Avatar Creation System and Communication System
A centralized system manages and selects the best avatar generation APIs to create high-quality avatars efficiently, addressing the challenge of diverse service specifications and improving user convenience.
Patent Information
- Application Number
- JP2024061896
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2024-04-08
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-04-08
AI Technical Summary
Existing avatar generation services have different specifications and parameter setting methods, making it difficult for users to understand and efficiently use multiple services, leading to inconvenience and suboptimal results.
A system that centrally manages multiple avatar generation APIs, allowing users to easily generate avatars by inputting parameters, dynamically selects the most suitable API based on user requests, and integrates facial expression, voice, and personality information to create high-quality avatars.
Enables efficient and convenient avatar generation across multiple services, reduces costs, and improves user experience by automating the process while understanding and leveraging the capabilities of each API.
Smart Images

Figure 0007577392000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to a system that centrally manages multiple APIs, selects an appropriate API in response to a request, and generates an avatar, and a communication system that uses the avatar generated by the system. [Background technology]
[0002] In recent years, with the development of computer graphics technology, many services are being provided that generate avatars according to the user's preferences. In these services, users can generate their desired avatar by selecting parameters such as hairstyle, eye color, and clothing, and inputting them into an avatar generation API.
[0003] In this technical field, a method for creating and editing an avatar and navigating an avatar selection interface has been disclosed (see Patent Document 1), as well as a faster and more efficient interface for creating and editing avatars (Patent Document 2). [Prior art documents] [Patent documents]
[0004] [Patent Document 1] Patent Publication No. 2022-008470 [Patent Document 2] JP 2023-085356 A Summary of the Invention [Problem to be solved by the invention]
[0005] However, there are many businesses offering avatar generation services, and the specifications of the avatar generation APIs and the method of setting parameters differ for each service. As a result, when a user uses multiple avatar generation services, they need to understand the specifications of each service and set the parameters, which can be inconvenient.
[0006] In addition, since the avatar generation capabilities of each avatar generation service are different, users need to select an appropriate service to obtain the avatar they desire. However, it is not easy for users to understand the avatar generation capabilities of each service, and there is a problem that users have no choice but to use the services on a trial and error basis.
[0007] The present invention has been made in consideration of the above problems, and has an object to provide a system that makes it easier to generate avatars. [Means for solving the problem]
[0008] According to the present invention, is obtained. Effect of the Invention
[0009] According to the present invention, the following effects are obtained.
[0010] By centrally managing multiple avatar generation APIs, users can easily generate avatars without having to be aware of the specifications of each service.
[0011] By managing the avatar generation capabilities of each avatar generation API, it is possible to select the most suitable avatar generation API according to the user's request and generate an avatar. By utilizing the avatar generation history information, an avatar that matches the user's preferences can be generated.
[0012] By having a computer execute the avatar generation process, the generation of avatars can be automated, improving user convenience.
[0013] Centralized management allows us to understand the usage status of each avatar generation API, which can be used to improve services and provide new services.
[0014] By combining multiple avatar generation APIs, it is possible to generate avatars that cannot be achieved with a single service.
[0015] It reduces the cost of generating avatars. Compared to using multiple services individually, centralized management can reduce API usage fees.
[0016] As described above, according to the present invention, a plurality of avatar generation services can be efficiently used, improving user convenience. [Brief description of the drawings]
[0017] [Figure 1] 1 is a diagram showing an example of the configuration of an avatar generation system (hereinafter referred to as the "system") according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a functional block diagram of the system of FIG. 1. [Diagram 3] 2 is an example of a management screen provided to a user by the system avatar management server of FIG. 1. [Figure 4] FIG. 2 is a sequence diagram of the processing of the system of FIG. [Diagram 5] FIG. 2 is a schematic diagram showing a fixed conversation registration function of a communication system that uses an avatar generated by the system of FIG. 1. [Figure 6] 2 is a schematic diagram showing a fixed conversation candidate registration function of a communication system that uses an avatar generated by the system of FIG. 1. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0018] The present invention will be described below with reference to the preferred embodiments. [Item 1] An avatar generation system including at least a facial expression generation API providing server, a voice generation API providing server, a personality generation API providing server, and an avatar management server, The avatar management server, a parameter receiving unit for receiving input of facial expression parameters, voice parameters, and personality parameters from a user; a parameter transmission unit that transmits the facial expression parameters, the voice parameters, and the personality parameters to the corresponding API providing servers; A generated information acquisition unit that receives facial expression information, voice information, and personality information generated by each of the API providing servers; an avatar generating unit that generates an avatar by integrating the facial expression information, the voice information, and the personality information; An avatar generation system comprising: [Item 2] Item 1 is an avatar generation system according to the present invention, The avatar management server further includes an avatar storage unit that stores the generated avatar. Avatar generation system. [Item 3] The avatar generation system according to item 1 or 2, the avatar management server further comprises a preview unit that reads out and displays the stored avatar in response to a preview request from the user; Avatar generation system. [Item 4] An avatar generation system according to any one of items 1 to 3, the avatar management server further comprises an avatar editing unit that edits the generated avatar based on an editing instruction from a user; Avatar generation system. [Item 5] An avatar generation system according to any one of items 1 to 4, the avatar management server further includes an avatar sharing unit that shares the generated avatar with other users based on a sharing instruction from a user; Avatar generation system. [Item 6] 6. An avatar generation system according to any one of claims 1 to 5, The avatar management server, Further comprising an API selection unit that selects an optimal API providing server from among the plurality of facial expression generation API providing servers, the plurality of voice generation API providing servers, and the plurality of personality generation API providing servers. Avatar generation system.
[0019] <Details of the embodiment> Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
[0020] <Summary of the Invention> As shown in Fig. 1, an avatar generation system (hereinafter sometimes referred to as "system") 1 according to an embodiment of the present invention relates to a system that generates an avatar by combining multiple APIs. In the following embodiment, a description will be given of system 1 that is configured from a facial expression generation server 30, a voice generation API providing server 31, and a personality generation API providing server 33, which respectively provide a facial expression generation API, a voice generation API, and a personality generation API, and an avatar management server 20 that integrates these APIs to generate an optimal avatar.
[0021] According to the present invention, a user can easily generate an avatar by simply inputting parameters of facial expression, voice, and personality on the platform system provided by the avatar management server 20. Furthermore, when there are multiple API providers, the system performance and efficiency can be improved by dynamically selecting the optimal API.
[0022] <Hardware configuration example> This system is configured to be able to communicate with each other via the Internet. This system may be configured as a cloud / network type system provided by a specified business operator, or as an on-premise type system that is operated independently within the company that introduces the system.
[0023] Each of the above-mentioned functional blocks can be configured, for example, by hardware provided in a server device (terminal device), a DSP (Digital Signal Processor), or software. For example, when configured by software, each of the above-mentioned functional blocks is actually configured with a CPU, RAM, ROM, etc. of a computer, and is realized by the operation of a program stored in a recording medium such as the RAM, ROM, hard disk, or semiconductor memory.
[0024] <Network configuration> This system is composed of a facial expression generation API providing server, a voice generation API providing server, a personality generation API providing server, and an avatar management server. Each server is an independent computer system and is connected to each other via a network so that they can communicate with each other. The avatar management server accepts requests from user terminals and transmits and receives data to and from each API providing server. The avatar management server also has a database for storing the generated avatars.
[0025] <Avatar management server> As shown in FIG. 2, avatar management server 20 according to this embodiment has the following functions for configuring the system.
[0026] <Storage section> The storage unit 101 is implemented in a storage device such as a hard disk or SSD in the avatar management server. Data is managed using a relational database, a NoSQL database, or the like. The storage unit 101 is configured to ensure data consistency and permanence, and to enable high-speed reading and writing.
[0027] The storage unit 101 is provided in the avatar management server and stores various data necessary for the operation of the system. The main data to be stored are as follows: Avatar Data Save the data of the generated avatar, such as images, voices, personalities, and movements. Store the data received from the avatar storage unit in a format that is easy to search and reuse. · User data Save the information of the users who use the system. It includes user IDs, passwords, personal settings, purchase histories, etc. · API data Save the information of the servers that provide various APIs used by the system, such as the expression generation API, voice generation API, personality generation API, etc. It includes the access information, authentication information, usage status, etc. of the API-providing servers. · Setting data Save various setting information for controlling the operation of System 1. It includes the criteria for API selection, the format of data storage, security settings, etc. In addition, the storage unit 101 appropriately reads and writes data from other functional departments of the avatar management server. For example, the avatar data generated by the avatar generation unit may be saved in the storage unit 101, or the API data used by the API selection unit may be read from the storage unit 101.
[0028] <Parameter reception unit> The parameter reception unit 102 receives the input of expression parameters, voice parameters, and personality parameters necessary for avatar generation from the user terminal. These parameters are used by the user to customize the expression, voice, and personality of the avatar. The parameter reception unit provides an interface with the user terminal, analyzes and validates the parameters input by the user, and makes them available for subsequent processing within the system.
[0029] <API selection unit> The API selection unit 103 is responsible for selecting the optimal server from among multiple API providing servers available for facial expression generation, voice generation, and personality generation. Selection criteria include API response speed, the quality of the generated facial expression, voice, and personality, the cost of using the API, and the reliability of the API. The API selection unit may evaluate the APIs based on these criteria and dynamically select the optimal API for each task. This allows the system to efficiently use resources and generate high-quality avatars.
[0030] <Parameter transmission section> The parameter transmission unit 104 transmits corresponding parameters to the API providing server selected by the API selection unit. Facial expression parameters are transmitted to the facial expression generation API, voice parameters to the voice generation API, and personality parameters to the personality generation API. The parameter transmission unit converts the parameters according to the data format required by each API, and transmits them to the API providing server via the network. The parameter transmission unit also monitors responses from the API providing server, and takes appropriate action if an error occurs.
[0031] <Generation information acquisition section> The generation information acquisition unit 105 receives facial expression information, voice information, and personality information returned from the facial expression generation API, voice generation API, and personality generation API. The generation information acquisition unit manages communication with each API and verifies the consistency of the received data. The received information is passed to the avatar generation unit and integrated.
[0032] <Avatar Generation> The avatar generator 106 integrates the facial expression, voice, and personality information received from the generation information acquisition unit to generate a final avatar. The avatar generator uses 3D modeling and rendering techniques to create a consistent avatar with facial expression, voice, and personality. The generated avatar is displayed on the user terminal and passed to the avatar storage unit for further processing.
[0033] <Avatar Storage Department> The avatar storage unit 107 stores the avatar generated by the avatar generation unit in a database. The avatar data includes information on expressions, voices, and personalities. The avatar storage unit stores the avatar data in the database in a structured format that is easy to search and update. The stored avatar is used for the user to reuse or edit the avatar later.
[0034] <Avatar reading unit> The avatar reading unit 108 reads out the stored avatar from the database in response to an avatar playback request from the user terminal. When the user requests avatar playback, the avatar reading unit acquires the avatar data from the database and transmits it to the user terminal. The avatar reading unit manages the connection to the database and realizes efficient data search and access.
[0035] <Avatar editing unit> The avatar editing unit 109 provides a function to edit the generated avatar based on an editing instruction from the user terminal. The user sends an editing instruction to change the expression, voice, personality, etc. of the avatar. The avatar editing unit receives these instructions and modifies the avatar data. The edited avatar is stored in the database and transmitted to the user terminal.
[0036] <Avatar sharing unit> The avatar sharing unit 110 provides a function to share the generated avatar with other users based on a sharing instruction from the user terminal. The user can send the avatar to other users or share it on social media. The avatar sharing unit receives the user's sharing instruction, converts the avatar data into an appropriate format, and transmits it to the specified destination. In addition, the avatar sharing unit performs privacy settings and permission management to prevent unauthorized sharing of the avatar.
[0037] <Configuration of the API providing server> The API providing server according to this embodiment has the following functions according to their respective characteristics.
[0038] <Facial expression generation processing section> The facial expression generation API server generates facial expressions for the avatar based on the facial expression parameters received from the avatar management server. The facial expression parameters include the degree of eye opening, the shape of the mouth, the position of the eyebrows, etc. The facial expression generation API uses these parameters as input to generate facial expressions in the form of 3D models or 2D images. The generated facial expression information is sent back to the avatar management server.
[0039] <Speech generation processing unit> The voice generation API server generates the voice of the avatar based on the voice parameters received from the avatar management server. The voice parameters include pitch, speed, intonation, etc. The voice generation API uses these parameters to generate the voice of the avatar using text-to-speech and voice synthesis technology. The generated voice information is sent back to the avatar management server.
[0040] <Personality generation processing section> The personality generation API provision server generates an avatar's personality based on the personality parameters received from the avatar management server. The personality parameters include cheerfulness, positivity, friendliness, etc. The personality generation API uses these parameters as input to generate an avatar's personality using natural language processing and dialogue system technology. The generated personality information is used to control the avatar's dialogue and behavior, and is sent back to the avatar management server.
[0041] In addition to the API providing server described above, the following APIs may be used in combination or independently. ·Movement generation API Generates body movements and gestures for avatars. Actions such as walking, running, jumping, and waving can be generated naturally, allowing for more realistic and lifelike avatars. ·Facial expression recognition API The system recognizes the user's facial expressions and reflects them on the avatar. When the user smiles or gets angry in front of the camera, the avatar reproduces the same facial expression. This allows for emotional synchronization between the user and the avatar. Voice Recognition API It recognizes the user's voice and reflects it in the avatar's responses and actions. When the user speaks, the avatar responds appropriately or takes the requested action. This allows for interactive communication with the avatar. Natural Language Processing API Realize natural conversation with avatars. Understand what the user says and generate appropriate responses based on the context. This enables realistic dialogue with avatars. ·Sentiment analysis API Emotions are analyzed from text and voice, and reflected in the avatar's facial expressions and speaking style. The avatar can read the emotions expressed by the user and respond empathetically. This allows for more natural and empathetic interactions with the avatar. Rendering API Render your avatar in high-quality 3D graphics, smoothly animating your avatar in real time and displaying it in high resolution, for a more immersive visual experience. Physics Simulation API It physically simulates the movement of avatar hair and clothes. It can express hair fluttering in the wind and clothes swaying with movement. This makes avatars even more realistic. Virtual Background API Place avatars in various virtual environments. Any background can be generated, such as a room, a city, or a natural environment, and the avatar can blend in seamlessly. This allows avatars to be used in a variety of scenes. Accessory generation API Users can equip their avatars with hats, glasses, accessories, etc. to dress up their avatars according to their preferences. This allows for a wider variety of avatar looks. Animation control API Control avatar behavior. You can apply animations to avatars and customize their movements through the API, allowing you to fine-tune the behavior of your avatar.
[0042] Combining these APIs makes it possible to create more expressive and attractive avatars. It is possible to enhance the avatar's appearance, movement, dialogue, emotional expression, etc. in multiple ways, deepening interaction with the user.
[0043] <Processing flow> The flow of processing in the system 1 according to this embodiment will be described with reference to FIGS.
[0044] When a user logs in and accesses avatar management server 20, the management screen shown in Fig. 3 is displayed. As shown in the figure, the management screen displays an API selection area G and an avatar management area A. In the API selection area G, buttons Btn for inputting parameters for various APIs are displayed. When each button Btn is selected, a parameter input screen for the respective QPI is displayed.
[0045] When the user inputs facial expression parameters, voice parameters, and personality parameters into each parameter input screen (SQ001), the parameter reception unit of avatar management server 20 receives the parameters, and the API selection unit selects the optimal API providing server (SQ002).
[0046] Next, the parameter transmission unit transmits the corresponding parameters to the selected API providing server. That is, the avatar management server 20 transmits the parameters required to generate facial expressions to the facial expression generation API providing server 30 (SQ003). The parameters here include not only whether or not to generate the facial expression, but also items for adjusting the generation such as instructions, numerical values, degree, frequency, intensity, start and end times input by the user. The technology provided by the facial expression generation API according to this embodiment is lip-sync technology. Specifically, the user uploads an image to which the user wants to apply lip-sync to the avatar management server. The uploaded image is transmitted to the selected facial expression generation API. The facial expression generation API performs the following process on the received image. Detect faces in an image and extract facial feature points (mouth, eyes, nose, etc.). Analyzes the specified audio data and extracts audio features (phonemes, pitch, volume, etc.). -Lip sync is generated by moving facial feature points over time based on voice characteristics. Generate an image with lip sync applied and return it to the avatar management server. This technology allows users to apply lip sync to still images, making it possible to generate moving images that make it appear as if the images are speaking.
[0047] Similarly, avatar management server 20 transmits parameters required for generating facial expressions to voice generation API providing server 31 (SQ005). The technology provided by the voice generation API providing server according to this embodiment provides technology that allows a user to upload a voice sample of about several minutes, and learns the features of that person's voice from the voice sample, enabling all voices to be generated in the same voice as that of that person. Specifically, the user uploads a voice sample of a person for whom voice generation is desired via the avatar management server. The uploaded voice sample is sent to the selected voice generation API providing server. The voice generation API performs the following processes on the received voice sample. Analyze voice samples and extract the person's vocal characteristics (timbre, pitch, intonation, etc.). The extracted features are used to train a speech synthesis model to reproduce the person's voice. Using a trained speech synthesis model, any text can be input and a speech output is generated reading the text in the person's voice. The generated voice data is returned to the avatar management server. Such technology allows users to create a voice synthesis model that reproduces the voice of a particular person from a short voice sample.
[0048] Similarly, avatar management server 20 transmits parameters required to generate an avatar's personality to personality generation API providing server 32 (SQ007). The technology provided by the personality generation API providing server according to this embodiment provides technology for generating the personality, tone of voice, etc. of the generated avatar when the avatar uses a generation system AI to respond in chat or voice. Specifically, the user specifies the personality, tone of voice, etc. that he or she wishes to give to the avatar as a prompt input via the avatar management server. The specified prompt is sent to the selected personality generation API. The personality generation API performs the following processes based on the received prompt input. Analyze prompt input and extract characteristics such as personality and tone of voice specified. The extracted features are used to generate a personality model to define the avatar's personality and tone of voice. By applying the generated personality model to generative AI, chat and voice responses can be based on the user's personality and tone of voice. The generated personality model is returned to the avatar management server. This technology allows users to freely define the personality and tone of their avatar by simply entering a few prompts. The personality model generated by this technology is seamlessly integrated with generative AI, allowing for consistent responses based on the personality and tone of voice, providing a more immersive experience for users.
[0049] In this way, facial expression information, voice information, and personality information are generated based on the parameters received by each API providing server. Each piece of generated information is returned to the avatar management server (SQ004, SQ006, SQ008).
[0050] The generation information acquisition unit of the avatar management server receives the generation information from each API providing server, and the avatar generation unit integrates the received information to generate an avatar (SQ009).
[0051] The avatar management server stores the generated avatar in a database and provides it to the user terminal 10 (SQ010). When a user requests to play, edit, or share an avatar, the avatar reading unit, avatar editing unit, and avatar sharing unit are each able to perform the corresponding process.
[0052] As described above, the present invention is a system that manages multiple avatar generation APIs in a centralized manner and selects the optimal API in response to a user request to generate an avatar. Specifically, the management system of the present invention is capable of communicating with avatar generation APIs provided by multiple businesses and selects the optimal API in response to an avatar generation request from a user. Then, the management system assigns parameters based on the user's request to the selected API and requests avatar generation. The generated avatar is acquired by the management system and provided to the user. This series of processes allows the user to obtain a desired avatar with simple operations without being aware of multiple avatar generation services.
[0053] According to this invention, users can easily generate avatars through one management system without having to understand the specifications of multiple avatar generation services individually. Also, the management system can efficiently generate high-quality avatars by understanding the avatar generation capabilities of each API and selecting the optimal API according to the user's request. Furthermore, when adding a new avatar generation API, it can be provided to users simply by establishing a connection with the management system, ensuring the flexibility and scalability of the system.
[0054] <Communication System> The avatars generated by the avatar generation system according to the above-described embodiment can be implemented as a communication system as follows: That is, the communication system according to the present embodiment includes a statement receiving unit that receives statements from users via chat, an answer information acquiring unit that communicates with an answer generation API providing server that generates answers according to the statements and acquires answer information for the statements, and an avatar statement generating unit that generates statements for the generated avatar based on the answer information.
[0055] The comment receiving unit provides a chat interface between the user and the avatar, and receives comments from the user in the form of text or voice. The received comments are sent to the answer information acquiring unit.
[0056] The answer information acquisition unit communicates with the answer generation API providing server to generate an answer according to the received utterance. The answer generation API providing server generates a natural answer to the utterance using a large-scale language model. The generated answer information is transmitted to the avatar utterance generating unit via the answer information acquisition unit.
[0057] The avatar comment generator generates a comment for the avatar generated by the avatar generation system based on the response information. The generated comment is converted into text or voice and presented to the user via a chat interface.
[0058] The avatar statement generator can also generate facial expressions and movements for the avatar based on the response information and display them in sync with the utterance, allowing for more realistic and natural communication with the avatar.
[0059] According to the communication system of the present embodiment, it is possible to have a natural conversation with a user by using an avatar generated by the avatar generation system. By utilizing advanced language processing technology by the answer generation API providing server, the avatar can generate appropriate and natural answers to the user's comments, realizing realistic communication.
[0060] <Fixed conversation registration function> As shown in Fig. 5, the communication system may be added with a question and answer registration unit that registers predetermined question and answer contents, and a question and answer determination unit that directly sends the registered answer contents to the avatar comment generation unit when the user's comment contents match the question contents. This makes it possible to return a prepared answer without going through the generative AI, preventing unintended answers and enabling faster answering speed.
[0061] The question and answer registration unit has a database for registering predetermined questions and answers. For example, the following pairs of questions and answers are registered in this database. Questions include: What is your favorite animal? Answer: I like dogs. Questions asked: What is your favorite food? Answer: Apples. The question and answer determination unit analyzes the content of the user's comment received by the comment receiving unit and compares it with the question registered in the question and answer registration unit. If the content of the comment matches the registered question or can be interpreted as a location, the question and answer determination unit transmits the corresponding answer registered in the question and answer registration unit directly to the avatar comment generation unit without going through the answer information acquisition unit.
[0062] For example, if a user says, "What is your favorite animal?", the question and answer determination unit detects that the content of this statement matches the question content registered in the question and answer registration unit, and obtains the corresponding answer content, "I like dogs," and sends it to the avatar statement generation unit.
[0063] The avatar statement generator generates a statement for the avatar using the answer content received from the question answer determination unit. In this case, the prepared answer content is used as the avatar statement without going through the answer generation API server.
[0064] In this way, by registering questions and answers in advance, the avatar can return appropriate answers without using generative AI. This prevents unintended answers, shortens the processing time for answer generation, and enables high-speed response.
[0065] <Fixed conversation candidate registration function> 6, the system may further include a fixed conversation registration unit that registers the user's conversation content received by the conversation receiving unit and the avatar's conversation content generated by the avatar conversation generation unit as a question and an answer in the question and answer registration unit based on an instruction from the user. This allows the user to register the question and answer at any time as a "fixed conversation" while communicating with the avatar using the generative AI.
[0066] For example, if a user asks, "What are some recommended tourist spots?" and the avatar replies, "My recommendation is Kamakura. The hydrangeas at Hasedera Temple are very beautiful," if the user likes this exchange, they can register it in the fixed conversation registration section, so that the same answer will be returned for the same question in the future.
[0067] The fixed conversation registration unit has a function of registering the user's statement content accepted by the statement accepting unit and the avatar's statement content generated by the avatar statement generation unit as question content and answer content in the question and answer registration unit based on instructions from the user.
[0068] When a user is having a conversation with an avatar and wants to register the question and answer as a fixed conversation, the user performs a specific operation (for example, clicking the "Register this conversation as a fixed conversation" button). When the fixed conversation registration unit detects this operation, it obtains the previous user's statement and the avatar's statement, and registers them in the question and answer registration unit.
[0069] For example, suppose the following exchange took place: User: What food do you dislike? Avatar: A pear. If the user likes this conversation and operates the button to register it as a fixed conversation, the fixed conversation registration unit registers the user's statement as a question and the avatar's statement as an answer in the question and answer registration unit.
[0070] Once this registration is complete, when the user subsequently utters "What is your least favorite food?", the question and answer determination unit detects that the utterance matches the question registered in the question and answer registration unit, and sends the registered answer to the avatar utterance generation unit. As a result, the avatar will always respond with "Pears."
[0071] In this way, by providing a fixed conversation registration section, users can fix their favorite exchanges from natural conversations with generative AI, realizing reproducible communication. This makes it possible to customize communication with the avatar according to the user's preferences.
[0072] <Industrial application fields> The avatar generation system according to the embodiment of the present invention described above can be applied to avatar generation in various fields such as games, entertainment, education, and communication. In particular, by combining multiple APIs, high-quality avatars with different elements such as facial expressions, voices, and personalities can be efficiently generated, which can greatly contribute to the development and provision of services that utilize avatars. In addition, the API selection function can generate the optimal avatar depending on the situation, which can also contribute to improving user satisfaction.
[0073] The above-described embodiment is merely an example for facilitating understanding of the present invention, and is not intended to limit the present invention. The present invention can be modified or improved without departing from the spirit of the present invention, and it goes without saying that the present invention includes equivalents thereof. [Explanation of symbols]
[0074] 10 Legal Affairs Officer Terminal 20 Client terminal 100 Legal consultation support server
Claims
1. An avatar generation system including at least a facial expression generation API providing server, a voice generation API providing server, a personality generation API providing server, and an avatar management server, The avatar management server, a parameter receiving unit for receiving input of facial expression parameters, voice parameters, and personality parameters from a user; a parameter transmission unit that transmits the facial expression parameters, the voice parameters, and the personality parameters to the corresponding API providing servers; a generated information acquisition unit that receives facial expression information, voice information, and personality information generated by each of the API providing servers; an avatar generating unit that generates an avatar by integrating the facial expression information, the voice information, and the personality information; An avatar generation system comprising:
2. The avatar generation system according to claim 1, The avatar management server further includes an avatar storage unit that stores the generated avatar. Avatar generation system.
3. The avatar generation system according to claim 1 or 2, the avatar management server further comprises a preview unit that reads out and displays the stored avatar in response to a preview request from the user; Avatar generation system.
4. The avatar generation system according to claim 1, the avatar management server further comprises an avatar editing unit that edits the generated avatar based on an editing instruction from a user; Avatar generation system.
5. The avatar generation system according to claim 1, the avatar management server further includes an avatar sharing unit that shares the generated avatar with other users based on a sharing instruction from a user; Avatar generation system.
6. The avatar generation system according to claim 1, The avatar management server, and an API selection unit that selects an optimal API providing server from among the plurality of facial expression generation API providing servers, the plurality of voice generation API providing servers, and the plurality of personality generation API providing servers. Avatar generation system.
7. A communication system for having a conversation with an avatar generated by the avatar generation system according to claim 1, a comment receiving unit that receives comments from users via chat; an answer information acquisition unit that communicates with an answer generation API providing server that generates answers in response to the comments and acquires answer information for the comments; an avatar comment generating unit that generates a comment for the generated avatar based on the answer information; A communication system comprising:
8. A communication system according to claim 7, a question and answer registration unit that accepts registration of predetermined question contents and answers; a question and answer determination unit that transmits the answer registered in the question and answer registration unit to the avatar comment generation unit without going through the answer information acquisition unit when the content of the comment received by the comment receiving unit matches the content of the question registered in the question and answer registration unit; A communication system comprising:
9. 9. A communication system according to claim 8, The system further includes a fixed conversation registration unit that registers the question and answer contents in the question and answer registration unit based on an instruction from a user, The fixed conversation registration unit includes: registering the content of the user's comment received by the comment receiving unit and the content of the avatar's comment generated by the avatar comment generating unit as a question content and an answer content in the question and answer registration unit in response to an instruction from the user; Communication system.
Citation Information
Patent Citations
Avatar creation user interface
JP2023085356A
Apparatus and method for servicing emotional contents on telecommunication devices, apparatus and method for recognizing emotion thereof, apparatus and method for generating ...
KR1020130022434A
Avatar creation user interface
JP2022008470A
Cited By
Communication system and service processing method for the communication system
JP2026167820A
