Meta-universe-based heating system customer service intelligent processing method and system

Abstract

The application discloses a kind of based on meta-universe's heating system customer service intelligent processing method, comprising: heating system meta-universe platform is established: the heating system meta-universe platform including physical fusion layer, model fusion layer, data fusion layer and service fusion layer is established;Passive customer service: based on the heating system meta-universe platform, customer virtual image and service personnel virtual image are established in the same meta-universe virtual space, real-time business communication is carried out, and customer business type is determined according to customer virtual image, business communication result and customer heating appeal, and passive processing of customer service is carried out;Active customer service: based on the heating system meta-universe platform, the multi-source heterogeneous data related to heating system customer service is fused and analyzed, customer portrait and the running state of the heating system are monitored, customer data is used to actively contact customers before they raise business appeal, and active precision service for customers is carried out.

Description

Technical Field

[0001] This invention belongs to the field of intelligent heating customer service technology, specifically involving an intelligent processing method for customer service in heating systems based on the metaverse. Background Technology

[0002] With rapid economic development, the scale of centralized heating in urban areas is constantly increasing. During the heating season, there are often various customer service needs. Therefore, the intelligent heating customer service system has emerged to address these needs. It mainly solves problems such as billing management, customer complaints, temperature measurement, inspection, and work order dispatch. For example, for customer requests for repairs or complaints, the customer service center can uniformly dispatch, track, and follow up on the work orders to achieve a rapid response to customer needs.

[0003] The metaverse is a virtual world created and linked through technological means, mapping and interacting with the real world, and possessing a new social system within its digital living space. Essentially, the metaverse is the virtualization and digitization of the real world, requiring significant modifications to content production, economic systems, user experience, and physical world content. However, the development of the metaverse is gradual, taking shape through the continuous integration and evolution of numerous tools and platforms, supported by shared infrastructure, standards, and protocols. It provides immersive experiences based on extended reality technology, generates mirror images of the real world based on digital twin technology, and builds an economic system based on blockchain technology, closely integrating the virtual and real worlds in terms of economic, social, and identity systems, and allowing each user to produce content and edit their own world.

[0004] However, in actual customer service applications, the business communication between customers and the customer service center is ineffective, business processing is not timely, and some customer service needs cannot be analyzed in advance, making it difficult to provide proactive service. As a result, customers face problems such as poor heating satisfaction and numerous customer complaints.

[0005] Based on the aforementioned technical issues, a new intelligent customer service processing method for heating systems based on the metaverse needs to be designed. Summary of the Invention

[0006] The technical problem this invention aims to solve is to overcome the shortcomings of existing technologies and provide an intelligent customer service processing method for heating systems based on a metaverse. On the one hand, customers and service centers can conduct business communication within the same metaverse virtual space. Moreover, in practical applications, service centers can dispatch personnel to participate in customer service scenarios and virtual environments anytime and anywhere according to actual business needs, providing passive customer service and improving customer satisfaction and work efficiency. On the other hand, based on the heating system metaverse platform, customer profiles can be established and the operating status of the heating system and customer heating data can be monitored. Machine learning algorithms can be used to analyze historical customer service work order data, historical system operation data, and customer heating information. Furthermore, heating risks and target customers with customer service needs can be identified in advance, and proactive contact can be made to provide services, enabling proactive and precise customer service.

[0007] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0008] This invention provides an intelligent customer service processing method for heating systems based on a metaverse, the method comprising:

[0009] Establishment of a Metaverse Platform for Heating Systems: Establish a metaverse platform for heating systems that includes a physical fusion layer, a model fusion layer, a data fusion layer, and a service fusion layer, to enable ubiquitous perception, virtual mapping, simulation, and intelligent management of heating system equipment entities and the metaverse space;

[0010] Passive customer service: Based on the heating system metaverse platform, virtual customer images and virtual service personnel images are established in the same metaverse virtual space to conduct business communication in real time. The customer business type is determined according to the customer virtual image, the business communication results and the customer's heating needs, and customer service is handled passively.

[0011] Proactive customer service: Based on the aforementioned heating system metaverse platform, multi-source heterogeneous data related to heating system customer service are integrated and analyzed to establish customer profiles and monitor the operation status of the heating system and customer heat consumption data. Before customers raise business requests, customers are proactively contacted to handle potential problems and provide proactive and precise customer service.

[0012] The customer service services mentioned above include at least business acceptance, intelligent order dispatch, work order tracking, temperature measurement management, operation and maintenance diagnosis, heating inspection and billing management.

[0013] Furthermore, the establishment of the heating system metaverse platform, which includes a physical fusion layer, a model fusion layer, a data fusion layer, and a service fusion layer, includes:

[0014] The physical fusion layer is used to effectively connect the physical entity resources of the heating system and build an intelligent IoT sensing network for the heating system that covers the entire domain and all time periods; it is also used to acquire, fuse, and transmit multi-source heterogeneous data obtained from the intelligent IoT sensing network of the heating system in real time; it is used to monitor and control the acquired multimodal data in real time; and it is used to perform virtual-real fusion between physical entities and the metaverse space.

[0015] The model fusion layer is used to construct digital models of the physical entity resources of the heating system in the metaverse space, as well as digital models of the business logic, attribute characteristics, and relationships involved in the operation of the metaverse space of the heating system; it is also used to verify the model through metaverse model evaluation and verification technology; and it is used to establish semantic associations and real-time mapping relationships between virtual digital models of the physical entity resources of the heating system, including physics, structure, behavior, and rules.

[0016] The data fusion layer is used to collect, store, process, iterate, optimize, integrate, and fuse data on the physical entities of the heating system and its metaverse model.

[0017] The service integration layer is used for collaborative interaction of service resources, intelligent supervision of service processes, simulation of service content, and self-optimization of service rules.

[0018] Furthermore, the establishment of a customer's virtual avatar includes:

[0019] Customer images are obtained by taking pictures of customers using image acquisition devices, and the working status of heating equipment and room temperature in customers' homes are obtained using data acquisition devices installed in customers' homes, or the operating status of heating stations is obtained using data acquisition devices installed in subordinate heating stations, and basic customer attribute information is obtained through the heating system backend; the customers include at least heat users and subordinate heating station managers; the basic customer attributes include at least the heat user's name, residential community, building number, and room number, as well as the name of the subordinate heating station manager, the name of the heating branch company to which they belong, and the heating station number;

[0020] A virtual 3D image of the customer is created using 3D reconstruction technology based on the customer's image. The virtual 3D image of the customer is then labeled with the working status of the heating equipment in the customer's home, the room temperature, and the customer's basic attribute information to obtain the virtual image of the customer.

[0021] Furthermore, the process of determining the customer's service type based on their virtual avatar, business communication results, and heating needs, and then passively handling customer service, includes:

[0022] The customer's virtual avatar, the customer's description of their home heating needs, and the results of business communication with the customer are used as customer service demand information. The expert algorithm set in the heating system metaverse platform is used to extract keywords from the customer service demand information. For customer demands that can be directly and intuitively resolved, the next step of customer service processing is carried out. For customer demands that cannot be directly resolved, the keywords are input into a pre-trained machine learning algorithm for business identification to predict the next customer service processing method.

[0023] Furthermore, for customer requests that cannot be directly addressed, the method also includes: using a pre-established similarity model to obtain similarity data between the customer and customer requests in the historical database, and recommending subsequent customer service handling methods for similar customers with similarity greater than a preset value for reference by heating service managers.

[0024] Furthermore, the fusion analysis of multi-source heterogeneous data related to heating system customer service establishes customer profiles, including:

[0025] Acquire initial data information of target customers related to heating system customer service, and obtain initial attribute data and initial behavior data after preprocessing and identification extraction;

[0026] The initial attribute data is standardized to obtain target attribute data, and customer attribute tags are generated based on the target attribute data.

[0027] The initial behavioral data is normalized to obtain target behavioral data, and the target behavioral data is input into a trained neural network model to obtain customer behavior labels. The customer behavior labels include at least heating behavior, payment behavior, and interaction behavior. The heating behavior includes heating characteristics and load characteristics. The payment behavior includes payment method and payment time. The interaction behavior includes at least appeal behavior, interaction characteristics, channel preference, and notification method.

[0028] A preset algorithm is used to perform tag mining on the customer attribute tags and customer behavior tags to obtain tag mining results, and a customer profile of the target customer is obtained based on the tag mining results; the preset algorithm includes clustering analysis algorithm, classification analysis algorithm, and regression analysis algorithm; the clustering analysis algorithm includes K-means algorithm and hierarchical clustering algorithm; the classification analysis algorithm includes decision tree algorithm, principal component analysis method, and convolutional neural network algorithm; the regression analysis algorithm includes linear regression analysis and nonlinear regression analysis.

[0029] Furthermore, the establishment of customer profiles and monitoring of the heating system's operational status and customer heating data, along with proactively contacting customers before they raise business requests, addressing potential issues, and providing proactive and precise customer services, includes:

[0030] Based on existing customer service work orders, we acquire heating operation data of heating stations in areas with high-frequency service demands, as well as customer heating data of typical floors in the corresponding communities. We combine these data samples with weather factors and use a CNN-BiGRU network based on an attention mechanism to establish a heating station water supply temperature prediction model and a customer room temperature prediction model.

[0031] Based on the heating station water supply temperature prediction model and the customer room temperature prediction model, the heating station water supply temperature and the customer room temperature are predicted. If the error exceeds the preset heating station water supply temperature and customer room temperature, an active order is dispatched to carry out heating inspection, diagnosis and analysis and active temperature measurement, and the corresponding heating parameters are adjusted to handle potential risk issues and provide proactive and precise customer service.

[0032] In addition, based on customer profiles, we adopt communication and service methods that match the customer tags for customers with different heating behaviors, payment behaviors, and interaction behaviors.

[0033] Furthermore, the provision of proactive and precise customer service also includes: acquiring customer service work order data of complaints that have occurred, and after preprocessing the data in conjunction with the corresponding heating operation data, using machine learning methods to extract data features and establish a customer complaint tendency prediction model, applying the customer complaint tendency prediction model to the customer group that has not yet made a complaint, identifying the target identifier of the user group with complaint tendency, calculating the probability of potential complaint risk, and proactively contacting the customer to provide services.

[0034] Furthermore, the aforementioned use of an attention-based CNN-BiGRU network to establish a prediction model for the water supply temperature of the heating station and a prediction model for the room temperature of the customer includes:

[0035] The data vector is input into the CNN network model and subjected to convolution, max pooling and fully connected layer operations to obtain the extracted data feature vector, which is then input into the BiGRU network model structure for model training.

[0036] An attention mechanism is used to obtain the probability corresponding to different data feature vectors based on the weight allocation principle from the data feature vectors processed by the BiGRU network. The optimal weight parameter matrix is ​​continuously updated and iterated to obtain a CNN-BiGRU hybrid network model composed of CNN network and BiGRU network.

[0037] The trained CNN-BiGRU hybrid network model is used to predict the water supply temperature of the heating station and the room temperature of the customers.

[0038] The probability of obtaining different data feature vectors according to the weight allocation principle is expressed as follows:

[0039] e t =u tanh(wh) t +b);

[0040]

[0041]

[0042]

[0043]

[0044]

[0045] e t Let h be the output vector of the BiGRU network layer at time t. t The corresponding attention probability distribution values; u and w are weight coefficients; b is the bias coefficient; s t The output at time t is the result of using an attention mechanism; a t For vector matching weights; i represents time; j represents a time point before time t; This is the forward hidden layer state; This is the backward hidden state; W t for The corresponding weight; V t for The corresponding weight; b t x is the bias of the hidden state at time t; t For the input vector; F GRU The function transforms the input vector into the corresponding GRU hidden state.

[0046] This invention also provides a heating system customer service intelligent processing system based on the metaverse, the heating system customer service intelligent processing system comprising:

[0047] Heating System Metaverse Platform Establishment Unit: Used to establish a heating system metaverse platform including a physical fusion layer, a model fusion layer, a data fusion layer, and a service fusion layer, to perform ubiquitous perception, virtual mapping, simulation, and intelligent management of heating system equipment entities and metaverse space;

[0048] Passive Customer Service Unit: Based on the heating system's metaverse platform, it establishes virtual customer and service personnel images in the same metaverse virtual space, conducts real-time business communication, and determines the customer's business type based on the customer's virtual image, business communication results, and customer's heating needs, and performs passive customer service processing.

[0049] Proactive Customer Service Unit: Based on the heating system metaverse platform, it integrates and analyzes multi-source heterogeneous data related to heating system customer service, establishes customer profiles and monitors the operating status of the heating system and customer heat consumption data, proactively contacts customers before they raise business requests, handles potential problems, and provides proactive and precise customer service.

[0050] The customer service services mentioned above include at least business acceptance, intelligent order dispatch, work order tracking, temperature measurement management, operation and maintenance diagnosis, heating inspection and billing management.

[0051] The beneficial effects of this invention are:

[0052] This invention establishes a heating system metaverse platform: This platform includes a physical fusion layer, a model fusion layer, a data fusion layer, and a service fusion layer. Passive customer service: Based on this platform, virtual customer and service personnel avatars are created within the same virtual space for real-time business communication. The customer's service type is determined based on their virtual avatar, communication results, and heating needs, enabling passive customer service processing. Proactive customer service: Based on this platform, multi-source heterogeneous data related to heating system customer service is integrated and analyzed to create customer profiles and monitor the heating system's operational status and customer heating data. Customers are proactively contacted before they submit service requests, providing proactive and precise customer service. This allows for digital modeling, semantic description, and real-time processing of the heating system's physical components, data, models, and services based on cyber-physical fusion technology. Mapping provides crucial support for the collaborative interaction and virtual-real integration of diverse elements such as people, machines, objects, and the environment in the physical world of the heating system and the metaverse space. Establishing a metaverse platform for the heating system allows customers and service centers to conduct business communication within the same virtual space. In practical applications, service centers can dispatch personnel to participate in customer service scenarios and virtual environments anytime and anywhere, providing passive customer service and improving customer satisfaction and work efficiency. On the other hand, the metaverse platform can also be used to create customer profiles and monitor the operating status of the heating system and customer heating data. Machine learning algorithms can be used to analyze historical customer service work order data, historical system operation data, and customer heating information, and to proactively identify heating risks and target customers with customer service needs, enabling proactive and precise customer service.

[0053] Other features and advantages will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0054] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0055] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0056] Figure 1 This is a schematic diagram of the process of a customer service intelligent management method for a heating system based on the metaverse, according to the present invention.

[0057] Figure 2 This is a schematic diagram of the passive customer service method of the present invention;

[0058] Figure 3 This is a schematic diagram of the basic structure of the BiGRU network of the present invention;

[0059] Figure 4 This is a schematic diagram of the structure of an intelligent management system for customer service of a heating system based on the metaverse, according to the present invention. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0061] Example 1

[0062] Figure 1 This is a schematic diagram of a customer service intelligent management method for a heating system based on the metaverse, which is involved in this invention.

[0063] Figure 2 This is a schematic diagram of the passive customer service method involved in this invention.

[0064] like Figure 1-2 As shown, this embodiment 1 provides a heating system customer service intelligent processing method based on the metaverse. The heating system customer service intelligent processing method includes:

[0065] Establishment of a Metaverse Platform for Heating Systems: Establish a metaverse platform for heating systems that includes a physical fusion layer, a model fusion layer, a data fusion layer, and a service fusion layer, to enable ubiquitous perception, virtual mapping, simulation, and intelligent management of heating system equipment entities and the metaverse space;

[0066] Passive customer service: Based on the heating system metaverse platform, virtual customer images and virtual service personnel images are established in the same metaverse virtual space to conduct business communication in real time. The customer business type is determined according to the customer virtual image, the business communication results and the customer's heating needs, and customer service is handled passively.

[0067] Proactive customer service: Based on the aforementioned heating system metaverse platform, multi-source heterogeneous data related to heating system customer service are integrated and analyzed to establish customer profiles and monitor the operation status of the heating system and customer heat consumption data. Before customers raise business requests, customers are proactively contacted to handle potential problems and provide proactive and precise customer service.

[0068] The customer service services mentioned above include at least business acceptance, intelligent order dispatch, work order tracking, temperature measurement management, operation and maintenance diagnosis, heating inspection and billing management.

[0069] In this embodiment, the establishment of the heating system metaverse platform, which includes a physical fusion layer, a model fusion layer, a data fusion layer, and a service fusion layer, includes:

[0070] The physical fusion layer is used to effectively connect the physical resources of the heating system through intelligent IoT sensing and interconnection technologies, constructing an intelligent IoT sensing network for the heating system covering the entire domain and all time periods; it is also used to acquire, fuse, and transmit multi-source heterogeneous data obtained in the intelligent IoT sensing network of the heating system in real time through the fusion and transmission technology of multi-source heterogeneous IoT sensor data; it is used to monitor and control the acquired multi-modal data in real time through multi-modal data real-time interaction and control technology; and it is used to achieve virtual-real fusion of physical entities and metaverse space through collaborative interaction and virtual-real fusion technology.

[0071] The model fusion layer is used to construct digital models of the physical entity resources of the heating system in the metaverse space through metaverse model construction technology, as well as digital models of business logic, attribute characteristics, and relationships involved in the operation of the heating system in the metaverse space; it is also used to verify the model through metaverse model evaluation and verification technology; and it is used to establish semantic associations and real-time mapping relationships between virtual digital models of the physical entity resources of the heating system, including physics, structure, behavior, and rules.

[0072] The data fusion layer is used to collect, store, process, iterate, optimize, integrate, and fuse data on the physical entities of the heating system and its metaverse model.

[0073] The service integration layer is used for collaborative interaction of service resources, intelligent supervision of service processes, simulation of service content, and self-optimization of service rules.

[0074] It's important to note that the metaverse is a new type of internet application and social form that combines the virtual and the real. It provides immersive experiences based on extended reality technology, generates mirror images of the real world based on digital twin technology, and constructs an economic system based on blockchain technology. It integrates the virtual and real worlds comprehensively and from multiple perspectives, allowing each user to create and edit within it. The heating system in the metaverse serves as an effective verification method for building digital, information-based, and intelligent new heating systems. These new heating systems require extensive digital simulation modeling and analysis, and will demonstrate a high degree of integration between real-world and digital equipment within the metaverse.

[0075] In this embodiment, establishing a customer's virtual avatar includes:

[0076] Customer images are obtained by taking pictures of customers using image acquisition devices, and the working status of heating equipment and room temperature in customers' homes are obtained using data acquisition devices installed in customers' homes, or the operating status of heating stations is obtained using data acquisition devices installed in subordinate heating stations, and basic customer attribute information is obtained through the heating system backend; the customers include at least heat users and subordinate heating station managers; the basic customer attributes include at least the heat user's name, residential community, building number, and room number, as well as the name of the subordinate heating station manager, the name of the heating branch company to which they belong, and the heating station number;

[0077] A virtual 3D image of the customer is created using 3D reconstruction technology based on the customer's image. The virtual 3D image of the customer is then labeled with the working status of the heating equipment in the customer's home, the room temperature, and the customer's basic attribute information to obtain the virtual image of the customer.

[0078] In this embodiment, the step of determining the customer's service type based on the customer's virtual avatar, business communication results, and customer's heating needs, and then performing passive customer service processing, includes:

[0079] The customer's virtual avatar, the customer's description of their home heating needs, and the results of business communication with the customer are used as customer service demand information. The expert algorithm set in the heating system metaverse platform is used to extract keywords from the customer service demand information. For customer demands that can be directly and intuitively resolved, the next step of customer service processing is carried out. For customer demands that cannot be directly resolved, the keywords are input into a pre-trained machine learning algorithm for business identification to predict the next customer service processing method.

[0080] It should be noted that the human-computer interaction system is the medium for communication with users within the metaverse platform of the heating system. It uses XR devices and holographic projection for information display and wearable controllers for operation control. XR devices include augmented reality, virtual reality, and mixed reality devices. AR devices are used for interaction in the real environment, using smart sensors and visual interfaces to provide virtual experiences or digital information to real users. VR devices are used for interaction in the virtual environment; their interaction effects only affect the virtual world and not the real world. MR devices can simultaneously achieve interaction between the real and virtual worlds, allowing manipulation of real-world objects in the virtual world with the help of robots. Holographic projection is a virtual reproduction technology that presents a true three-dimensional image of an object through optical means. Holographic projection directly presents three-dimensional images to users, who can view the images from different angles with the naked eye without wearing XR devices. With the development of holographic projection technology, the boundary between the real and virtual worlds is becoming blurred, laying a solid foundation for realizing ubiquitous information visualization in meta-heating.

[0081] By establishing virtual customer avatars and virtual spaces, and placing these avatars alongside virtual service personnel avatars within the same virtual environment, communication regarding customer needs is facilitated. Ultimately, based on the customer's virtual avatar, the results of this communication, and the customer's heating requirements, the customer service type is determined, and the next steps for customer service are outlined. Using 3D reconstruction technology, customer images are reconstructed into virtual 3D avatars. These avatars are then annotated with the operating status of the heating equipment in the customer's home, room temperature, and basic customer attributes. This ensures that the virtual 3D avatar accurately reflects the customer's actual situation, providing more information for customer service assessments and improving customer satisfaction. When maintenance personnel are required to provide customer service, MR devices can provide them with digital information about both the real and virtual heating systems, offering more data and improving the accuracy of analysis during inspections. Holographic projection directly presents virtual 3D images of the real heating equipment to maintenance personnel. Maintenance personnel can obtain the operating information of electrical equipment without wearing XR equipment. After obtaining digital information from the virtual heating system, maintenance personnel need to make decisions and take actions based on the information they have obtained. Maintenance personnel enter the virtual heating system to try various operations and finally obtain an optimal operation plan. The optimal operation plan obtained in the virtual heating system is then implemented in the real heating system.

[0082] In practical applications, the main customer service requests are usually dissatisfaction with heating, temperature measurement, and inspection. The virtual avatar of the customer can provide basic information for subsequent services, making it easier for the customer service center to dispatch orders, conduct inspections, and track, supervise, and provide feedback in a timely manner, so as to achieve a rapid response to customer needs. Moreover, the virtual heating system based on the Metaverse platform can enable the customer service center to make timely decisions and operations.

[0083] In this embodiment, for customer requests that cannot be directly resolved, the method further includes: using a pre-established similarity model to obtain similarity data between the customer and customer requests in the historical database, and recommending subsequent customer service handling methods for similar customers with similarity greater than a preset value for reference by heating service managers.

[0084] In this embodiment, the process of fusing and analyzing multi-source heterogeneous data related to customer service in the heating system to establish a customer profile includes:

[0085] Acquire initial data information of target customers related to heating system customer service, and obtain initial attribute data and initial behavior data after preprocessing and identification extraction;

[0086] The initial attribute data is standardized to obtain target attribute data, and customer attribute tags are generated based on the target attribute data.

[0087] The initial behavioral data is normalized to obtain target behavioral data, and the target behavioral data is input into a trained neural network model to obtain customer behavior labels. The customer behavior labels include at least heating behavior, payment behavior, and interaction behavior. The heating behavior includes heating characteristics and load characteristics. The payment behavior includes payment method and payment time. The interaction behavior includes at least appeal behavior, interaction characteristics, channel preference, and notification method.

[0088] A preset algorithm is used to perform tag mining on the customer attribute tags and customer behavior tags to obtain tag mining results, and a customer profile of the target customer is obtained based on the tag mining results; the preset algorithm includes clustering analysis algorithm, classification analysis algorithm, and regression analysis algorithm; the clustering analysis algorithm includes K-means algorithm and hierarchical clustering algorithm; the classification analysis algorithm includes decision tree algorithm, principal component analysis method, and convolutional neural network algorithm; the regression analysis algorithm includes linear regression analysis and nonlinear regression analysis.

[0089] In this embodiment, the establishment of customer profiles and monitoring of the heating system's operational status and customer heating data, proactively contacting customers before they raise business requests, addressing potential issues, and providing proactive and precise customer services include:

[0090] Based on existing customer service work orders, we acquire heating operation data of heating stations in areas with high-frequency service demands, as well as customer heating data of typical floors in the corresponding communities. We combine these data samples with weather factors and use a CNN-BiGRU network based on an attention mechanism to establish a heating station water supply temperature prediction model and a customer room temperature prediction model.

[0091] Based on the heating station water supply temperature prediction model and the customer room temperature prediction model, the heating station water supply temperature and the customer room temperature are predicted. If the error exceeds the preset heating station water supply temperature and customer room temperature, an active order is dispatched to carry out heating inspection, diagnosis and analysis and active temperature measurement, and the corresponding heating parameters are adjusted to handle potential risk issues and provide proactive and precise customer service.

[0092] In addition, based on customer profiles, we adopt communication and service methods that match the customer tags for customers with different heating behaviors, payment behaviors, and interaction behaviors.

[0093] In this embodiment, the proactive and precise customer service further includes: acquiring customer service work order data of complaints that have occurred, and after data preprocessing in combination with corresponding heating operation data, using machine learning methods to extract data features and establish a customer complaint tendency prediction model, applying the customer complaint tendency prediction model to the customer group that has not made any complaints, identifying the target identifier of the user group with complaint tendency, calculating the probability of potential complaint risk, and proactively contacting the customer to provide services.

[0094] Figure 3 This is a schematic diagram of the basic structure of the BiGRU network involved in this invention.

[0095] like Figure 3 As shown, in this embodiment, the use of an attention-based CNN-BiGRU network to establish a prediction model for the water supply temperature of the heating station and a prediction model for the room temperature of the customer includes:

[0096] The data vector is input into the CNN network model and subjected to convolution, max pooling and fully connected layer operations to obtain the extracted data feature vector, which is then input into the BiGRU network model structure for model training.

[0097] An attention mechanism is used to obtain the probability corresponding to different data feature vectors based on the weight allocation principle from the data feature vectors processed by the BiGRU network. The optimal weight parameter matrix is ​​continuously updated and iterated to obtain a CNN-BiGRU hybrid network model composed of CNN network and BiGRU network.

[0098] The trained CNN-BiGRU hybrid network model is used to predict the water supply temperature of the heating station and the room temperature of the customers.

[0099] The probability of obtaining different data feature vectors according to the weight allocation principle is expressed as follows:

[0100] e t =u tanh(wh) t +b);

[0101]

[0102]

[0103]

[0104]

[0105]

[0106] e t Let h be the output vector of the BiGRU network layer at time t. t The corresponding attention probability distribution values; u and w are weight coefficients; b is the bias coefficient; s t The output at time t is the result of using an attention mechanism; a t For vector matching weights; i represents time; j represents a time point before time t; This is the forward hidden layer state; This is the backward hidden state; W t for The corresponding weight; V t for The corresponding weight; b t x is the bias of the hidden state at time t; t For the input vector; F GRU The function transforms the input vector into the corresponding GRU hidden state.

[0107] Example 2

[0108] Figure 4 This is a schematic diagram of the structure of an intelligent management system for customer service of a heating system based on the metaverse, which is involved in this invention.

[0109] like Figure 4 As shown, this embodiment 2 provides a heating system customer service intelligent processing system based on the metaverse. The heating system customer service intelligent processing system includes:

[0110] Heating System Metaverse Platform Establishment Unit: Used to establish a heating system metaverse platform including a physical fusion layer, a model fusion layer, a data fusion layer, and a service fusion layer, to perform ubiquitous perception, virtual mapping, simulation, and intelligent management of heating system equipment entities and metaverse space;

[0111] Passive Customer Service Unit: Based on the heating system's metaverse platform, it establishes virtual customer and service personnel images in the same metaverse virtual space, conducts real-time business communication, and determines the customer's business type based on the customer's virtual image, business communication results, and customer's heating needs, and performs passive customer service processing.

[0112] Proactive Customer Service Unit: Based on the heating system metaverse platform, it integrates and analyzes multi-source heterogeneous data related to heating system customer service, establishes customer profiles and monitors the operating status of the heating system and customer heat consumption data, proactively contacts customers before they raise business requests, handles potential problems, and provides proactive and precise customer service.

[0113] The customer service services mentioned above include at least business acceptance, intelligent order dispatch, work order tracking, temperature measurement management, operation and maintenance diagnosis, heating inspection and billing management.

[0114] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0115] In addition, the functional modules in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0116] If the functionality is implemented as a software module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0117] Based on the above-described preferred embodiments of the present invention, and through the foregoing description, those skilled in the art can make various changes and modifications without departing from the inventive concept. The technical scope of this invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A method for intelligent customer service processing in a heating system based on the metaverse, characterized in that, The intelligent customer service processing method for the heating system includes: Establishment of a Metaverse Platform for Heating Systems: Establish a metaverse platform for heating systems that includes a physical fusion layer, a model fusion layer, a data fusion layer, and a service fusion layer, to enable ubiquitous perception, virtual mapping, simulation, and intelligent management of heating system equipment entities and the metaverse space; The establishment of the metaverse platform for the heating system, comprising a physical fusion layer, a model fusion layer, a data fusion layer, and a service fusion layer, includes: The physical fusion layer is used to effectively connect the physical entity resources of the heating system and build an intelligent IoT sensing network for the heating system that covers the entire domain and all time periods; it is also used to acquire, fuse, and transmit multi-source heterogeneous data obtained from the intelligent IoT sensing network of the heating system in real time; it is used to monitor and control the acquired multimodal data in real time; and it is used to perform virtual-real fusion between physical entities and the metaverse space. The model fusion layer is used to construct digital models of the physical entity resources of the heating system in the metaverse space, as well as digital models of the business logic, attribute characteristics, and relationships involved in the operation of the metaverse space of the heating system; it is also used to verify the model through metaverse model evaluation and verification technology; and it is used to establish semantic associations and real-time mapping relationships between virtual digital models of the physical entity resources of the heating system, including physics, structure, behavior, and rules. The data fusion layer is used to collect, store, process, iterate, optimize, integrate, and fuse data on the physical entities of the heating system and its metaverse model. The service integration layer is used for collaborative interaction of service resources, intelligent supervision of service processes, simulation of service content, and self-optimization of service rules. Passive customer service: Based on the heating system metaverse platform, virtual customer images and virtual service personnel images are established in the same metaverse virtual space to conduct business communication in real time. The customer business type is determined according to the customer virtual image, the business communication results and the customer's heating needs, and customer service is handled passively. Proactive customer service: Based on the aforementioned heating system metaverse platform, multi-source heterogeneous data related to heating system customer service are integrated and analyzed to establish customer profiles and monitor the operation status of the heating system and customer heat consumption data. Before customers raise business requests, customers are proactively contacted to handle potential problems and provide proactive and precise customer service. The customer service services mentioned above include at least business acceptance, intelligent order dispatch, work order tracking, temperature measurement management, operation and maintenance diagnosis, heating inspection and billing management.

2. The intelligent customer service processing method for heating systems according to claim 1, characterized in that, The establishment of a customer's virtual avatar includes: Customer images are obtained by taking pictures of customers using image acquisition devices, and the working status of heating equipment and room temperature in customers' homes are obtained using data acquisition devices installed in customers' homes, or the operating status of heating stations is obtained using data acquisition devices installed in subordinate heating stations, and basic customer attribute information is obtained through the heating system backend; the customers include at least heat users and subordinate heating station managers; the basic customer attributes include at least the heat user's name, residential community, building number, and room number, as well as the name of the subordinate heating station manager, the name of the heating branch company to which they belong, and the heating station number; A virtual 3D image of the customer is created using 3D reconstruction technology based on the customer's image. The virtual 3D image of the customer is then labeled with the working status of the heating equipment in the customer's home, the room temperature, and the customer's basic attribute information to obtain the virtual image of the customer.

3. The intelligent customer service processing method for heating systems according to claim 1, characterized in that, The process of determining customer service types based on customer virtual avatars, business communication results, and customer heating needs, and then passively handling customer service, includes: The customer's virtual avatar, the customer's description of their home heating needs, and the results of business communication with the customer are used as customer service demand information. The expert algorithm set in the heating system metaverse platform is used to extract keywords from the customer service demand information. For customer demands that can be directly and intuitively resolved, the next step of customer service processing is carried out. For customer demands that cannot be directly resolved, the keywords are input into a pre-trained machine learning algorithm for business identification to predict the next customer service processing method.

4. The intelligent customer service processing method for heating systems according to claim 3, characterized in that, The measures for addressing customer requests that cannot be directly resolved also include: using a pre-established similarity model to obtain similarity data between the customer and customer requests in the historical database, and recommending post-service customer handling methods for similar customers with similarity scores greater than a preset value for reference by heating service managers.

5. The intelligent customer service processing method for heating systems according to claim 1, characterized in that, The fusion analysis of multi-source heterogeneous data related to heating system customer service establishes customer profiles, including: Acquire initial data information of target customers related to heating system customer service, and obtain initial attribute data and initial behavior data after preprocessing and identification extraction; The initial attribute data is standardized to obtain target attribute data, and customer attribute tags are generated based on the target attribute data. The initial behavioral data is normalized to obtain target behavioral data, and the target behavioral data is input into a trained neural network model to obtain customer behavior labels. The customer behavior labels include at least heating behavior, payment behavior, and interaction behavior. The heating behavior includes heating characteristics and load characteristics. The payment behavior includes payment method and payment time. The interaction behavior includes at least appeal behavior, interaction characteristics, channel preference, and notification method. A preset algorithm is used to perform tag mining on the customer attribute tags and customer behavior tags to obtain tag mining results, and a customer profile of the target customer is obtained based on the tag mining results; the preset algorithm includes clustering analysis algorithm, classification analysis algorithm, and regression analysis algorithm; the clustering analysis algorithm includes K-means algorithm and hierarchical clustering algorithm; the classification analysis algorithm includes decision tree algorithm, principal component analysis method, and convolutional neural network algorithm; the regression analysis algorithm includes linear regression analysis and nonlinear regression analysis.

6. The intelligent customer service processing method for heating systems according to claim 1, characterized in that, The establishment of customer profiles and monitoring of the heating system's operational status and customer heating data, along with proactively contacting customers before they raise business requests, addressing potential issues, and providing proactive and precise customer services, includes: Based on existing customer service work orders, we acquire heating operation data of heating stations in areas with high-frequency service demands, as well as customer heating data of typical floors in the corresponding communities. We combine these data samples with weather factors and use a CNN-BiGRU network based on an attention mechanism to establish a heating station water supply temperature prediction model and a customer room temperature prediction model. Based on the heating station water supply temperature prediction model and the customer room temperature prediction model, the heating station water supply temperature and the customer room temperature are predicted. If the error exceeds the preset heating station water supply temperature and customer room temperature, an active order is dispatched to carry out heating inspection, diagnosis and analysis and active temperature measurement, and the corresponding heating parameters are adjusted to handle potential risk issues and provide proactive and precise customer service. In addition, based on customer profiles, we adopt communication and service methods that match the customer tags for customers with different heating behaviors, payment behaviors, and interaction behaviors.

7. The intelligent customer service processing method for heating systems according to claim 6, characterized in that, The aforementioned proactive and precise customer service also includes: acquiring customer service work order data of complaints that have occurred, and after preprocessing the data in conjunction with the corresponding heating operation data, using machine learning methods to extract data features and establish a customer complaint tendency prediction model, applying the customer complaint tendency prediction model to the customer group that has not yet made a complaint, identifying the target identifier of the user group with complaint tendency, calculating the probability of potential complaint risk, and proactively contacting the customer to provide services.

8. The intelligent customer service processing method for a heating system according to claim 6, characterized in that, The aforementioned CNN-BiGRU network based on an attention mechanism is used to establish a prediction model for the water supply temperature of the heating station and a prediction model for the room temperature of the customers, including: The data vector is input into the CNN network model and subjected to convolution, max pooling and fully connected layer operations to obtain the extracted data feature vector, which is then input into the BiGRU network model structure for model training. An attention mechanism is used to obtain the probability corresponding to different data feature vectors based on the weight allocation principle from the data feature vectors processed by the BiGRU network. The optimal weight parameter matrix is ​​continuously updated and iterated to obtain a CNN-BiGRU hybrid network model composed of CNN network and BiGRU network. The trained CNN-BiGRU hybrid network model is used to predict the water supply temperature of the heating station and the room temperature of the customers. The probability of obtaining different data feature vectors according to the weight allocation principle is expressed as follows: ； ； ； ； ； ； The output vector of the BiGRU network layer at time t. The corresponding attention probability distribution value; and These are the weighting coefficients; This is the bias coefficient; This is the output at time t using the attention mechanism; Weights are matched to the vector; For time; It is a time before time t; This is the forward hidden layer state; This is a backward hidden state; for The corresponding weights; for The corresponding weights; The bias of the hidden state at time t; The input vector; The function transforms the input vector into the corresponding GRU hidden state.

9. A customer service intelligent processing system for a heating system based on the metaverse, characterized in that, The intelligent customer service processing system for the heating system includes: Heating System Metaverse Platform Establishment Unit: Used to establish a heating system metaverse platform including a physical fusion layer, a model fusion layer, a data fusion layer, and a service fusion layer, to perform ubiquitous perception, virtual mapping, simulation, and intelligent management of heating system equipment entities and metaverse space; The establishment of the metaverse platform for the heating system, comprising a physical fusion layer, a model fusion layer, a data fusion layer, and a service fusion layer, includes: The physical fusion layer is used to effectively connect the physical entity resources of the heating system and build an intelligent IoT sensing network for the heating system that covers the entire domain and all time periods; it is also used to acquire, fuse, and transmit multi-source heterogeneous data obtained from the intelligent IoT sensing network of the heating system in real time; it is used to monitor and control the acquired multimodal data in real time; and it is used to perform virtual-real fusion between physical entities and the metaverse space. The model fusion layer is used to construct digital models of the physical entity resources of the heating system in the metaverse space, as well as digital models of the business logic, attribute characteristics, and relationships involved in the operation of the metaverse space of the heating system; it is also used to verify the model through metaverse model evaluation and verification technology; and it is used to establish semantic associations and real-time mapping relationships between virtual digital models of the physical entity resources of the heating system, including physics, structure, behavior, and rules. The data fusion layer is used to collect, store, process, iterate, optimize, integrate, and fuse data on the physical entities of the heating system and its metaverse model. The service integration layer is used for collaborative interaction of service resources, intelligent supervision of service processes, simulation of service content, and self-optimization of service rules. Passive Customer Service Unit: Based on the heating system's metaverse platform, it establishes virtual customer and service personnel images in the same metaverse virtual space, conducts real-time business communication, and determines the customer's business type based on the customer's virtual image, business communication results, and customer's heating needs, and performs passive customer service processing. Proactive Customer Service Unit: Based on the heating system metaverse platform, it integrates and analyzes multi-source heterogeneous data related to heating system customer service, establishes customer profiles and monitors the operating status of the heating system and customer heat consumption data, proactively contacts customers before they raise business requests, handles potential problems, and provides proactive and precise customer service. The customer service services mentioned above include at least business acceptance, intelligent order dispatch, work order tracking, temperature measurement management, operation and maintenance diagnosis, heating inspection and billing management.

Images