A customer management method and system based on cloud server

Abstract

The present invention relates to the field of customer management technology, and in particular to a customer management method and system based on a cloud server. The method comprises the following steps: obtaining customer information data using a cloud server; introducing an intelligent interactive plug-in based on the customer information data to obtain intelligent question and answer plug-in usage data; screening customer question and answer content of the customer information data through the intelligent question and answer plug-in usage data to obtain customer question and answer content collection data; performing data preprocessing on the customer question and answer content collection data to generate standard customer question and answer content data; performing semantic analysis on the standard customer question and answer content data to generate customer question and answer content semantic analysis data; performing user behavior modeling on the customer information data according to the customer question and answer content semantic analysis data to generate a virtual digital twin model. The present invention improves the dynamics and accuracy of customer management through cloud servers, intelligent customer behavior modeling and dynamic interaction strategies.

Description

Technical Field

[0001] The present invention relates to the technical field of customer management, and in particular to a customer management method and system based on a cloud server. Background Art

[0002] Initially, customer management systems mainly relied on local servers for data storage and processing, and most of them used stand-alone software. This approach had disadvantages such as data silos, poor scalability, and high maintenance costs. With the expansion of enterprise scale and the growth of data volume, traditional methods are increasingly unable to meet the requirements of enterprises for efficient and real-time customer management. The rise of cloud computing technology has provided a new solution for customer management. By migrating the calculation and data storage of the customer management system to the cloud, cloud servers enable enterprises to avoid investing a lot of hardware resources and management costs. The operation and maintenance of the system are the responsibility of professional cloud service providers. This transformation not only greatly reduces the IT costs of enterprises, but also improves the scalability, flexibility and real-time synchronization capabilities of the system. However, traditional customer management is usually based on "batch" processing of customers, and the management of customers is relatively rigid, which makes customer management more dynamic and less accurate. Summary of the invention

[0003] Based on this, it is necessary to provide a customer management method and system based on a cloud server to solve at least one of the above technical problems.

[0004] To achieve the above object, a customer management method based on a cloud server is provided, the method comprising the following steps: Step S1: using a cloud server to obtain customer information data; introducing an intelligent interactive plug-in based on the customer information data to obtain intelligent question and answer plug-in usage data; filtering customer question and answer content on the customer information data using the intelligent question and answer plug-in usage data to obtain customer question and answer content collection data; performing data preprocessing on the customer question and answer content collection data to generate standard customer question and answer content data; Step S2: semantically parse the standard customer question and answer content data to generate customer question and answer content semantic parsing data; perform user behavior modeling on the customer information data based on the customer question and answer content semantic parsing data to generate a virtual digital twin model, wherein the virtual digital twin model includes a surface digital model and a hidden digital model; Step S3: Track customer behavior on the hidden digital model to obtain customer behavior tracking data; predict customer behavior on the hidden digital model based on the customer behavior tracking data to generate customer behavior prediction data; use the customer behavior prediction data to dynamically adjust the interaction strategy of the surface digital model to generate an intelligent customer interaction strategy; Step S4: Collect customer sentiment feedback from customer Q&A content through intelligent customer interaction strategies to generate customer sentiment feedback data; construct a profile based on the customer sentiment feedback data to obtain a virtual customer profile, and store the virtual customer profile in the cloud to perform customer management tasks.

[0005] The present invention obtains customer information data through a cloud server, and introduces an intelligent question-and-answer plug-in based on these data for screening and preprocessing to generate standard customer question-and-answer content data. This step ensures the high quality and structure of customer information data, so that subsequent processing can be carried out accurately; through data screening and preprocessing, noise is removed, and the availability and accuracy of data are improved. The standard customer question-and-answer content data is semantically parsed, and user behavior modeling is performed on customer information based on the parsing results to generate a virtual digital twin model. The hidden digital model is used to track customer behavior, and the surface digital model is adjusted using behavior prediction data to generate an intelligent customer interaction strategy. Real-time tracking and prediction of customer behavior enables the interaction strategy to be dynamically adjusted based on the real-time needs and behaviors of customers, improves the accuracy and personalization of customer interaction, and enhances customer experience. Customer emotional feedback is performed based on the intelligent customer interaction strategy, customer emotional feedback data is generated, and a virtual customer portrait is constructed for cloud storage. Through emotional feedback, the system can better capture customer emotional changes, adjust the interaction strategy in a timely manner, and optimize customer experience. The generation and cloud storage of virtual customer portraits ensure the continuous updating and accessibility of customer data, which is convenient for long-term customer relationship management. Therefore, the present invention improves customer management to be more dynamic and accurate through cloud servers, intelligent customer behavior modeling and dynamic interaction strategies.

[0006] Preferably, step S1 comprises the following steps: Step S11: Obtain customer information data using a cloud server; Step S12: Perform customer information port compatibility analysis based on the customer information data to generate customer information port compatibility data; introduce the intelligent interactive plug-in based on the customer information port compatibility data to obtain intelligent question and answer plug-in usage data; Step S13: Using the intelligent question and answer plug-in to use data, the customer information data is screened for customer question and answer content to obtain customer question and answer content collection data; Step S14: preprocess the data collected from customer question and answer content to generate standard customer information data, wherein the data preprocessing includes data cleaning, data denoising, missing value filling and data standardization.

[0007] The present invention centrally acquires customer information data through a cloud server, can realize efficient data collection and storage, ensures that the data source is unified and reliable, and provides sufficient data support for subsequent analysis. At the same time, the high-performance computing capability of the cloud server can accelerate data processing and improve efficiency. By performing compatibility analysis on the customer information port, it is ensured that the data interacts smoothly between different devices, platforms or systems, and the adaptability and scalability of the system are improved. The introduction of intelligent interactive plug-ins can optimize the customer's question-and-answer interactive experience, improve the efficiency and accuracy of information collection, and reduce the cost of manual participation. The intelligent question-and-answer plug-in is used to screen the customer information data for question-and-answer content, and the core needs and key information of the customer can be accurately extracted to avoid redundant data interference. Through the question-and-answer content, data is collected to lay the foundation for the in-depth analysis of customer behavior and needs, and the pertinence and practicality of the data are improved. Cleaning, denoising, missing value filling and standardization of the collected data can effectively improve the quality and consistency of the data, avoid the accuracy of the subsequent analysis results affected by the messy or missing data, and this process ensures the high-quality output of standard customer information data, and provides reliable basic data support for subsequent steps. By collecting data through cloud servers, optimizing interactions with intelligent plug-ins, carefully screening Q&A content, and preprocessing high-quality data, we have achieved efficient acquisition, cleaning, and standardization of customer information data, laying a solid foundation for subsequent intelligent analysis and decision-making. The entire process has improved the efficiency, accuracy, and adaptability of data processing, and significantly optimized customer information management and service experience.

[0008] Preferably, introducing the intelligent interactive plug-in based on the customer information port compatible data includes: Perform demand feature analysis on customer information data based on customer information port compatibility data, thereby obtaining customer demand feature data; screen matching intelligent interactive plug-in types based on customer demand feature data, and perform plug-in adaptability evaluation, thereby obtaining intelligent plug-in adaptation data; According to the smart plug-in adaptation data, the smart question and answer plug-in configuration parameters corresponding to the smart plug-in are loaded to generate plug-in initialization parameter data; according to the plug-in initialization parameter data, the smart question and answer plug-in function module is loaded on the customer information data to generate smart plug-in interaction binding data; According to the smart plug-in interaction binding data, customer information and plug-in interaction records are integrated to generate smart question and answer plug-in usage data.

[0009] The present invention analyzes the demand characteristics of customer information data, accurately mines the real needs and preferences of customers, enables the system to provide targeted solutions, improves customer satisfaction, and provides a clear basis for plug-in screening to avoid resource waste. According to the customer demand feature data, the appropriate intelligent interactive plug-in type is matched, and the adaptability evaluation is performed, which can ensure the high compatibility of the selected plug-in with the customer information system, avoid the lack of function or performance degradation caused by the incompatibility of the plug-in, and improve the stability and interaction efficiency of the system operation. Through the initialization parameter configuration of the intelligent plug-in, it is ensured that the plug-in can run correctly and respond to customer needs quickly when loaded, improve the startup efficiency of the intelligent question and answer plug-in, shorten the user waiting time, and optimize the user experience. Functional module loading and interactive binding can accurately integrate the plug-in function into the customer information data, realize the seamless connection between the intelligent question and answer plug-in and customer needs, and improve the intelligent and personalized service level of the interactive process. By integrating customer information and plug-in interaction records, the key data in the interactive process can be fully recorded, providing valuable data support for subsequent optimization of plug-in performance, improvement of service strategies, and analysis of customer behavior. The above steps realize the accurate screening, adaptation and loading of the intelligent interactive plug-in, thereby effectively improving the compatibility and operation efficiency of the plug-in with the customer system. Through the introduction of intelligent question-and-answer plug-ins and the integration of interaction records, efficient response to customer needs and comprehensive optimization of service experience are achieved, while providing a scientific basis for dynamic adjustment and continuous improvement of the system.

[0010] Preferably, step S2 comprises the following steps: Step S21: performing a customer question and answer keyword search on the standard customer question and answer content data to obtain the customer question and answer keywords; performing a user question and answer semantic analysis on the standard customer question and answer content data based on the customer question and answer keywords to generate customer question and answer content semantic analysis data; Step S22: mining customer behavior feature patterns on customer information data according to the semantic analysis data of customer question and answer content to generate customer behavior pattern feature data, wherein the customer behavior pattern feature data includes interaction behavior pattern data, browsing behavior pattern data, and time and environment behavior pattern data; Step S23: using the customer behavior pattern feature data to model the customer's explicit behavior on the customer information data, and generating surface digital model data; Step S24: Perform deep inference modeling of customer hidden behaviors on customer information data through surface digital model data and customer behavior pattern feature data to generate hidden digital model data; perform multi-layer information fusion of surface digital model data and hidden digital model data to generate a virtual digital twin model.

[0011] The present invention can quickly extract the core content that customers care about through keyword retrieval, and improve data processing efficiency; semantic analysis can deeply understand the potential intentions and contextual relationships expressed by customers, and provide semantically accurate data support for subsequent behavior analysis and pattern mining. By mining the behavioral feature pattern of semantic analysis data, it is possible to reveal the multi-dimensional characteristics of customers' interaction, browsing, time and environmental behavior, and form a comprehensive customer behavior portrait, which is helpful to accurately identify customer needs and preferences and support more targeted service optimization. Based on customer behavior pattern feature data, explicit behavior modeling can clearly present the direct behavior characteristics of customers, such as clicks, access paths, etc., provide intuitive reference basis for real-time interaction and personalized services, and improve the response speed and efficiency of the system. Through explicit behavior data and pattern feature data, the implicit behavior characteristics of customers, such as potential needs, preference tendencies, etc., are inferred, the deficiencies of explicit behavior modeling are supplemented, and a deep understanding of customer behavior is achieved, providing a scientific basis for precision marketing and personalized recommendations. The surface and hidden models are multi-layered and information is fused to generate a virtual digital twin model, which can fully simulate customer behavior characteristics and change rules, provide dynamic customer portraits, support multi-scenario business optimization, trend prediction and intelligent decision-making, and improve customer experience and corporate competitiveness. By accurately extracting customer intentions through keyword retrieval and semantic analysis, and comprehensively presenting explicit and implicit behavioral characteristics through behavioral feature pattern mining and modeling, and generating digital twin models through multi-layer information fusion, an accurate, dynamic and comprehensive customer data analysis system has been built. This system can enhance data insight and provide strong support for the optimization, accurate recommendation and behavior prediction of intelligent interactive systems.

[0012] Preferably, step S23 includes the following steps: Step S231: using the interactive behavior pattern data in the customer behavior pattern feature data to collect customer direct operation records from the customer information data, and analyzing the customer operation sequence based on the extracted customer direct operation records to construct a user operation path sequence; extracting the user operation frequency, operation duration, and key operation points from the customer information data according to the user operation path sequence, and marking them as direct operation feature data; Step S232: using the browsing behavior pattern data in the customer behavior pattern feature data to capture the target elements clicked by the customer in the customer information data, and obtain the customer click event; performing click hot zone statistics on the customer click event, and obtain user click hot zone data; analyzing the click preference of the customer click event based on the user click hot zone data, and marking the analysis result as click behavior feature data; Step S233: using the time and environment behavior pattern data in the customer behavior pattern feature data to monitor the explicit demand expression input by the user in the customer information data, and generate user input demand data; performing demand type analysis on the user input demand data, and marking the analysis result as explicit demand feature data; Step S234: performing digital index and parameter conversion on the direct operation feature data, the click behavior feature data and the explicit demand feature data, so as to generate surface digital model data.

[0013] By constructing a sequence of user operation paths, the present invention can clearly present the logic and process of the customer's operation behavior, help identify key interaction nodes, and optimize the user interface design and functional layout; extracting the operation frequency, operation duration, and key operation points can accurately describe the customer's direct operation behavior, and provide data support for the in-depth analysis of the operation behavior and system improvement. Capturing customer click events and performing click hot zone statistics can help identify the high-frequency interaction areas and unpopular areas of the user interface, providing an intuitive basis for interface optimization; by analyzing the click preference characteristics, it is possible to gain insight into the customer's interest in different functional modules or content, and support personalized recommendations and precise content push. Explicit demand expression monitoring can capture the direct needs of customer input in real time to ensure that user needs are responded to quickly; by analyzing the explicit demand type, it is possible to identify the customer's specific goals or expectations, and support the system to dynamically adjust the functional modules to better meet customer needs. Digitally transforming direct operation features, click behavior features, and explicit demand features can standardize and structure customer behavior data and generate an accurate surface digital model; the model can provide an intuitive overview of customer behavior and provide a solid foundation for subsequent deep modeling and data application. By comprehensively capturing and analyzing customer operation paths, click preferences, and explicit demands, we have built a systematic digital model of customer behavior surfaces. This model can clearly reflect the direct behavioral characteristics of customers, provide an important reference for user experience optimization, interface design improvement, and personalized services, and significantly improve the interaction efficiency of intelligent systems and customer satisfaction.

[0014] Preferably, performing deep inference modeling of customer implicit behavior on customer information data through surface digital model data and customer behavior pattern feature data includes: Through the surface digital model data, cross-feature extraction is performed on the customer behavior pattern feature data to obtain customer joint behavior feature data; based on the customer joint behavior feature data, a Bayesian network structure is constructed to generate Bayesian network topology data; Divide the customer information data into data sets to generate model training sets and model test sets; use the model training sets to calculate the conditional probability distribution of the Bayesian network topology data to obtain conditional probability distribution data; perform customer implicit demand probability inference on the conditional probability distribution data to generate demand probability distribution data; The customer information data is decomposed into potential intentions according to the demand probability distribution data to generate potential intention feature data; the intention score is calculated for the potential intention feature data to obtain the intention score data, wherein the formula for the intention score calculation is as follows: ; In the formula, Denoted as the intent score, Expressed as The weight of a requirement, Expressed as the demand probability, Expressed as the weight of the feature function, Expressed as customer characteristic function value, Represented as a set of customer characteristics; The prediction accuracy of the demand probability distribution data is verified through the model test set to generate the hidden layer digital model data.

[0015] The present invention can integrate multi-dimensional behavioral features, explore the potential correlation of customer behavior, and form a more comprehensive description of joint behavioral features through cross-feature extraction of surface digital models and customer behavior pattern feature data. By using the Bayesian network topology structure, the causal relationship between features can be presented in the form of a probability model, providing a scientific and reliable modeling basis for the inference of customer implicit behavior. The Bayesian network inference model based on conditional probability calculation can infer the probability distribution of unknown features through known features, thereby accurately capturing the implicit demand probability of customers. Demand probability distribution data can provide a quantitative basis for potential demand mining and help the system identify future behavioral tendencies of customers. Potential intention decomposition can concretize implicit needs into a feature set, making each demand interpretable, which is convenient for subsequent precision marketing or product recommendations. The intention scoring formula is used to comprehensively evaluate the weights and customer characteristics of different needs, and quantitative intention scoring data can be generated to provide a clear priority basis for personalized services and product optimization. The feature weights and function flexibility in the intention scoring formula can adapt to the needs of different scenarios and achieve efficient decision support. The division of model training and test sets can ensure the universality and reliability of the model, avoid overfitting, and improve the generalization ability of the model. Hidden digital model generation fully integrates explicit and implicit behaviors to build a multi-dimensional digital portrait of customers, providing a solid foundation for deeper data analysis and prediction. Unified modeling of explicit and implicit behaviors covers different dimensions of customer behavior and provides a more complete data perspective for intelligent systems. Through Bayesian network inference and intent scoring calculation, the accuracy of implicit demand inference is significantly improved, providing accurate data support for intelligent interaction and personalized recommendations.

[0016] Preferably, step S3 comprises the following steps: Step S31: tracking customer behavior on the hidden layer digital model to obtain customer behavior tracking data; calculating the emotion trend based on the customer behavior tracking data to obtain customer emotion trend data; Step S32: predicting customer behavior patterns using the latent digital model according to the customer emotion trend data, thereby obtaining customer behavior prediction data; Step S33: using the customer behavior prediction data to evaluate the interaction strategy of the surface digital model, generating interaction strategy evaluation data; formulating a dynamic adjustment plan according to the interaction strategy evaluation data, and optimizing the interaction design in the surface digital model based on the dynamic adjustment plan, thereby obtaining a dynamic interaction strategy plan; Step S34: Deploy and adjust the interaction design in real time according to the dynamic interaction strategy plan, so as to generate an intelligent customer interaction strategy.

[0017] The present invention tracks customer behavior on a hidden digital model, records the customer's real-time behavior data, and forms customer behavior tracking data. By using the customer behavior tracking data and combining the sentiment analysis technology, the sentiment trend of the customer in different interaction scenarios is calculated to generate customer sentiment trend data. Through behavior tracking and sentiment analysis, the customer's status and demand changes can be understood in real time. The sentiment trend data provides an important basis for further predicting customer behavior and optimizing interaction design. By using the customer sentiment trend data, the behavior pattern in the hidden digital model is dynamically predicted to generate customer behavior prediction data. The prediction result includes the customer's operation path, preference and potential demand. The behavior pattern prediction helps the system predict the customer's next operation or demand, so as to formulate a response strategy in advance. By predicting customer preferences, personalized recommendations and intelligent interactions are achieved. Based on the customer behavior prediction data, the interaction strategy in the surface digital model is evaluated to form interaction strategy evaluation data. According to the evaluation results, a dynamic adjustment plan is formulated to optimize the interaction design in the model and generate a dynamic interaction strategy plan. The interaction strategy evaluation can locate the deficiencies in the interaction design and achieve continuous optimization through dynamic adjustment. The dynamic interaction strategy plan enables the system to adapt to the real-time changes in customer behavior and enhance the interaction experience. According to the dynamic interaction strategy plan, the interaction design is deployed and adjusted in real time. Through the continuous optimization of the design, an intelligent customer interaction strategy is generated to meet the personalized needs of customers. The interaction strategy is data-driven and can respond to customer needs in real time and provide efficient services. The ability to deploy in real time ensures that the system can maintain efficient operation in complex and changing scenarios.

[0018] Preferably, formulating a dynamic adjustment plan according to the interaction strategy evaluation data, and optimizing the interaction design in the surface digital model based on the dynamic adjustment plan includes: Conduct customer behavior feedback analysis on interaction strategy evaluation data to obtain customer behavior feedback data; classify and identify high-frequency demands, low-frequency demands, and abnormal demands in user interactions based on user behavior feedback data to obtain interaction demand classification data; The interactive interface layout and interactive logic are adjusted based on the high-frequency demand identification results in user interaction through interactive demand classification data, so as to obtain high-frequency interaction optimization design data; the low-frequency demand identification results in user interaction are improved by adding guidance information or optimizing the operation path, so as to obtain low-frequency interaction optimization design data; According to the interaction demand classification data, an exception handling mechanism is introduced into the abnormal demand identification results in user interaction to obtain abnormal interaction processing data, wherein the introduction of the exception handling mechanism includes multiple rounds of question-and-answer processes or manual intervention; a dynamic adjustment plan is constructed based on high-frequency interaction optimization design data, low-frequency interaction optimization design data and abnormal interaction processing data to generate dynamic optimization interaction design data; The interactive design in the surface digital model is optimized using dynamic optimization interactive design data to obtain a dynamic interactive strategy solution.

[0019] The present invention conducts customer behavior feedback analysis on interaction strategy evaluation data, mines potential problems and improvement points in user interaction, and generates customer behavior feedback data. According to the customer behavior feedback data, three types of needs in user interaction are classified and identified: functions and operation paths frequently used by users. Functions that users occasionally use but have low usage rates due to inconvenient design. Needs that are not expected or exceed conventional interaction logic in user behavior. The interaction demand classification provides a targeted basis for subsequent optimization design. The comprehensive coverage of high-frequency, low-frequency and abnormal needs ensures that the optimization design does not miss any important scenarios. Using the interaction demand classification data, the high-frequency needs are optimized: the interface layout of high-frequency operations is adjusted to reduce the user's click path and improve the convenience of operation. The operation logic of high-frequency functions is improved to make it more intuitive and efficient. The optimized interface and logic greatly improve the efficiency of users in high-frequency operations. The smooth high-frequency operation experience improves user satisfaction with the system. According to the interaction demand classification data, the low-frequency needs are optimized: tool tips, operation guides, etc. are added to guide users to use low-frequency functions more efficiently. The operation steps of low-frequency needs are simplified to improve their convenience of use. Through guidance and optimization, low-frequency functions are easier for users to discover and use. The simplified design of low-frequency requirements reduces the user's learning cost.

[0020] Preferably, step S4 comprises the following steps: Step S41: performing customer emotional feedback on the customer question and answer content collection data through an intelligent customer interaction strategy to generate customer emotional feedback data; Step S42: construct a portrait based on the customer sentiment feedback data to obtain a virtual customer portrait; stratify the virtual customer portrait to generate virtual customer portrait hierarchical data; label the virtual customer portrait according to the virtual customer portrait hierarchical data, and store the labeled virtual customer portrait in the cloud to perform customer management operations.

[0021] The present invention can more accurately capture the emotional tendencies of customers by performing emotional feedback analysis on customer question and answer content, thereby improving the quality of interaction with customers and enhancing customer experience. Constructing a virtual customer portrait based on customer emotional feedback data helps to fully understand customer needs and preferences. This portrait not only reflects the basic information of the customer, but also includes their emotional reactions and behavior patterns. By layering and labeling the virtual customer portrait, more personalized services and marketing strategies can be provided for customer groups of different levels and labels, thereby improving customer satisfaction and loyalty. The labeled virtual customer portrait is stored in the cloud for quick access and analysis, which can achieve more efficient customer management and decision support, especially when processing large amounts of customer data.

[0022] In this specification, a cloud server-based customer management system is provided, which is used to execute the above-mentioned cloud server-based customer management method, and the cloud server-based customer management system includes: The interactive plug-in introduction module is used to obtain customer information data using the cloud server; introduce intelligent interactive plug-ins based on the customer information data to obtain intelligent question and answer plug-in usage data; filter customer question and answer content on the customer information data through the intelligent question and answer plug-in usage data to obtain customer question and answer content collection data; perform data preprocessing on the customer question and answer content collection data to generate standard customer question and answer content data; The behavior modeling module is used to perform semantic analysis on standard customer question and answer content data to generate customer question and answer content semantic analysis data; perform user behavior modeling on customer information data based on the customer question and answer content semantic analysis data to generate a virtual digital twin model, wherein the virtual digital twin model includes a surface digital model and a hidden digital model; The dynamic interaction module is used to track customer behavior on the hidden digital model to obtain customer behavior tracking data; predict customer behavior on the hidden digital model based on the customer behavior tracking data to generate customer behavior prediction data; use the customer behavior prediction data to adjust the dynamic interaction strategy of the surface digital model to generate intelligent customer interaction strategy; The emotional feedback module is used to collect customer emotional feedback on customer question and answer content through intelligent customer interaction strategies to generate customer emotional feedback data; construct a portrait based on the customer emotional feedback data to obtain a virtual customer portrait, and store the virtual customer portrait in the cloud to perform customer management tasks.

[0023] The beneficial effect of the present invention is that through the combination of cloud server and intelligent interactive plug-in, customer information data can be quickly and accurately obtained, and effective customer question and answer content screening can be performed through intelligent question and answer plug-in. This module can significantly improve the processing speed and quality of customer information and reduce the workload of manual screening. Standard customer question and answer content data is generated through data preprocessing to ensure the consistency and availability of data, laying a good foundation for subsequent modeling and analysis. Through semantic parsing and behavioral modeling, customers can be deeply analyzed to generate virtual digital twin models. This model not only includes surface digital information, but also captures the hidden behavioral characteristics of customers, provides a more comprehensive customer portrait, and helps enterprises better understand customer needs and behavior patterns. Through the construction of virtual digital twin models, enterprises can achieve more accurate customer behavior prediction and customized service strategies. By tracking the customer behavior of the hidden digital model, the customer's behavior dynamics can be grasped in real time, thereby achieving accurate prediction of customer behavior. Enterprises can adjust the interaction strategy based on these predicted data to achieve personalized and dynamic customer communication and service. By dynamically adjusting the interaction strategy, the customer service process will become more flexible and efficient, improve customer satisfaction and reduce invalid interactions. By generating and analyzing customer emotional feedback, it is possible to understand the customer's emotional state in real time and provide emotional services to customers, which helps to improve customer loyalty, deal with potential negative emotions in a timely manner, and reduce customer churn. By building and updating virtual customer portraits with emotional feedback data, companies can ensure the real-time and dynamic nature of customer information, better follow up on customer needs and optimize service strategies. Therefore, the present invention improves customer management to be more dynamic and accurate through cloud servers, intelligent customer behavior modeling and dynamic interaction strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic diagram of the steps of a customer management method based on a cloud server; Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart; Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG. The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0025] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0026] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0027] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, and the term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0028] To achieve this, please refer to Figures 1 to 3 , a customer management method based on a cloud server, the method comprising the following steps: Step S1: using a cloud server to obtain customer information data; introducing an intelligent interactive plug-in based on the customer information data to obtain intelligent question and answer plug-in usage data; filtering customer question and answer content on the customer information data using the intelligent question and answer plug-in usage data to obtain customer question and answer content collection data; performing data preprocessing on the customer question and answer content collection data to generate standard customer question and answer content data; Step S2: semantically parse the standard customer question and answer content data to generate customer question and answer content semantic parsing data; perform user behavior modeling on the customer information data based on the customer question and answer content semantic parsing data to generate a virtual digital twin model, wherein the virtual digital twin model includes a surface digital model and a hidden digital model; Step S3: Track customer behavior on the hidden digital model to obtain customer behavior tracking data; predict customer behavior on the hidden digital model based on the customer behavior tracking data to generate customer behavior prediction data; use the customer behavior prediction data to dynamically adjust the interaction strategy of the surface digital model to generate an intelligent customer interaction strategy; Step S4: Collect customer sentiment feedback from customer Q&A content through intelligent customer interaction strategies to generate customer sentiment feedback data; construct a profile based on the customer sentiment feedback data to obtain a virtual customer profile, and store the virtual customer profile in the cloud to perform customer management tasks.

[0029] The present invention obtains customer information data through a cloud server, and introduces an intelligent question-and-answer plug-in based on these data for screening and preprocessing to generate standard customer question-and-answer content data. This step ensures the high quality and structure of customer information data, so that subsequent processing can be carried out accurately; through data screening and preprocessing, noise is removed, and the availability and accuracy of data are improved. The standard customer question-and-answer content data is semantically parsed, and user behavior modeling is performed on customer information based on the parsing results to generate a virtual digital twin model. The hidden digital model is used to track customer behavior, and the surface digital model is adjusted using behavior prediction data to generate an intelligent customer interaction strategy. Real-time tracking and prediction of customer behavior enables the interaction strategy to be dynamically adjusted based on the real-time needs and behaviors of customers, improves the accuracy and personalization of customer interaction, and enhances customer experience. Customer emotional feedback is performed based on the intelligent customer interaction strategy, customer emotional feedback data is generated, and a virtual customer portrait is constructed for cloud storage. Through emotional feedback, the system can better capture customer emotional changes, adjust the interaction strategy in a timely manner, and optimize customer experience. The generation and cloud storage of virtual customer portraits ensure the continuous updating and accessibility of customer data, which is convenient for long-term customer relationship management. Therefore, the present invention improves customer management to be more dynamic and accurate through cloud servers, intelligent customer behavior modeling and dynamic interaction strategies.

[0030] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a schematic diagram of a step flow of a customer management method based on a cloud server of the present invention. In this example, the customer management method based on a cloud server includes the following steps: Step S1: using a cloud server to obtain customer information data; introducing an intelligent interactive plug-in based on the customer information data to obtain intelligent question and answer plug-in usage data; filtering customer question and answer content on the customer information data using the intelligent question and answer plug-in usage data to obtain customer question and answer content collection data; performing data preprocessing on the customer question and answer content collection data to generate standard customer question and answer content data; In an embodiment of the present invention, a customer information management system is built by using a cloud server platform (such as AWS, Azure, etc.), and basic information (such as name, contact information, purchase records, etc.) and interaction data (such as customer service records, customer feedback, etc.) of the customer are obtained by connecting with the enterprise's CRM (customer relationship management) system, online customer service system or other data sources. Through the API interface or database synchronization, these customer information data are uploaded to the cloud server for centralized storage and management. An intelligent question and answer plug-in (such as a chat robot or FAQ automatic answering system based on natural language processing) is integrated in the customer information management system. The intelligent question and answer plug-in automatically answers the customer's questions based on the customer's input (such as through online customer service, voice assistant or web form, etc.), and records the use of the plug-in (including customer question content, plug-in answer content, customer interaction time, etc.) as usage data. The usage data of the intelligent question and answer plug-in is analyzed to screen out specific questions raised by customers and related question and answer content. Through data cleaning, deduplication and classification, effective customer question and answer content is screened to ensure the quality and accuracy of the question and answer content. Natural language processing technology (such as keyword extraction, topic modeling, etc.) is used to screen the question and answer content to remove irrelevant or repeated information. Standardize and pre-process the screened customer Q&A content. Specific operations include: removing unnecessary punctuation and stop words, and unifying the format (such as uppercase and lowercase, tense, etc.). Use word segmentation tools to segment the text and mark the parts of speech to prepare for subsequent semantic analysis and behavior modeling. According to business needs, standardize the Q&A data, such as unifying the date format, number format, etc. Save the cleaned customer Q&A content data to a cloud database or data warehouse to ensure data accessibility and security. Perform quality checks on the generated standard customer Q&A content data to ensure data accuracy and completeness. Correct erroneous or abnormal data through manual review and automated verification.

[0031] Step S2: semantically parse the standard customer question and answer content data to generate customer question and answer content semantic parsing data; perform user behavior modeling on the customer information data based on the customer question and answer content semantic parsing data to generate a virtual digital twin model, wherein the virtual digital twin model includes a surface digital model and a hidden digital model; In an embodiment of the present invention, the standard customer Q&A content data is semantically analyzed by using NLP technology. The specific steps include: first, the customer's Q&A content is segmented, and the part of speech of each word (such as verb, noun, adjective, etc.) is marked to ensure the accuracy of semantic analysis. Identify key entities in customer Q&A (such as customer name, product name, service type, etc.), and provide a basis for subsequent analysis through entity extraction. Analyze the emotional tendencies (such as positive, negative or neutral emotions) in customer Q&A to understand the emotional needs and experience of customers. Construct a syntactic tree of the Q&A content through syntactic analysis to capture the sentence structure and ensure accurate understanding of customer intentions during semantic analysis. Based on the above steps, generate a vector representation of each customer Q&A content (such as embedding word vectors or sentence vectors using Word2Vec, BERT and other technologies), and construct semantic analysis data of customer Q&A content in combination with semantic tags. Model customer behavior by combining the semantic analysis data of the customer's Q&A content and the customer's historical interaction records (such as purchase history, browsing history, service requests, etc.). Analyze customer interests (such as a certain type of product, service type, common questions, etc.) based on the semantic information of the question and answer content, and combine these interests with the customer's historical behavior to form a customer behavior portrait. Use machine learning algorithms (such as decision trees, support vector machines, deep learning, etc.) to predict customer needs, and identify customer needs or behavior changes in the future based on semantic analysis data. According to the customer's basic information, question and answer content, behavioral data, etc., establish a surface digital model of the customer. This model represents the customer's basic attributes (such as identity information, purchase preferences, emotional tendencies, etc.), and is updated frequently, reflecting the customer's immediate needs. The hidden model generates the customer's deep behavioral pattern by integrating the customer's deep behavioral pattern (such as potential needs, long-term preferences, etc.). Based on a large amount of behavioral data, prediction algorithms and historical trend analysis, this model reflects the customer's long-term development trend and potential changes. The surface and hidden models are combined to form a virtual digital twin model. The surface model provides immediate and superficial customer information, while the hidden model reveals the customer's long-term development trend and potential needs. The two work together to ensure that the customer management system can conduct comprehensive and accurate digital management of customers. Based on new customer Q&A content, behavioral data, and real-time interactive feedback, the surface and hidden digital models are regularly updated and optimized to reflect changes in customer behavior. Through further customer interaction (such as follow-up questions, purchase behavior, or satisfaction feedback), the parameters in the virtual digital twin model are adjusted to ensure the continued effectiveness of the model.

[0032] Step S3: Track customer behavior on the hidden digital model to obtain customer behavior tracking data; predict customer behavior on the hidden digital model based on the customer behavior tracking data to generate customer behavior prediction data; use the customer behavior prediction data to dynamically adjust the interaction strategy of the surface digital model to generate an intelligent customer interaction strategy; In an embodiment of the present invention, customer behavior data is collected through multiple channels, such as website browsing history, APP usage, social media interaction, purchase history, customer support interaction, etc. These data can be collected in real time through log analysis, sensors and API integration. Time series analysis, sequence annotation (such as HMM or LSTM network) and other technologies are used to track customer behavior in real time. These algorithms can capture customer behavior patterns in different time periods and help identify customer interest changes, demand fluctuations and potential actions. Key features (such as click-through rate, dwell time, behavior frequency, etc.) are extracted from customer behavior tracking data to provide data support for subsequent behavior prediction and model optimization. Machine learning or deep learning algorithms (such as random forest, XGBoost, neural network, reinforcement learning, etc.) are used to train and optimize the hidden layer digital model to predict the customer's future behavior. Predict customer behavior changes in the short term, such as the possibility of recent purchases, attention to product updates, etc. Based on customer historical behavior and its changing trends, predict customer long-term demand changes, potential departure risks or loyalty changes. Taking multiple customer behavior data (such as purchase, browsing, comment, interaction, etc.) as input, use multi-task learning methods to simultaneously perform multiple prediction tasks (such as purchase prediction, sentiment prediction, demand prediction, etc.) to generate specific customer behavior prediction data, including customer future needs, behavior conversion probability, loyalty, etc. Dynamically adjust the customer interaction strategy in the surface digital model based on customer behavior prediction data. For example: Based on the predicted customer purchase behavior, adjust product or service recommendations to better meet the customer's current needs. Adjust prices or discount strategies based on customer purchase predictions to enhance customer purchase intentions. Combine real-time data and customer behavior predictions to dynamically adjust the parameters of the surface digital model, such as adjusting service content or recommendation strategies based on the customer's real-time status, so that customer interaction can be more accurate and personalized. Design intelligent customer interaction strategies based on the adjusted surface digital model. Strategy content includes: Push customized content such as promotional information, product recommendations, coupons, etc. through different channels based on customer interests and needs. Provide customers with personalized customer service support based on their historical behavior and future predictions, such as solutions to specific problems or exclusive customer manager services. Implement the generated intelligent customer interaction strategy to the customer interaction platform (such as customer service system, email marketing platform, social media, etc.). Further optimize the interaction strategy through feedback on the implementation results (such as customer participation rate, purchase conversion rate, customer satisfaction, etc.). Through self-learning mechanisms such as deep learning or reinforcement learning, the interaction strategy is automatically adjusted according to customer behavior feedback, so that the customer interaction experience is continuously optimized and customer satisfaction and business value are maximized.

[0033] Step S4: Collect customer sentiment feedback from customer Q&A content through intelligent customer interaction strategies to generate customer sentiment feedback data; construct a profile based on the customer sentiment feedback data to obtain a virtual customer profile, and store the virtual customer profile in the cloud to perform customer management tasks.

[0034] In an embodiment of the present invention, the data collected from the customer's Q&A content is processed by using advanced sentiment analysis technology. The sentiment analysis algorithm can analyze the customer's emotional tendency through text sentiment classification (such as positive, negative, and neutral). Based on NLP (natural language processing) technology, each customer's Q&A content is mapped to emotional feedback through semantic understanding, sentiment tag generation, and other means. Identifying positive feedback in customer emotions, such as satisfaction, gratitude, excitement, etc., indicates that the customer highly recognizes the product or service. Identifying negative emotional feedback from customers, such as disappointment, frustration, anger, etc., indicates that the customer is dissatisfied and needs further processing or service optimization. In addition to sentiment classification, quantitative analysis can also be performed based on sentiment intensity. For example, the strength of emotion is represented by sentiment scores to further improve the refinement of sentiment analysis. The emotional feedback information (such as sentiment category, sentiment intensity, sentiment keywords, etc.) extracted from the customer's Q&A content is integrated into customer emotional feedback data. This data may include multiple dimensions: an emotional label (such as "positive", "negative", "neutral") is provided for each customer's Q&A content. An emotional intensity score is generated for each customer feedback to characterize the depth of customer emotion. Generate a data model about customer emotion changes by analyzing the trend of customer emotion feedback (such as the time series of customer emotion changes). De-noise and standardize the emotion feedback data to remove irrelevant data and ensure the accuracy and consistency of the feedback data. Extract the customer's behavior pattern and emotion characteristics based on the customer's emotion feedback data and their behavior data (such as purchase history, interaction records, etc.). For example, analyze the customer's emotion fluctuations in different situations and identify the customer's emotional tendencies at different stages. Identify whether the customer's emotion is positive (such as loyal customers) or negative (such as lost customers). Evaluate the fluctuation of customer emotions to determine whether the customer's emotions are stable and whether there is potential dissatisfaction. Based on the above feature data, build a detailed virtual customer portrait, including but not limited to the following: such as the customer's basic identity information (age, gender, region, etc.), customer's interests, preferences, purchasing behavior, etc., including the customer's emotion type (such as common emotional state) and emotion fluctuation trend. According to the customer's emotional stability and behavior pattern, evaluate their loyalty level, and predict the customer's potential needs and future behavior through the combination of emotion feedback and behavior data. Use data visualization tools to display the various dimensions of the customer portrait, so that managers can quickly understand the overall picture of the customer. The constructed virtual customer profile data is stored in a cloud database through cloud services (such as AWS, Google Cloud, Azure, etc.). Use an efficient database management system (such as NoSQL or relational database) to ensure efficient data storage and fast query. To ensure the privacy and security of customer data, the stored data should be protected by encryption technology to prevent unauthorized access. Customer profiles should be updated regularly to ensure that they reflect the customer's latest behavior, emotions, and needs at any time.Ensure the real-time and accuracy of customer portrait data through automated data synchronization and update mechanisms. Perform specific customer management tasks based on virtual customer portraits stored in the cloud, such as precision marketing based on customer portraits, and push customized promotions, product recommendations and other information. Optimize customer service processes based on customer emotions and behavior patterns, such as personalized customer support services, customized interactive experiences, etc. Identify potential lost customers through emotional feedback data and provide corresponding recovery measures.

[0035] Preferably, step S1 comprises the following steps: Step S11: Obtain customer information data using a cloud server; Step S12: Perform customer information port compatibility analysis based on the customer information data to generate customer information port compatibility data; introduce the intelligent interactive plug-in based on the customer information port compatibility data to obtain intelligent question and answer plug-in usage data; Step S13: Using the intelligent question and answer plug-in to use data, the customer information data is screened for customer question and answer content to obtain customer question and answer content collection data; Step S14: preprocess the data collected from customer question and answer content to generate standard customer information data, wherein the data preprocessing includes data cleaning, data denoising, missing value filling and data standardization.

[0036] In an embodiment of the present invention, a cloud server is used to obtain customer information from various channels (such as websites, CRM systems, social platforms, etc.) using distributed computing and data storage technology. The cloud server can process a large amount of data and ensure real-time updating and storage of data. The diversity of customer information data and the compatibility of different sources are analyzed to ensure that the information can be uniformly formatted for further processing. The analysis can use a data matching algorithm to determine the compatibility of data between different ports and generate compatible data. Based on the compatible data, a suitable intelligent question and answer plug-in (such as an AI plug-in based on natural language processing) is selected to conduct in-depth analysis and interaction on customer information. The intelligent question and answer plug-in can process customer questions in real time and provide corresponding feedback. Through the plug-in usage data, the plug-in performance and customer feedback can be analyzed. The intelligent question and answer plug-in collects questions and feedback raised by customers and filters out effective question and answer content. The screening process includes semantic analysis of the question and answer content, filtering irrelevant or repeated questions, and extracting data that customers really need. Text classification, keyword extraction, and sentiment analysis can be used. The collected data is de-duplicated, formatted, and processed for outliers to ensure the accuracy of the data. Use denoising techniques (such as filters, clustering, etc.) to eliminate noise in the Q&A content to ensure the extraction of effective information. Use appropriate filling methods (such as mean filling, median filling, KNN filling, etc.) to handle missing items in the data to ensure data integrity. Standardize all data (such as Z-score standardization, Min-Max scaling, etc.) to ensure that the data can be used in different systems. Maintain consistency and facilitate subsequent analysis and processing.

[0037] Preferably, introducing the intelligent interactive plug-in based on the customer information port compatible data includes: Perform demand feature analysis on customer information data based on customer information port compatibility data, thereby obtaining customer demand feature data; screen matching intelligent interactive plug-in types based on customer demand feature data, and perform plug-in adaptability evaluation, thereby obtaining intelligent plug-in adaptation data; According to the smart plug-in adaptation data, the smart question and answer plug-in configuration parameters corresponding to the smart plug-in are loaded to generate plug-in initialization parameter data; according to the plug-in initialization parameter data, the smart question and answer plug-in function module is loaded on the customer information data to generate smart plug-in interaction binding data; According to the smart plug-in interaction binding data, customer information and plug-in interaction records are integrated to generate smart question and answer plug-in usage data.

[0038] In an embodiment of the present invention, the customer information data is analyzed by using machine learning and data mining technology to identify the potential pattern of customer demand. For example, based on the customer's historical behavior, purchase record, interest preference, etc., clustering algorithm, association rule mining and other methods are used to extract specific demand characteristics from the data. Use data preprocessing technology (such as standardization, normalization) to process customer information, combine classification algorithm (such as decision tree, SVM) or deep learning model (such as neural network) to analyze customer demand characteristics and generate customer demand characteristic data. According to the customer demand characteristic data, the most suitable intelligent interactive plug-in type is screened out. The recommendation system algorithm (such as collaborative filtering, content recommendation) can be used to recommend the most suitable plug-in type. The selected plug-in type is evaluated for adaptability to analyze whether it can be effectively integrated with the existing customer information data system and platform. The evaluation criteria may include performance, compatibility, response time, etc. The evaluation process can be carried out by means of automated testing, regression analysis, etc. The adaptability of the plug-in is evaluated using the adaptability model and index scoring system to generate intelligent plug-in adaptation data. Load the configuration information corresponding to the intelligent interactive plug-in (such as plug-in version, functional module, etc.) according to the adaptation data. Configuration parameters include language settings, interface configuration, database connection settings, etc. Organize the loaded configuration parameters into standardized initialization parameter data for subsequent plug-in initialization. Use configuration management tools (such as Ansible, Chef) to automatically configure the initialization parameters of the plug-in to ensure that all parameters meet the requirements of the intelligent interaction plug-in. According to the initialization parameter data, load the specific functional modules of the intelligent question and answer plug-in (such as natural language processing module, speech recognition module, sentiment analysis module, etc.). During the loading process, it is necessary to ensure that the plug-in module can seamlessly access the existing customer information system and accurately process customer input. Generate binding data for each functional module and customer information data, which includes customer historical interaction data, customer demand feature data, etc. Binding data connects customer information with the plug-in's functional module to ensure that the plug-in can provide personalized services to customers. Connect the functional module with the customer data system through API integration technology (such as RESTful API, GraphQL) to generate interaction binding data. Integrate the interaction records between customers and plug-ins into an analyzable format. These records include questions raised by customers, plug-in answers, plug-in feedback, etc. Integrate these interaction records through log analysis tools (such as ELK Stack, Splunk). Based on the integrated interaction records, the usage data of the smart question-answering plug-in is generated, including the plug-in's response time, accuracy, customer satisfaction, etc. This data helps evaluate the performance of the plug-in and provides a basis for future plug-in optimization. Use data analysis tools (such as Apache Spark and Pandas) to analyze the interaction data and generate usage data of the smart question-answering plug-in to ensure data integrity and traceability.

[0039] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S21: performing a customer question and answer keyword search on the standard customer question and answer content data to obtain the customer question and answer keywords; performing a user question and answer semantic analysis on the standard customer question and answer content data based on the customer question and answer keywords to generate customer question and answer content semantic analysis data; Step S22: mining customer behavior feature patterns on customer information data according to the semantic analysis data of customer question and answer content to generate customer behavior pattern feature data, wherein the customer behavior pattern feature data includes interaction behavior pattern data, browsing behavior pattern data, and time and environment behavior pattern data; Step S23: using the customer behavior pattern feature data to model the customer's explicit behavior on the customer information data, and generating surface digital model data; Step S24: Perform deep inference modeling of customer hidden behaviors on customer information data through surface digital model data and customer behavior pattern feature data to generate hidden digital model data; perform multi-layer information fusion of surface digital model data and hidden digital model data to generate a virtual digital twin model.

[0040] In an embodiment of the present invention, keyword extraction of customer Q&A content data is performed by using natural language processing (NLP) technology. The TF-IDF (term frequency-inverse document frequency) algorithm or a deep learning model (such as BERT, GPT) can be used for keyword extraction. The goal of keyword retrieval is to find the words that best represent the core of each question and answer, so as to help subsequent semantic parsing and behavior analysis. Use open source NLP tool libraries (such as spaCy, NLTK) for preprocessing and extract keywords. More accurate keywords can be obtained through TF-IDF calculation or context-based Embedding models (such as BERT). Based on the extracted keywords, semantic analysis is performed to understand the deep meaning of the Q&A content. Semantic parsing can be performed through pre-trained language models (such as BERT, T5) to understand the context of the text. By parsing the Q&A content, the customer's needs, intentions, and emotional attitudes are identified, thereby generating semantic parsing data of the customer's Q&A content. Semantic analysis tools (such as SpaCy's NER (named entity recognition), OpenAI GPT series, etc.) are used to perform semantic parsing on standard Q&A data. Further judge the customer's emotional attitude and needs through sentiment analysis models (such as VADER, BERT sentiment classification). Use mining algorithms (such as association rule mining, cluster analysis) to mine customer behavior patterns from semantic parsing data. Analyze customer interaction behaviors (such as question and answer frequency, keyword occurrence frequency, etc.) based on the customer's question and answer content. Perform cluster analysis on customer behavior data, identify different behavior patterns, and label customer behaviors to generate behavior pattern feature data. Clustering algorithms (such as K-means, DBSCAN) or deep learning-based clustering methods (such as autoencoders) can be used to mine customer behavior patterns. Use association rule mining technology (such as Apriori) to analyze the connection between customer behaviors. Customer behavior pattern feature data can be generated according to the following types: such as customer question frequency, question type, question time, etc. Such as customer browsing history, browsing time, browsing frequency, etc. Such as customer behavior changes in different time periods, different devices or environments. Use data processing frameworks (such as Apache Spark, Pandas) to extract features from behavior data and generate multi-dimensional behavior feature data sets. Use time series analysis, environmental analysis and other methods to extract behavioral characteristics related to time and environment. Build an explicit behavior model based on the customer's explicit behavior (such as browsing history, click data, purchase history, etc.). Use traditional machine learning models (such as decision trees, random forests, support vector machines, etc.) or deep learning models (such as LSTM, CNN) to generate surface digital model data. This model mainly focuses on directly observable behavioral data. Use regression models or classification models to model customer explicit behaviors and predict customers' future behaviors or preferences. Use deep learning methods (such as DNN) to model behavioral characteristics at a deeper level.Based on the explicit behavior model data, the implicit behavior of customers (such as unexpressed needs, potential interests, etc.) can be inferred. In this step, deep learning technologies such as autoencoders and generative adversarial networks (GANs) can be used to infer implicit features, generate implicit digital model data, and capture customers' potential behaviors or implicit needs. Use autoencoders or variational autoencoders (VAEs) to learn the potential representation of customers' implicit behaviors from the surface digital model. GANs (generative adversarial networks) can be used to generate data that approximates real customer behaviors. The surface digital model data and the implicit digital model data are fused to form a complete virtual digital twin model of the customer. This model not only represents the customer's explicit behavior, but also infers his implicit needs. Multi-layer perceptrons (MLPs) and ensemble learning are used to fuse the two models to achieve deep integration of information. Ensemble learning methods (such as random forests and XGBoost) are used to weightedly fuse the results of the surface and implicit models. Combined with cross-modal fusion technology in deep learning, explicit and implicit data are integrated to generate a virtual digital twin model of the customer.

[0041] Preferably, step S23 includes the following steps: Step S231: using the interactive behavior pattern data in the customer behavior pattern feature data to collect customer direct operation records from the customer information data, and analyzing the customer operation sequence based on the extracted customer direct operation records to construct a user operation path sequence; extracting the user operation frequency, operation duration, and key operation points from the customer information data according to the user operation path sequence, and marking them as direct operation feature data; Step S232: using the browsing behavior pattern data in the customer behavior pattern feature data to capture the target elements clicked by the customer in the customer information data, and obtain the customer click event; performing click hot zone statistics on the customer click event, and obtain user click hot zone data; analyzing the click preference of the customer click event based on the user click hot zone data, and marking the analysis result as click behavior feature data; Step S233: using the time and environment behavior pattern data in the customer behavior pattern feature data to monitor the explicit demand expression input by the user in the customer information data, and generate user input demand data; performing demand type analysis on the user input demand data, and marking the analysis result as explicit demand feature data; Step S234: performing digital index and parameter conversion on the direct operation feature data, the click behavior feature data and the explicit demand feature data, so as to generate surface digital model data.

[0042] In an embodiment of the present invention, each operation data of the customer is captured by using a log recording system on the Web or application side to record the customer's clicks, scrolling, input, submission and other behaviors on the platform. These operations are classified to ensure that the operation sequence and timestamp of each customer can be tracked, and an operation record set is constructed. The operation is recorded in detail using the front-end JavaScript SDK or the event tracking tool of the mobile application (such as Google Analytics, Mixpanel). The data includes information such as the operation type, the operation object, and the timestamp. The customer's operation records are analyzed in chronological order to construct a user operation path sequence. Sequence mining techniques (such as FP-Growth and Apriori) are used to analyze the customer's common operation paths and conversion paths. The frequency, duration, and key operation points (such as click-to-buy, add to shopping cart, etc.) of the operation are extracted through path analysis and marked as direct operation feature data. The operations are sorted based on the timestamp, and then the common operation sequences are analyzed using a sequence pattern mining algorithm (such as sequence pattern mining and Markov chain). The key operation points are extracted using a time series analysis algorithm, such as the user's behavior before and after completing a certain operation. According to the user operation path, count the frequency of each operation, the average operation duration, and key nodes (such as the frequency of visits to the checkout page and the frequency of clicks on specific products). Mark each operation as direct operation feature data for subsequent modeling. Use data processing tools (such as Pandas) to count the frequency of customer operation records. Combine the behavior analysis framework (such as RFM analysis) to analyze the duration of the operation and mark it as feature data. Capture user click events on the page through front-end JavaScript code or mobile SDK. Record the elements clicked by the customer (such as buttons, links, pictures, etc.) and the corresponding timestamps. The captured data includes the click location, the ID of the clicked object, the URL, etc. Use the front-end event listener (such as addEventListener) to capture all user click operations and upload the relevant data to the back-end database. For mobile applications, you can use a dedicated SDK, such as Firebase Analytics, to capture click events. Perform hot zone statistics on customer click events and use heat map analysis tools (such as Hotjar, Crazy Egg) to generate user click heat map. Count which page areas (such as buttons, images, links, etc.) are clicked more frequently. Extract click frequency data for each hot zone and count the user's attention to a specific area. Use heat map analysis tools to automatically generate click heat map to indicate areas with high user click density. Perform cluster analysis on the hot zone data to identify hot spots. Based on the hot zone data, analyze customers' click preferences and identify which page elements or products are most popular with customers. Combined with the heat data of the click location, analyze the customer's preferred product categories, price ranges, layout preferences, etc. Mark these preferences as click behavior feature data and use them as input for subsequent analysis.Use data visualization tools (such as Tableau and Power BI) to display click hotspots and preference distribution. Perform cluster analysis on click behaviors and use K-means or DBSCAN methods to classify customers' click preferences. Monitor customers' explicit demand expressions when interacting with the system (such as search box input, question asking, etc.), and record their input content, frequency, and context. Identify customers' explicit needs (such as product specifications, service requests, etc.) by extracting keywords from the input content. Use text analysis tools (such as NLTK and spaCy) to extract keywords from customer input content. Perform sentiment analysis on the input natural language to determine whether the customer has expressed a need. Classify the demand type based on the customer's input needs and identify the customer's demand type (such as product demand, service consultation, technical support, etc.). Mark the demand type results as explicit demand feature data. Use classification models (such as logistic regression and SVM) to automatically classify customer needs. Combine NLP technology to train the demand classification model on a large number of user input data sets to improve classification accuracy. The collected behavioral feature data (such as operation frequency, click hotspots, demand types, etc.) are digitized, and text and classification data are converted into numerical indicators (such as using unique hot encoding, standardization, normalization, etc.). The converted data includes operation frequency, duration, number of clicks in hotspots, demand classification labels, etc. Use data preprocessing libraries (such as Pandas and Scikit-learn) to standardize and normalize the feature data to ensure data consistency and comparability. Perform unique hot encoding on discrete demand types and convert text categories into numerical values. Integrate all digitized feature data into a unified surface digital model to form a customer behavior feature model. The surface digital model data includes multi-dimensional features such as operation behavior, click behavior, and explicit demand, which constitute a comprehensive digital description of customer behavior. Combine all converted feature data to form a structured data set, which is suitable for subsequent machine learning model training or data analysis. Use table processing tools (such as Excel and Pandas) and databases (such as SQL and NoSQL) to store and manage these surface digital model data.

[0043] Preferably, performing deep inference modeling of customer implicit behavior on customer information data through surface digital model data and customer behavior pattern feature data includes: Through the surface digital model data, cross-feature extraction is performed on the customer behavior pattern feature data to obtain customer joint behavior feature data; based on the customer joint behavior feature data, a Bayesian network structure is constructed to generate Bayesian network topology data; Divide the customer information data into data sets to generate model training sets and model test sets; use the model training sets to calculate the conditional probability distribution of the Bayesian network topology data to obtain conditional probability distribution data; perform customer implicit demand probability inference on the conditional probability distribution data to generate demand probability distribution data; The customer information data is decomposed into potential intentions according to the demand probability distribution data to generate potential intention feature data; the intention score is calculated for the potential intention feature data to obtain the intention score data, wherein the formula for the intention score calculation is as follows: ; In the formula, Denoted as the intent score, Expressed as The weight of a requirement, Expressed as the demand probability, Expressed as the weight of the feature function, Expressed as customer characteristic function value, Represented as a set of customer characteristics; The prediction accuracy of the demand probability distribution data is verified through the model test set to generate the hidden layer digital model data.

[0044] In an embodiment of the present invention, cross-feature extraction is performed by utilizing multi-dimensional features in surface digital model data and customer behavior pattern feature data. Cross-features refer to the combination of different features to generate new features, which helps reveal hidden associations. For example, a new feature of "demand and operation frequency" can be generated by crossing the two features of "operation frequency" and "explicit demand type" to form customer joint behavior feature data. Multiple features are combined into new composite features using feature engineering methods (such as feature crossing, merge operation in Pandas). For categorical variables, label encoding or unique hot encoding can be used for conversion. A Bayesian network is constructed using customer joint behavior feature data. The Bayesian network is a directed acyclic graph (DAG) in which nodes represent variables and edges represent dependencies between variables. The purpose of constructing a Bayesian network is to infer the conditional dependency structure between each feature. The network topology is constructed by calculating the relationship between each feature. For example, the dependency between variables is evaluated using methods such as information gain, mutual information, and chi-square test. Bayesian networks can be constructed using Python's pgmpy library or pomegranate library, which support automated learning of network structure and parameter estimation. Learn conditional probabilities using Maximum Likelihood Estimation (MLE) or Bayesian Parameter Estimation. Divide customer information data into training and test sets, usually using a ratio of 80 / 20 or 70 / 30. The training set is used for model training, and the test set is used to evaluate model performance, ensuring that there is no data leakage between the training data and the test data. Use the train_test_split (from sklearn.model_selection) function to randomly divide the data to ensure that the feature distribution of the training set and the test set is consistent. Parameter learning of the Bayesian network is performed using the training set data to calculate the conditional probability distribution (CPD) of each node (feature). CPD describes the conditional probability of each feature given its parent node. Use Bayesian network learning algorithms such as the EM (Expectation-Maximization) algorithm or maximum likelihood estimation to estimate the conditional probability of each node. Use methods in libraries such as pgmpy or pomegranate to estimate conditional probabilities in Bayesian networks. The specific method is fit(), which automatically learns the conditional probability distribution in the data. Use methods in libraries such as pgmpy or pomegranate to estimate conditional probabilities in Bayesian networks. The specific method is fit(), which automatically learns the conditional probability distribution in the data. Use Bayesian network inference methods (such as VariableElimination in pgmpy) to make probabilistic inferences on demand, thereby generating demand probability distribution data. Based on the demand probability distribution data, decompose potential intent.Potential intention is the underlying motivation behind customer behavior, which can be inferred by analyzing the changes in demand probability. Reduce the dimension of demand data through clustering algorithm or principal component analysis (PCA) to extract potential intention features. Use clustering algorithm (such as K-means, DBSCAN) or PCA to reduce the dimension of demand probability distribution data and extract potential intention feature data. Calculate the customer's intention score using the given formula. The intention score calculation formula is:. ; In the formula, Denoted as the intent score, Expressed as The weight of a requirement, Expressed as the demand probability, Expressed as the weight of the feature function, Expressed as customer characteristic function value, Represented as a set of customer features; in the data set, for each customer, use a Python script to calculate the intent score according to the formula. Enter the customer's weight and probability value into the formula and score it in combination with the customer's features. Use the test set data to verify the prediction accuracy of the model and calculate the error between the predicted value and the actual value of the demand probability distribution. Common evaluation indicators include accuracy, precision, recall, F1 score, etc. Evaluate the performance of the model in predicting implicit demand based on these indicators. Use the evaluation functions in sklearn.metrics (such as accuracy_score, mean_squared_error) to evaluate the prediction results. Ensure the generalization ability of the model through cross-validation.

[0045] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes: Step S31: tracking customer behavior on the hidden layer digital model to obtain customer behavior tracking data; calculating the emotion trend based on the customer behavior tracking data to obtain customer emotion trend data; Step S32: predicting customer behavior patterns using the latent digital model according to the customer emotion trend data, thereby obtaining customer behavior prediction data; Step S33: using the customer behavior prediction data to evaluate the interaction strategy of the surface digital model, generating interaction strategy evaluation data; formulating a dynamic adjustment plan according to the interaction strategy evaluation data, and optimizing the interaction design in the surface digital model based on the dynamic adjustment plan, thereby obtaining a dynamic interaction strategy plan; Step S34: Deploy and adjust the interaction design in real time according to the dynamic interaction strategy plan, so as to generate an intelligent customer interaction strategy.

[0046] In an embodiment of the present invention, by tracking customer behavior on a hidden digital model, customer behavior data in multiple interaction stages are collected, including operation logs, click events, session history, purchase behavior, etc. Customer behavior data is tracked through aspects such as user access paths, number of interactions, and interactive content to construct behavior trajectory data. Event tracking tools (such as Google Analytics, Mixpanel, or a custom behavior analysis system) are used to collect and store user behavior data. Behavior data is transmitted to the analysis platform through JavaScript, API calls, or SDK integration. Data storage can be managed using a log database (such as Elasticsearch) or a time series database (such as InfluxDB). Sentiment trends are calculated for customer behavior tracking data using sentiment analysis algorithms. For example, based on customer text feedback, social media dynamics, or interaction records, the customer's emotional tendencies (such as positive, negative, or neutral) are identified. The customer's emotional trends are dynamically tracked, the trend of emotional changes is analyzed, and modeling is performed based on time series to generate customer emotional trend data. Text data is sentimentally classified using natural language processing (NLP) technology and sentiment analysis algorithms (such as VADER, TextBlob, and BERT models). For non-text data, sentiment trends can be inferred by combining changes in behavioral data (such as changes in clicks and purchase behaviors). Machine learning methods (such as LSTM and RNN) can be used to predict trends in time series sentiment data. Based on customer sentiment trend data and historical behavior data, predict future customer behavior patterns. Use prediction models to identify the relationship between sentiment changes and behavior changes, and predict future customer behavior (such as continued purchases, churn, demand changes, etc.) based on these patterns. The model can predict future customer behavior, such as customer behavior conversion rate, preference changes, etc., through time series analysis methods. Use time series analysis methods (such as ARIMA and LSTM networks) or regression models based on customer segmentation (such as Logistic regression) to predict future customer behavior. For large data sets, ensemble learning algorithms such as XGBoost can be used to improve prediction accuracy. Use customer behavior prediction data to evaluate existing interaction strategies in surface digital models. Analyze the effectiveness and potential problems of interaction design by simulating customer behavior changes in different scenarios. Use methods such as A / B testing to evaluate the effects of different interaction strategies, such as comparing the responsiveness of different user interfaces, message push or recommendation strategies. Use multivariate regression analysis or reinforcement learning algorithms to evaluate interaction strategies. Reverse testing can be combined with simulated data to predict customer performance under different interaction strategies. Multi-dimensional data needs to be considered in the evaluation, covering customer sentiment data, historical behavior, environmental data, etc. Based on the interaction strategy evaluation data, the deficiencies in the current interaction design can be dynamically adjusted, such as adjusting the UI / UX design, information prompt strategy, push content or interaction process.Dynamic adjustment plans should be formulated based on customer behavior prediction data to make interaction design more personalized and effective. Use optimization algorithms (such as genetic algorithms and particle swarm optimization) to dynamically adjust interaction strategies. Through real-time data feedback, establish an adaptive interaction design system to automatically adjust the display order of interactive elements, content presentation methods, etc. to improve user satisfaction and engagement. Deploy the optimized interaction design plan to the customer interaction platform in real time, including Web, mobile applications, chatbots, customer service systems, etc. Dynamically adjust the interaction design to adapt to the personalized needs and emotional changes of customers, and update the interaction elements in the system (such as recommendations, prompts, notifications, etc.) in real time. Use CI / CD (continuous integration / continuous deployment) tools (such as Jenkins, GitLab CI) to realize real-time deployment and adjustment of interaction design. Integrate real-time data stream processing platforms (such as Apache Kafka, Apache Flink) to realize real-time streaming processing and feedback of customer interaction data.

[0047] Preferably, formulating a dynamic adjustment plan according to the interaction strategy evaluation data, and optimizing the interaction design in the surface digital model based on the dynamic adjustment plan includes: Conduct customer behavior feedback analysis on interaction strategy evaluation data to obtain customer behavior feedback data; classify and identify high-frequency demands, low-frequency demands, and abnormal demands in user interactions based on user behavior feedback data to obtain interaction demand classification data; The interactive interface layout and interactive logic are adjusted based on the high-frequency demand identification results in user interaction through interactive demand classification data, so as to obtain high-frequency interaction optimization design data; the low-frequency demand identification results in user interaction are improved by adding guidance information or optimizing the operation path, so as to obtain low-frequency interaction optimization design data; According to the interaction demand classification data, an exception handling mechanism is introduced into the abnormal demand identification results in user interaction to obtain abnormal interaction processing data, wherein the introduction of the exception handling mechanism includes multiple rounds of question-and-answer processes or manual intervention; a dynamic adjustment plan is constructed based on high-frequency interaction optimization design data, low-frequency interaction optimization design data and abnormal interaction processing data to generate dynamic optimization interaction design data; The interactive design in the surface digital model is optimized using dynamic optimization interactive design data to obtain a dynamic interactive strategy solution.

[0048] In an embodiment of the present invention, the behavioral data generated by the customer during use is analyzed in detail, mainly including the customer's clicks, operation time, page jumps, feedback and ratings. By counting and mining these data, the customer's feedback on the interaction strategy is identified to help evaluate the effect of the current interaction strategy. Customer behavior feedback data can be extracted from customer behavior analysis tools, such as heat map analysis tools (such as Hotjar), user behavior analysis platforms (such as Mixpanel), etc. Use data analysis tools (such as Pandas and NumPy in Python) and visualization tools (such as Tableau and Power BI) to perform statistical analysis on customer operation records, stay time, click streams, etc. to generate behavior feedback data. By counting the customer's common operations, frequently accessed functional modules, and recurring operation processes, the user's high-frequency needs are identified. For example, customers frequently view the details of a product and frequently use a specific function. Identify infrequent operations or needs, but when they occur, they have an important impact on the customer experience, such as service requests for special needs or complex operations. Identify some unconventional operation modes or behaviors, such as operation steps that do not meet expectations, abnormal jumps, or page loading failures. Use data mining algorithms (such as cluster analysis, K-means algorithm, decision tree) to analyze user behavior data and classify user behavior data according to demand type. Use natural language processing (NLP) technology to analyze text feedback to identify potential abnormal needs. Adjust the interface layout according to the customer's high-frequency needs to ensure that the functions and content commonly used by customers are more prominent and easy to access. For example, adjust the size, color or position of important buttons, or place the functional modules that users often visit in a prominent position. Simplify and optimize the interaction process so that customers can reach their goals more quickly. Improve the response efficiency of high-frequency needs by reducing unnecessary steps or adding shortcuts. Use UX / UI design tools (such as Sketch, Figma) to design and optimize the interface layout and interaction process. Combine customer behavior data and conduct A / B testing to verify the effectiveness of the optimization plan. For low-frequency needs, provide customers with detailed guidance information, such as help documents, FAQs or guide prompts, which can help users quickly understand how to operate and reduce uncertainty in operation. For low-frequency needs, optimize the operation path, such as simplifying the operation steps of certain functions or adding quick operation entrances to improve the convenience of low-frequency needs. Design a dynamic prompt system or pop-up window guidance to display guidance information in the form of prompt boxes, floating help buttons, etc. Combine the user's behavior path and use user behavior analysis tools (such as Google Analytics) to perform path optimization analysis. For abnormal needs, such as users repeatedly asking questions or unable to complete tasks, introduce multiple rounds of questions and answers or conversational interfaces to gradually guide users to find solutions.For example, when a user cannot complete registration through conventional means, the system can help the user complete registration through a series of questions. For problems that the system cannot solve, provide a manual customer service intervention mechanism to solve problems for customers through chatbots or manual customer service to ensure that the customer experience is not affected. Use dialogue systems (such as Dialogflow, Microsoft Bot Framework) to implement multi-round question-and-answer processes, and combine chatbot algorithms to handle user abnormal requests. For abnormal demands that cannot be handled through automation, guide users to the manual customer service channel. Combine high-frequency demand optimization design, low-frequency demand optimization design, and abnormal demand handling solutions to build a dynamic interactive adjustment solution. The solution should be personalized according to different user needs, behaviors, and emotional trends, and support real-time adjustment. In the process of solution construction, give priority to user experience, ensure that personalization and flexibility are reflected in the design solution, and enable the interactive design to adapt to different situations. Use agile development methods (such as Scrum) to quickly develop and test dynamic adjustment solutions to ensure that the design solution can respond to changes in user behavior in real time. Combine real-time feedback and data stream processing platforms (such as Apache Kafka, AWS Kinesis) for dynamic optimization and adjustment. Based on the dynamic optimization of interaction design data, optimize the interaction design in the surface digital model, including updating the interface layout, interaction process and functional modules to better meet customer needs. Regularly re-evaluate and adjust the interaction strategy based on user feedback, behavior data and sentiment analysis results to ensure continuous optimization of the interaction strategy. Integrate the dynamic optimization interaction design data into the surface digital model, and continuously improve the interaction strategy through A / B testing, user feedback and data flow analysis. Achieve cross-platform synchronous updates to ensure that the user experience on mobile, PC and other devices can be consistently optimized.

[0049] Preferably, step S4 comprises the following steps: Step S41: performing customer emotional feedback on the customer question and answer content collection data through an intelligent customer interaction strategy to generate customer emotional feedback data; Step S42: construct a portrait based on the customer sentiment feedback data to obtain a virtual customer portrait; stratify the virtual customer portrait to generate virtual customer portrait hierarchical data; label the virtual customer portrait according to the virtual customer portrait hierarchical data, and store the labeled virtual customer portrait in the cloud to perform customer management operations.

[0050] In an embodiment of the present invention, the customer's emotions are evaluated by analyzing the customer's questions and answers through natural language processing (NLP) technology in an intelligent customer interaction system. Use sentiment analysis models (such as VADER, BERT) to classify the customer's language in the interaction, and judge their emotional tendency (such as positive, negative or neutral) and emotional intensity. Collect the customer's voice and text feedback when interacting with the system, as well as the keywords, emoticons, etc. used in the question and answer process, analyze their emotional tendency, and generate emotional feedback data. Use sentiment analysis APIs (such as Google Cloud Natural Language API, IBM Watson NLU) to perform sentiment analysis on the customer's question and answer content. Use text analysis libraries in Python (such as TextBlob, NLTK) to perform sentiment scoring on the collected customer questions and answers, classify them as positive, negative or neutral, and generate emotional feedback data, such as the customer's emotional score and emotional type (for example, joy, anger, confusion, etc.). Based on the customer's emotional feedback data, combined with their past interactive behaviors, consumption habits, preference settings and other information, a virtual customer portrait is constructed. The virtual customer portrait not only includes the customer's basic information, but also covers multi-dimensional information such as emotional trends, purchasing behaviors, and feedback patterns. Through data mining and analysis, identify customer behavior characteristics, such as frequently visited pages, preferred services, common problems, etc., to comprehensively build personalized virtual customer portraits. Combine customer behavior data (such as click streams, operation paths, historical purchase records, etc.) with sentiment data, and use machine learning algorithms (such as cluster analysis and K-means algorithm) to build virtual customer portraits. Combine the results of sentiment analysis with customer behavior data, use Scikit-learn, TensorFlow and other libraries in Python for analysis, and generate portrait data containing characteristics such as sentiment, preference, and purchase intention. Layer virtual customer portraits according to dimensions such as customer activity, value, and demand. For example, customers can be divided into high-value customers, potential customers, ordinary customers, and low-value customers, and different strategies can be adjusted according to these levels. Use the behavioral patterns of customer portraits (such as purchase frequency, browsing behavior, and emotional feedback) to stratify customers, ensuring that the customer portraits at each level are more accurate and convenient for implementing personalized service strategies. Use cluster analysis methods (such as K-means clustering, DBSCAN, etc.) to divide customer portraits into levels. Based on the customer's emotional feedback data, interaction frequency, purchase history and other characteristics, create a hierarchical model and assign a corresponding label to each level. Use the Sklearn library in Python to perform cluster analysis, or use deep learning models (such as Autoencoder) to stratify customers. Add labels to each virtual customer portrait based on its hierarchical data, behavioral characteristics, emotional feedback and other information.For example, labels include "highly active", "potential customers", "loyal customers", "price sensitive", etc., so as to enable targeted management. Each label should be dynamically adjusted based on the customer's behavior and emotional feedback. For example, if the customer's emotional feedback becomes negative, the label can be automatically updated to "needs attention". Use a label generation system (such as ElasticSearch, Apache Solr) to automatically add labels to each customer portrait. Customers can be appropriately labeled based on rule engines or machine learning algorithms, combining customer behavior data, sentiment analysis data, and information in hierarchical models. Store labeled customer portraits in cloud data warehouses such as AWS, Google Cloud Storage, or Azure to ensure that customer data can be accessed and updated in real time. Synchronize all labeled customer portrait data to the cloud for cross-platform access and update. Use API interfaces (such as RESTful APIs) to ensure data flow between different systems. Cloud data management platforms (such as AWS S3, Google BigQuery) can be used to store and analyze customer portrait data, and integrate with customer relationship management (CRM) systems to implement personalized customer management strategies.

[0051] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0052] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A customer management method based on a cloud server, characterized in that: The following steps are involved: Step S1: Obtain customer information data using a cloud server; Introduce intelligent interactive plug-ins based on customer information data to obtain usage data of intelligent question-and-answer plug-ins; The intelligent question and answer plug-in uses data to filter customer information data for customer question and answer content, thereby obtaining customer question and answer content collection data; Pre-process the collected data of customer Q&A content to generate standard customer Q&A content data; Step S2: semantically parse the standard customer question and answer content data to generate customer question and answer content semantic parsing data; perform user behavior modeling on the customer information data based on the customer question and answer content semantic parsing data to generate a virtual digital twin model, wherein the virtual digital twin model includes a surface digital model and a hidden digital model; Step S3: Track customer behavior on the hidden digital model to obtain customer behavior tracking data; predict customer behavior on the hidden digital model based on the customer behavior tracking data to generate customer behavior prediction data; use the customer behavior prediction data to dynamically adjust the interaction strategy of the surface digital model to generate an intelligent customer interaction strategy; Step S4: performing customer sentiment feedback on the customer question and answer content collection data through an intelligent customer interaction strategy to generate customer sentiment feedback data; A profile is constructed based on customer sentiment feedback data to obtain a virtual customer profile, which is then stored in the cloud to perform customer management tasks.

2. The cloud server-based customer management method according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Obtain customer information data using a cloud server; Step S12: Perform customer information port compatibility analysis based on the customer information data to generate customer information port compatibility data; introduce the intelligent interactive plug-in based on the customer information port compatibility data to obtain intelligent question and answer plug-in usage data; Step S13: Using the intelligent question and answer plug-in to use data, the customer information data is screened for customer question and answer content to obtain customer question and answer content collection data; Step S14: preprocess the data collected from customer question and answer content to generate standard customer information data, wherein the data preprocessing includes data cleaning, data denoising, missing value filling and data standardization.

3. The cloud server-based customer management method according to claim 2, characterized in that: The introduction of intelligent interactive plug-ins based on customer information port compatible data includes: Perform demand feature analysis on customer information data based on customer information port compatibility data, thereby obtaining customer demand feature data; screen matching intelligent interactive plug-in types based on customer demand feature data, and perform plug-in adaptability evaluation, thereby obtaining intelligent plug-in adaptation data; According to the smart plug-in adaptation data, the smart question and answer plug-in configuration parameters corresponding to the smart plug-in are loaded to generate plug-in initialization parameter data; according to the plug-in initialization parameter data, the smart question and answer plug-in function module is loaded on the customer information data to generate smart plug-in interaction binding data; According to the smart plug-in interaction binding data, customer information and plug-in interaction records are integrated to generate smart question and answer plug-in usage data.

4. The method for managing customers based on a cloud server according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing a customer question and answer keyword search on the standard customer question and answer content data to obtain the customer question and answer keywords; performing a user question and answer semantic analysis on the standard customer question and answer content data based on the customer question and answer keywords to generate customer question and answer content semantic analysis data; Step S22: mining customer behavior feature patterns on customer information data according to the semantic analysis data of customer question and answer content to generate customer behavior pattern feature data, wherein the customer behavior pattern feature data includes interaction behavior pattern data, browsing behavior pattern data, and time and environment behavior pattern data; Step S23: using the customer behavior pattern feature data to model the customer's explicit behavior on the customer information data, and generating surface digital model data; Step S24: Perform deep inference modeling of customer hidden behaviors on customer information data through surface digital model data and customer behavior pattern feature data to generate hidden digital model data; perform multi-layer information fusion of surface digital model data and hidden digital model data to generate a virtual digital twin model.

5. The cloud server-based customer management method according to claim 4, characterized in that: Step S23 includes the following steps: Step S231: using the interactive behavior pattern data in the customer behavior pattern feature data to collect customer direct operation records from the customer information data, and analyzing the customer operation sequence based on the extracted customer direct operation records to construct a user operation path sequence; extracting the user operation frequency, operation duration, and key operation points from the customer information data according to the user operation path sequence, and marking them as direct operation feature data; Step S232: using the browsing behavior pattern data in the customer behavior pattern feature data to capture the target elements clicked by the customer in the customer information data, and obtain the customer click event; performing click hot zone statistics on the customer click event, and obtain user click hot zone data; analyzing the click preference of the customer click event based on the user click hot zone data, and marking the analysis result as click behavior feature data; Step S233: using the time and environment behavior pattern data in the customer behavior pattern feature data to monitor the explicit demand expression input by the user in the customer information data, and generate user input demand data; performing demand type analysis on the user input demand data, and marking the analysis result as explicit demand feature data; Step S234: performing digital index and parameter conversion on the direct operation feature data, the click behavior feature data and the explicit demand feature data, so as to generate surface digital model data.

6. The cloud server-based customer management method according to claim 4, characterized in that: The deep inference modeling of customer implicit behavior based on customer information data through surface digital model data and customer behavior pattern feature data includes: Perform cross-feature extraction on customer behavior pattern feature data through surface digital model data to obtain customer joint behavior feature data; construct a Bayesian network structure based on customer joint behavior feature data to generate Bayesian network topology data; Divide the customer information data into data sets to generate model training sets and model test sets; use the model training sets to calculate the conditional probability distribution of the Bayesian network topology data to obtain conditional probability distribution data; perform customer implicit demand probability inference on the conditional probability distribution data to generate demand probability distribution data; The customer information data is decomposed into potential intentions according to the demand probability distribution data to generate potential intention feature data; the intention score is calculated for the potential intention feature data to obtain the intention score data, wherein the formula for the intention score calculation is as follows: ； In the formula, is represented as the intent score, Expressed as The weight of a requirement, Expressed as the demand probability, Expressed as the weight of the feature function, Expressed as customer characteristic function value, Represented as a set of customer characteristics; The prediction accuracy of the demand probability distribution data is verified through the model test set to generate the hidden layer digital model data.

7. The method for managing customers based on a cloud server according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: tracking customer behavior on the hidden layer digital model to obtain customer behavior tracking data; calculating the emotion trend based on the customer behavior tracking data to obtain customer emotion trend data; Step S32: predicting customer behavior patterns on the latent digital model according to the customer emotion trend data, thereby obtaining customer behavior prediction data; Step S33: using the customer behavior prediction data to evaluate the interaction strategy of the surface digital model, generating interaction strategy evaluation data; formulating a dynamic adjustment plan according to the interaction strategy evaluation data, and optimizing the interaction design in the surface digital model based on the dynamic adjustment plan, thereby obtaining a dynamic interaction strategy plan; Step S34: Deploy and adjust the interaction design in real time according to the dynamic interaction strategy plan, so as to generate an intelligent customer interaction strategy.

8. The cloud server-based customer management method according to claim 7, characterized in that: Formulate dynamic adjustment plans based on interaction strategy evaluation data, and optimize the interaction design in the surface digital model based on the dynamic adjustment plans, including: Conduct customer behavior feedback analysis on interaction strategy evaluation data to obtain customer behavior feedback data; classify and identify high-frequency demands, low-frequency demands, and abnormal demands in user interactions based on user behavior feedback data to obtain interaction demand classification data; The interactive interface layout and interactive logic are adjusted based on the high-frequency demand identification results in user interaction through interactive demand classification data, so as to obtain high-frequency interaction optimization design data; the low-frequency demand identification results in user interaction are improved by adding guidance information or optimizing the operation path, so as to obtain low-frequency interaction optimization design data; According to the interaction demand classification data, an exception handling mechanism is introduced into the abnormal demand identification results in user interaction to obtain abnormal interaction processing data, wherein the introduction of the exception handling mechanism includes multiple rounds of question-and-answer processes or manual intervention; a dynamic adjustment plan is constructed based on high-frequency interaction optimization design data, low-frequency interaction optimization design data and abnormal interaction processing data to generate dynamic optimization interaction design data; The interactive design in the surface digital model is optimized using dynamic optimization interactive design data to obtain a dynamic interactive strategy solution.

9. The method for managing customers based on a cloud server according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing customer emotional feedback on the customer question and answer content collection data through an intelligent customer interaction strategy to generate customer emotional feedback data; Step S42: construct a portrait based on the customer sentiment feedback data to obtain a virtual customer portrait; stratify the virtual customer portrait to generate virtual customer portrait hierarchical data; label the virtual customer portrait according to the virtual customer portrait hierarchical data, and store the labeled virtual customer portrait in the cloud to perform customer management operations.

10. A customer management system based on a cloud server, characterized in that: Used to execute the cloud server-based customer management method according to claim 1, the cloud server-based customer management system comprises: The interactive plug-in introduction module is used to obtain customer information data using the cloud server; introduce intelligent interactive plug-ins based on the customer information data to obtain intelligent question and answer plug-in usage data; filter customer question and answer content on the customer information data through the intelligent question and answer plug-in usage data to obtain customer question and answer content collection data; perform data preprocessing on the customer question and answer content collection data to generate standard customer question and answer content data; The behavior modeling module is used to perform semantic analysis on standard customer question and answer content data to generate customer question and answer content semantic analysis data; perform user behavior modeling on customer information data based on the customer question and answer content semantic analysis data to generate a virtual digital twin model, wherein the virtual digital twin model includes a surface digital model and a hidden digital model; The dynamic interaction module is used to track customer behavior on the hidden digital model to obtain customer behavior tracking data; predict customer behavior on the hidden digital model based on the customer behavior tracking data to generate customer behavior prediction data; use the customer behavior prediction data to adjust the dynamic interaction strategy of the surface digital model to generate intelligent customer interaction strategy; The emotional feedback module is used to collect customer emotional feedback on customer question and answer content through intelligent customer interaction strategies to generate customer emotional feedback data; construct a portrait based on the customer emotional feedback data to obtain a virtual customer portrait, and store the virtual customer portrait in the cloud to perform customer management tasks.

Images