's historical communication record text and historical purchase behavior information; Generating a historical customer intention level for each customer based on the historical communication record text and historical purchase behavior information of each customer; storing the historical customer intention level of each customer as a set; Merging repeated historical customer intention levels in the set to obtain a plurality of preset customer intention levels; The data quantification conditions input for each preset customer intention level are received and bound to obtain the data quantification conditions for each preset customer intention level.

3. The method according to claim 2, It is characterized in that Generating the historical customer intention level of each customer according to the historical communication record text and historical purchase behavior information of each customer includes: Performing stem extraction or lemma restoration on the historical communication record text of each customer to obtain a standard communication record of each customer; Sorting out the order transaction data included in the historical purchase behavior information of each customer to obtain the standard purchase behavior of each customer; Generating text features of keywords and phrases based on the standard communication records, and generating numerical features related to purchase frequency, average transaction amount, and last purchase time based on the standard purchase behavior, to obtain text features and numerical features of each customer; Calculating the historical customer intention degree of each customer based on the text features and numerical features of each customer; From the pre-constructed mapping relationship between historical customer intention degree intervals and customer intention degree levels, the customer intention degree level corresponding to the historical customer intention degree interval containing the historical customer intention degree of each customer is obtained as the historical customer intention degree level of each customer.

4. The method according to claim 3, It is characterized in that The calculating the historical customer intention degree of each customer based on the text features and numerical features of each customer includes: Counting the probability of a preset keyword appearing from the text features of each customer; Extracting purchase frequency, average transaction amount, and last purchase time from the numerical features of each customer; According to historical business data, dynamically assign weights to the probability of occurrence of the preset keywords, purchase frequency, average transaction amount, and last purchase time to obtain probability weight, frequency weight, amount weight, and time weight; The probability of occurrence of the preset keyword, purchase frequency, average transaction amount, and last purchase time are normalized to a range of 0-1 to obtain a probability value, a frequency value, an amount value, and a time value; The probability weight, frequency weight, amount weight and time weight are used to weight the probability value, frequency value, amount value and time value respectively; The weighted results are summed to obtain the historical customer intention of each customer; wherein, in, For each customer's historical customer intention, is the probability weight, is the frequency weight, is the amount weight, is the time weight, is the probability value, is the frequency value, is the amount value, is the time value, + + + =1.

5. The method according to claim 4, It is characterized in that The weights are dynamically assigned to the probability of occurrence, purchase frequency, average transaction amount, and last purchase time of the preset keywords based on historical business data, including: Based on historical business data, obtain quantitative indicators of customer purchase intention as the dependent variable; The probability of occurrence of the preset keywords, purchase frequency, average transaction amount, and last purchase time are used as independent variables; Calculate the means of the dependent variable and the independent variable respectively; Using the dependent variable and the independent variable, and the means of the dependent variable and the independent variable, the Pearson correlation coefficient of each independent variable is calculated to determine the correlation between the probability of occurrence of the preset keyword, the purchase frequency, the average transaction amount, the last purchase time and the customer's purchase intention; According to the size of the Pearson correlation coefficient of each independent variable, weights are dynamically assigned to the probability of occurrence, purchase frequency, average transaction amount, and last purchase time of the preset keyword; wherein, in, is the Pearson correlation coefficient for each independent variable, is the independent variable, is the dependent variable, and are the means of the independent and dependent variables, respectively.

6. The method according to claim 1, It is characterized in that The data quantification conditions for presetting each customer intention level include keyword occurrence frequency conditions, purchase frequency conditions, average transaction amount conditions, and last purchase time conditions; The step of performing customer intention analysis on the data to be analyzed according to the preset data quantification conditions of each customer intention level to obtain the customer intention level corresponding to the target customer includes: Generating target text features of the target customer according to the interaction data; Generate numerical features related to purchase frequency, average transaction amount, and last purchase time based on the historical sales business data to obtain target numerical features of the target customers; Based on the target text features of the target customers, the target probability of the preset keywords appearing is counted; Based on the target numerical characteristics of the target customers, statistics are collected on the target purchase frequency, the target average transaction amount, and the target last purchase time; Comparing the target probability with the keyword occurrence frequency condition to obtain a first comparison result; Compare the target purchase frequency, target average transaction amount, and target last purchase time with the purchase frequency condition, average transaction amount condition, and last purchase time condition, respectively, to obtain a second comparison result; According to the first comparison result and the second comparison result, the optimal customer intention level is obtained from each preset customer intention level as the customer intention level corresponding to the target customer.

7. The method according to claim 6, It is characterized in that The acquiring, according to the first comparison result and the second comparison result, the optimal customer intention level from the preset customer intention levels as the customer intention level corresponding to the target customer, comprises: In the case where the preset customer intention level corresponding to the first comparison result and the preset customer intention level corresponding to the second comparison result are the same, the preset customer intention level is used as the customer intention level corresponding to the target customer; or When the preset customer intention level corresponding to the first comparison result is not the same as the preset customer intention level corresponding to the second comparison result, the preset customer intention level that meets the most conditions is determined, and the preset customer intention level that meets the most conditions is used as the customer intention level corresponding to the target customer.

8. The method according to claim 1, It is characterized in that The following steps generate a pre-built mapping between customer intent ratings and sales strategy data, including: Receiving sales strategy data input for each preset customer intention level, and obtaining sales strategy data for each preset customer intention level; the sales strategy data includes strategy information for providing personalized discounts, strategy information for information education and product display, and strategy information for improving brand and product awareness; The mapping relationship between the preset customer intention level and the sales strategy data for each customer intention level is stored to obtain a pre-constructed mapping relationship between the customer intention level and the sales strategy data.

9. The method according to claim 1, It is characterized in that After sending the sales strategy data belonging to the target customer to the client of the salesperson for data display, the method further includes: Collecting in real time first interaction data and first sales business data generated by the salesperson interacting with the target customer within a preset time period; generating a first text feature of the target customer and a first numerical feature of the target customer according to the first interaction data and the first sales business data; Determining current sales strategy data of the target customer according to the first text feature of the target customer and the first numerical feature of the target customer; Compare the current sales strategy data of the target customer with the sales strategy data displayed by the client of the salesperson to see whether they are consistent, so as to determine whether the salesperson is advancing according to the displayed sales strategy data, and obtain a determination result; The determination result is sent to the administrator's client for data display.

10. A data processing system based on customer intention analysis, It is characterized in that The system comprises: A data collection module is used to collect data to be analyzed, wherein the data to be analyzed includes historical sales business data and interaction data of target customers, wherein the interaction data is generated by the interaction between the salesperson and the target customer within a preset time period; A customer intention analysis processing module is used to perform customer intention analysis on the data to be analyzed according to the data quantification conditions preset for each customer intention level, so as to obtain the customer intention level corresponding to the target customer; wherein the data quantification conditions preset for each customer intention level are obtained by binding the data quantification conditions input for each customer intention level, and the preset intention level of each customer is obtained based on the historical communication record text and historical purchase behavior information of each customer, and the historical communication record text and historical purchase behavior information of each customer are obtained based on the collection and preprocessing of historical sales case data; A sales strategy data acquisition module, used to acquire corresponding sales strategy data from a pre-constructed mapping relationship between the customer intention level and the sales strategy data according to the customer intention level; The sales strategy data display module is used to send the sales strategy data belonging to the target customer to the client of the salesperson for data display.

Images