Evaluation system and method based on business personnel and clients

Abstract

The invention relates to the technical field of evaluation systems, in particular to an evaluation system and method based on business personnel and clients, and the system comprises a data collection module which is used for collecting the position information, daily behavior data, access data and client interaction records of the business personnel; the customer big data management module is used for collecting, storing, analyzing and managing interaction data, customer behavior data and demand data between business personnel and customers; the data analysis module preprocesses the data of the customer big data management module and the data acquisition module, and identifies the behavior pattern of business personnel and customer demands; the strategy control module carries out strategy reporting and reporting reminding according to the data analysis result, and optimizes the working process of the business personnel; and the execution module performs automatic reporting, data reporting and reminding sending according to strategy control. According to the method, data relevance between business personnel and clients is analyzed, mode clustering analysis is carried out on the business personnel and the clients, and an evaluation system of performance of the business personnel is constructed.

Description

Technical Field

[0001] The present invention relates to the technical field of evaluation systems, and in particular to an evaluation system and method based on business personnel and customers. Background Art

[0002] With the rapid development of the Internet and big data cloud platforms, customer data management systems have gradually become popular in enterprise management, but the following problems still exist:

[0003] 1. Single data collection method:

[0004] Existing systems usually only support manual input or simple automated operations, and cannot make intelligent adjustments based on the behavior of business personnel and real-time environmental data changes. They lack flexible customer information configuration options and cannot meet the personalized needs of different business scenarios.

[0005] 2. Poor data integration and linkage:

[0006] It is difficult to effectively integrate and link data between different customers, resulting in serious data silos and the inability to achieve cross-departmental or cross-platform data sharing and collaboration, affecting overall business efficiency.

[0007] 3. Imperfect data security and privacy protection:

[0008] The system lacks effective encryption and protection measures during data transmission and storage, which can easily lead to data leakage and abuse. The lack of privacy awareness among business personnel and customers may cause legal and ethical issues.

[0009] 4. There is a lack of methods to evaluate the closeness of the relationship between business personnel and customers, and to generate corresponding strategies based on the evaluation results. Summary of the invention

[0010] In view of the deficiencies of existing systems and methods, the present invention analyzes the data correlation between business personnel and customers, performs pattern clustering analysis on the two, and constructs an evaluation system for the performance of business personnel.

[0011] The technical solution adopted by the present invention is: an evaluation system based on business personnel and customers includes:

[0012] Data collection module, customer big data management module, data analysis module, strategy control module and execution module; among them,

[0013] The data collection module is used to collect business personnel's location information, daily behavior data, access data and customer interaction records;

[0014] The customer big data management module is used to collect, store, analyze and manage the interaction data between business personnel and customers, customer behavior data, and demand data;

[0015] The data analysis module is used to pre-process the data from the customer big data management module and the data collection module, and identify the behavior patterns of business personnel and customer needs;

[0016] The policy control module reports policies and reporting reminders based on data analysis results, optimizing the workflow of business personnel;

[0017] The execution module automatically reports, uploads data, and sends reminders according to policy control.

[0018] As a preferred implementation mode of the present invention, the location information of the business personnel includes: longitude and latitude, timestamp, WiFi positioning, network base station information, accelerometer, and gyroscope.

[0019] As a preferred embodiment of the present invention, the daily behavior data of business personnel includes: clocking in and out data, itinerary arrangements, step and exercise data, business trip records and task data.

[0020] As a preferred implementation mode of the present invention, the visit data of the business personnel include: visit time, visit location, visit type, visit form, visit target, task achievement status and visit content.

[0021] As a preferred implementation mode of the present invention, the customer interaction record of the business personnel includes: customer visit record and the follow-up status after the visit.

[0022] As a preferred implementation of the present invention, the customer big data management module includes: customer basic data, customer transaction data, customer access data, external market and industry data, customer life cycle data and data security and privacy protection.

[0023] As a preferred embodiment of the present invention, an evaluation method based on business personnel and customers includes:

[0024] Step 1: Identify the behavior patterns of business personnel and customer needs. First, pre-process the data of business personnel and customers;

[0025] Step 2: De-noise and normalize the pre-processed data;

[0026] Step 3: extract the behavior characteristics of the business personnel and calculate the feature vector of the behavior characteristics;

[0027] As a preferred implementation mode of the present invention, the behavior characteristics of the business personnel include: access frequency characteristics, response time characteristics, sales conversion rate characteristics and customer satisfaction characteristics.

[0028] Step 4: Calculate the distance metric of the behavior feature clustering using the feature vector of the behavior feature;

[0029] Step 5: Extract customer demand characteristics;

[0030] Step 6: Correlate the behavior characteristics of the business personnel with the customer demand characteristics to obtain the correlation strength between the behavior characteristics and the customer demand characteristics;

[0031] As a preferred embodiment of the present invention, the formula for the correlation strength between the behavior characteristics and the customer demand characteristics is:

[0032]

[0033] Among them, B i is the behavioral feature vector of the ith business person, D i’ is the demand feature vector of the i'th customer, AR(B i ,D i' ) is B i With D i’ degree of correlation.

[0034] Step 7: Generate and optimize strategies using correlation strength;

[0035] As a preferred implementation of the present invention, the formula for strategy generation is:

[0036] S' i =β·AS(B i ,D i' ) (13)

[0037] Among them, AS(B i ,D i' ) is B i With D i’ , and β is the adjustment coefficient generated by a certain strategy.

[0038] Beneficial effects of the present invention:

[0039] 1. By integrating data collection, customer information management, data analysis, policy control generation and execution modules, intelligent management of business personnel's daily behavior and personalized data reporting are realized; by real-time collection and analysis of business personnel's location and behavior data, operation strategies can be dynamically adjusted according to specific business scenarios, thereby improving the work efficiency of business personnel and the intelligent level of customer management;

[0040] 2. Focus on data security and privacy protection, providing users with a more reliable and efficient experience;

[0041] 3. It realizes intelligent management of the daily behavior of business personnel, and can dynamically adjust management strategies according to the real-time behavior of business personnel and environmental changes, making business management more flexible and efficient; it automatically generates and submits data information, reduces the tedious process of manual operation, and improves work efficiency;

[0042] 4. Integrate the geographic location data, behavior data and customer information of business personnel to form a complete data chain and break the data silos;

[0043] 5. Use encryption technology to ensure the security of data during transmission and storage and prevent data leakage;

[0044] 6. Provides real-time data updates to ensure data accuracy and timeliness, and provides the latest data support for business decisions;

[0045] 7. Extract the behavioral characteristics of business personnel and combine them with customer demand characteristics, analyze the correlation between business personnel and customers, and use strategy generation algorithms to evaluate the overall performance of business personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a logic block diagram of the evaluation system based on business personnel and customers of the present invention;

[0047] Figure 2 It is a flow chart of the evaluation method based on business personnel and customers. DETAILED DESCRIPTION

[0048] The present invention is further described below in conjunction with the accompanying drawings and embodiments. This figure is a simplified schematic diagram, which only illustrates the basic structure of the present invention in a schematic manner, and therefore it only shows the components related to the present invention.

[0049] like Figure 1 As shown, an evaluation system based on business personnel and customers includes:

[0050] Data collection module, customer big data management module, data analysis module, strategy control module and execution module; among them,

[0051] The data collection module collects the daily behavior data of business personnel and combines it with the customer data corresponding to the business personnel in the customer big data management module to provide comprehensive analysis data for the data analysis module;

[0052] Data collection can be done through mobile devices or sensors, which can transfer the collected data to the server for storage; mobile devices include smartphones with built-in GPS modules or devices that support communication such as smart bracelets, which can record the location information, identity and various business activity data of business personnel in real time; when business personnel enter the location area set by the client company, it will automatically trigger the approval of identity data information and start the data collection instructions for location information and business activities.

[0053] The data collection module is used to collect business personnel's location information, daily behavior data, access data and customer interaction records.

[0054] The location information of business personnel is used to determine the current location, activity range and other related geographic or spatial data of business personnel; among them,

[0055] 1. The location information of business personnel includes:

[0056] Longitude and latitude: used to indicate the precise location of business personnel or equipment;

[0057] Timestamp: The time when each location information is collected, which facilitates the correlation analysis between time and location;

[0058] WiFi positioning: The signal strength of the WiFi hotspot is used to estimate the distance of the device relative to the hotspot, thereby determining the location of the device.

[0059] Network base station information: Determine the approximate location by estimating the distance between the device and the base station through the location of the base station in the mobile network;

[0060] Accelerometer and gyroscope: used to obtain the direction and distance of business personnel.

[0061] 2. Daily behavior data of business personnel mainly refers to the behavior data generated by business personnel in their daily work process. These data can reflect the work habits, task execution and frequency and quality of customer interaction of business personnel; specifically include:

[0062] Punch-in and punch-in data: reflects the attendance, lateness, early departure, overtime and other behaviors of business personnel, and counts the daily working hours, whether they work overtime, overtime hours, etc.;

[0063] Itinerary: Records of daily itineraries, such as meeting arrangements, visit arrangements, etc., can be combined with geographic location data to analyze movement trajectories;

[0064] Step count and exercise data: The number of steps and exercise volume collected by the sensors of mobile devices reflect the daily activity volume of business personnel;

[0065] Business trip records: business personnel's business trip locations, business trip times, task contents, etc.;

[0066] Task data: record and count task creation time, task type, task duration and completion status;

[0067] These data can be collected through various channels such as mobile devices, office software, work management systems, etc., and then further analyzed through data analysis modules to derive the behavior patterns of business personnel and trends in customer demand.

[0068] 3. The business personnel’s access data covers their interactions with customers, including:

[0069] The visit time includes the start time, end time and visit duration; the start time is the start time of the interaction between the business personnel and the customer; the end time is the end time of the interaction between the business personnel and the customer; the visit duration is the duration of each visit, calculated by subtracting the start time from the end time;

[0070] The visit location includes: the visit location and distance; the geographic location of the business personnel when interacting with the customer (obtained through GPS, WiFi or base station); distance calculation: the distance from the business personnel's company or designated location to the customer's visit location.

[0071] Visit types include: first visit, follow-up visit, and regular maintenance.

[0072] The visiting forms include: face-to-face visits, telephone visits, video conferences, etc.

[0073] Visit objectives include: signing contracts, providing technical support, after-sales service, customer satisfaction surveys, etc.

[0074] Task achievement refers to whether the goals set during the visit are achieved, such as whether the contract is signed successfully, whether the customer agrees to visit next time, etc.

[0075] Interview content is the main topic or issue discussed when business personnel interact with customers.

[0076] The services or products provided are the specific services or products that the business personnel demonstrate or provide to the customer during the visit.

[0077] 4. Customer interaction records include: customer visit records and follow-up after the visit; among which,

[0078] Customer access records include: access history, customer history data;

[0079] The visit history is the record of all previous visits between a business person and a customer, including all visit times, visit purposes, interaction situations, etc.

[0080] Customer history data refers to the customer's historical purchase behavior, complaint records, support requests and other business-related records.

[0081] Follow-up after the visit includes:

[0082] Follow-up action refers to whether the salesperson keeps in touch with the customer after the visit and takes corresponding follow-up actions, such as returning the call, sending product information, etc.;

[0083] Customer response refers to whether the customer provides further feedback after the visit or participates in follow-up activities.

[0084] Customer interaction records provide a basis for subsequent business analysis and customer demand forecasting, and through analysis, key business information such as business personnel's work patterns, customer preferences, and interaction effects can be identified.

[0085] The customer big data management module is used to collect, store, analyze and manage the interaction data between business personnel and customers, customer behavior data, demand data, etc. This module can operate the following data and includes specific processing procedures:

[0086] 1. Customer basic data includes: basic customer information and historical cooperation records;

[0087] Basic customer information includes customer name, contact information, address, industry type, scale, etc.;

[0088] Historical cooperation records include contract signing status with customers, cooperation cycle, product or service type, business history, etc.

[0089] process:

[0090] Data collection: obtained from customer management systems (CRM), information provided by business personnel or external databases;

[0091] Storage and Update: Store customer base data in the system and update customer information regularly to ensure data accuracy.

[0092] 2. Customer transaction data includes: purchase behavior, service requests, and interaction data;

[0093] Purchase behavior refers to the customer’s purchase history, frequency, amount, purchase channel, etc.

[0094] Service requests are after-sales service requests, support tickets, consulting questions, etc. submitted by customers;

[0095] Interaction data is the record of interactions between customers and business personnel, including the content and frequency of emails, phone calls, and face-to-face meetings.

[0096] process:

[0097] Data collection: Collect data related to customer behavior through business personnel's access record system, CRM, and customer feedback mechanism;

[0098] Behavioral analysis: Analyze customers’ purchasing patterns and demand trends to provide data support for personalized services and recommendations.

[0099] 3. Customer access data, including: access frequency and access content;

[0100] Visit frequency is the frequency of interaction between business personnel and customers;

[0101] The visit content is the focus of each visit, including product introductions provided by business personnel, customer questions, solutions discussed, etc.

[0102] process:

[0103] Access log records automatically obtain detailed data such as access frequency and content when business personnel access the system;

[0104] Visit effectiveness evaluation is to evaluate the effectiveness of visits through data analysis to ensure that the goals of business personnel's visits are consistent with the actual results.

[0105] 4. External market and industry data including: market dynamics, competitor data;

[0106] Market dynamics include industry trends, market competition, policy changes, etc.;

[0107] Competitor data is the impact on customer purchasing behavior and analysis of competitors’ market strategies.

[0108] process:

[0109] External data collection: obtained through third-party market databases, public data platforms, industry reports, etc.;

[0110] Data correlation analysis: Correlate external market data with customer behavior data to analyze the impact of market dynamics on customer behavior.

[0111] 5. Customer life cycle data includes: customer life cycle stage, life cycle management;

[0112] The customer life cycle stages are the different stages from first contact with the customer, potential customer, intended customer to formal partner;

[0113] Lifecycle management is to provide customized services or sales strategies for different stages of the customer life cycle.

[0114] process:

[0115] Lifecycle monitoring: monitor the customer's lifecycle in real time to determine the stage the customer is currently in;

[0116] Strategy optimization: Customize corresponding service strategies for customers according to their life cycle stage, such as marketing activities, product recommendations, etc.

[0117] 6. Data security and privacy protection include: customer data encryption and data privacy management;

[0118] Customer data encryption is to encrypt and protect sensitive customer information to ensure the security of data transmission and storage;

[0119] Data privacy management is to comply with relevant laws and regulations, ensure the legal use of customer data, and provide privacy setting options.

[0120] process:

[0121] Data encryption and access control: Encrypt sensitive data and set strict access rights;

[0122] Privacy compliance review: Regularly review whether the use of customer data complies with relevant laws and the company's internal privacy policy.

[0123] The data analysis module obtains the final business data by calling the policy control module and reports it to the cloud platform through the execution module.

[0124] The data analysis module uses machine learning algorithms to analyze data from the customer big data management module and the data collection module to identify business personnel's behavior patterns and customer needs.

[0125] The data analysis module first pre-processes the collected data, including data cleaning, conversion and compression; extracts the behavioral characteristics of business personnel and uses machine learning algorithms to identify the behavioral patterns of business personnel; analyzes customer data, builds customer portraits, and predicts customer needs; generates visual charts and dynamic reports to provide intuitive data display; and generates task recommendations and optimization suggestions based on the analysis results.

[0126] The data analysis module is responsible for data preprocessing, behavior pattern recognition, customer demand analysis and data visualization; the data preprocessing module is responsible for cleaning invalid data and converting the format; the behavior pattern recognition module uses machine learning algorithms to analyze the activity data of business personnel and identify behavior patterns; the customer demand analysis module uses historical transaction data and interaction data to analyze customer needs; the data visualization module generates location trajectory maps, behavior pattern maps and customer demand maps, etc.

[0127] When the data analysis module receives location data, it considers some important factors, such as the frequency of data sampling, real-time accuracy, etc., and then performs data cleaning, filtering out data with positioning drift through coordinates; converting data in different formats and unifying them into a standard format that the system can handle, and compressing and storing large-scale location data; using machine learning algorithms to analyze the activity data of business personnel, identifying behavioral patterns such as visiting customers, working, and resting; building a behavioral feature model of business personnel based on historical data, and predicting future behavior; using customers' historical transaction data and interaction data to analyze customer preferences and demand changes; using behavioral pattern clustering analysis to discover potential patterns of customer demand and generate customer portraits; based on data analysis results, recommending the best customer visit path and schedule, and providing personalized business suggestions, such as potential customer recommendations and customer care reminders.

[0128] The policy control module generates corresponding data reporting strategies and reporting reminders based on data analysis results to optimize the workflow of business personnel.

[0129] Generate rule-based operational strategies based on data analysis results, and dynamically adjust them based on real-time data; generate reporting reminders and task reminders, and trigger them based on business personnel's schedules and behavioral changes; provide efficiency optimization and effect optimization strategies to improve work efficiency and business results; track strategy execution, evaluate execution results, and make optimization adjustments based on feedback information.

[0130] The policy control module formulates reporting and data reporting strategies based on business rules and data analysis results, and monitors the policy execution status in real time; the policy control module includes a policy formulation module, a reporting reminder module, an optimization strategy generation module and a policy execution monitoring module; among them, the policy formulation module dynamically adjusts the visiting strategies of business personnel based on preset rules and real-time data; the reporting reminder module automatically generates and sends reminder information; the optimization strategy generation module analyzes work efficiency and generates optimization suggestions; the policy execution monitoring module monitors the policy execution status in real time and records feedback information; the policy control module also formulates the reporting and data reporting strategies of business personnel based on preset business rules (such as customer importance and visiting frequency); based on real-time data analysis results, dynamically adjusts the visiting strategies of business personnel (such as increasing the visiting frequency of high-demand customers);

[0131] The strategy control module generates optimization suggestions by analyzing the work efficiency and task completion status of business personnel, such as adjusting visit routes and increasing task priorities; uses machine learning algorithms to continuously optimize business personnel's business strategies and improve work efficiency; the system monitors the task execution status of business personnel in real time, records execution results and feedback information; and dynamically adjusts and optimizes business strategies based on feedback data to ensure effective implementation of strategies.

[0132] The execution module performs operations including automatic reporting, data reporting, and sending reminders according to policy control.

[0133] The execution module automatically reports the policies generated by the policy control module and submits them to the customer big data management module; data reporting is to collect real-time data from business personnel, organize and upload them to the cloud server or enterprise data center; sending reminders is to generate and send reminder information, and notify business personnel through SMS, email, application notifications, etc.; monitor the policy execution status, collect feedback information from business personnel, evaluate the execution effect, and ensure the accuracy and effectiveness of the policy.

[0134] The execution module automatically generates reporting information, regularly or when events trigger data reporting, generates and sends reminder information, monitors task execution and records feedback; the execution module ensures that the system can effectively implement policy control, improve the work efficiency of business personnel and the intelligent level of customer management; when business personnel visit customers, the system automatically generates visit records and work logs, and submits them to the server; business personnel do not need to operate manually, the system automatically processes reporting information, and improves work efficiency; the module automatically collects the location information and behavior data of business personnel regularly or when triggered by specific events; the collected data is uploaded to the data receiving device in real time to ensure the timeliness and accuracy of the data; the module will also generate reminder information according to policy control, and send it to business personnel through notification methods such as applications, text messages or emails; personalized reminder time and frequency can be set to ensure that important tasks are not missed; the module monitors the task execution of business personnel in real time, records execution status and feedback information; based on feedback information, evaluates the effectiveness of policy execution, and makes optimization adjustments.

[0135] Each module node uses a private encrypted tunnel protocol to encrypt data transmission, thereby improving the work efficiency of business personnel while also strengthening data security; the module nodes include data acquisition modules, customer big data management modules, data analysis modules, policy control modules and execution modules; private protocols are used between modules for two-way data transmission; for example, after the customer big data management module collects all business data (customer basic data, user access data, order data, etc.), it transmits the data to the data analysis module through a private protocol for data analysis. The data analysis module will feed back the results to the big data management module, and will also synchronize the data to the policy control module through a private protocol to improve the system strategy.

[0136] like Figure 2 ,The evaluation methods based on business personnel and customers include: identifying the behavior patterns of business personnel and extracting the business needs of customers;,including data preprocessing, behavior pattern recognition, demand feature extraction, behavior and demand association analysis, and strategy generation and execution;

[0137] Step 1: Data preprocessing;

[0138] The preprocessed data includes: the location information of the business personnel. The location information data preprocessing includes:

[0139] Coordinate conversion: convert the location information of different systems (such as GPS coordinates, Baidu map coordinates, etc.) into a unified coordinate system;

[0140] Remove abnormal data: Eliminate location information with large errors, such as location information that obviously does not conform to the normal working range (such as business personnel suddenly appearing in a location far away from the work area);

[0141] Trajectory smoothing: Smooth the movement trajectory of business personnel to reduce jumps or noise caused by GPS errors.

[0142] The pre-processed data also includes the daily behavior data of business personnel;

[0143] Daily behavior data preprocessing includes:

[0144] Access frequency calculation: Count the number of visits made by business personnel in a unit of time. It is necessary to process access timestamps and eliminate duplicate or abnormal access data.

[0145] Working hours filtering: Filter out the behavior data during non-working hours to ensure that only the behavior during working hours is analyzed;

[0146] Abnormal behavior detection: Identifying data that does not conform to normal business behavior, such as multiple visits to the same customer in one day, may need to be marked as abnormal.

[0147] Preprocessed data also includes customer interaction data preprocessing;

[0148] Customer interaction data preprocessing includes:

[0149] Response time correction: Correct the length of time it takes to respond to a customer, eliminating errors or unreasonable time periods (such as responses outside of working hours);

[0150] Deduplication of duplicate data: Eliminate interaction records submitted repeatedly by customers and business personnel to avoid affecting the accuracy of data analysis.

[0151] The preprocessed data also includes access log data preprocessing;

[0152] Access log data preprocessing includes:

[0153] Log deduplication: merge or delete duplicate access logs to ensure that each customer has only one valid record.

[0154] Log formatting: Unify the log formats generated by different devices or systems to ensure data consistency.

[0155] Preprocessed data also includes customer behavior data preprocessing;

[0156] Customer behavior data preprocessing includes:

[0157] Missing value processing: fill in or remove unrecorded customer behavior data (such as customers who did not respond to feedback);

[0158] Data standardization: unify the formats of different customer behavior data for subsequent analysis.

[0159] Preprocessed data also includes time series data preprocessing;

[0160] Time series data preprocessing includes:

[0161] Time alignment: Synchronize the interaction data between business personnel and customers based on timestamps to ensure the order of each event is consistent;

[0162] Missing value filling: interpolation or other missing value processing is performed on missing data points in the time series to avoid interruptions in the time series data affecting the analysis;

[0163] By preprocessing these data, we can ensure that the data quality of the algorithm input is higher, which is more conducive to subsequent analysis and prediction.

[0164] Step 2: De-noise and normalize the pre-processed data;

[0165] For the above preprocessed data, data cleaning will first be performed to remove or correct the errors, missing or inconsistent parts in the data, and then denoising will be performed; denoising uses the moving average method, and the formula is:

[0166]

[0167] Among them, MA i is the moving average of the i-th data; n is the displacement size of the moving window.

[0168] The data normalization formula is as follows:

[0169]

[0170] Among them, x i ′ is the standardized data, x i is the original data retained after sampling, min(X) is the minimum value in the original data, and max(X) is the maximum value in the original data set.

[0171] For example: Suppose there is a data set [10, 20, 30, 40, 50], and the normalized data is [0, 0.25, 0.5, 0.75, 1].

[0172] Step 3: In the behavior pattern recognition stage, extract the behavior characteristics of business personnel and conduct behavior pattern cluster analysis.

[0173] The behavioral characteristics of sales personnel refer to the various quantifiable activity patterns and operating habits that sales personnel display during work. Through these characteristics, we can deeply understand the work habits of sales personnel and further analyze their performance and efficiency. By quantitatively analyzing these characteristics, we can explore the specific performance of sales personnel in customer management, task execution, sales conversion, etc.

[0174] Step 31, calculating the business personnel behavior characteristics and feature vectors;

[0175] Calculate the access frequency feature V i , V i The formula is extracted based on the number of visits that business personnel make to customers every day:

[0176]

[0177] For example, in one month, a business person visits a customer 40 times, and the visit frequency is

[0178] Calculate the response time characteristic R i , R i The total response time of business personnel to customer questions and customer question data extraction are used, and the formula is:

[0179]

[0180] For example, a business person handled 20 customer issues, which took a total of 600 minutes, and the response time was

[0181] Calculate sales conversion rate feature C i , C i It is the ratio of sales personnel who successfully convert potential customers into actual customers. The formula is:

[0182]

[0183] For example, a salesperson contacted 50 potential customers, 15 of whom successfully signed contracts, and the sales conversion rate was

[0184] Calculate customer satisfaction characteristics S i , S iIt is the customer's rating of the salesperson's service, collected through customer surveys or feedback forms. The formula is:

[0185]

[0186] For example, the average customer satisfaction score of a salesperson is 4.7 / 5, indicating that the service quality of the salesperson is high.

[0187] Step 32: The above are four features. The calculation method of each feature vector is as follows:

[0188] First, the features are standardized. Since the dimensions of each feature are different, in order to eliminate the influence of different dimensions, the features are usually standardized first.

[0189] Standardization (Z-score) is to subtract the mean of each feature from the feature and then divide it by the standard deviation. The formula is:

[0190]

[0191] Among them, X i is the original eigenvalue (such as V i ,C i Equivalent eigenvalues); μ is the mean of the feature, the mean of the eigenvalues ​​of the same set of feature samples; σ is the standard deviation of the feature, the standard deviation of the eigenvalues ​​of the same set of feature samples.

[0192] The standardized feature Z i will be dimensionless (i.e. a quantity without units) and can be uniformly compared.

[0193] Secondly, construct the feature vector, and after standardization, put each feature value into a vector to form the feature vector of the business person; business person i has 4 behavioral characteristics, so the feature vector T of this business person i It is expressed as:

[0194] T i =(ZV i +Z Ri +ZC i +ZS i ) (8)

[0195] Among them, Z Vi is the access frequency V i The standardized value, Z Ri is the response time R i The standardized value, Z Ci is the sales conversion rate C i The standardized value, Z Si is customer satisfaction S i The standardized value of .

[0196] Example of feature vector calculation, assuming actual data of four behavioral features: access frequency V i 10 times / day; response time R i 30 minutes; sales conversion rate C i 20%; Customer satisfaction S i For: 4.5 / 5.

[0197] Calculate the mean and standard deviation of the feature (assuming the following values): μ V =8,σ V =2(mean and standard deviation of access frequency); μ R ,σ R =10 (mean and standard deviation of response time); μ C =15%,σ C =5% (mean and standard deviation of sales conversion rate); μ S =4.0,σ S =0.5 (mean and standard deviation of customer satisfaction)

[0198] Normalize each feature: access frequency Z Vi =(10-8) / 2=1; response time Z Ri =(30-40) / 10=-1; Sales conversion rate Z Ci =(20%-15%) / 5%=1; Customer satisfaction Z Si =(4.5-4.0) / 0.5=1.

[0199] Construct feature vector: Standardized feature vector T i for:

[0200] T i =(1,-1,1,1,1)

[0201] Therefore, through the above method, the behavioral data of business personnel can be converted into feature vectors to measure the performance of different business personnel; the standardized processing of each feature value allows each feature to be compared uniformly, and through mathematical methods such as distance measurement, the differences between business personnel can be quantified, helping the system to better understand and optimize business processes.

[0202] The above is a method for converting business personnel behavior data into feature vectors.

[0203] Step 33, the specific algorithm formula of the behavior pattern recognition stage is as follows:

[0204] B i =[b i1 ,b i2 ,...,b im ] (9)

[0205] Among them, B i is the behavioral feature vector of the ith business person, b im is the mth behavior feature vector of the i-th business person;

[0206] Step 4: Calculate the distance metric for behavior pattern clustering. The formula is:

[0207]

[0208] Among them, d(B i ,B j ) is the distance between the i-th and j-th business personnel, w k is the weight of the k-th behavior feature.

[0209] For example: Assuming that the behavioral feature vectors of two business personnel are [1,2,3] and [4,5,6] respectively, and the weights are both 1, then the distance between the two business personnel is: |1-4|+|2-5|+|3-6|=9.

[0210] The smaller the distance value is, the more similar the behavioral characteristics of the two business personnel are, and their work habits, customer handling methods and behavioral strategies may be similar; the company can summarize best practices by analyzing these business personnel and promote them to other team members; conversely, for business personnel with a larger distance, the calculated differences can generate personalized optimization plans for the system; the system can recommend business personnel to take specific actions to narrow the gap between them and high-performing business personnel.

[0211] When multiple groups of distance values ​​are equal or close, the similar behavior patterns mean that business personnel have similar cognition or operations on certain work methods or strategies, and managers can use this to make decisions on team allocation; similar business personnel can collaborate in the same team, and business personnel with large differences in behavioral characteristics can complement each other.

[0212] Extract customer demand features. In the demand feature extraction stage, define customer demand features and extract relevant demand features.

[0213] Step 5: Extract customer demand features. The formula is:

[0214] D i' =[d i'1 ,d i'2 ,...,d i'n ] (11)

[0215] Among them, D i’ is the demand feature vector of the i'th customer, d i’n is the nth demand feature of the i'th customer.

[0216] For example: Suppose a customer's demand feature vector is [7,8,9], which represents the feature values ​​of the customer's three different demands.

[0217] Step 6: Analyze the correlation between behavioral characteristics and customer demand characteristics;

[0218] In the behavior and demand correlation analysis stage, the correlation between the behavior patterns of business personnel and customer needs is explored, and the correlation strength is calculated;

[0219] The formula for correlation is as follows:

[0220]

[0221] Among them, AR(B i ,D j ) is the correlation between the behavior characteristics of the ith business personnel and the characteristics of the ith customer demand; a kl is the weight of the kth behavior feature and the lth demand feature.

[0222] The calculation formula of association strength is as follows:

[0223]

[0224] Among them, AS(B i ,D j ) is the overall correlation strength between the behavior characteristics of the ith business personnel and the i'th customer demand characteristics.

[0225] For example: Assume that the behavior feature vector of a business person is [1,2,3], and the demand feature vector of a customer is [7,8,9], and the weights are all 1, then the correlation between them is

[0226] |1-7|+|2-8|+|3-9|=15|1-7|+|2-8|+|3-9|=

[0227] 15|1-7|+|2-8|+|3-9|=15, the correlation strength is 15 / (3×3)=1.67.

[0228] Assuming that the frequency of interaction between business person A and customer B is high, and the customer evaluates their service very well, the value of the association strength will be high, indicating that the potential association between them is strong.

[0229] If it is found that the number of interactions between customer C and salesperson D decreases over a period of time and customer satisfaction decreases, the value of the association strength will decrease, indicating that the association may be weakened. The system can suggest that the salesperson adjust the strategy.

[0230] Step 7: Generate and optimize strategies using correlation strength;

[0231] In the strategy generation and execution stage, based on the results of correlation analysis, optimization strategies are formulated for business personnel, and the effectiveness of these strategies is executed and evaluated.

[0232] The formula for strategy generation is:

[0233] S' i =β·AS(B i ,D i' ) (13)

[0234] Among them, S' i is the strategy score of the ith business person, and β is the adjustment coefficient for a certain strategy generation.

[0235] For example:

[0236] If S' 1 For business person A, the overall association strength AS is 1.37, and the adjustment coefficient β is 0.5, so the strategy score of this business person is S' 1 =0.5×1.37=0.685; This indicates that the overall performance of this salesperson is good, but there is still room for improvement. The customer visit frequency may be low, and the correlation between the salesperson and customer quality inspection is low. The system will suggest that the salesperson adjust the existing interaction strategy and increase interaction with customers. If S' 2 For business person B, the overall association strength AS is 1.72, and the adjustment coefficient β is 0.65. Then the strategy score of this business person is S' 2 =0.55×1.72=0.946; This indicates that this business person performs very well in all aspects and is able to maintain a high degree of relevance with customers. The system may encourage him to maintain the existing strategy.

[0237] S' i It is the comprehensive behavioral performance and optimization strategy of business personnel. The various parameters (such as customer visit frequency, task completion rate, customer satisfaction, etc.) combined with the interaction information between business personnel and customers, such as task completion status, customer feedback, visit frequency, etc. can reflect the intensity of interaction between business personnel and specific customers; therefore, it can predict the potential connection between business personnel and customers, and formulate personalized strategies for different business personnel to optimize the efficiency of the customer management system and user experience.

[0238] Based on the above ideal embodiments of the present invention, the relevant staff can make various changes and modifications without departing from the technical concept of the present invention through the above description. The technical scope of the present invention is not limited to the contents of the specification, and its technical scope must be determined according to the scope of the claims.

Claims

1. An evaluation system based on business personnel and customers, characterized in that: include: Data collection module, customer big data management module, data analysis module, strategy control module and execution module; among them, The data collection module is used to collect business personnel's location information, daily behavior data, access data and customer interaction records; The customer big data management module is used to collect, store, analyze and manage the interaction data between business personnel and customers, customer behavior data, and demand data; The data analysis module pre-processes the data from the customer big data management module and the data collection module, and identifies the behavior patterns of business personnel and customer needs; The policy control module reports policies and reporting reminders based on data analysis results, optimizing the workflow of business personnel; The execution module automatically reports, uploads data, and sends reminders according to policy control.

2. The evaluation system based on business personnel and customers according to claim 1, characterized in that: The location information of business personnel includes: longitude and latitude, timestamp, WiFi positioning, network base station information, accelerometer, and gyroscope.

3. The evaluation system based on business personnel and customers according to claim 1 is characterized in that: The daily behavior data of business personnel include: clocking in and out data, itinerary arrangements, steps and exercise data, business trip records and task data.

4. The evaluation system based on business personnel and customers according to claim 1, characterized in that: The visit data of business personnel include: visit time, visit location, visit type, visit form, visit goal, task achievement status and visit content.

5. The evaluation system based on business personnel and customers according to claim 1, characterized in that: The business personnel’s customer interaction records include: customer visit records and follow-up after the visit.

6. The evaluation system based on business personnel and customers according to claim 1, characterized in that: The customer big data management module includes: customer basic data, customer transaction data, customer access data, external market and industry data, customer life cycle data and data security and privacy protection.

7. An evaluation method based on business personnel and customers, characterized in that: include: Step 1: Identify the behavior patterns of business personnel and customer needs. First, pre-process the business personnel and customer data; Step 2: De-noise and normalize the pre-processed data; Step 3: extract the behavior characteristics of the business personnel and calculate the feature vector of the behavior characteristics; Step 4: Calculate the distance metric of the behavior feature clustering using the feature vector of the behavior feature; Step 5: Extract customer demand characteristics; Step 6: Correlate the behavior characteristics of the business personnel with the customer demand characteristics to obtain the correlation strength between the behavior characteristics and the customer demand characteristics; Step 7: Use the correlation strength to generate and optimize strategies.

8. The evaluation method based on business personnel and customers according to claim 7, characterized in that: The behavioral characteristics of business personnel include: access frequency characteristics, response time characteristics, sales conversion rate characteristics and customer satisfaction characteristics.

9. The evaluation method based on business personnel and customers according to claim 7, characterized in that: The formula for the strength of association between behavioral characteristics and customer demand characteristics is: Among them, B i is the behavioral feature vector of the ith business person, D i’ is the demand feature vector of the i'th customer, AR(B i ,D i' ) is B i With D i’ degree of correlation.

10. The evaluation method based on business personnel and customers according to claim 7, characterized in that: The formula for strategy generation is: S' i =β·AS(B i ,D i' ) (13) Among them, AS(B i ,D i' ) is B i With D i’ , and β is the adjustment coefficient generated by a certain strategy.

Images