Command center digital human interaction method and device based on generative artificial intelligence

Abstract

The invention provides a command center digital human interaction method and device based on generative artificial intelligence, and belongs to the technical field of artificial intelligence interaction.The method comprises the steps that a first instruction of a user is received; in response to the first instruction, identifying an intention corresponding to the first instruction through an AI algorithm; when the intention is identified as specified content introduction, generating a driving parameter corresponding to the specified content; based on the driving parameters, media data are output, and the media data comprise pages corresponding to the specified content and animations and voices corresponding to the digital human. According to the method provided by the embodiment of the invention, the page corresponding to the specified content can be a vibrating digital production operation platform, the platform can comprise a plurality of modules, and when the intention of the user is determined, the page containing the digital production operation platform and the digital person can be displayed on a large screen; and the digital person can introduce each module of the digital production operation platform, so that questions of the user for specific requirements are met.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence interaction technology, and in particular to an interaction method and device for a digital human in a command center based on generative artificial intelligence. Background Art

[0002] Artificial Intelligence (AI) refers to the intelligent behavior exhibited by computer systems. It includes machine learning, deep learning, natural language processing, computer vision and other fields. The social impact of artificial intelligence is becoming increasingly prominent. As the core force of a new round of scientific and technological revolution and industrial transformation, it is promoting the upgrading of traditional industries, driving the rapid development of the "unmanned economy", and having a positive impact on people's livelihood areas such as smart transportation, smart home, and smart medical care. In terms of international competition, the competition in the field of AI has begun. We will promote the development of AI by funding research and development and encouraging private investment, and actively participate in global governance to ensure the healthy development and application of AI technology. Technology integration and innovative application is another important trend in the development of AI. AI technology will be integrated with other technologies to create new application scenarios, such as AI painting, digital entertainment, and smart logistics. These innovative applications not only improve work efficiency, but also greatly improve people's quality of life. In the future, artificial intelligence technology will be more widely used and developed in various fields. At the same time, we also need to pay close attention to the development of AI and take effective measures to deal with possible problems to ensure that artificial intelligence can bring us greater benefits.

[0003] At present, in the application scenario of the full-scenario introduction of an enterprise, a professional is needed to introduce the entire company profile or specific products. If the questioner wants to know more extensive content, this will require the introducer to have more professional knowledge. In addition, sometimes multiple languages ​​are required for interpretation or introduction, and usually multiple talents are needed to meet these needs, occupying human resources.

[0004] The background of 3D virtual human technology has gradually matured with the rapid development of technologies such as artificial intelligence and computer graphics. It covers virtual characters with human appearance and behavioral characteristics generated by computer technology. These characters can not only simulate human appearance realistically, but also achieve natural movements, expressions and interactions. The foundation of 3D virtual human technology includes 3D human modeling, avatar generation, action generation, etc. These technologies enable digital humans to develop from simple static models to dynamic, intelligent interactive characters. In terms of 3D human modeling, the 3D human modeling method based on deep learning has made a breakthrough and can reconstruct high-quality 3D human models from 2D images or videos. In terms of action generation, technology has developed from traditional manual animation to using motion capture technology to drive the actions of virtual characters in real time. However, in the existing enterprise full-scene application scenarios, there is no better way to interact with 3D people, so it is necessary to develop an interaction method with 3D people to meet the needs of enterprise full-scene introduction. Summary of the invention

[0005] In view of this, the present invention provides an interactive method and device for a digital human of a command center based on generative artificial intelligence, which can interpret, analyze and report the overall profile of the enterprise's command center based on the digital human of the AI ​​large model, which can not only satisfy the questioner's in-depth understanding of various types of knowledge, but also can switch between multiple languages ​​​​at will, solving the problem of occupying too many human resources.

[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0007] The interactive method of a command center digital human based on generative artificial intelligence according to an embodiment of the present invention includes:

[0008] receiving a first instruction from a user;

[0009] In response to the first instruction, identifying a first intention corresponding to the first instruction through an AI algorithm;

[0010] When the first intention is identified as a designated content introduction, a driving parameter corresponding to the designated content is generated;

[0011] Based on the driving parameters, media data are output, wherein the media data includes a page corresponding to the specified content, and animation and voice corresponding to the digital human.

[0012] As an embodiment of the present invention, the output media data includes:

[0013] Displaying a first interface on the screen of the command center, wherein the first interface includes a page of the digital production operation platform corresponding to the specified content and the digital human;

[0014] The digital human broadcasts the content in the page of the digital production operation platform and outputs corresponding animation.

[0015] As an embodiment of the present invention, the page of the digital production operation platform includes multiple functional modules, including:

[0016] receiving a second instruction from a user for the functional module;

[0017] In response to the second instruction, displaying a second interface corresponding to the functional module;

[0018] The digital human is controlled to broadcast the content in the second interface, and output corresponding animations and corresponding subtitles in multiple languages.

[0019] As an embodiment of the present invention, when the functional module is an introduction module of a product model, the content in the second interface includes a three-dimensional model of the product, and when the digital human voice broadcasts, the three-dimensional model is controlled to move according to the broadcast content.

[0020] As an embodiment of the present invention, the action includes: coloring, flipping or exploding the three-dimensional model.

[0021] As an embodiment of the present invention, when the first instruction is a voice instruction, identifying the first intention corresponding to the first instruction by using an AI algorithm includes:

[0022] Receive the voice command through the AI ​​assistant and convert the voice command into text;

[0023] The text is sent to the intelligent agent model for semantic understanding to obtain the first intention of the user.

[0024] As an embodiment of the present invention, when the first intention is identified as a designated content introduction, generating a driving parameter corresponding to the designated content includes:

[0025] The agent model sends the first instruction to the robotic process automation module;

[0026] The robotic process automation module jumps to the page according to the first instruction, and extracts the module text receipt that the user wants and sends it back to the intelligent agent model;

[0027] The intelligent body model organizes the text of the receipt into a smooth broadcast text as the voice broadcast text of the digital human.

[0028] As an embodiment of the present invention, the interactive method of the command center digital human based on generative artificial intelligence also includes: editing the gender, image, voice, and broadcasting style of the digital human.

[0029] In a second aspect, the present invention further discloses an electronic device, comprising: a memory for storing instructions executed by one or more processors of the electronic device, and a processor for executing the interaction method described in the embodiment of the first aspect.

[0030] In a third aspect, the present invention further discloses a computer-readable storage medium, on which instructions are stored. When the instructions are executed on an electronic device, the electronic device executes the interaction method described in the embodiment of the first aspect.

[0031] The above technical solution of the present invention has at least one of the following beneficial effects:

[0032] According to the interactive method of the digital human in the command center based on generative artificial intelligence in an embodiment of the present invention, the questioner's questions are analyzed through the AI ​​big model, and driving parameters for driving the digital human are generated, so that the digital human can answer the questioner's questions in combination with the specified content displayed on the interface, solving the problem of occupying human resources. In addition, the overall scene supports multi-language questions and answers, the digital human needs to support corresponding lip shapes and movements, and is highly anthropomorphic. AI-driven RPA can realize scene replacement, which greatly improves the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A scene diagram of the interaction between a user and a digital human according to an embodiment of the present invention;

[0034] Figure 2 A flow chart showing an interactive method of a command center digital human based on generative artificial intelligence according to an embodiment of the present invention is shown;

[0035] Figure 3 Another flow chart showing the interactive method of command center digital human based on generative artificial intelligence according to an embodiment of the present invention;

[0036] Figure 4 A schematic diagram of the system architecture of an embodiment of the present invention is shown;

[0037] Figure 5 The following is a flowchart showing the interaction between the modules of the command center according to an embodiment of the present invention;

[0038] Figure 6 An interface diagram of a large-screen device according to an embodiment of the present invention is shown;

[0039] Figure 7 Another interface diagram of a large-screen device according to an embodiment of the present invention is shown;

[0040] Figure 8 A schematic diagram showing the image of a digital human according to an embodiment of the present invention is shown;

[0041] Fig. 9 A diagram showing a setting interface of a digital human according to an embodiment of the present invention is shown;

[0042] Fig.10 A block diagram of a SoC system on chip according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0044] refer to Figure 1 , Figure 1 FIG. 1 shows a scene diagram of the interaction between a user and a digital human in an embodiment of the present invention. Figure 1 As shown in the figure, the scene diagram includes cloud device 01, large screen device 02, digital human 03 and user 04. Digital human 03 is a 3D virtual human, which looks like a conversation with a real person. User 04 can ask questions to digital human 03. Large screen device 02 will receive the user's questions and send them to cloud device 01. After cloud device 01 determines the answer, it will send it to large screen device 02. Large screen device 02 controls the display screen based on the returned answer, so that digital human 03 outputs the corresponding animation and controls the audio player to output audio. The user experience is like a conversation with a real person, which brings a different interactive experience to the user.

[0045] The following first describes in detail the interactive method of a digital human in a command center based on generative artificial intelligence according to an embodiment of the present invention in conjunction with the accompanying drawings. The method can be executed by an electronic device. In the following embodiments, a large-screen device is used as an example for explanation.

[0046] refer to Figure 2 and Figure 3 , Figure 2 A flow chart of an interactive method of a command center digital human based on generative artificial intelligence according to an embodiment of the present invention is shown. Figure 3 Another flow chart of the interactive method of command center digital human based on generative artificial intelligence in an embodiment of the present invention is shown. Figure 2 As shown, the method may include:

[0047] S210, receiving a first instruction from a user.

[0048] The first instruction may be an audio input, or an action gesture, etc. For example, the first instruction may be a specific keyword, etc. Figure 3As shown, the user says "introduce the "Enter Zhenhua" module", which is the first instruction.

[0049] In some embodiments, Figure 3 As shown in the figure, before officially starting the digital human, the user can first wake up the digital human, for example, the user calls the digital human "Xiaohua Xiaohua". The large-screen device receives the user's call, executes a specific word wake-up, turns on language-to-text, and sends the response text to the digital human after AI recognizes the wake-up intention. After the digital human is awakened, it plays "Hello, I'm here". After completing the wake-up operation, it starts to monitor the user's instructions.

[0050] In an embodiment of the present invention, the user's voice input can be monitored by an AI assistant monitoring program. The AI ​​assistant monitoring program can be awakened by the "Xiao Hua Xiao Hua" command and can maintain silent monitoring for a period of time to eliminate interfering commands as needed.

[0051] S220, in response to the first instruction, identifying the intention corresponding to the first instruction through an AI algorithm.

[0052] For example, if the user inputs a voice keyword, the AI ​​algorithm model preprocesses the first instruction: including word segmentation: dividing the user's input text into separate words or phrases. Removing stop words, morphological restoration or stemming, converting words to their basic form for better matching. After feature extraction and context perception to enhance understanding, the user's intention is finally determined.

[0053] like Figure 3 As shown, the user says "Let me introduce the module "Enter Zhenhua"". The large-screen device uses AI algorithm and voice-to-text conversion to introduce Zhenhua to determine the user's intention and whether to convert it into a command.

[0054] S230: When the recognition intention is to introduce the designated content, a driving parameter corresponding to the designated content is generated.

[0055] In an embodiment of the present invention, the introduction of the designated content may be pre-set content, for example, introduction to Zhenhua may belong to the designated content. When it is recognized that the user's intention is to introduce Zhenhua, it may be determined to be the introduction of the designated content. At this time, the corresponding inner tube is output on the large screen according to a specific process, thereby completing the introduction of the designated content.

[0056] like Figure 3 As shown in the figure, when it is judged that the intention recognition is not to be converted into a command (the intention is not to introduce the specified content), the AI ​​recognizes it as a natural dialogue and responds reasonably, and the digital human broadcasts at the default position. When it is judged that the intention recognition is to be converted into a command (the intention is to introduce the specified inner tube), the PRA command is sent to generate the "Enter Zhenhua" text, jump to the specified page, and the digital human moves to the specified position and prepares to broadcast.

[0057] S240: Output media data based on the driving parameters.

[0058] The media data includes the page corresponding to the specified content, and the animation and voice corresponding to the digital human. In addition, the driving parameters also include the actions and specific positions set for the digital human. For example, through the way of the command center AI assistant coordinating the digital human, the large screen is combined with a customized digital human and integrated with the AI ​​assistant. The AI ​​assistant's broadcast matches the digital human's body language, and the AI ​​assistant realizes the function of text-to-speech playback, making the overall broadcast effect look more vivid and more humanized.

[0059] like Figure 3 As shown, the digital human can broadcast the content of the "Enter Zhenhua" module. In some embodiments, the broadcast content can also be translated into multiple languages. For example, after reading the text feedback, the Chinese and English subtitles will be displayed on the screen of the large-screen device. For example, the AI ​​assistant supports multiple languages ​​and language-to-text functions. It can not only introduce the content and the user's voice questions according to the prepared script, but also accept the text content through voice-to-text conversion, support Chinese and English input, and answer the corresponding language according to the user's question language.

[0060] In the embodiment of the present invention, the page corresponding to the specified content can be Zhenhua's digital production and operation platform, which can be composed of multiple modules. When the user's intention is determined, the page containing the digital production and operation platform and the digital human can be displayed on the large screen. The digital human can introduce each module of the digital production and operation platform to meet the user's questions about specific needs. Not only can users better understand the situation of the enterprise, but also human resources can be reduced, and this interactive process provides users with a more comfortable interactive experience.

[0061] It can be understood that the interaction method of the embodiment of the present invention can be applied to electronic devices, including but not limited to mobile phones, large-screen devices, smart TVs, wearable devices, tablet computers, desktop computers, computers, wearable devices (for example, smart watches, smart glasses, helmets), virtual reality (VR) devices, augmented reality (AR) devices, wireless devices in industrial control, wireless devices in self-driving, wireless devices in smart grids, wireless devices in transportation safety, wireless devices in smart cities, wireless devices in smart homes, servers, and the like.

[0062] The following describes the system architecture diagram of an embodiment of the present invention in conjunction with the accompanying drawings.

[0063] refer to Figure 4 , Figure 4 FIG. 1 shows a schematic diagram of the system architecture of an embodiment of the present invention. Figure 4 As shown, the system architecture diagram includes six modules, namely, client hardware, software module, service module, tool module and enterprise resource planning and data warehouse module. Among them, the client side may include the above-mentioned electronic devices, such as large-screen devices, which have user interfaces, and users can watch or operate corresponding content based on the user interface for easy interaction. Software modules may include openAI protocol adapters, tools and large language models. These modules can realize the judgment and recognition of user intentions, etc. The service module can meet the basic services of the platform, such as delivery services, data warehouse billing services and query services. Practical tools can realize the acquisition of some data, as well as the processing of natural language. Enterprise resource planning and data warehouse can meet the management of the resources of the entire platform, including big data platform, dictation module, subtitle module, translation engine and robotic process automation. The entire interaction process is coordinated through overall planning and management to realize the process from asking questions to outputting media data.

[0064] The following describes in detail the steps of the command center digital human interaction method based on generative artificial intelligence in an embodiment of the present invention in conjunction with specific embodiments.

[0065] refer to Figure 5 , Figure 6 and Figure 7 , Figure 5 The flowchart of the interaction between the modules of the command center in the embodiment of the present invention is shown. Figure 2 and Figure 3 The content corresponds to Figure 6 An interface diagram of a large-screen device according to an embodiment of the present invention is shown; Figure 7 Another interface diagram of a large-screen device according to an embodiment of the present invention is shown.

[0066] like Figure 5 As shown, the command center mainly includes three modules to execute the interactive method of the embodiment of the present invention, namely Robotic Process Automation (RPA), Artificial Intelligence (AI) and Digital Human. Then execute the first step: the opening monologue and the introduction of the eight modules. Figure 6As shown, the digital production and operation platform is displayed on the interface, including the contents of each module, and users can select the module to be introduced as needed. For example, when the user enters the first instruction, the AI ​​module recognizes that the user intends to give an overall introduction to the central large screen. The AI ​​assistant connects with the RPA, and the AI ​​assistant disassembles the text instructions, and then infers and sends the sequence of RPA actions and execution instructions to the RPA. At the same time, the digital human explains the company's profile and introduces the brief content of each module of the platform on the entire large screen. The broadcasting process is that AI sends text to the digital human, and the digital human broadcasts it. For example, Figure 7 As shown, enter the beam pitch operation room, the interface will display the corresponding 3D map of the beam, and the digital human can broadcast the corresponding text based on the content displayed in the SD map. In addition, when accepting further display instructions from the user, the 3D map is further displayed, including coloring of the three-dimensional model, flipping or explosion map, and partial map display actions. In addition, during the broadcast process, the digital human will feedback to AI when reading sentences, and the AI-driven subtitle application will display bilingual subtitles in Chinese and English, and can control the Chinese and English spacing, subtitle color, xy coordinate position, and subtitle default display time through interface parameters. When the broadcast is completed, feedback is given to AI, and AI confirms that the first step is completed.

[0067] Step 2: Execute the introduction to the Zhenhua module. AI sends a text about the introduction to the Zhenhua module to the digital human, sends a click to enter Zhenhua to the RPA, and the digital human voice broadcasts the text. After the user clicks on the big screen, the feedback clicks to confirm, completing the second step.

[0068] The third step is the introduction of the operation management module. AI receives instructions and gives instructions to RPA and the digital human respectively. The large screen shows the confirmation of the module click, and the digital human voice broadcasts the introduction content. After the user confirms, the entire module is introduced until it is completed. Among them, the specific process of AI assistant docking with RPA and bilingual subtitles can refer to the description of the first step. After the above process is repeated, each time the user proposes a corresponding content introduction, each module of the command center executes the steps one by one to complete the content introduction. The whole process is convenient for users to operate, and they can get a detailed introduction to each part of the enterprise, which has a very good interactive experience.

[0069] In an embodiment of the present invention, in order to better introduce the company's command center, the AI ​​agent technology application is embedded in the setting module BI of the command center. At the same time, it is combined with a digital virtual human. Through the user's oral questions and after AI large model reasoning, the RPA is commanded to drive the BI and broadcast the information through the digital human. The overall scene supports bilingual questions and answers in Chinese and English, the digital human needs to support corresponding lip shapes and movements, and is highly anthropomorphic. AI-driven RPA can realize scene replacement.

[0070] The following is an overview of the business process of Digital Human: The main business requirements of Digital Human AI Big Screen include: Agent model training, users wake up Digital Human by speaking natural language, and say what they want to know or view, and convert the user's audio into text through the voice-to-text dictation engine. The AI ​​big screen gives the text to the Agent for semantic understanding and sends a certain instruction to the RPA robot. The RPA robot will jump to the page according to the instruction and extract the module text that the user wants and send it back to the Agent. The Agent will then polish the language to make the incoherent data into a coherent broadcast article (some fixed texts do not need to be polished), and then send it to the Digital Human for broadcast. In addition, the Agent will also issue the specified action and specific location at the same time to make the overall broadcast effect look more vivid and more humanized. At the same time, it will also issue BI-adjusted instructions based on the content of the broadcast for RPA to execute, so that the picture, characters and sound are synchronized.

[0071] In the embodiment of the present invention, the digital human can be configured to be more suitable for the content of the broadcast.

[0072] refer to Figure 8 and Fig. 9 , Figure 8 A schematic diagram of the image of a digital human according to an embodiment of the present invention is shown. Fig. 9 FIG. 1 shows a setting interface diagram of a digital human in an embodiment of the present invention. Figure 8 As shown in the figure, the digital person can choose two people to broadcast together, or select gender through the interface. Fig. 9 As shown in FIG. 1 , it is also possible to select a digital person dressed in a suitable style according to the content of the broadcast. For example, it includes the selection of voice and action. The user can Fig. 9 The interface shown in the figure can be used to select the appropriate digital human, further improving the user experience.

[0073] It should be noted that the above interaction method can be implemented by a system including a cloud server and a large-screen device. The AI ​​recognition process can be performed on the cloud server, while the display and output are completed in the large-screen device. In some embodiments, both can be completed in the large-screen device. The present invention does not limit the operating mode of the execution subject.

[0074] The present invention also provides an electronic device, comprising:

[0075] a memory for storing instructions to be executed by one or more processors of the device, and

[0076] A processor is used to execute the above embodiment in combination with Figures 1 to 9 The method explained.

[0077] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor executes the above-mentioned embodiment. Figures 1 to 9 The method explained.

[0078] The present invention also provides a computer program product comprising instructions, which, when executed on an electronic device, enables a processor to execute the above-mentioned embodiments. Figures 1 to 9 The method explained.

[0079] Reference now Fig.10 , which is a block diagram of a SoC (System on Chip) 1000 according to an embodiment of the present invention. Fig.10 In the FIG, similar components have the same reference numerals. In addition, the dashed boxes are optional features of more advanced SoCs. Fig.10 In the embodiment, SoC 1000 includes: an interconnect unit 1050, which is coupled to an application processor 1010; a system agent unit 1080; a bus controller unit 1090; an integrated memory controller unit 1040; a group or one or more coprocessors 1020, which may include integrated graphics logic, an image processor, an audio processor, and a video processor; a static random access memory (SRAM) unit 1030; and a direct memory access (DMA) unit 1060. In one embodiment, the coprocessor 1020 includes a dedicated processor, such as, for example, a network or communication processor, a compression engine, a general purpose computing on GPU (GPGPU), a high throughput integrated multi-core architecture (MIC) processor, or an embedded processor.

[0080] The static random access memory (SRAM) unit 1030 may include one or more computer-readable media for storing data and / or instructions. The computer-readable storage medium may store instructions, specifically, temporary and permanent copies of the instructions. The instructions may include: when executed by at least one unit in the processor, the Soc1000 executes the processing method according to the above embodiment, which may be specifically referred to in the above embodiment. Figure 1 and Fig. 9 The interaction method explained will not be repeated here.

[0081] The various embodiments of the mechanism disclosed in the present invention can be implemented in hardware, software, firmware or a combination of these implementation methods. The embodiments of the present invention can be implemented as a computer program or program code executed on a programmable system, which includes at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device and at least one output device.

[0082] Program code can be applied to input instructions to perform the functions described in the present invention and generate output information. The output information can be applied to one or more output devices in a known manner. For purposes of the present invention, a processing system includes any system having a processor such as, for example, a digital signal processor (DSP), a microcontroller, an application specific integrated circuit (ASIC), or a microprocessor.

[0083] Program code can be implemented with high-level programming language or object-oriented programming language to communicate with the processing system. When necessary, program code can also be implemented with assembly language or machine language. In fact, the mechanism described in the present invention is not limited to the scope of any specific programming language. In either case, the language can be a compiled language or an interpreted language.

[0084] In some cases, the disclosed embodiments may be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments may also be implemented as instructions carried or stored on one or more temporary or non-temporary machine-readable (e.g., computer-readable) storage media, which may be read and executed by one or more processors. For example, instructions may be distributed over a network or through other computer-readable media. Therefore, machine-readable media may include any mechanism for storing or transmitting information in a machine (e.g., computer) readable form, including, but not limited to, floppy disks, optical disks, optical disks, read-only memories (CD-ROMs), magneto-optical disks, read-only memories (ROMs), random access memories (RAMs), erasable programmable read-only memories (EPROMs), electrically erasable programmable read-only memories (EEPROMs), magnetic or optical cards, flash memory, or a tangible machine-readable memory for transmitting information (e.g., carrier waves, infrared signals, digital signals, etc.) using the Internet in electrical, optical, acoustic, or other forms of propagation signals. Therefore, machine-readable media include any type of machine-readable media suitable for storing or transmitting electronic instructions or information in a machine (e.g., computer) readable form.

[0085] In the accompanying drawings, some structural or method features may be shown in a specific arrangement and / or order. However, it should be understood that such a specific arrangement and / or order may not be required. Instead, in some embodiments, these features may be arranged in a manner and / or order different from that shown in the illustrative drawings. In addition, the inclusion of structural or method features in a particular figure does not mean that such features are required in all embodiments, and in some embodiments, these features may not be included or may be combined with other features.

[0086] It should be noted that the units / modules mentioned in the various device embodiments of the present invention are all logical units / modules. Physically, a logical unit / module can be a physical unit / module, or a part of a physical unit / module, or can be implemented as a combination of multiple physical units / modules. The physical implementation of these logical units / modules themselves is not the most important. The combination of functions implemented by these logical units / modules is the key to solving the technical problems proposed by the present invention. In addition, in order to highlight the innovative part of the present invention, the above-mentioned device embodiments of the present invention do not introduce units / modules that are not closely related to solving the technical problems proposed by the present invention, which does not mean that there are no other units / modules in the above-mentioned device embodiments.

[0087] It should be noted that in the examples and description of this patent, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including one" do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0088] While the present invention has been shown and described with reference to certain preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.

Claims

1. A command center digital human interaction method based on generative artificial intelligence, characterized in that: include: receiving a first instruction from a user; In response to the first instruction, identifying, by an AI algorithm, an intention corresponding to the first instruction; When the intention is identified as an introduction to a specified content, a driving parameter corresponding to the specified content is generated; Based on the driving parameters, media data are output, wherein the media data includes a page corresponding to the specified content, and animation and voice corresponding to the digital human.

2. The interactive method of command center digital human based on generative artificial intelligence according to claim 1 is characterized in that: The output media data includes: Displaying a first interface on the screen of the command center, wherein the first interface includes a page of the digital production operation platform corresponding to the specified content and the digital human; The digital human broadcasts the content in the page of the digital production operation platform and outputs corresponding animation.

3. The interactive method of command center digital human based on generative artificial intelligence according to claim 2 is characterized in that: The page of the digital production operation platform includes multiple functional modules, and the method further includes: receiving a second instruction from a user for the functional module; In response to the second instruction, displaying a second interface corresponding to the functional module; The digital human is controlled to broadcast the content in the second interface, and output corresponding animations and corresponding subtitles in multiple languages.

4. The interactive method of command center digital human based on generative artificial intelligence according to claim 3 is characterized in that: When the functional module is an introduction module of a product model, the content in the second interface includes a three-dimensional model of the product, and when the digital human voice broadcasts, the three-dimensional model is controlled to move according to the broadcast content.

5. The interactive method of command center digital human based on generative artificial intelligence according to claim 4 is characterized in that: The action includes: at least one of coloring, flipping and exploding the three-dimensional model.

6. The interactive method of command center digital human based on generative artificial intelligence according to claim 3 is characterized in that: When the first instruction is a voice instruction, identifying the first intention corresponding to the first instruction by using an AI algorithm includes: Receive the voice command through the AI ​​assistant and convert the voice command into text; The text is sent to the intelligent agent model for semantic understanding to obtain the first intention of the user.

7. The interactive method of command center digital human based on generative artificial intelligence according to claim 6 is characterized in that: When the first intention is identified as a designated content introduction, generating a driving parameter corresponding to the designated content includes: The agent model sends the first instruction to the robotic process automation module; The robotic process automation module jumps to a page according to the first instruction, and extracts the module text receipt desired by the user and returns it to the intelligent agent model; The intelligent agent model processes the text of the receipt to form a smooth broadcast text, which serves as the voice broadcast text of the digital human.

8. The interactive method of command center digital human based on generative artificial intelligence according to claim 2 is characterized in that: Also includes: The gender, image, voice and broadcasting style of the digital person are edited.

9. An electronic device, characterized in that: include: A memory for storing instructions executed by one or more processors of an electronic device, and a processor for executing the interaction method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, which, when executed on an electronic device, enable the electronic device to execute the interaction method according to any one of claims 1 to 8.

Images