Real-time interaction driving system of electric power service virtual digital human

Abstract

The invention relates to the technical field of electric power service, in particular to a real-time interaction driving system of an electric power service virtual digital human, which comprises a data receiving module, a natural language processing module, a central processing module, a voice synthesis module, an action expression driving module and a virtual digital human model which are connected in sequence, the system further comprises a knowledge graph module. Natural language communication between the virtual digital human and the user is achieved through voice recognition, voice instructions of the user can be processed in real time, the virtual digital human is driven to conduct corresponding voice reply, all-weather work can be achieved, limitation of time and fatigue is avoided, consultation of clients can be quickly responded, the waiting time of the user is shortened, and the user experience is improved. And part of manual customer service work can be replaced, especially for certain repeated question answering, and the investment of enterprises in the aspect of human resources is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power services, and in particular to a real-time interactive driving system for a virtual digital human serving an electric power service. Background Art

[0002] With the continuous development of social economy and the improvement of people's living standards, the demand for electricity continues to grow. Power companies not only need to provide stable and reliable power supply, but also need to continuously improve service quality and efficiency to meet the increasingly diverse needs of users. In order to better provide services to customers, more and more self-service terminals are being used in offline or upward corporate service scenarios.

[0003] In the field of power services, traditional customer service methods mainly rely on manual customer service, which has problems such as limited service time, slow response speed, and high labor costs. With the development of artificial intelligence technology, virtual digital people have gradually become a new service method. However, the existing application of virtual digital people in power services still has defects such as non-real-time interaction, single function, and inability to accurately understand user needs.

[0004] In view of this, a real-time interactive driving system for virtual digital humans in power services is needed. Summary of the invention

[0005] In view of the problems in the prior art, the present invention provides a real-time interactive driving system for a virtual digital human in electric power services. The specific technical solution is as follows: A real-time interactive driving system for a virtual digital human of electric power service, comprising a data receiving module, a natural language processing module, a central processing module, a speech synthesis module, an action expression driving module, and a virtual digital human model connected in sequence; and also comprising a knowledge graph module; the knowledge graph module is connected to the central processing module; the knowledge graph module is used to store knowledge related to electric power service, and provide an accurate basis for answering user questions; The data receiving module is used to receive information data input by the user in real time; The natural language processing module is used to understand the information data input by the user and convert it into semantic representation data that can be processed by the computer; The central processing module is used to identify and process the semantic representation data sent by the natural language processing module, and obtain voice data for interaction with the user based on the knowledge stored in the knowledge graph module; The speech synthesis module is used to synthesize speech data for the virtual digital human to interact with the user, so as to realize the speech interaction between the user and the virtual digital human; The action and expression driving module is used to drive the virtual digital human to make natural actions and expressions according to the dialogue content and scene; The virtual digital human model is used to present the image of the virtual digital human according to the information output by the speech synthesis module and the action expression driving module.

[0006] Preferably, the data receiving module receives information data input by the user including text data and voice data. When receiving the voice data, the module also pre-processes the voice data to generate denoised voice data.

[0007] Preferably, the natural language processing module includes a language understanding unit, a language generation unit, and a semantic disambiguation unit; The language understanding unit is used to analyze and understand the natural language input by the user; The language generation unit is used to generate an answer text based on the understanding of the user's question; The semantic disambiguation unit is used to perform context analysis on the semantic ambiguity problem of multiple meanings of a word in the answer text to achieve semantic disambiguation.

[0008] Preferably, the language understanding unit trains the power service related texts through a Transformer architecture model in deep learning.

[0009] Preferably, the speech synthesis module includes a speech recognition unit, a speech reading unit, and a speech synthesis unit; The speech recognition unit is used to convert the user's speech into text; The speech reading unit is used to read the text converted by the speech recognition module, so as to find the corresponding answer of the virtual digital human; The speech synthesis unit is used to convert the text content of the virtual digital person's answer into speech output.

[0010] Preferably, the system further comprises a dialogue management module and a storage module, wherein the dialogue management module is connected to the virtual digital human model and the storage module respectively; the storage module is connected to the knowledge graph module; The dialogue management module is used to control the dialogue process between the user and the virtual digital person and guide the user to provide necessary information; The storage module is used to store the interactive information data generated by the dialogue management module; The knowledge graph module is also used to store conversation cases between virtual humans and users based on interactive information data.

[0011] Preferably, the system further comprises an intelligent adjustment module, which is respectively connected to the central processing module and the virtual digital human model; the intelligent adjustment module is used to adjust different virtual digital human parameters according to different customers in the conversation.

[0012] Preferably, the intelligent adjustment module includes an image adjustment unit, a voice adjustment unit, and a clothing adjustment unit; The image adjustment unit is used to configure the image of the virtual digital human; The voice adjustment unit is used to adjust the voice of the virtual digital person according to the voice characteristics of the user; The clothing adjustment unit is used to configure the clothing of the virtual digital person.

[0013] Preferably, the system further comprises a lip synchronization module, which is respectively connected to the central processing module and the speech synthesis module, and is used for matching the speech data interacting with the user with the lip shape synchronized with the virtual digital human.

[0014] Preferably, the lip synchronization module includes a speech input unit, a speech analysis unit, a lip model library, a lip generation unit, a synchronization adjustment unit and an output display unit; The voice input unit is used to receive voice signals; The speech analysis unit is used to perform in-depth analysis on the input speech and extract key features; The lip shape model library is used to store lip shape data; The lip shape generation unit is used to select appropriate lip shape data from the lip shape model library according to the analysis result of the speech analysis unit, and combine and adjust them to generate a lip shape sequence synchronized with the speech; The synchronization adjustment unit is used to ensure that the change of lip shape is synchronized with the time axis of speech; The output display unit is used to present the generated synchronized lip shape in a visual manner.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a real-time interactive driving system for a virtual digital human in electric power services, comprising a data receiving module, a natural language processing module, a central processing module, a speech synthesis module, an action expression driving module, and a virtual digital human model connected in sequence; and also comprising a knowledge graph module. The present invention realizes natural language communication between a virtual digital human and a user through speech recognition. The present invention can process the user's voice instructions in real time, drive the virtual digital human to make corresponding voice replies, can work around the clock, is not limited by time and fatigue, can quickly respond to customer inquiries, reduce user waiting time, and can replace part of the work of manual customer service, especially for some repetitive questions, reducing the company's investment in human resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0017] Figure 1 This is a system principle diagram of Embodiment 1 of the present invention.

[0018] Figure 2 This is a schematic diagram of the natural language processing module of the present invention.

[0019] Figure 3 It is a schematic diagram of the speech synthesis module of the present invention.

[0020] Figure 4 This is the schematic diagram of the intelligent adjustment module.

[0021] Figure 5 This is a system schematic diagram of Example 2.

[0022] Figure 6 The schematic diagram of the lip sync module. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0025] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0026] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0027] Embodiment 1: like Figure 1 As shown, this embodiment provides a real-time interactive driving system for a virtual digital human of electric power service, comprising a data receiving module, a natural language processing module, a central processing module, a speech synthesis module, an action expression driving module, and a virtual digital human model connected in sequence; and also comprising a knowledge graph module; the knowledge graph module is connected to the central processing module; the knowledge graph module is used to store knowledge related to electric power service, and provide an accurate basis for answering user questions; the data receiving module is used to receive information data input by the user in real time; the natural language processing module is used to understand the information data input by the user and convert it into semantic representation data that can be processed by a computer; the central processing module is used to identify and process the semantic representation data issued by the natural language processing module, and obtain speech data for interacting with the user based on the knowledge stored in the knowledge graph module; the speech synthesis module is used to synthesize speech data for interacting with the user for the virtual digital human, so as to realize speech interaction between the user and the virtual digital human; the action expression driving module is used to drive the virtual digital human to make natural actions and expressions according to the content and scene of the dialogue; the virtual digital human model is used to present the image of the virtual digital human according to the information output by the speech synthesis module and the action expression driving module.

[0028] The data receiving module receives information data input by the user including text data and voice data. When receiving the voice data, the module also pre-processes the voice data to generate denoised voice data.

[0029] The natural language processing module is responsible for understanding the text information input by the user. For example, if a user asks "There is a power outage at my home, what should I do?", the natural language processing module will perform lexical analysis, syntactic analysis, and semantic understanding on this sentence. It can break down the sentence into words, such as "my home", "power outage", and "what should I do", analyze the grammatical relationship between words, and understand that the actual intention of the sentence is to ask about the solution to the power outage.

[0030] like Figure 2 As shown, the natural language processing module includes a language understanding unit, a language generation unit, and a semantic disambiguation unit; the language understanding unit is used to analyze and understand the natural language input by the user; the language generation unit is used to generate an answer text based on the understanding of the user's question; the semantic disambiguation unit is used to perform context analysis on the semantic ambiguity problem of multiple meanings of a word in the answer text to achieve semantic disambiguation.

[0031] Among them, the language understanding unit trains the power service-related text through the Transformer architecture model in deep learning, which can accurately identify the user's question intention and extract key information, which can improve the accuracy of understanding the user's question. For example, when a user asks "Why is my electricity bill so high this month?", the system can understand that the user is questioning the amount of the electricity bill and extract key information such as "this month" and "high electricity bill". The language generation unit can answer "Maybe your electricity consumption has increased this month, or there are high-power appliances running for a long time. You can log in to our power service platform to view detailed electricity usage details." The semantic disambiguation unit mainly solves semantic ambiguity problems such as polysemy. For example, the word "power outage" may mean a power outage in the entire area, or it may be that a certain appliance in the user's home cannot work properly and is mistaken for a power outage. The system performs semantic disambiguation through context analysis and other methods to ensure accurate understanding of the user's true intention.

[0032] The knowledge graph module integrates various knowledge in the power field, including power policies and regulations, electricity fee calculation rules, troubleshooting methods, power equipment information, etc., to build a comprehensive power knowledge graph. For example, the knowledge graph will include the calculation methods of electricity fees for different types of electricity consumption, the causes and solutions of common power failures, etc. When the language processing module understands the user's question, the knowledge graph can provide accurate knowledge to answer the question. For example, if a user asks "What's wrong with the abnormal meter reading?", the knowledge graph can list possible reasons based on the stored knowledge, such as meter failure, line interference, and other situations.

[0033] like Figure 3 As shown, the speech synthesis module includes a speech recognition unit, a speech reading unit, and a speech synthesis unit; the speech recognition unit is used to convert the user's speech into text for the system to process. For example, when the user says "I want to check the electricity bill for this month" by voice, the speech recognition unit will convert it into the corresponding text; the speech reading unit is used to read the text converted by the speech recognition module to find the corresponding answer of the virtual digital person; the speech synthesis unit is used to convert the text content of the virtual digital person's answer into speech output, so that the user can get the answer by listening.

[0034] The action and expression driving module is used to drive the virtual digital human to make natural actions and expressions according to the content and scene of the conversation, enhancing the realism of the interaction. The action and expression driving module enables the virtual digital human to have more natural body movements and expressions. According to the content and scene of the conversation, the digital human can make actions such as nodding, smiling, and waving. Generate natural actions for the virtual digital human according to the content and emotional tendency of the conversation. For example, when the virtual digital human welcomes the user, it can make a waving action; when the user asks a question, the virtual digital human can make a listening action. Enable the virtual digital human to show rich expressions and enhance the realism and affinity of the interaction. For example, when the user encounters a problem and feels anxious, the virtual digital human can show a caring expression; when the user's problem is solved, the virtual digital human can smile, enhancing the realism of the interaction. It is realized through the skeletal animation technology and expression binding technology in computer graphics. The parameters of various actions and expressions are pre-set, and the digital human is driven to make corresponding responses according to the emotional tendency and content of the conversation.

[0035] Virtual digital human model: It is the visualization part of the system, which presents a realistic virtual digital human image through computer graphics technology. It can provide users with a variety of services such as electricity bill inquiry, fault repair, and electricity knowledge popularization to meet the different needs of users. Through natural language processing and knowledge graph technology, it accurately understands the user's question intention and gives an accurate answer. According to the user's historical interaction records and preferences, it realizes personalized interactive services and improves user satisfaction. The image of the virtual digital human is vivid and lifelike, and can enhance the effect of interaction through actions and expressions, thereby improving user acceptance.

[0036] As a preferred embodiment, the system also includes a dialogue management module and a storage module. The dialogue management module is connected to the virtual digital human model and the storage module respectively; the storage module is connected to the knowledge graph module; the dialogue management module is used to control the dialogue process between the user and the virtual digital human, and guide the user to provide necessary information to ensure efficient dialogue; the storage module is used to store the interactive information data generated by the dialogue management module; the knowledge graph module is also used to store dialogue cases between the virtual human and the user based on the interactive information data.

[0037] The dialogue management module is used to control the flow of the dialogue. It determines when the digital human asks questions, when to answer, how to guide the dialogue, etc. For example, when a user asks a vague question, such as "There is a problem with the electricity in my house", the dialogue management module will guide the user to provide more details, such as "Can you tell me whether there is a power outage, electrical appliances cannot be used, or other situations?"

[0038] As a preferred embodiment, the system also includes an intelligent adjustment module, which is connected to the central processing module and the virtual digital human model respectively; the intelligent adjustment module is used to adjust different virtual digital human parameters according to different customers in the conversation.

[0039] As a preferred embodiment, Figure 4 As shown, the intelligent adjustment module includes an image adjustment unit, a voice adjustment unit, and a clothing adjustment unit. The image adjustment unit is used to configure the image of the virtual digital person, and to select different appearance images according to the needs of different users.

[0040] The voice adjustment unit is used to adjust the voice of the virtual digital person according to the voice characteristics of the user, including voice color, language, dialect, low, medium and high pitch, etc. For example, when the user in the conversation uses a dialect to talk, the virtual digital person can immediately use the dialect to talk, which is not only easy to understand but also more friendly. When the user in the conversation uses English, the virtual digital person can also use English to talk, reducing language communication barriers. The voice adjustment unit can also adjust the channel balance, and can adjust the volume of different channels (such as left channel, right channel, center channel, surround channel, etc.) and the tone. When the user in the conversation is depressed, it can soften the tone and improve the intimacy. The voice adjustment unit can also adjust different tones according to the age of the user. For example, a more lively tone can be used for young people, a more formal tone can be used for young people, and a slower language style can be used for the elderly. The speed of speech can be slowed down and the questions can be answered in a more understandable language.

[0041] The clothing adjustment unit is used to configure the clothing of the virtual digital person, including clothes, pants, skirts, and various styles such as long and short ones.

[0042] The system of the present invention is specifically implemented as follows: (1) This system is deployed on the power service platform, and users can interact with virtual digital humans through channels such as web pages and mobile apps.

[0043] (2) When the user enters a question or instruction, the natural language processing module analyzes and understands it to determine the type and intent of the question.

[0044] (3) The knowledge graph module queries relevant knowledge based on the intent of the question and returns the results to the central processing module.

[0045] (4) The central processing module generates the answer text based on the results of the knowledge graph and passes it to the speech synthesis module and the action expression driving module.

[0046] (5) The speech synthesis module converts the answer text into speech output, and the action and expression driving module enables the virtual digital human to make corresponding actions and expressions.

[0047] (6) The dialogue management module guides the user to provide more information or take the next step according to the progress of the dialogue.

[0048] Embodiment 2: like Figure 5 As shown, the system further includes a lip synchronization module, which is connected to the central processing module and the speech synthesis module respectively, and is used to match the speech data interacting with the user with the lip shape synchronized with the virtual digital human. Others are the same as in the first embodiment.

[0049] like Figure 6 As shown, the lip synchronization module includes a speech input unit, a speech analysis unit, a lip model library, a lip generation unit, a synchronization adjustment unit and an output display unit; The voice input unit is used to receive voice signals; The speech analysis unit is used to conduct in-depth analysis of the input speech and extract key features; The lip shape model library is used to store lip shape data; The lip shape generation unit is used to select appropriate lip shape data from the lip shape model library according to the analysis result of the speech analysis unit, and combine and adjust them to generate a lip shape sequence synchronized with the speech; The synchronization adjustment unit is used to ensure that the changes in lip shape are synchronized with the time axis of speech; The output display unit is used to present the generated synchronized lip shape in a visual manner.

[0050] The voice signal received by the voice input unit can be real-time voice collected by a microphone or a pre-recorded audio file. The input voice signal can also be pre-processed, such as noise reduction, filtering, etc., to improve the voice quality.

[0051] The speech analysis unit includes (1) phoneme recognition: breaking down speech into basic phoneme units, such as vowels, consonants, etc. Each phoneme corresponds to a specific lip shape state. For example, in Chinese, the "p" sound requires the lips to be tightly closed and then suddenly opened, while the "a" sound requires the mouth to be wide open with the lips in a naturally relaxed state; (2) rhythmic analysis: including analysis of pitch, speaking speed, stress, etc. Rhythmic features will affect the speed and amplitude of lip shape changes. For example, when speaking faster, the lip shape changes will also speed up accordingly; the lip shape movement of the stressed part may be more obvious.

[0052] The lip shape model library stores a large amount of lip shape data for different phonemes, syllables and various emotional states. These data can be obtained through three-dimensional scanning of the lip shapes of real people, or they can be virtual lip shape models generated by computer graphics technology. For a virtual character's lip shape speech synchronization system, the model library may contain lip shape templates for different expressions, such as smile, surprise, anger, etc., so that the corresponding lip shape can be called when the voice carries a specific emotion.

[0053] In the lip shape generation unit, if the input speech is "Hello", the lip shape generation unit will search for the lip shapes corresponding to each phoneme "H", "e", "l", "l", and "o" in turn, and then combine them in the correct time sequence to form a continuous lip shape change animation.

[0054] The synchronization adjustment unit will accurately control the speed and timing of lip shape changes based on factors such as the duration and rhythm of the speech. If a syllable takes a long time to pronounce, the synchronization adjustment module will allow the corresponding lip shape to slowly transition from the starting state to the target state during this period of time, rather than switching instantly, to achieve a more natural synchronization effect.

[0055] In this embodiment, the output display unit acts on the image of the virtual digital human. The output display unit renders the synchronized lip shape onto the face of the virtual digital human in real time, allowing the user to experience a more realistic interactive experience in an immersive environment.

[0056] In the present invention, the image of the virtual digital person can be designed to be more friendly and kind, and its interaction method can be personalized according to the user's habits. For young users, a more lively language style can be adopted; for elderly users, the speech speed can be slowed down and questions can be answered in more easy-to-understand language, which can provide an experience similar to natural communication between people, which is conducive to improving the satisfaction of power customer service.

[0057] Those of ordinary skill in the art will appreciate that the modules of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0058] In the embodiments provided by the present invention, it should be understood that the division of modules is only a logical function division, and there may be other division methods in actual implementation, for example, multiple modules can be combined into one module, one module can be split into multiple modules, or some features can be ignored, etc.

[0059] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of software functional modules.

[0060] If the integrated module is implemented in the form of a software function 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 the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nlyMemory), random access memory (RAM, RandomAccessMemory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0061] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A real-time interactive driving system for a virtual digital human in electric power services, characterized in that: It includes a data receiving module, a natural language processing module, a central processing module, a speech synthesis module, an action expression driving module, and a virtual digital human model connected in sequence; it also includes a knowledge graph module; the knowledge graph module is connected to the central processing module; the knowledge graph module is used to store knowledge related to power services to provide an accurate basis for answering user questions; The data receiving module is used to receive information data input by the user in real time; The natural language processing module is used to understand the information data input by the user and convert it into semantic representation data that can be processed by the computer; The central processing module is used to identify and process the semantic representation data sent by the natural language processing module, and obtain the voice data for interaction with the user based on the knowledge stored in the knowledge graph module; The speech synthesis module is used to synthesize speech data for the virtual digital human to interact with the user, so as to realize the speech interaction between the user and the virtual digital human; The action and expression driving module is used to drive the virtual digital human to make natural actions and expressions according to the dialogue content and scene; The virtual digital human model is used to present the image of the virtual digital human according to the information output by the speech synthesis module and the action expression driving module.

2. A real-time interactive driving system for a virtual digital human for electric power services according to claim 1, characterized in that: The data receiving module receives information data input by the user including text data and voice data. When receiving the voice data, it also includes pre-processing the voice data to generate denoised voice data.

3. A real-time interactive driving system for a virtual digital human for electric power services according to claim 1, characterized in that: The natural language processing module includes a language understanding unit, a language generation unit, and a semantic disambiguation unit; The language understanding unit is used to analyze and understand the natural language input by the user; The language generation unit is used to generate an answer text based on the understanding of the user's question; The semantic disambiguation unit is used to perform context analysis on the semantic ambiguity problem of multiple meanings of a word in the answer text to achieve semantic disambiguation.

4. A real-time interactive driving system for a virtual digital human for electric power services according to claim 3, characterized in that: The language understanding unit trains power service related texts through a Transformer architecture model in deep learning.

5. The real-time interactive driving system of a virtual digital human for electric power services according to claim 1, characterized in that: The speech synthesis module includes a speech recognition unit, a speech reading unit, and a speech synthesis unit; The speech recognition unit is used to convert the user's speech into text; The speech reading unit is used to read the text converted by the speech recognition module, so as to find the corresponding answer of the virtual digital human; The speech synthesis unit is used to convert the text content of the virtual digital person's answer into speech output.

6. A real-time interactive driving system for virtual digital human in electric power service according to claim 1, characterized in that: The system also includes a dialogue management module and a storage module, wherein the dialogue management module is connected to the virtual digital human model and the storage module respectively; the storage module is connected to the knowledge graph module; The dialogue management module is used to control the dialogue process between the user and the virtual digital person and guide the user to provide necessary information; The storage module is used to store the interactive information data generated by the dialogue management module; The knowledge graph module is also used to store conversation cases between virtual humans and users based on interactive information data.

7. A real-time interactive driving system for virtual digital human of electric power service according to claim 1, characterized in that: The system also includes an intelligent adjustment module, which is connected to the central processing module and the virtual digital human model respectively; the intelligent adjustment module is used to adjust different virtual digital human parameters according to different customers in the conversation.

8. A real-time interactive driving system for virtual digital human in electric power service according to claim 7, characterized in that: The intelligent adjustment module includes an image adjustment unit, a voice adjustment unit, and a clothing adjustment unit; The image adjustment unit is used to configure the image of the virtual digital human; The voice adjustment unit is used to adjust the voice of the virtual digital person according to the voice characteristics of the user; The clothing adjustment unit is used to configure the clothing of the virtual digital person.

9. The real-time interactive driving system of a virtual digital human for electric power services according to claim 1, characterized in that: The system also includes a lip synchronization module, which is connected to the central processing module and the speech synthesis module respectively, and is used to match the speech data interacting with the user with the lip shape synchronized with the virtual digital human.

10. A real-time interactive driving system for virtual digital human of electric power service according to claim 9, characterized in that: The lip synchronization module includes a speech input unit, a speech analysis unit, a lip model library, a lip generation unit, a synchronization adjustment unit and an output display unit; The voice input unit is used to receive voice signals; The speech analysis unit is used to perform in-depth analysis on the input speech and extract key features; The lip shape model library is used to store lip shape data; The lip shape generation unit is used to select appropriate lip shape data from the lip shape model library according to the analysis result of the speech analysis unit, and combine and adjust them to generate a lip shape sequence synchronized with the speech; The synchronization adjustment unit is used to ensure that the change of lip shape is synchronized with the time axis of speech; The output display unit is used to present the generated synchronized lip shape in a visual manner.

Images