Intelligent heat supply customer service system, method, medium, equipment and program product

Abstract

The invention discloses an intelligent heat supply customer service system and method, a medium, equipment and a program product, and belongs to the field of intelligent heat supply and artificial intelligence customer service. The system comprises a voice recognition module which transwrites acquired audio data into a text and adaptively adjusts the text according to professional vocabularies in the heat supply field; the user intention recognition module is used for performing semantic analysis on the text based on a first large language model to obtain an intention type of a user corresponding to the text; the user question answering module is used for determining the type of a second large language model for answering the text question according to the intention type corresponding to the text, and answering the text question by utilizing the corresponding second large language model; generating a question answer text corresponding to the text according to a retrieval result returned by the vector database constructed based on the heat supply field and a retrieval result returned by the real-time business database; and the voice generation module is used for converting the answer text output by the second large language model into natural voice and feeding back the natural voice to the user.

Description

Technical Field

[0001] This application relates to the fields of smart heating and artificial intelligence customer service technology, and in particular to a smart heating customer service system, method, medium, equipment and program product. Background Technology

[0002] Existing customer service systems of heating companies mainly rely on human agents or interaction methods based on fixed question-and-answer databases. However, these systems generally suffer from the following shortcomings: First, low service efficiency; when call volume exceeds the capacity of human agents, users have to wait for a long time, seriously affecting the service experience. Second, limited knowledge coverage; systems based on fixed question-and-answer databases cannot cope with complex heating scenarios, especially in cases of repair requests, policy inquiries, or multiple factors, where they struggle to provide accurate answers. Third, unnatural interaction; existing rule-based question-and-answer systems can only respond to simple commands, lacking understanding of context and unable to support multi-turn continuous dialogues. Fourth, insufficient personalization; traditional systems cannot combine specific community conditions, user historical data, and personal information to provide differentiated answers.

[0003] Therefore, there is an urgent need for a smart customer service system that combines large-scale artificial intelligence models with heating business knowledge to improve the intelligence level of heating companies in customer service and solve the above-mentioned shortcomings. Summary of the Invention

[0004] To address the problem that existing customer service systems cannot intelligently answer questions, this application mainly provides a smart heating customer service system, method, medium, equipment, and program product.

[0005] To achieve the above objectives, the first technical solution adopted in this application is: a smart heating customer service system, comprising: a speech recognition module, which transcribes acquired audio data into text and adaptively adjusts the text according to professional terminology in the heating field; a user intent recognition module, which performs semantic analysis on the text based on a first major language model to obtain the user's intent type corresponding to the text, wherein the user's intent type includes reporting repairs, inquiries, and casual conversation; a user question answering module, which determines the type of a second major language model for answering the text question based on the intent type corresponding to the text, and uses the corresponding second major language model to generate the question answer text corresponding to the text based on the retrieval results returned by the vector database constructed based on the heating field and the retrieval results returned by the real-time business database; and a speech generation module, which converts the answer text output by the second major language model into natural speech and feeds it back to the user.

[0006] Optionally, in the speech recognition module, audio data input by the user is collected, the start and end points of the audio data are identified through speech activity detection, and the audio data is transcribed into text using an automatic speech recognition algorithm.

[0007] Optionally, the user's intent type can be output through the primary language model using prompt words or fine-tuning the model.

[0008] Optionally, the speech generation module supports streaming synthesis.

[0009] Optionally, in the user question answering module, user information is verified based on the real-time business database. After the user passes the verification, the text corresponding to the user's current question is input into the vector database for retrieval. At the same time, the user's business information is retrieved from the real-time business database. The results returned from the vector database and the real-time business database are input into the second language model to generate the corresponding question answer text. Additionally, further questions are asked to users who fail the verification.

[0010] Optionally, when the semantic parsing result of the user intent recognition module is ambiguous or exceeds the model's processing capacity, the user input will be transferred to a human customer service representative.

[0011] The second technical solution adopted in this application is: a smart heating customer service method, which includes: a speech recognition step, which transcribes the acquired audio data into text and adaptively adjusts the text according to professional terminology in the heating field; a user intent recognition step, which performs semantic parsing on the text based on a first major language model to obtain the user's intent type corresponding to the text, wherein the user's intent type includes reporting repairs, inquiries, and casual conversation; a user question answering step, which determines the type of a second major language model for answering the text question based on the intent type corresponding to the text, and uses the corresponding second major language model to generate the question answer text corresponding to the text based on the retrieval results returned by the vector database constructed based on the heating field and the retrieval results returned by the real-time business database; and a speech generation step, which converts the answer text output by the second major language model into natural speech and feeds it back to the user.

[0012] The third technical solution adopted in this application is: a computer-readable storage medium storing a computer program / instruction, which is operated to execute the smart heating customer service method in Solution 2.

[0013] The fourth technical solution adopted in this application is: a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the intelligent heating customer service method in Solution 2.

[0014] The fifth technical solution adopted in this application is: a computer program product, including a computer program / instruction, which, when executed by a processor, implements the intelligent heating customer service method as in Solution 2.

[0015] The beneficial effects that the technical solution of this application can achieve are: by combining automatic speech recognition, large language model, retrieval enhancement and speech synthesis technology, the intelligence and automation level of customer service of heating companies can be improved. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of a specific implementation of a smart heating customer service system according to this application; Figure 2 This is a schematic diagram of the processing flow of a smart heating customer service system according to this application; Figure 3 This is a schematic diagram of a specific implementation of a smart heating customer service method according to this application.

[0018] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0019] The preferred embodiments of this application will now be described in detail with reference to the accompanying drawings, so that the advantages and features of this application can be more easily understood by those skilled in the art, thereby providing a clearer and more definite definition of the scope of protection of this application.

[0020] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0021] This application relates to the fields of smart heating and artificial intelligence customer service technology, and in particular to a smart heating customer service system that combines automatic speech recognition, large language model, retrieval enhancement and speech synthesis technology. This application can improve the intelligence and automation level of customer service for heating companies.

[0022] The inventive concept of this application is to achieve efficient, natural, multi-turn, and personalized customer service interaction in heating business scenarios by integrating speech activity detection, automatic speech recognition, large language model, retrieval enhancement generation, intelligent agent and speech synthesis technologies, thereby solving the shortcomings of existing customer service systems in terms of efficiency, knowledge breadth, interactive intelligence and personalization.

[0023] The technical solution of this application and how it solves the above-mentioned technical problems will be described in detail below with specific embodiments. The specific embodiments described below can be combined with each other to form new embodiments. The same or similar ideas or processes described in one embodiment may not be repeated in other embodiments.

[0024] Figure 1 This paper illustrates one embodiment of a smart heating customer service system according to this application.

[0025] Figure 1 The intelligent heating customer service system shown includes: a speech recognition module 101, which transcribes acquired audio data into text and adaptively adjusts the text based on professional terminology in the heating field; a user intent recognition module 102, which performs semantic analysis on the text based on a first major language model to obtain the user's intent type corresponding to the text, where the user's intent type includes reporting repairs, inquiries, and casual conversation; a user question answering module 103, which determines the type of the second major language model for answering the text question based on the intent type corresponding to the text, and uses the corresponding second major language model to generate the question answer text corresponding to the text based on the retrieval results returned by the vector database built based on the heating field and the retrieval results returned by the real-time business database; and a speech generation module 104, which converts the answer text output by the second major language model into natural speech and feeds it back to the user.

[0026] This specific implementation method, by combining automatic speech recognition, large language models, retrieval enhancement, and speech synthesis technologies, can improve the intelligence and automation level of customer service for heating companies.

[0027] Specifically, Figure 2 This is a schematic diagram of the processing flow of a smart heating customer service system according to this application. Figure 2As shown, the acquired audio data is transcribed into text through speech recognition, and the text is adaptively adjusted based on professional terminology in the heating industry to optimize the accuracy of the first language model in recognizing user intent. Then, the first language model is used to perform semantic parsing on the text to obtain the user intent types corresponding to the text, such as repair requests, inquiries, and casual conversation. Based on the intent type corresponding to the text, the type of the second language model corresponding to the text question is determined. For example, the second language model for repair requests is determined based on the repair request type, the second language model for inquiries is determined based on the inquiry type, and the second language model for casual conversation is determined based on the casual conversation type. After determining the second language model to be used for the text question, the text corresponding to the user's current question is input into a pre-established vector database based on the heating industry and a real-time business database, respectively. The returned search results are input into the corresponding second language model to generate the question answer text. Finally, the answer text output by the second language model is converted into natural speech and fed back to the user.

[0028] Figure 1 The intelligent heating customer service system shown includes: a voice recognition module 101, which transcribes the acquired audio data into text and adaptively adjusts the text based on professional terminology in the heating field.

[0029] In one specific embodiment of this application, the speech recognition module collects audio data input by the user, identifies the start and end points of the audio data through speech activity detection, and uses an automatic speech recognition algorithm to transcribe the audio data into text.

[0030] Specifically, the system collects user-input audio data in real time via microphone or telephone line, uses Voice Activity Detection (VAD) to identify the start and end points of the user's speech, and then transcribes the audio data into text using an Automatic Speech Recognition (ASR) algorithm. During the transcription process, the text is adaptively adjusted based on heating industry terminology, enabling optimized recognition of terms such as "cooling down," "valve," "heat exchange station," and "return water temperature," thereby improving recognition accuracy and ensuring more accurate and intelligent responses to user questions.

[0031] Figure 1 The intelligent heating customer service system shown includes: a user intent recognition module 102, which performs semantic parsing of text based on the first language model to obtain the user intent type corresponding to the text. The user intent types include reporting repairs, inquiries, and casual conversation.

[0032] In one specific embodiment of this application, the user's intent type is output through a first large language model using prompt words or fine-tuning models.

[0033] In one specific embodiment of this application, when the semantic parsing result of the user intent recognition module is ambiguous or exceeds the model's processing capacity, the user input is transferred to a human customer service representative.

[0034] Specifically, based on the text output by the speech recognition module, semantic parsing is performed on the text using a first large language model to determine the user's intent type. This large language model can control the type of user intent it outputs through preset prompts, and its semantic understanding ability can be optimized by fine-tuning on a heating industry corpus, thereby improving the accuracy of intent recognition. Alternatively, the user's intent type can be output through the first large language model using prompts; or, by fine-tuning the output of the first large language model using a heating industry corpus, the user's intent type output by the first large language model can be obtained—that is, by fine-tuning the model, the user's intent type can be output through the first large language model. User intent recognition can identify various user intents, including repair requests, inquiries, and casual conversation, each corresponding to different business processing flows. Furthermore, when the semantic parsing results are ambiguous or exceed the model's processing capacity, the user input can be transferred to human customer service to ensure the integrity and continuity of service. In particular, the user intent classification here is only an example, and this application does not limit the specific classification method.

[0035] Figure 1 The intelligent heating customer service system shown includes: a user question answering module 103, which determines the type of the second major language model for answering text questions based on the intent type corresponding to the text, and uses the corresponding second major language model to generate question answer text corresponding to the text based on the retrieval results returned by the vector database built based on the heating field and the retrieval results returned by the real-time business database.

[0036] In one specific embodiment of this application, in the user question answering module, user information is verified according to the real-time business database. After the user passes the verification, the text corresponding to the user's current question is input into the vector database for retrieval. At the same time, the user's business information is retrieved in the real-time business database. The results returned from the vector database and the real-time business database are input into the second language model to generate the corresponding question answer text. Furthermore, users who fail the verification are further questioned.

[0037] Specifically, when the second major language model for repair requests is needed to respond to a problem, the system guides the user to provide key information through multiple rounds of interaction. The second major language model also accesses the business database to verify the consistency of the user's personal information. Upon successful verification, a work order is automatically generated and pushed to the smart heating work order system. Simultaneously, after the work order is generated, information of interest to the user, such as the work order details and contact information for maintenance personnel, can be sent to the user via SMS, app push notifications, or other means. In other words, when the system recognizes that the text corresponds to a repair request intent, it uses the second major language model for repair requests to guide the user to provide key information such as address and equipment status, and verifies the consistency between the user's input and the database information. This requires multiple rounds of information interaction with the user. After successful verification, the second major language model for repair requests generates repair information and automatically generates a work order, which is then pushed to the heating work order system.

[0038] For example, when a user inputs the voice message "My heating isn't working" via telephone, the system accurately identifies the intent as a "repair request" through automatic speech recognition and semantic analysis using the first major language model. Based on a preset dialogue guidance strategy, the system replies to the user, "Is it the whole house that's not heating up, or just some rooms?", guiding the user to provide further key information. In the second round of interaction, when the user adds, "The whole house isn't heating up, and the kitchen radiator is leaking," the system, while maintaining contextual continuity, records "insufficient heating throughout the house" and "leaking kitchen equipment" as a combined problem. Simultaneously, the system verifies the repair address by accessing the user database and asks in the form of a prompt, "Is your address XX Community, Building XX, Room XXX?", ensuring consistency between the user's input and the system's existing data. In the third round of interaction, when the user confirms, "Yes, it's Room XXX," the system completes address verification and automatically generates a work order through the smart heating platform's work order system. Meanwhile, the system can access real-time monitoring data from the heat exchange station through the real-time business database, identifying the current low water supply temperature in the community. This dynamic information is integrated into the response, generating the message: "According to the monitoring, the water supply temperature at your community's heat exchange station is indeed low, and we are currently dispatching personnel. I have also generated a work order for you, and an engineer will arrive within 24 hours for repairs. Would you like to receive a text message notification?" In the fourth round of interaction, when the user enters "Yes, please send me a text message," the system automatically invokes the push notification service, enabling SMS notifications and replying, "You will receive the work order information and the repair personnel's contact information shortly." Through these multiple rounds of dialogue, the system completes a closed-loop process of repair intent recognition, key information collection, context fusion, operational data retrieval, automatic work order generation, and multi-channel notification.

[0039] When a user inquires about payment information, the system retrieves heating fee standards from the retrieval vector database and the real-time business database, verifies the user's residential area data, and finally calculates the payment amount using the second-largest language model for inquiries. When a user inquires about policy-related issues, the system retrieves relevant clauses from the retrieval vector database and the real-time business database, and the second-largest language model for inquiries generates a natural language response. In other words, when the text question is identified as an inquiry, the system calls upon the vector database and the real-time business database built based on the heating sector to perform keyword and semantic searches, and inputs the search results into the prompts of the second-largest language model for inquiries. This allows the second-largest model to generate an accurate answer by combining domain knowledge with the search results.

[0040] For example, when a user inputs an inquiry via telephone or voice terminal, such as "How much is my heating cost this year?", the system first uses speech recognition and a large language model intent parsing module to identify the input as an "inquiry—fee query" type. Subsequently, the system retrieves user information from the real-time business database and accesses the user's residential area data. Simultaneously, the system retrieves local heating fee standards from a vector database and inputs the returned search results into the corresponding second large language model for calculation and to generate an answer. Finally, the system replies to the user, "According to the city's heating fee standard of X yuan / square meter, and your house's building area is XX square meters, therefore, the heating fee payable this year is XXX yuan." Through this method, the system achieves automatic calculation and accurate response to the user's personalized fees, significantly improving the intelligence and automation level of the customer service system.

[0041] For example, when a user enters "What is the city's policy on compensation for heating outages?", the system uses speech recognition and semantic analysis modules to identify the question as belonging to the "Consultation Category—Policy Consultation" type. In this case, the system does not need to access the real-time business database. Instead, it performs vectorized semantic retrieval by comparing the user's input with the heating policy knowledge base in the vector database, extracting relevant policy clauses and inputting the search results into the prompts of the corresponding consultation category's second language model. This second language model generates a structured, natural language answer based on the search results, such as, "According to the city's heating management regulations, if heating is interrupted for more than 24 hours due to equipment failure or scheduling reasons, users can apply for corresponding heating fee reductions." Through this method, the system achieves rapid response to purely policy-related inquiries, ensuring the accuracy and authority of the answers, avoiding access to irrelevant databases, thereby improving the system's response efficiency and resource utilization.

[0042] When the user's intent is casual conversation, the user input is directly processed by the second major language model for casual conversation, generating a natural and coherent response, thereby ensuring the naturalness of the interaction and the user experience.

[0043] For example, when a user inputs "Is it cold outside today?" or "Can you tell me a joke?" via voice, the system uses a speech recognition module to transcribe the user's speech into text, and the first large language model semantic analysis module identifies the input as belonging to the "casual conversation intent" type. In this type of scenario, the system does not need to call the business database or the retrieval-enhanced vector database, but instead directly hands the user input over to the casual conversation large language model for processing. When generating a response, the casual conversation large language model can provide a natural, coherent, and friendly reply based on the context, such as "Yes, the temperature is indeed quite low today, remember to wear more clothes" or "Okay, I'll tell you a little joke." This scenario setting ensures the naturalness and fun of user interaction in non-business scenarios, thereby improving the user experience and service stickiness of the smart heating customer service system.

[0044] Figure 1 The intelligent heating customer service system shown includes: a voice generation module 104, which converts the response text output by the second language model into natural speech and feeds it back to the user.

[0045] In one specific embodiment of this application, the speech generation module supports streaming synthesis.

[0046] Specifically, the text generated by the large language model is synthesized into a natural and fluent speech signal through a text-to-speech (TTS) algorithm, and finally broadcast to the user through a telephone line or smart terminal. The speech generation module supports streaming synthesis, enabling parallel generation and playback of response speech while the user is speaking, achieving near real-time dialogue interaction. Furthermore, the speech generation module supports multi-voice configuration, allowing users to select different voice styles based on business scenarios or user preferences to meet their personalized needs.

[0047] Figure 3 A schematic diagram of a specific embodiment of a smart heating customer service method according to this application is shown.

[0048] exist Figure 3In the specific implementation shown, the intelligent heating customer service method mainly includes: a speech recognition step 301, which transcribes the acquired audio data into text and adaptively adjusts the text based on professional terminology in the heating field; a user intent recognition step 302, which performs semantic parsing on the text based on a first major language model to obtain the user's intent type corresponding to the text, wherein the user's intent type includes reporting repairs, inquiries, and casual conversation; a user question answering step 303, which determines the type of the second major language model for answering the text question based on the intent type corresponding to the text, and uses the corresponding second major language model to generate the question answer text corresponding to the text based on the retrieval results returned by the vector database built based on the heating field and the retrieval results returned by the real-time business database; and a speech generation step 304, which converts the answer text output by the second major language model into natural speech and feeds it back to the user. The intelligent heating customer service method provided in this application can be used to execute the intelligent heating customer service system described in any of the above embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0049] In one specific embodiment of this application, the functional modules of the intelligent heating customer service method of this application can be directly in hardware, in software modules executed by a processor, or in a combination of both.

[0050] Software modules may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in this art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium.

[0051] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination thereof. A general-purpose processor can be a microprocessor, but alternatively, it can be any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors incorporating a DSP core, or any other such configuration. Alternatively, the storage medium can be integrated with the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in the user terminal. Alternatively, the processor and storage medium can reside as discrete components in the user terminal.

[0052] In another specific embodiment of this application, a computer-readable storage medium is provided, which stores a computer program / instructions that are operated to perform the smart heating customer service method described in the above embodiments.

[0053] In one specific embodiment of this application, a computer device includes a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the smart heating customer service method described in the above embodiments.

[0054] In one specific embodiment of this application, a computer program product includes a computer program / instruction that, when executed by a processor, implements the smart heating customer service method described in the above embodiments.

[0055] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0056] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0057] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A smart heating customer service system, characterized in that, include: The speech recognition module transcribes the acquired audio data into text and adaptively adjusts the text based on professional terminology in the heating industry. Specifically, it collects audio data input by the user, identifies the start and end points of the audio data through speech activity detection, and uses an automatic speech recognition algorithm to transcribe the audio data into text. The user intent recognition module performs semantic parsing on the text based on the first major language model to obtain the user intent type corresponding to the text. The user intent type includes reporting repairs, inquiries, and casual conversation. The user question answering module determines the type of the second major language model for the answer text question based on the intent type corresponding to the text, and uses the corresponding second major language model to generate the question answer text corresponding to the text based on the retrieval results returned by the vector database built based on the heating field and the retrieval results returned by the real-time business database. The speech generation module converts the response text output by the second language model into natural speech and feeds it back to the user.

2. The intelligent heating customer service system according to claim 1, characterized in that, By using prompt words or fine-tuning the model, the user's intent type is output through the first large language model.

3. The intelligent heating customer service system according to claim 1, characterized in that, The speech generation module supports streaming synthesis.

4. The intelligent heating customer service system according to claim 1, characterized in that, In the user question answering module, user information is verified according to the real-time business database. After the user passes the verification, the text corresponding to the user's current question is retrieved from the vector database. At the same time, the user's business information is retrieved from the real-time business database. The results returned from the vector database and the real-time business database are input into the second language model to generate the corresponding question answer text. In addition, further inquiries will be made to users whose verification fails.

5. The intelligent heating customer service system according to claim 1, characterized in that, When the semantic parsing result of the user intent recognition module is ambiguous or exceeds the model's processing capacity, the user input will be transferred to a human customer service representative.

6. A smart heating customer service method, characterized in that, include: The speech recognition step involves transcribing the acquired audio data into text and adaptively adjusting the text based on professional terminology in the heating industry. Specifically, the audio data input by the user is collected, the start and end points of the audio data are identified through speech activity detection, and the audio data is transcribed into text using an automatic speech recognition algorithm. The user intent recognition step involves semantic parsing of the text based on the first major language model to obtain the user intent type corresponding to the text. The user intent type includes reporting repairs, inquiries, and casual conversation. The user question answering steps involve determining the type of the second major language model for the answer text question based on the intent type corresponding to the text, and using the corresponding second major language model to generate the question answer text corresponding to the text based on the retrieval results returned by the vector database built based on the heating field and the retrieval results returned by the real-time business database. The speech generation step involves converting the response text output by the second language model into natural speech and feeding it back to the user.

7. A computer-readable storage medium storing a computer program / instructions, characterized in that, The computer program / instructions are operated to perform the smart heating customer service method as described in claim 6.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the intelligent heating customer service method as described in claim 6.

9. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the intelligent heating customer service method as described in claim 6.

Images