Customer demand management method and system based on big data analysis

Abstract

The invention relates to the technical field of customer demand management, and particularly discloses a customer demand management method and system based on big data analysis, and the method comprises the steps: S1, collecting the image data of a customer through a collection module; s2, analyzing and extracting features of five sense organs and a dressing image of the customer through a feature extraction module, preliminarily predicting characters and demands of the customer through a big data analysis module based on a big data analysis technology, and pushing a preliminary prediction result to service personnel; s3, in the service process, customer expression and body language features are analyzed and extracted in real time through a feature extraction module and analyzed in real time through an emotion analysis module, the emotion state of the customer is monitored in real time, and service personnel are assisted in service; according to the method, client image data is collected, client characters and demands are preliminarily predicted based on big data analysis, and the preliminary prediction result is pushed to service personnel, so that the service personnel can better grasp the client demands.

Description

Technical Field

[0001] The present invention relates to the technical field of customer demand management, and specifically to a customer demand management method and system based on big data analysis. Background Art

[0002] With the vigorous development of the online economy, the traditional retail industry has suffered an unprecedented impact. In order to gain a foothold in the fierce market competition, offline stores have gradually shifted their core competitiveness to personalized service capabilities. However, there are still many shortcomings in the current customer demand management of offline stores.

[0003] Traditional customer demand management relies heavily on the experience and judgment of service personnel, which is highly subjective and lacks precision. It is difficult to quickly and accurately grasp the real needs and emotional changes of customers. For example, it is difficult for service personnel to capture the emotional signals conveyed by customers' subtle expressions and body language by relying solely on visual observation, and it is even more impossible to conduct in-depth analysis based on large amounts of data. Moreover, during the service process, service strategies are often relatively simple and cannot be flexibly adjusted according to the real-time emotional state of customers, resulting in poor customer experience and easy customer loss. At the same time, there is also a lack of scientific and reasonable mechanisms for the deployment and coordination of service personnel, making it difficult to give full play to the team's advantages and improve the overall service quality. Summary of the Invention

[0004] The purpose of this invention is to provide a customer demand management method and system based on big data analysis to solve the following technical problems:

[0005] The question is how to use advanced technology to accurately analyze customer needs and emotions to enhance the personalized service capabilities of offline stores.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A customer demand management method based on big data analysis, the method comprising:

[0008] S1. Collect the customer's image data through the acquisition module;

[0009] S2. Analyze and extract the customer's facial features and clothing images through the feature extraction module, make a preliminary prediction of the customer's personality and needs based on big data analysis technology through the big data analysis module, and push the preliminary prediction results to the service personnel;

[0010] S3. During the service process, the feature extraction module extracts the customer's facial expressions and body language features in real time and uses the emotion analysis module to analyze the customer's emotional state in real time and assist service personnel in providing services;

[0011] S4. Continuously monitor the cumulative emotion value of customers within the sliding time window through the early warning analysis module, and compare the cumulative emotion value with the preset emotion threshold range. When the cumulative emotion value is greater than the maximum value of the preset emotion threshold range, the emotion analysis module will continue to assist the service personnel in providing service. When the cumulative emotion value is within the preset emotion threshold range, the emotion analysis module analysis mode will be switched to manual intervention mode, and other service personnel in the store will intervene to provide collaborative service. When the cumulative emotion value is less than the minimum value of the preset emotion threshold range, a service handover instruction will be automatically generated to prompt other service personnel in the store to take over the service work of the current customer.

[0012] Furthermore, in step S2, the process of the big data analysis module making a preliminary prediction of the customer's personality based on big data analysis technology includes:

[0013] Extract facial features from the customer's facial image and construct a facial feature set Q;

[0014] Match the facial features set Q with the facial features-personality association rule library established based on big data analysis;

[0015] If the similarity between the feature combination in Q and a certain facial feature combination in the rule base reaches the preset similarity threshold, the personality type corresponding to the facial feature combination is used as the preliminary prediction result of the customer's personality;

[0016] If the similarity between the feature combination in Q and any facial feature combination in the rule base does not reach the preset similarity threshold, the personality types corresponding to the top three facial feature combinations in the rule base with the highest similarity to the feature combination in Q will be used as the preliminary prediction results of the customer's personality.

[0017] Furthermore, in step S2, the process of the big data analysis module making a preliminary forecast of customer demand based on big data analysis technology includes:

[0018] Segment customer clothing images, identify clothing style, color, and material features, and construct a clothing feature set W;

[0019] Calculate the similarity between the clothing feature set W and each clothing feature combination in the clothing-demand association rule library established based on big data analysis;

[0020] The product categories corresponding to the clothing feature combinations with the highest similarity are used as preliminary predictions of customer demand.

[0021] Furthermore, in step S3, the process of the emotion analysis module monitoring the customer's emotional state in real time includes:

[0022] Identify and extract customer facial expressions and body language features;

[0023] By formula Analyze and calculate to obtain the customer's emotional characteristic value R;

[0024] Among them, N is the number of preset expression features, , is the emotional evaluation value of the i-th facial expression feature, M is the number of preset body language features, , is the emotional evaluation value of the j-th body language feature, 、 is the first weight coefficient;

[0025] With the timestamp as the X-axis and the customer emotion characteristic value R obtained by analysis as the Y-axis, a rectangular coordinate system is established. The distribution points composed of each time node and emotion characteristic value in the process of serving customers are connected in sequence with a smooth curve to form a curve of the customer's emotional state. .

[0026] Furthermore, in step S4, the process of the early warning analysis module continuously monitoring the accumulated emotion value of the customer within the sliding time window includes:

[0027]

[0028]

[0029] The cumulative emotion value of customers in the sliding time window is obtained by analyzing and calculating formulas (1)-(2) ;

[0030] in, is a sliding time window, is the curve showing the change of customer negative emotion value over time. 、 is the second weight coefficient;

[0031] The accumulated emotion value and preset emotion threshold range Make a comparison;

[0032] when When the service personnel are in a hurry, the sentiment analysis module will continue to assist the service personnel in providing services;

[0033] when When the store is busy, other service personnel in the store will intervene to provide collaborative services;

[0034] when When the service staff in the store is prompted to take over the service work of the current customer.

[0035] Furthermore, the maximum value of the preset emotion threshold range can be intelligently adjusted in the following manner:

[0036] Establish a service personnel evaluation index system to quantitatively score service personnel based on three dimensions: service time, service quality, and on-site service performance;

[0037] By formula Analyze and calculate the maximum value of the preset emotion threshold range ;

[0038] in, is the base value of the maximum value of the preset emotion threshold range, is the adjustment coefficient, is the cumulative service time of the service personnel, X is the historical evaluation value of the service quality of the service personnel, and C is the service performance of the service personnel in the current service process. 、 、 is the third weight coefficient.

[0039] Furthermore, the other service personnel screening process includes:

[0040] Establish a service personnel screening index system to quantitatively score service personnel based on three dimensions: service experience, service evaluation, and service rights;

[0041] By formula Analyze and calculate the comprehensive score of each service staff ;

[0042] in, is the service experience evaluation value of the service personnel, is the service evaluation value of the service personnel, is the service rights evaluation value of the service personnel, 、 、 is the fourth weight coefficient;

[0043] Service personnel are sorted from high to low according to their comprehensive scores, and service personnel with higher comprehensive scores are selected to intervene in collaborative services or take over the service work of current customers; when the comprehensive scores are the same, service personnel with higher service authority levels are given priority.

[0044] A customer demand management system based on big data analysis, wherein the system is applied to a customer demand management method based on big data analysis, and the system comprises:

[0045] The acquisition module is used to collect the customer's image data and service-related data of the service personnel;

[0046] Feature extraction module, used to analyze and extract customer facial features, clothing images, expressions, and body language features;

[0047] The big data analysis module is used to analyze the customer's facial features and clothing images to make preliminary predictions about the customer's personality and needs to assist service personnel in providing services;

[0048] The emotion analysis module is used to monitor the customer's emotional state in real time based on their facial expressions and body language characteristics to assist service personnel in providing services;

[0049] The early warning analysis module continuously monitors the customer's cumulative emotion value within a sliding time window, compares it with the preset emotion threshold range, and triggers different service response mechanisms based on the comparison results; intelligently adjusts the maximum value of the preset emotion threshold range; and screens other service personnel when selecting them to intervene in collaborative services or take over the current customer's service work;

[0050] The communication module is used to transmit information such as the preliminary prediction results of the big data analysis module on customer personality and needs, the customer emotional status monitoring results of the emotion analysis module, and the service response instructions of the early warning analysis module in real time to the headphones worn by service personnel.

[0051] Beneficial effects of the present invention:

[0052] (1) The present invention collects customer image data, makes preliminary predictions about customer personality and needs based on big data analysis, and pushes the preliminary prediction results to service personnel to improve their understanding of customer needs. During the service process, the present invention monitors the customer's emotional state in real time and pushes the emotional state to service personnel to assist service personnel in providing better services. Different service responses are triggered based on the customer's accumulated emotional value, which can accurately grasp customer needs and thus improve service quality and customer satisfaction.

[0053] (2) The present invention establishes a service personnel evaluation index system, comprehensively considers factors such as service time, service quality and on-site performance of service personnel, and dynamically adjusts the maximum value of the preset emotion threshold range, so that the service response mechanism is more in line with the actual ability of service personnel, and improves the scientificity and flexibility of service management.

[0054] (3) The present invention establishes a service personnel screening index system, comprehensively considers factors such as service personnel's service experience, service evaluation and service rights, calculates comprehensive scores and performs sorting and screening, and can select the most suitable personnel when other service personnel need to intervene, thereby ensuring the continuity and high quality of service. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The present invention will be further described below with reference to the accompanying drawings.

[0056] Figure 1This is a flowchart of the steps of a customer demand management method based on big data analysis proposed by the present invention;

[0057] Figure 2 This is a schematic block diagram of a customer demand management system based on big data analysis proposed by the present invention. DETAILED DESCRIPTION

[0058] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0059] See also Figure 1 As shown, in one embodiment, a customer demand management method based on big data analysis is provided, the method comprising:

[0060] S1. Capturing customer image data through a capture module. The capture module may be an image capture device such as a high-definition camera installed in the store. The camera captures images of customers entering the store and obtains image data containing information such as the customer's face, clothing, expression, and body language.

[0061] S2. Analyze and extract the customer's facial features and clothing images through the feature extraction module, make a preliminary prediction of the customer's personality and needs based on big data analysis technology through the big data analysis module, and push the preliminary prediction results to the service personnel;

[0062] S3. During the service process, the feature extraction module extracts the customer's facial expressions and body language features in real time and uses the emotion analysis module to analyze the customer's emotional state in real time and assist service personnel in providing services;

[0063] S4. Continuously monitor the cumulative emotion value of customers within the sliding time window through the early warning analysis module, and compare the cumulative emotion value with the preset emotion threshold range. When the cumulative emotion value is greater than the maximum value of the preset emotion threshold range, the emotion analysis module will continue to assist the service personnel in providing service. When the cumulative emotion value is within the preset emotion threshold range, the emotion analysis module analysis mode will be switched to manual intervention mode, and other service personnel in the store will intervene to provide collaborative service. When the cumulative emotion value is less than the minimum value of the preset emotion threshold range, a service handover instruction will be automatically generated to prompt other service personnel in the store to take over the service work of the current customer.

[0064] Through the above technical solution, this embodiment provides a customer demand management method based on big data analysis. The method collects customer image data, makes a preliminary prediction of the customer's personality and needs based on big data analysis, and pushes the preliminary prediction results to service personnel to improve the service personnel's grasp of customer needs. During the service process, the customer's emotional state is monitored in real time, and the emotional state is pushed to the service personnel to assist the service personnel in providing better service, and different service responses are triggered according to the customer's accumulated emotional value, which can accurately grasp customer needs and thus improve service quality and customer satisfaction.

[0065] In one embodiment, in step S2, the process of the big data analysis module making a preliminary prediction of the customer's personality based on big data analysis technology includes:

[0066] Extract facial features from the customer's facial image and construct a facial feature set Q. Image processing and computer vision techniques can be used to extract facial features from the customer's facial image. For example, key point detection algorithms can be used to identify features such as the outline, shape, and size of the customer's facial features.

[0067] Match the facial feature set Q with the facial feature-personality association rule base established based on big data analysis. The facial feature-personality association rule base can be established by collecting facial feature image data of a large number of people with known personality types and applying cluster analysis, machine learning and other algorithms to mine the association between facial feature combinations and personality types. It can also be established manually based on experience.

[0068] If the similarity between the feature combination in Q and a certain facial feature combination in the rule base reaches a preset similarity threshold (the preset similarity threshold can be adjusted based on actual conditions and experimental results, for example, set to 80%), the personality type corresponding to the facial feature combination will be used as the preliminary prediction result of the customer's personality;

[0069] If the similarity between the feature combination in Q and any facial feature combination in the rule base does not reach the preset similarity threshold, the personality types corresponding to the top three facial feature combinations in the rule base with the highest similarity to the feature combination in Q will be used as the preliminary prediction results of the customer's personality.

[0070] In step S2, the process of the big data analysis module making a preliminary forecast of customer demand based on big data analysis technology includes:

[0071] Segment the customer's clothing image. Clothing image segmentation can use image segmentation algorithms to separate the customer's clothing from the overall image and identify clothing style, color, and material features. The identification of clothing style, color, and material features can be trained and recognized with the help of deep learning models, such as convolutional neural networks, to construct a clothing feature set W;

[0072] Calculate the similarity between the clothing feature set W and each clothing feature combination in the clothing-demand association rule library established based on big data analysis. The clothing-demand association rule library is also constructed based on big data analysis of a large amount of customer purchase data and clothing data. It collects customer purchase records and their clothing information at the time, and uses data mining algorithms to analyze the association between clothing features and purchased product categories to form a rule library. The similarity can be determined using algorithms such as cosine similarity.

[0073] The product categories corresponding to the clothing feature combinations with the highest similarity are used as preliminary predictions of customer demand.

[0074] Through the above technical solution, this embodiment provides a method for preliminary prediction of customer personality and needs based on big data analysis. The method extracts the customer's facial features and clothing features, constructs a facial feature set Q and a clothing feature set W, respectively, and matches and calculates similarity with the facial feature-personality association rule library and clothing-demand association rule library established based on big data. Based on the customer's external features, it can preliminarily judge their personality type and potential needs, providing an important reference basis for service personnel to formulate targeted service strategies and prepare product information in advance, effectively improving the adaptability and accuracy of the service, and enhancing the customer service experience.

[0075] In one embodiment, in step S3, the process of the emotion analysis module monitoring the customer's emotional state in real time includes:

[0076] Identify and extract customer facial expressions and body language features;

[0077] By formula Analyze and calculate to obtain the customer's emotional characteristic value R;

[0078] Among them, N is the number of preset expression features, and the appropriate value can be determined based on actual research and experiments. For example, it is set to 10 common expression features. , is the emotion evaluation value of the i-th facial expression feature. Various facial expression features can be manually assigned corresponding emotion evaluation scores. The emotion evaluation value of the facial expression feature that can feedback positive emotions is a positive number, and the emotion evaluation value of the facial expression feature that can feedback negative emotions is a negative number. For example, the frowning expression can be set to -0.8 emotion evaluation value, and the smiling expression can be set to 0.7 emotion evaluation value. M is the preset number of body language features, which can be set according to actual conditions, such as 8. , is the emotional evaluation value of the jth body language feature. Various body languages ​​can be manually assigned corresponding emotional evaluation scores. Similarly, the emotional evaluation value of the body language that reflects positive emotions can be positive, and the emotional evaluation value of the body language that reflects negative emotions can be negative. For example, the body language of nodding can be set to an emotional evaluation value of 0.5, and the body language of shaking the head can be set to an emotional evaluation value of -0.4. 、 is the first weight coefficient, which can be obtained based on experience;

[0079] With the timestamp as the X-axis and the customer emotion characteristic value R obtained by analysis as the Y-axis, a rectangular coordinate system is established. The distribution points composed of each time node and emotion characteristic value in the process of serving customers are connected in sequence with a smooth curve to form a curve of the customer's emotional state. When the customer emotion characteristic value R is above the X-axis, it means that the customer emotion state is positive; when the customer emotion characteristic value R is below the X-axis, it means that the customer emotion state is negative.

[0080] Through the above technical solution, this embodiment provides a real-time monitoring method for customer emotional status. The method identifies customer facial expressions and body language characteristics, uses specific formulas to calculate emotional characteristic values ​​and draws emotional status curves. It can intuitively and in real time present the customer's emotional changes during the service process, and assist service personnel to adjust the service methods in a timely manner.

[0081] In one embodiment, in step S4, the process of the early warning analysis module continuously monitoring the accumulated emotion value of the customer within the sliding time window includes:

[0082]

[0083]

[0084] The cumulative emotion value of customers in the sliding time window is obtained by analyzing and calculating formulas (1)-(2) ;

[0085] in, It is a sliding time window, and its size can be set according to the actual service scenario and needs. For example, it can be set to 10 minutes, 15 minutes, etc. The curve of customer negative emotion value changing over time is obtained by analyzing customer emotion feature value. After analysis and processing, 、 is the second weight coefficient, which can be optimized through experiments and data analysis;

[0086] The accumulated emotion value and preset emotion threshold range The preset emotion threshold range can be obtained by preset according to experience;

[0087] when When the service personnel are in a hurry, the sentiment analysis module will continue to assist the service personnel in providing services;

[0088] when When the customer is not satisfied with the service provided by the current service staff, it means that there is a small probability that the current customer is not satisfied with the service provided by the current service staff. Other service staff in the store will intervene to provide collaborative services. The collaborative services provided by other service staff can be divided into various types. For example, other service staff can make suggestions to the current service staff in the background through wireless communication equipment, or other service staff can appear on site to cooperate with the current service staff. The specific options are set by the store manager.

[0089] when When the current customer is dissatisfied with the service provided by the current service staff, it means that the current customer is likely to be dissatisfied with the service provided by the current service staff. If the current service staff continues to provide services to the customer, the current customer may be lost, prompting other service staff in the store to take over the service work of the current customer.

[0090] Through the above technical solution, this embodiment provides a customer service early warning method based on cumulative emotional values. The method monitors the cumulative emotional values ​​of customers within a sliding time window and compares them with a preset threshold range. It triggers corresponding service responses according to different situations, and can respond to changes in customer emotions in a timely manner, thereby accurately analyzing customer needs, ensuring service quality, and improving customer experience.

[0091] In one embodiment, the maximum value of the preset emotion threshold range can be intelligently adjusted by:

[0092] Establish a service personnel evaluation index system to quantitatively score service personnel based on three dimensions: service time, service quality, and on-site service performance. Service time can be obtained by recording the cumulative time service personnel have served customers through the system; historical service quality evaluation values ​​can be calculated based on customers' evaluations of service personnel's past services, combined with factors such as the number of evaluations; and on-site service performance can be obtained through observation and scoring by on-site management personnel and real-time customer feedback (e.g., the number of times customer needs were misjudged).

[0093] By formula Analyze and calculate the maximum value of the preset emotion threshold range ;

[0094] in, It is the basic value of the maximum value of the preset emotion threshold range. An initial value can be set according to the general situation of the industry or the historical experience of the enterprise. To determine the adjustment coefficient, we can establish an optimization model that includes multiple objectives such as customer satisfaction and service efficiency, and conduct regression analysis or machine learning training based on historical service data. We can also use A / B testing to compare the service effects under different coefficients and select the optimal value. is the service staff's cumulative service time, that is, the total time the service staff has participated in customer service since joining the company. X is the service staff's historical service quality evaluation value. Specifically, the historical evaluation value can be calculated by integrating customer active evaluations (such as satisfaction scores and text feedback), quality inspection scores (evaluated by the internal quality inspection team based on service audio / video recordings), complaint records, and other data according to certain scoring rules (such as weighted average). C is the service staff's on-site performance during the current service process. Specifically, real-time speech analysis technology and behavior monitoring systems can be used to identify on-site performance indicators such as the service staff's tone, speaking speed, use of professional terms, and problem-solving speed. These indicators are then converted into performance values ​​using a preset algorithm model. 、 、 For the third weight coefficient, we can design multiple sets of preset emotion threshold calculation schemes with different weight combinations, conduct small-scale pilot projects in actual business scenarios, and use statistical methods to determine the optimal weight coefficients of different evaluation dimensions in the calculation by comparing key indicators such as customer complaint rate and service dispute handling efficiency under each set of schemes.

[0095] Through the above technical solution, this embodiment provides an intelligent adjustment method for the maximum value of the preset emotion threshold range. The method establishes a service personnel evaluation index system, comprehensively considers factors such as the service personnel's service time, service quality, and on-site performance, and dynamically adjusts the maximum value of the preset emotion threshold range, so that the service response mechanism is more in line with the actual capabilities of the service personnel, and improves the scientificity and flexibility of service management.

[0096] In one embodiment, the other service personnel screening process includes:

[0097] Establish a service personnel screening index system to quantitatively score service personnel based on three dimensions: service experience, service evaluation, and service rights. The service experience evaluation value can be quantified based on factors such as the number of years the service personnel have engaged in related service work and the number of projects they have participated in. The service evaluation value can be calculated based on the customer's historical evaluation score of the service personnel. The service rights evaluation value can be set at different levels based on the service personnel's position and authority within the company.

[0098] By formula Analyze and calculate the comprehensive score of each service staff ;

[0099] in, The service experience evaluation value of the service personnel can be obtained by the following methods: statistically analyzing the service personnel's years of service experience, the number of projects they have participated in, the number of times they have handled complex problems, and other dimensional data, and performing weighted calculations based on the preset scoring model. The service evaluation value of the service personnel can be specifically obtained through the customer's evaluation of the service process of the service personnel, including service attitude, response speed, problem-solving effect, etc. Customer ratings can be collected through online evaluation systems, questionnaires, etc., and the ratings can be summarized and weighted. The service rights evaluation value of service personnel can be evaluated based on factors such as the service personnel's position authority within the company, resource allocation ability, decision-making influence, etc., and the company's management or relevant departments will score and determine it based on the established evaluation standards. 、 、 The fourth weight coefficient is used to determine the relative importance of service experience, service evaluation, and service rights in the calculation of the comprehensive score, which can be obtained and adjusted based on actual business needs and data analysis;

[0100] Service personnel are sorted from high to low according to their comprehensive scores, and service personnel with higher comprehensive scores are selected to intervene in collaborative services or take over the service work of current customers; when the comprehensive scores are the same, service personnel with higher service authority levels are given priority.

[0101] Through the above technical solution, this embodiment provides a method for screening other service personnel. The method establishes a service personnel screening index system, comprehensively considers factors such as the service personnel's service experience, service evaluation, and service rights, calculates a comprehensive score, and performs sorting and screening. When other service personnel need to intervene, the most suitable personnel can be selected to ensure the continuity and high quality of the service.

[0102] See also Figure 2 As shown, in one embodiment, a customer demand management system based on big data analysis is provided, and the system is applied to a customer demand management method based on big data analysis, and the system includes:

[0103] The acquisition module is used to collect customer image data and service-related data of service personnel. The hardware equipment of the acquisition module can be multiple high-definition cameras distributed in different areas of the store to collect customer image data in all directions. At the same time, the system records the service-related data of service personnel, such as service time and service evaluation;

[0104] The feature extraction module is used to analyze and extract the customer's facial features, clothing images, expressions, and body language features. The feature extraction module can use a variety of advanced image processing and machine learning algorithms to accurately extract various customer characteristics;

[0105] The big data analysis module uses a big data processing platform and algorithms to analyze and mine large amounts of data, establish an association rule library, and conduct big data analysis based on customer facial features and clothing images to make preliminary predictions about customer personality and needs to assist service personnel in providing services;

[0106] The emotion analysis module is used to monitor the customer's emotional state in real time based on their facial expressions and body language characteristics to assist service personnel in providing services;

[0107] The early warning analysis module continuously monitors the customer's cumulative emotion value within a sliding time window, compares it with the preset emotion threshold range, and triggers different service response mechanisms based on the comparison results; intelligently adjusts the maximum value of the preset emotion threshold range; and screens other service personnel when selecting them to intervene in collaborative services or take over the current customer's service work;

[0108] The communication module uses wireless technologies such as Bluetooth and Wi-Fi to transmit information such as the big data analysis module's preliminary prediction results on customer personality and needs, the emotion analysis module's customer emotional status monitoring results, and the early warning analysis module's service response instructions in real time to the headphones worn by service personnel, so that service personnel can obtain information in a timely manner and make corresponding service strategy adjustments.

[0109] Through the above technical solution, this embodiment provides a customer demand management system based on big data analysis. The system realizes full-process management from data collection, feature extraction, demand and personality prediction, emotion monitoring to service response and personnel management through the collaborative work of various functional modules, providing strong technical support for enterprises to efficiently manage customer needs and improve service levels.

[0110] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A customer demand management method based on big data analysis, characterized in that: The method comprises: S1. Collect the customer's image data through the acquisition module; S2. Analyze and extract the customer's facial features and clothing images through the feature extraction module, make a preliminary prediction of the customer's personality and needs based on big data analysis technology through the big data analysis module, and push the preliminary prediction results to the service personnel; S3. During the service process, the feature extraction module extracts the customer's facial expressions and body language features in real time and uses the emotion analysis module to analyze the customer's emotional state in real time and assist service personnel in providing services; S4. Continuously monitor the cumulative emotion value of customers within the sliding time window through the early warning analysis module, and compare the cumulative emotion value with the preset emotion threshold range. When the cumulative emotion value is greater than the maximum value of the preset emotion threshold range, the emotion analysis module will continue to assist the service personnel in providing service. When the cumulative emotion value is within the preset emotion threshold range, the emotion analysis module analysis mode will be switched to manual intervention mode, and other service personnel in the store will intervene to provide collaborative service. When the cumulative emotion value is less than the minimum value of the preset emotion threshold range, a service handover instruction will be automatically generated to prompt other service personnel in the store to take over the service work of the current customer.

2. The customer demand management method based on big data analysis according to claim 1, characterized in that: In step S2, the process of the big data analysis module making a preliminary prediction of the customer's personality based on big data analysis technology includes: Extract facial features from the customer's facial image and construct a facial feature set Q; Match the facial features set Q with the facial features-personality association rule library established based on big data analysis; If the similarity between the feature combination in Q and a certain facial feature combination in the rule base reaches the preset similarity threshold, the personality type corresponding to the facial feature combination is used as the preliminary prediction result of the customer's personality; If the similarity between the feature combination in Q and any facial feature combination in the rule base does not reach the preset similarity threshold, the personality types corresponding to the top three facial feature combinations in the rule base with the highest similarity to the feature combination in Q will be used as the preliminary prediction results of the customer's personality.

3. The customer demand management method based on big data analysis according to claim 2 is characterized in that: In step S2, the process of the big data analysis module making a preliminary forecast of customer demand based on big data analysis technology includes: Segment customer clothing images, identify clothing style, color, and material features, and construct a clothing feature set W; Calculate the similarity between the clothing feature set W and each clothing feature combination in the clothing-demand association rule library established based on big data analysis; The product categories corresponding to the clothing feature combinations with the highest similarity are used as preliminary predictions of customer demand.

4. The customer demand management method based on big data analysis according to claim 3 is characterized in that: In step S3, the process of the emotion analysis module monitoring the customer's emotional state in real time includes: Identify and extract customer facial expressions and body language features; By formula Analyze and calculate to obtain the customer's emotional characteristic value R; Among them, N is the number of preset expression features, , is the emotional evaluation value of the i-th facial expression feature, M is the number of preset body language features, , is the emotional evaluation value of the j-th body language feature, 、 is the first weight coefficient; With the timestamp as the X-axis and the customer emotion characteristic value R obtained by analysis as the Y-axis, a rectangular coordinate system is established. The distribution points composed of each time node and emotion characteristic value in the process of serving customers are connected in sequence with a smooth curve to form a curve of the customer's emotional state. .

5. The customer demand management method based on big data analysis according to claim 4 is characterized in that: In step S4, the process of the early warning analysis module continuously monitoring the accumulated emotion value of the customer within the sliding time window includes: The cumulative emotion value of customers in the sliding time window is obtained by analyzing and calculating formulas (1)-(2) ; in, is a sliding time window, is the curve showing the change of customer negative emotion value over time. 、 is the second weight coefficient; The accumulated emotion value and preset emotion threshold range Make a comparison; when When the service personnel are in a hurry, the sentiment analysis module will continue to assist the service personnel in providing services; when When the store is busy, other service personnel in the store will intervene to provide collaborative services; when When the service staff in the store is prompted to take over the service work of the current customer.

6. The customer demand management method based on big data analysis according to claim 5 is characterized in that: The maximum value of the preset emotion threshold range can be intelligently adjusted in the following ways: Establish a service personnel evaluation index system to quantitatively score service personnel based on three dimensions: service time, service quality, and on-site service performance; By formula Analyze and calculate the maximum value of the preset emotion threshold range ; in, is the base value of the maximum value of the preset emotion threshold range, is the adjustment coefficient, is the cumulative service time of the service personnel, X is the historical evaluation value of the service quality of the service personnel, and C is the service performance of the service personnel in the current service process. 、 、 is the third weight coefficient.

7. The customer demand management method based on big data analysis according to claim 6 is characterized in that: The other service personnel screening process includes: Establish a service personnel screening index system to quantitatively score service personnel based on three dimensions: service experience, service evaluation, and service rights; By formula Analyze and calculate the comprehensive score of each service staff ; in, is the service experience evaluation value of the service personnel, is the service evaluation value of the service personnel, is the service rights evaluation value of the service personnel, 、 、 is the fourth weight coefficient; Service personnel are sorted from high to low according to their comprehensive scores, and service personnel with higher comprehensive scores are selected to intervene in collaborative services or take over the service work of current customers; when the comprehensive scores are the same, service personnel with higher service authority levels are given priority.

8. A customer demand management system based on big data analysis, characterized in that: The system is applied to a customer demand management method based on big data analysis according to any one of claims 1 to 7, and the system includes: The acquisition module is used to collect the customer's image data and service-related data of the service personnel; Feature extraction module, used to analyze and extract customer facial features, clothing images, expressions, and body language features; The big data analysis module is used to analyze the customer's facial features and clothing images to make preliminary predictions about the customer's personality and needs to assist service personnel in providing services; The emotion analysis module is used to monitor the customer's emotional state in real time based on their facial expressions and body language characteristics to assist service personnel in providing services; The early warning analysis module continuously monitors the customer's cumulative emotion value within a sliding time window, compares it with the preset emotion threshold range, and triggers different service response mechanisms based on the comparison results; intelligently adjusts the maximum value of the preset emotion threshold range; and screens other service personnel when selecting them to intervene in collaborative services or take over the current customer's service work; The communication module is used to transmit information such as the preliminary prediction results of the big data analysis module on customer personality and needs, the customer emotional status monitoring results of the emotion analysis module, and the service response instructions of the early warning analysis module in real time to the headphones worn by service personnel.

Images