System

Abstract

To provide a system that efficiently selects and utilizes a plurality of generative AI services.SOLUTION: A system comprises a reception unit, a selection unit, a processing unit, and a provision unit. The reception unit receives user instructions. The selection unit selects a generative AI service on the basis of the instructions received by the reception unit. The processing unit makes the selected generative AI service perform processing of a prompt. The provision unit provides the result generated by the processing unit to the user.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to efficiently select and use multiple generative AI services.

[0005] The system according to the embodiment aims to efficiently select and use multiple generative AI services. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a selection unit, a processing unit, and a providing unit. The reception unit receives a user's instruction. The selection unit selects a generating AI service based on the instruction received by the reception unit. The processing unit causes the selected generating AI service to process the prompt. The providing unit provides the result generated by the processing unit to the user. Effect of the Invention

[0007] The system according to the embodiment can efficiently select and use multiple generative AI services. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific process program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The system according to the embodiment of the present invention is a platform that aggregates and centrally manages multiple generative AI services. Since it is very laborious to select the optimal service from the countless generative AI services that are created every day, this platform centrally manages compatible generative AI services that exist on the market through API integration. A user can use the generative AI through the UI of this service, and the optimal generative AI is selected and the prompt is processed according to the user's instructions. For example, the user inputs an instruction to use the generative AI. This instruction includes specific generation content such as "text generation" or "image generation". Next, the platform centrally manages multiple generative AI services that exist on the market through API integration and selects the generative AI service that is optimal for the user's instructions. The selected generative AI service processes the prompt based on the user's instructions and provides the result to the user. For example, when the user inputs an instruction for "text generation", the platform selects the optimal one from multiple text generation AI services and processes the prompt. The generated text is provided to the user. Similarly, when the user inputs an instruction for "image generation", the platform selects the optimal one from multiple image generation AI services and processes the prompt. The generated image is provided to the user. In this way, users can use multiple generative AI services through a single UI, eliminating the need to select the most suitable generative AI service. In addition, by centrally managing generative AI services available on the market through API integration, users can always use the latest generative AI service. This allows the Fusion-AI system to select the most suitable generative AI service based on user instructions, process prompts, and provide the results.

[0029] The Fusion-AI system according to the embodiment includes a reception unit, a selection unit, a processing unit, and a provision unit. The reception unit receives a user's instruction. The user's instruction includes, for example, text input, voice instruction, gesture, and the like, but is not limited to such examples. For example, when the user inputs an instruction of "sentence generation" by text input, the reception unit receives this. The reception unit can also receive voice instructions. For example, when the user issues an instruction of "image generation" by voice, this is accepted. Furthermore, the reception unit can also accept an instruction using a gesture. For example, an instruction to use a specific generation AI service can be issued by a user performing a specific gesture. The selection unit centrally manages multiple generation AI services existing on the market through API cooperation, and selects the optimal generation AI service based on the user's instruction. For example, when the user issues an instruction of "sentence generation", the selection unit selects the optimal one from multiple sentence generation AI services. The selection unit can also select the optimal generation AI service using the selection criteria and algorithms of the generation AI service. For example, the selection unit selects the most suitable service based on the evaluation criteria and algorithms of the generation AI service. The processing unit causes the selected generation AI service to process the prompt. The processing of the prompt includes, for example, natural language processing, image analysis, and voice recognition, but is not limited to such examples. The processing unit causes, for example, the selected sentence generation AI service to process the prompt and generate a sentence. The processing unit can also cause the selected image generation AI service to process the prompt and generate an image. The providing unit provides the result generated by the processing unit to the user. The generated result includes, for example, text, image, voice, etc., but is not limited to such examples. The providing unit provides, for example, the generated sentence to the user. The providing unit can also provide the generated image to the user. Furthermore, the providing unit can also provide the generated voice to the user. As a result, the Fusion-AI system according to the embodiment can select an optimal generation AI service based on a user's instruction, process the prompt, and provide the result.

[0030] The reception unit receives user instructions. Examples of user instructions include, but are not limited to, text input, voice instructions, gestures, and the like. For example, when a user inputs an instruction such as "sentence generation" by text input, the reception unit receives this. The reception unit can also receive voice instructions. For example, when a user issues an instruction such as "image generation" by voice, the reception unit receives this. Furthermore, the reception unit can also receive instructions using gestures. For example, an instruction to use a specific generation AI service can be issued by a user performing a specific gesture. The reception unit is designed to integrally manage these various input means and to enhance user convenience. Specifically, in the case of text input, a user can input instructions using a keyboard or touch screen, and in the case of voice instructions, voice is recognized through a microphone, and the instruction content is analyzed using voice recognition technology. In the case of gesture input, the user's movement is detected using a camera or motion sensor, and the instruction content is interpreted using a gesture recognition algorithm. In this way, the reception unit enables the user to intuitively and quickly issue instructions in any situation. The reception unit also has the role of analyzing the contents of instructions after receiving the user's instructions and transferring them to the appropriate processing department. For example, if the instruction "create sentences" is entered through text input, the reception unit analyzes this instruction and transfers it to the selection unit. Similarly, in the case of voice instructions or gesture instructions, the reception unit analyzes the contents of the instructions and transfers them to the appropriate processing department. This allows the reception unit to efficiently receive a variety of user instructions and support the smooth operation of the entire system.

[0031] The selection unit centrally manages multiple generation AI services available on the market through API integration, and selects the optimal generation AI service based on the user's instructions. For example, when the user issues an instruction for "text generation," the selection unit selects the optimal one from multiple text generation AI services. The selection unit can also select the optimal generation AI service using the selection criteria and algorithms of the generation AI service. For example, the selection unit selects the most suitable service based on the evaluation criteria and algorithms of the generation AI service. The selection unit uses a complex algorithm to evaluate the performance and characteristics of each generation AI service and select the service that best suits the user's needs. Specifically, the selection unit selects the optimal service by considering the past performance data, user reviews, processing speed, and quality of the generation results of each generation AI service. For example, in the case of a text generation AI service, the evaluation criteria can be the naturalness of the generated text, the accuracy of grammar, and the understanding of the context. In the case of an image generation AI service, the evaluation criteria can be the resolution, reality, and color accuracy of the generated image. In addition, the selection unit can provide an individually optimized service by considering the user's past usage history and preferences. For example, if a particular user has previously used a particular generation AI service, that service can be selected preferentially. Furthermore, the selection unit can monitor the status of each generation AI service in real time and dynamically change the selection depending on the usage and load of the service. This allows the selection unit to always select the optimal generation AI service and provide the user with high-quality generation results.

[0032] The processing unit processes the prompt from the selected generation AI service. Examples of the processing of the prompt include, but are not limited to, natural language processing, image analysis, and voice recognition. The processing unit processes the prompt from the selected text generation AI service and generates a text. The processing unit can also process the prompt from the selected image generation AI service and generate an image. The processing unit is responsible for sending the prompt to the selected generation AI service and receiving the result. Specifically, the processing unit generates an appropriate prompt for the generation AI service based on the user's instructions and sends it to the service through the API. For example, in the case of text generation, if the user instructs the processing unit to "generate a blog article about travel," the processing unit analyzes the instruction and sends an appropriate prompt to the generation AI service. Similarly, in the case of image generation, the processing unit generates a prompt based on the user's instructions and sends it to the image generation AI service. The processing unit receives a response from the generation AI service, analyzes the result, and prepares to provide it to the user. For example, when a text generated from a text generation AI service is received, the processing unit analyzes the text and formats it as necessary. Similarly, when an image generated from an image generation AI service is received, the resolution and format of the image can be adjusted. Furthermore, the processing unit can evaluate the processing results of the generation AI service and send the prompt again if necessary. For example, if the generated text or image does not meet the user's expectations, the processing unit can generate a prompt again and send it to the generation AI service to obtain a more appropriate result. This allows the processing unit to effectively utilize the generation AI service based on the user's instructions and provide a high-quality generation result.

[0033] The providing unit provides the user with the results generated by the processing unit. The generated results include, for example, text, images, and audio, but are not limited to such examples. For example, the providing unit provides the user with the generated text. The providing unit can also provide the user with the generated image. Furthermore, the providing unit can also provide the user with the generated audio. The providing unit provides an interface for quickly and appropriately providing the generated results to the user. Specifically, the providing unit has a function for the user to view, download, and share the generated results. For example, the generated text is displayed in a text editor or viewer so that the user can view it, and can be downloaded or copied as necessary. The generated image is displayed in an image viewer so that the user can view it, and can be downloaded or shared. The generated audio is displayed in an audio player so that the user can play it, and can be downloaded or shared. The providing unit also has a function for customizing the format and display method of the generated results to improve the user's convenience. For example, the font and layout of the generated text can be changed, and the size and resolution of the generated image can be adjusted. The providing unit can also provide an API for linking the generated results with other applications and services. This allows the user to utilize the generated results in other tools and platforms. Furthermore, the providing unit also has a function for collecting user feedback and continuously improving the quality of the generated results and the method of providing them. For example, the performance of the entire system can be improved by the user providing an evaluation or comment on the generated results. This allows the providing unit to quickly and appropriately provide high-quality generated results to the user, thereby increasing user satisfaction.

[0034] The reception unit can receive the user's instruction as a specific generation content. The specific generation content includes, for example, a text theme, an image style, a voice tone, and the like, but is not limited to such examples. For example, when the user gives an instruction for "text generation", the reception unit can specifically receive the theme. In addition, when the user gives an instruction for "image generation", the reception unit can specifically receive the style. Furthermore, when the user gives an instruction for "voice generation", the reception unit can specifically receive the tone. By this, by receiving the user's instruction as a specific generation content, it becomes possible to select a more accurate generation AI service. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's instruction to AI and extract the specific generation content.

[0035] The selection unit can centrally manage multiple generation AI services available on the market through API cooperation and select a generation AI service based on a user's instruction. API cooperation includes, for example, the type of API to be used, the protocol of cooperation, and the like, but is not limited to such examples. For example, when a user gives an instruction of "sentence generation", the selection unit selects the optimal one from multiple sentence generation AI services. The selection unit can centrally manage multiple generation AI services available on the market through API cooperation and select the optimal generation AI service for the user's instruction. This makes it possible to centrally manage multiple generation AI services available on the market through API cooperation and select the optimal generation AI service for the user's instruction. Some or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input a user's instruction to an AI and select the optimal generation AI service.

[0036] The processing unit allows the selected generation AI service to process the prompt. The processing of the prompt includes, for example, natural language processing, image analysis, and voice recognition, but is not limited to such examples. The processing unit allows, for example, the selected sentence generation AI service to process the prompt and generate a sentence. The processing unit also allows the selected image generation AI service to process the prompt and generate an image. Furthermore, the processing unit also allows the selected voice generation AI service to process the prompt and generate a voice. As a result, the selected generation AI service processes the prompt, and a generation result based on the user's instruction can be provided. Some or all of the above-mentioned processing in the processing unit may be performed, for example, using AI, or may be performed without using AI. For example, the processing unit can input a prompt to AI and output a generation result.

[0037] The providing unit can provide the generated result to the user. The generated result includes, for example, text, image, voice, etc., but is not limited to such examples. The providing unit, for example, provides the generated sentence to the user. The providing unit can also provide the generated image to the user. Furthermore, the providing unit can also provide the generated voice to the user. Thereby, by providing the generated result to the user, the user can use the result of the generation AI service. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the generation result to AI and provide it to the user.

[0038] The selection unit can select a generation AI service using the selection criteria and algorithm of the generation AI service. The selection criteria and algorithm include, for example, evaluation criteria, types of algorithms, etc., but are not limited to such examples. The selection unit selects the most suitable service based on, for example, the evaluation criteria and algorithm of the generation AI service. As a result, by using the selection criteria and algorithm of the generation AI service, it is possible to select a generation AI service with higher accuracy. Some or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input the evaluation criteria and algorithm of the generation AI service to AI and select the optimal service.

[0039] The providing unit can provide the generated result in a text format or an image format. Examples of the text format and the image format include, but are not limited to, PDF, JPEG, PNG, and the like. For example, the providing unit provides the generated text in a PDF format. The providing unit can also provide the generated image in a JPEG format. Furthermore, the providing unit can also provide the generated audio in an MP3 format. As a result, the generated result is provided in a text format or an image format, so that the user can use the generated result in various formats. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the generated result to AI and provide it in a text format or an image format.

[0040] The reception unit can analyze the user's past instruction history and select the optimal reception method. For example, the reception unit automatically displays instructions that the user frequently input in the past as candidates. The reception unit can also preferentially suggest input methods (such as voice and text) that the user used in the past. Furthermore, the reception unit can predict and suggest instructions to be used in a specific time period from the user's past instruction history. In this way, the optimal reception method can be provided to the user by analyzing the user's past instruction history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past instruction history into AI and select the optimal reception method.

[0041] The reception unit can perform filtering based on the user's current project and field of interest when receiving an instruction. For example, the reception unit preferentially receives instructions related to a project currently in progress by the user. The reception unit can also filter and receive related instructions based on the user's field of interest. Furthermore, the reception unit can also preferentially receive instructions related to fields in which the user has shown interest in the past. As a result, by filtering based on the user's current project and field of interest, it is possible to preferentially receive highly relevant instructions. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's project information and field of interest into AI and perform filtering.

[0042] The reception unit can preferentially receive highly relevant instructions based on the geographical location information of the user when receiving an instruction. For example, when the user is in a specific area, the reception unit preferentially receives instructions related to the area. In addition, when the user is moving, the reception unit can also suggest optimal instructions based on the current location. Furthermore, when the user is in a specific location, the reception unit can preferentially receive instructions related to the location. As a result, by preferentially receiving highly relevant instructions based on the geographical location information of the user, appropriate instruction reception according to the user's situation is possible. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the geographical location information of the user to AI and preferentially receive highly relevant instructions.

[0043] The reception unit can analyze the user's social media activity and receive related instructions when receiving the instruction. The reception unit preferentially receives related instructions based on, for example, information shared by the user on social media. The reception unit can also suggest instructions related to the user's field of interest from the user's social media activity. Furthermore, the reception unit can also receive related instructions based on accounts the user follows on social media. In this way, by analyzing the user's social media activity, it is possible to preferentially receive highly relevant instructions. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's social media activity data into AI and receive related instructions.

[0044] At the time of selection, the selection unit can select the optimal service by referring to the past performance data of the generation AI service. For example, the selection unit selects the generation AI service with the highest success rate from the past performance data. The selection unit can also analyze the past performance data and select the optimal generation AI service for a specific task. Furthermore, the selection unit can also select a generation AI service that can provide stable results based on the past performance data. In this way, the optimal generation AI service can be selected by referring to the past performance data of the generation AI service. Some or all of the above-mentioned processing in the selection unit may be performed, for example, using AI or may be performed without using AI. For example, the selection unit can input the past performance data of the generation AI service into AI to select the optimal service.

[0045] The selection unit can apply different selection algorithms for each category of the generation AI service at the time of selection. For example, the selection unit applies a selection algorithm that emphasizes the quality of the text to the text generation AI service. The selection unit can also apply a selection algorithm that emphasizes the resolution and color of the image to the image generation AI service. Furthermore, the selection unit can apply a selection algorithm that emphasizes the naturalness and clarity of the voice to the voice generation AI service. In this way, by applying different selection algorithms to each category of the generation AI service, it is possible to select the optimal generation AI service for each category. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI or may be performed without using AI. For example, the selection unit can input different selection algorithms to the AI ​​for each category of the generation AI service to select the optimal service.

[0046] At the time of selection, the selection unit can select the optimal service based on the geographic distribution of the generation AI service. For example, the selection unit selects the generation AI service closest to the user's region. The selection unit can also select the optimal service by considering the generation AI services that are geographically distributed. Furthermore, the selection unit can also select the generation AI service that is highly rated in a specific region. In this way, by selecting the optimal service based on the geographic distribution of the generation AI service, it is possible to select the generation AI service that is optimal for the user's region. Some or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input geographic distribution data of the generation AI service into AI to select the optimal service.

[0047] The selection unit can improve the accuracy of the selection by referring to related literature of the generation AI service at the time of selection. The selection unit, for example, refers to the latest research papers on the generation AI service and selects the optimal service. The selection unit can also improve the accuracy of the selection by referring to literature describing the technical details of the generation AI service. Furthermore, the selection unit can also select the optimal service by referring to literature on the evaluation of the generation AI service. In this way, the accuracy of the selection can be improved by referring to related literature of the generation AI service. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI or may be performed without using AI. For example, the selection unit can input related literature of the generation AI service into the AI ​​to improve the accuracy of the selection.

[0048] When processing a prompt, the processing unit can select the optimal processing method by referring to past processing results of the generation AI service. For example, the processing unit selects the processing method with the highest success rate from the past processing results. The processing unit can also analyze the past processing results and select the optimal processing method for a specific task. Furthermore, the processing unit can also select a processing method that can provide stable results based on the past processing results. In this way, the optimal prompt processing method can be selected by referring to the past processing results of the generation AI service. Some or all of the above-mentioned processing in the processing unit may be performed, for example, using AI or may be performed without using AI. For example, the processing unit can input the past processing results of the generation AI service to the AI ​​and select the optimal processing method.

[0049] The processing unit can apply different processing algorithms to each category of the generation AI service when processing the prompt. For example, the processing unit applies a processing algorithm that emphasizes the quality of the text to the text generation AI service. The processing unit can also apply a processing algorithm that emphasizes the resolution and color of the image to the image generation AI service. Furthermore, the processing unit can also apply a processing algorithm that emphasizes the naturalness and clarity of the voice to the voice generation AI service. This allows optimal prompt processing for each category by applying different processing algorithms to each category of the generation AI service. Some or all of the above-mentioned processing in the processing unit may be performed, for example, using AI or may be performed without using AI. For example, the processing unit can input different processing algorithms to the AI ​​for each category of the generation AI service and select the optimal processing method.

[0050] The processing unit can select the optimal processing method based on the geographic distribution of the generating AI service when processing the prompt. The processing unit, for example, preferentially processes the generating AI service closest to the user's region. The processing unit can also select the optimal processing method in consideration of the generating AI service that is geographically distributed. Furthermore, the processing unit can also preferentially process the generating AI service that is highly evaluated in a specific region. This enables optimal prompt processing for the user's region by selecting the optimal processing method based on the geographic distribution of the generating AI service. Some or all of the above-mentioned processing in the processing unit may be performed, for example, using AI or may be performed without using AI. For example, the processing unit can input geographic distribution data of the generating AI service to the AI ​​and select the optimal processing method.

[0051] The processing unit can improve the accuracy of the processing when processing the prompt by referring to related literature of the generating AI service. The processing unit, for example, refers to the latest research papers on the generating AI service and selects the optimal processing method. The processing unit can also improve the accuracy of the processing by referring to literature describing the technical details of the generating AI service. Furthermore, the processing unit can also select the optimal processing method by referring to literature on the evaluation of the generating AI service. As a result, the accuracy of the prompt processing can be improved by referring to related literature of the generating AI service. Some or all of the above-mentioned processing in the processing unit may be performed, for example, using AI or may be performed without using AI. For example, the processing unit can input related literature of the generating AI service into the AI ​​to improve the accuracy of the processing.

[0052] When providing the generated result, the providing unit can select the optimal providing method by referring to the user's past usage history. For example, the providing unit preferentially selects a providing method that the user has used in the past. The providing unit can also prioritize providing in a specific format (text, image, etc.) from the user's past usage history. Furthermore, the providing unit can analyze the user's past usage history and select the most efficient providing method. In this way, the optimal providing method for the generated result can be selected by referring to the user's past usage history. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's past usage history into AI and select the optimal providing method.

[0053] The providing unit can perform filtering based on the user's current project or field of interest when providing the generation result. For example, the providing unit preferentially provides the generation result related to the project currently being carried out by the user. The providing unit can also filter and provide the related generation result based on the user's field of interest. Furthermore, the providing unit can also preferentially provide the generation result related to the field in which the user has shown interest in the past. Thereby, by filtering based on the user's current project or field of interest, it is possible to preferentially provide the highly relevant generation result. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's project information or field of interest into AI and perform filtering.

[0054] The providing unit can provide highly relevant results preferentially based on the geographical location information of the user when providing the generation results. For example, when the user is in a specific area, the providing unit can provide the generation results related to the area preferentially. In addition, when the user is moving, the providing unit can also suggest the optimal generation result based on the current location. Furthermore, when the user is in a specific location, the providing unit can also provide the generation results related to the location preferentially. As a result, by preferentially providing the highly relevant generation results based on the geographical location information of the user, it is possible to provide the appropriate generation results according to the user's situation. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the geographical location information of the user to AI and provide the highly relevant results preferentially.

[0055] The providing unit can analyze the user's social media activity and provide related results when providing the generated results. The providing unit can provide related generated results preferentially based on, for example, information shared by the user on social media. The providing unit can also suggest generated results related to the user's field of interest from the user's social media activity. Furthermore, the providing unit can provide related generated results based on accounts the user follows on social media. In this way, by analyzing the user's social media activity, it is possible to provide highly relevant generated results preferentially. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's social media activity data into AI and provide related results.

[0056] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0057] When accepting instructions from a user, the reception unit can analyze the user's past behavioral patterns and provide an optimal interface. For example, the reception unit can preferentially display input methods (text, voice, gestures, etc.) that the user has frequently used in the past. The reception unit can also present predicted instructions in advance based on instructions given by the user in a specific time period in the past. Furthermore, the reception unit can automatically select a specific generation AI service from the user's past behavioral patterns. This enables more efficient and personalized instruction acceptance by analyzing the user's past behavioral patterns.

[0058] The selection unit can take into consideration the progress of the user's current project when selecting a generating AI service. For example, the selection unit preferentially selects a generating AI service related to a project that the user is currently working on. The selection unit can also suggest a required generating AI service based on the progress of the user's project. Furthermore, the selection unit can dynamically change the selection criteria for the generating AI service according to the progress of the user's project. This makes it possible to select an optimal generating AI service based on the progress of the user's project.

[0059] When processing a prompt, the processing unit can select the optimal processing method by referring to the past performance data of the generation AI service. For example, the processing unit selects the processing method with the highest success rate from the past performance data. The processing unit can also analyze the past performance data and select the optimal processing method for a specific task. Furthermore, the processing unit can select a processing method that can provide stable results based on the past performance data. In this way, the optimal prompt processing method can be selected by referring to the past performance data of the generation AI service.

[0060] When providing the generation results, the providing unit can provide highly relevant results preferentially based on the geographical location information of the user. For example, when the user is in a specific area, the providing unit can provide generation results related to the area preferentially. In addition, when the user is moving, the providing unit can also suggest optimal generation results based on the current location. Furthermore, when the user is in a specific location, the providing unit can also provide generation results related to the location preferentially. This makes it possible to provide appropriate generation results according to the user's situation by preferentially providing highly relevant generation results based on the geographical location information of the user.

[0061] When providing the generated results, the providing unit can analyze the user's social media activity and provide related results. For example, based on information shared by the user on social media, the providing unit can provide related generated results preferentially. The providing unit can also suggest generated results related to the user's field of interest from the user's social media activity. Furthermore, the providing unit can provide related generated results based on accounts the user follows on social media. In this way, by analyzing the user's social media activity, it is possible to provide highly relevant generated results preferentially.

[0062] The process flow of the first embodiment will be briefly described below.

[0063] Step 1: The reception unit receives a user's instruction. The user's instruction includes text input, voice instruction, gesture, etc. For example, the user may input the instruction "create text" by text input, may give the instruction "create image" by voice, or may give an instruction by performing a specific gesture. Step 2: The selection unit centrally manages multiple generative AI services available on the market through API integration, and selects the optimal generative AI service based on the user's instructions. For example, if the user gives the instruction "generate text," the optimal one will be selected from multiple text generation AI services. The selection unit selects the optimal generative AI service using the evaluation criteria and algorithms of the generative AI services. Step 3: The processing unit processes the prompt using the selected generation AI service. The processing of the prompt may include natural language processing, image analysis, speech recognition, etc. For example, the selected sentence generation AI service processes the prompt and generates a sentence. Also, the selected image generation AI service may process the prompt and generate an image. Step 4: The providing unit provides the result generated by the processing unit to the user. The generated result includes text, images, audio, etc. For example, the generated text, image, and audio are provided to the user.

[0064] (Example 2) The system according to the embodiment of the present invention is a platform that aggregates and centrally manages multiple generative AI services. Since it is very laborious to select the optimal service from the countless generative AI services that are created every day, this platform centrally manages compatible generative AI services that exist on the market through API integration. A user can use the generative AI through the UI of this service, and the optimal generative AI is selected and the prompt is processed according to the user's instructions. For example, the user inputs an instruction to use the generative AI. This instruction includes specific generation content such as "text generation" or "image generation". Next, the platform centrally manages multiple generative AI services that exist on the market through API integration and selects the generative AI service that is optimal for the user's instructions. The selected generative AI service processes the prompt based on the user's instructions and provides the result to the user. For example, when the user inputs an instruction for "text generation", the platform selects the optimal one from multiple text generation AI services and processes the prompt. The generated text is provided to the user. Similarly, when the user inputs an instruction for "image generation", the platform selects the optimal one from multiple image generation AI services and processes the prompt. The generated image is provided to the user. In this way, users can use multiple generative AI services through a single UI, eliminating the need to select the most suitable generative AI service. In addition, by centrally managing generative AI services available on the market through API integration, users can always use the latest generative AI service. This allows the Fusion-AI system to select the most suitable generative AI service based on user instructions, process prompts, and provide the results.

[0065] The Fusion-AI system according to the embodiment includes a reception unit, a selection unit, a processing unit, and a provision unit. The reception unit receives a user's instruction. The user's instruction includes, for example, text input, voice instruction, gesture, and the like, but is not limited to such examples. For example, when the user inputs an instruction of "sentence generation" by text input, the reception unit receives this. The reception unit can also receive voice instructions. For example, when the user issues an instruction of "image generation" by voice, this is accepted. Furthermore, the reception unit can also accept an instruction using a gesture. For example, an instruction to use a specific generation AI service can be issued by a user performing a specific gesture. The selection unit centrally manages multiple generation AI services existing on the market through API cooperation, and selects the optimal generation AI service based on the user's instruction. For example, when the user issues an instruction of "sentence generation", the selection unit selects the optimal one from multiple sentence generation AI services. The selection unit can also select the optimal generation AI service using the selection criteria and algorithms of the generation AI service. For example, the selection unit selects the most suitable service based on the evaluation criteria and algorithms of the generation AI service. The processing unit causes the selected generation AI service to process the prompt. The processing of the prompt includes, for example, natural language processing, image analysis, and voice recognition, but is not limited to such examples. The processing unit causes, for example, the selected sentence generation AI service to process the prompt and generate a sentence. The processing unit can also cause the selected image generation AI service to process the prompt and generate an image. The providing unit provides the result generated by the processing unit to the user. The generated result includes, for example, text, image, voice, etc., but is not limited to such examples. The providing unit provides, for example, the generated sentence to the user. The providing unit can also provide the generated image to the user. Furthermore, the providing unit can also provide the generated voice to the user. As a result, the Fusion-AI system according to the embodiment can select an optimal generation AI service based on a user's instruction, process the prompt, and provide the result.

[0066] The reception unit receives user instructions. Examples of user instructions include, but are not limited to, text input, voice instructions, gestures, and the like. For example, when a user inputs an instruction such as "sentence generation" by text input, the reception unit receives this. The reception unit can also receive voice instructions. For example, when a user issues an instruction such as "image generation" by voice, the reception unit receives this. Furthermore, the reception unit can also receive instructions using gestures. For example, an instruction to use a specific generation AI service can be issued by a user performing a specific gesture. The reception unit is designed to integrally manage these various input means and to enhance user convenience. Specifically, in the case of text input, a user can input instructions using a keyboard or touch screen, and in the case of voice instructions, voice is recognized through a microphone, and the instruction content is analyzed using voice recognition technology. In the case of gesture input, the user's movement is detected using a camera or motion sensor, and the instruction content is interpreted using a gesture recognition algorithm. In this way, the reception unit enables the user to intuitively and quickly issue instructions in any situation. The reception unit also has the role of analyzing the contents of instructions after receiving the user's instructions and transferring them to the appropriate processing department. For example, if the instruction "create sentences" is entered through text input, the reception unit analyzes this instruction and transfers it to the selection unit. Similarly, in the case of voice instructions or gesture instructions, the reception unit analyzes the contents of the instructions and transfers them to the appropriate processing department. This allows the reception unit to efficiently receive a variety of user instructions and support the smooth operation of the entire system.

[0067] The selection unit centrally manages multiple generation AI services available on the market through API integration, and selects the optimal generation AI service based on the user's instructions. For example, when the user issues an instruction for "text generation," the selection unit selects the optimal one from multiple text generation AI services. The selection unit can also select the optimal generation AI service using the selection criteria and algorithms of the generation AI service. For example, the selection unit selects the most suitable service based on the evaluation criteria and algorithms of the generation AI service. The selection unit uses a complex algorithm to evaluate the performance and characteristics of each generation AI service and select the service that best suits the user's needs. Specifically, the selection unit selects the optimal service by considering the past performance data, user reviews, processing speed, and quality of the generation results of each generation AI service. For example, in the case of a text generation AI service, the evaluation criteria can be the naturalness of the generated text, the accuracy of grammar, and the understanding of the context. In the case of an image generation AI service, the evaluation criteria can be the resolution, reality, and color accuracy of the generated image. In addition, the selection unit can provide an individually optimized service by considering the user's past usage history and preferences. For example, if a particular user has previously used a particular generation AI service, that service can be selected preferentially. Furthermore, the selection unit can monitor the status of each generation AI service in real time and dynamically change the selection depending on the usage and load of the service. This allows the selection unit to always select the optimal generation AI service and provide the user with high-quality generation results.

[0068] The processing unit processes the prompt from the selected generation AI service. Examples of the processing of the prompt include, but are not limited to, natural language processing, image analysis, and voice recognition. The processing unit processes the prompt from the selected text generation AI service and generates a text. The processing unit can also process the prompt from the selected image generation AI service and generate an image. The processing unit is responsible for sending the prompt to the selected generation AI service and receiving the result. Specifically, the processing unit generates an appropriate prompt for the generation AI service based on the user's instructions and sends it to the service through the API. For example, in the case of text generation, if the user instructs the processing unit to "generate a blog article about travel," the processing unit analyzes the instruction and sends an appropriate prompt to the generation AI service. Similarly, in the case of image generation, the processing unit generates a prompt based on the user's instructions and sends it to the image generation AI service. The processing unit receives a response from the generation AI service, analyzes the result, and prepares to provide it to the user. For example, when a text generated from a text generation AI service is received, the processing unit analyzes the text and formats it as necessary. Similarly, when an image generated from an image generation AI service is received, the resolution and format of the image can be adjusted. Furthermore, the processing unit can evaluate the processing results of the generation AI service and send the prompt again if necessary. For example, if the generated text or image does not meet the user's expectations, the processing unit can generate a prompt again and send it to the generation AI service to obtain a more appropriate result. This allows the processing unit to effectively utilize the generation AI service based on the user's instructions and provide a high-quality generation result.

[0069] The providing unit provides the user with the results generated by the processing unit. The generated results include, for example, text, images, and audio, but are not limited to such examples. For example, the providing unit provides the user with the generated text. The providing unit can also provide the user with the generated image. Furthermore, the providing unit can also provide the user with the generated audio. The providing unit provides an interface for quickly and appropriately providing the generated results to the user. Specifically, the providing unit has a function for the user to view, download, and share the generated results. For example, the generated text is displayed in a text editor or viewer so that the user can view it, and can be downloaded or copied as necessary. The generated image is displayed in an image viewer so that the user can view it, and can be downloaded or shared. The generated audio is displayed in an audio player so that the user can play it, and can be downloaded or shared. The providing unit also has a function for customizing the format and display method of the generated results to improve the user's convenience. For example, the font and layout of the generated text can be changed, and the size and resolution of the generated image can be adjusted. The providing unit can also provide an API for linking the generated results with other applications and services. This allows the user to utilize the generated results in other tools and platforms. Furthermore, the providing unit also has a function for collecting user feedback and continuously improving the quality of the generated results and the method of providing them. For example, the performance of the entire system can be improved by the user providing an evaluation or comment on the generated results. This allows the providing unit to quickly and appropriately provide high-quality generated results to the user, thereby increasing user satisfaction.

[0070] The reception unit can receive the user's instruction as a specific generation content. The specific generation content includes, for example, a text theme, an image style, a voice tone, and the like, but is not limited to such examples. For example, when the user gives an instruction for "text generation", the reception unit can specifically receive the theme. In addition, when the user gives an instruction for "image generation", the reception unit can specifically receive the style. Furthermore, when the user gives an instruction for "voice generation", the reception unit can specifically receive the tone. By this, by receiving the user's instruction as a specific generation content, it becomes possible to select a more accurate generation AI service. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's instruction to AI and extract the specific generation content.

[0071] The selection unit can centrally manage multiple generation AI services available on the market through API cooperation and select a generation AI service based on a user's instruction. API cooperation includes, for example, the type of API to be used, the protocol of cooperation, and the like, but is not limited to such examples. For example, when a user gives an instruction of "sentence generation", the selection unit selects the optimal one from multiple sentence generation AI services. The selection unit can centrally manage multiple generation AI services available on the market through API cooperation and select the optimal generation AI service for the user's instruction. This makes it possible to centrally manage multiple generation AI services available on the market through API cooperation and select the optimal generation AI service for the user's instruction. Some or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input a user's instruction to an AI and select the optimal generation AI service.

[0072] The processing unit allows the selected generation AI service to process the prompt. The processing of the prompt includes, for example, natural language processing, image analysis, and voice recognition, but is not limited to such examples. The processing unit allows, for example, the selected sentence generation AI service to process the prompt and generate a sentence. The processing unit also allows the selected image generation AI service to process the prompt and generate an image. Furthermore, the processing unit also allows the selected voice generation AI service to process the prompt and generate a voice. As a result, the selected generation AI service processes the prompt, and a generation result based on the user's instruction can be provided. Some or all of the above-mentioned processing in the processing unit may be performed, for example, using AI, or may be performed without using AI. For example, the processing unit can input a prompt to AI and output a generation result.

[0073] The providing unit can provide the generated result to the user. The generated result includes, for example, text, image, voice, etc., but is not limited to such examples. The providing unit, for example, provides the generated sentence to the user. The providing unit can also provide the generated image to the user. Furthermore, the providing unit can also provide the generated voice to the user. Thereby, by providing the generated result to the user, the user can use the result of the generation AI service. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the generation result to AI and provide it to the user.

[0074] The selection unit can select a generation AI service using the selection criteria and algorithm of the generation AI service. The selection criteria and algorithm include, for example, evaluation criteria, types of algorithms, etc., but are not limited to such examples. The selection unit selects the most suitable service based on, for example, the evaluation criteria and algorithm of the generation AI service. As a result, by using the selection criteria and algorithm of the generation AI service, it is possible to select a generation AI service with higher accuracy. Some or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input the evaluation criteria and algorithm of the generation AI service to AI and select the optimal service.

[0075] The providing unit can provide the generated result in a text format or an image format. Examples of the text format and the image format include, but are not limited to, PDF, JPEG, PNG, and the like. For example, the providing unit provides the generated text in a PDF format. The providing unit can also provide the generated image in a JPEG format. Furthermore, the providing unit can also provide the generated audio in an MP3 format. As a result, the generated result is provided in a text format or an image format, so that the user can use the generated result in various formats. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the generated result to AI and provide it in a text format or an image format.

[0076] The reception unit can estimate the user's emotion and change the method of receiving instructions based on the estimated user's emotion. For example, when the user is stressed, the reception unit provides a simple interface and minimizes input procedures. In addition, when the user is relaxed, the reception unit can provide detailed input options and suggest a customizable input method. Furthermore, when the user is in a hurry, the reception unit can prioritize voice input and enable the user to input instructions quickly. This allows appropriate instruction reception according to the user's situation by adjusting the instruction reception method based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the AI ​​and adjust the interface based on the emotion.

[0077] The reception unit can analyze the user's past instruction history and select the optimal reception method. For example, the reception unit automatically displays instructions that the user frequently input in the past as candidates. The reception unit can also preferentially suggest input methods (such as voice and text) that the user used in the past. Furthermore, the reception unit can predict and suggest instructions to be used in a specific time period from the user's past instruction history. In this way, the optimal reception method can be provided to the user by analyzing the user's past instruction history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past instruction history into AI and select the optimal reception method.

[0078] The reception unit can perform filtering based on the user's current project and field of interest when receiving an instruction. For example, the reception unit preferentially receives instructions related to a project currently in progress by the user. The reception unit can also filter and receive related instructions based on the user's field of interest. Furthermore, the reception unit can also preferentially receive instructions related to fields in which the user has shown interest in the past. As a result, by filtering based on the user's current project and field of interest, it is possible to preferentially receive highly relevant instructions. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's project information and field of interest into AI and perform filtering.

[0079] The reception unit can estimate the user's emotion and determine the priority of instructions based on the estimated user's emotion. For example, when the user is stressed, the reception unit preferentially receives important instructions. In addition, when the user is relaxed, the reception unit can also receive instructions with normal priority. Furthermore, when the user is in a hurry, the reception unit can also receive urgent instructions with the highest priority. In this way, by determining the priority of instructions based on the user's emotion, important instructions can be preferentially received. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data into an AI and determine the priority.

[0080] The reception unit can preferentially receive highly relevant instructions based on the geographical location information of the user when receiving an instruction. For example, when the user is in a specific area, the reception unit preferentially receives instructions related to the area. In addition, when the user is moving, the reception unit can also suggest optimal instructions based on the current location. Furthermore, when the user is in a specific location, the reception unit can preferentially receive instructions related to the location. As a result, by preferentially receiving highly relevant instructions based on the geographical location information of the user, appropriate instruction reception according to the user's situation is possible. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the geographical location information of the user to AI and preferentially receive highly relevant instructions.

[0081] The reception unit can analyze the user's social media activity and receive related instructions when receiving the instruction. The reception unit preferentially receives related instructions based on, for example, information shared by the user on social media. The reception unit can also suggest instructions related to the user's field of interest from the user's social media activity. Furthermore, the reception unit can also receive related instructions based on accounts the user follows on social media. In this way, by analyzing the user's social media activity, it is possible to preferentially receive highly relevant instructions. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's social media activity data into AI and receive related instructions.

[0082] The selection unit can estimate the user's emotion and change the selection criteria of the generation AI service based on the estimated user's emotion. For example, when the user is relaxed, the selection unit selects a generation AI service with stable performance. In addition, when the user is in a hurry, the selection unit can also select a generation AI service that can quickly provide results. Furthermore, when the user is excited, the selection unit can also select a generation AI service that is visually stimulating. In this way, by adjusting the selection criteria of the generation AI service based on the user's emotion, it is possible to select an optimal generation AI service according to the user's situation. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the selection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the selection unit can input the user's emotion data into the AI ​​and adjust the selection criteria.

[0083] At the time of selection, the selection unit can select the optimal service by referring to the past performance data of the generation AI service. For example, the selection unit selects the generation AI service with the highest success rate from the past performance data. The selection unit can also analyze the past performance data and select the optimal generation AI service for a specific task. Furthermore, the selection unit can also select a generation AI service that can provide stable results based on the past performance data. In this way, the optimal generation AI service can be selected by referring to the past performance data of the generation AI service. Some or all of the above-mentioned processing in the selection unit may be performed, for example, using AI or may be performed without using AI. For example, the selection unit can input the past performance data of the generation AI service into AI to select the optimal service.

[0084] The selection unit can apply different selection algorithms for each category of the generation AI service at the time of selection. For example, the selection unit applies a selection algorithm that emphasizes the quality of the text to the text generation AI service. The selection unit can also apply a selection algorithm that emphasizes the resolution and color of the image to the image generation AI service. Furthermore, the selection unit can apply a selection algorithm that emphasizes the naturalness and clarity of the voice to the voice generation AI service. In this way, by applying different selection algorithms to each category of the generation AI service, it is possible to select the optimal generation AI service for each category. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI or may be performed without using AI. For example, the selection unit can input different selection algorithms to the AI ​​for each category of the generation AI service to select the optimal service.

[0085] The selection unit can estimate the user's emotion and change the selection order of the generation AI services based on the estimated user's emotion. For example, when the user is relaxed, the selection unit preferentially selects a generation AI service with stable performance. In addition, when the user is in a hurry, the selection unit can also preferentially select a generation AI service that can provide results quickly. Furthermore, when the user is excited, the selection unit can also preferentially select a visually stimulating generation AI service. In this way, by adjusting the selection order of the generation AI services based on the user's emotion, it is possible to preferentially select an optimal generation AI service according to the user's situation. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the selection unit can input the user's emotion data into the AI ​​and adjust the selection order.

[0086] At the time of selection, the selection unit can select the optimal service based on the geographic distribution of the generation AI service. For example, the selection unit selects the generation AI service closest to the user's region. The selection unit can also select the optimal service by considering the generation AI services that are geographically distributed. Furthermore, the selection unit can also select the generation AI service that is highly rated in a specific region. In this way, by selecting the optimal service based on the geographic distribution of the generation AI service, it is possible to select the generation AI service that is optimal for the user's region. Some or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input geographic distribution data of the generation AI service into AI to select the optimal service.

[0087] The selection unit can improve the accuracy of the selection by referring to related literature of the generation AI service at the time of selection. The selection unit, for example, refers to the latest research papers on the generation AI service and selects the optimal service. The selection unit can also improve the accuracy of the selection by referring to literature describing the technical details of the generation AI service. Furthermore, the selection unit can also select the optimal service by referring to literature on the evaluation of the generation AI service. In this way, the accuracy of the selection can be improved by referring to related literature of the generation AI service. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI or may be performed without using AI. For example, the selection unit can input related literature of the generation AI service into the AI ​​to improve the accuracy of the selection.

[0088] The processing unit can estimate the user's emotion and change the method of processing the prompt based on the estimated user's emotion. For example, the processing unit performs detailed prompt processing when the user is relaxed. Also, the processing unit can quickly process the prompt when the user is in a hurry. Furthermore, the processing unit can perform visually stimulating prompt processing when the user is excited. This allows for appropriate prompt processing according to the user's situation by adjusting the prompt processing method based on the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the processing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the processing unit can input the user's emotion data to the AI ​​and adjust the processing method.

[0089] When processing a prompt, the processing unit can select the optimal processing method by referring to past processing results of the generation AI service. For example, the processing unit selects the processing method with the highest success rate from the past processing results. The processing unit can also analyze the past processing results and select the optimal processing method for a specific task. Furthermore, the processing unit can also select a processing method that can provide stable results based on the past processing results. In this way, the optimal prompt processing method can be selected by referring to the past processing results of the generation AI service. Some or all of the above-mentioned processing in the processing unit may be performed, for example, using AI or may be performed without using AI. For example, the processing unit can input the past processing results of the generation AI service to the AI ​​and select the optimal processing method.

[0090] The processing unit can apply different processing algorithms to each category of the generation AI service when processing the prompt. For example, the processing unit applies a processing algorithm that emphasizes the quality of the text to the text generation AI service. The processing unit can also apply a processing algorithm that emphasizes the resolution and color of the image to the image generation AI service. Furthermore, the processing unit can also apply a processing algorithm that emphasizes the naturalness and clarity of the voice to the voice generation AI service. This allows optimal prompt processing for each category by applying different processing algorithms to each category of the generation AI service. Some or all of the above-mentioned processing in the processing unit may be performed, for example, using AI or may be performed without using AI. For example, the processing unit can input different processing algorithms to the AI ​​for each category of the generation AI service and select the optimal processing method.

[0091] The processing unit can estimate the user's emotion and change the processing order of the prompts based on the estimated user's emotion. For example, when the user is relaxed, the processing unit preferentially processes a generation AI service with stable performance. In addition, when the user is in a hurry, the processing unit can also preferentially process a generation AI service that can provide results quickly. Furthermore, when the user is excited, the processing unit can also preferentially process a visually stimulating generation AI service. This allows optimal prompt processing according to the user's situation by adjusting the processing order of the prompts based on the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the processing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the processing unit can input the user's emotion data to the AI ​​and adjust the processing order.

[0092] The processing unit can select the optimal processing method based on the geographic distribution of the generating AI service when processing the prompt. The processing unit, for example, preferentially processes the generating AI service closest to the user's region. The processing unit can also select the optimal processing method in consideration of the generating AI service that is geographically distributed. Furthermore, the processing unit can also preferentially process the generating AI service that is highly evaluated in a specific region. This enables optimal prompt processing for the user's region by selecting the optimal processing method based on the geographic distribution of the generating AI service. Some or all of the above-mentioned processing in the processing unit may be performed, for example, using AI or may be performed without using AI. For example, the processing unit can input geographic distribution data of the generating AI service to the AI ​​and select the optimal processing method.

[0093] The processing unit can improve the accuracy of the processing when processing the prompt by referring to related literature of the generating AI service. The processing unit, for example, refers to the latest research papers on the generating AI service and selects the optimal processing method. The processing unit can also improve the accuracy of the processing by referring to literature describing the technical details of the generating AI service. Furthermore, the processing unit can also select the optimal processing method by referring to literature on the evaluation of the generating AI service. As a result, the accuracy of the prompt processing can be improved by referring to related literature of the generating AI service. Some or all of the above-mentioned processing in the processing unit may be performed, for example, using AI or may be performed without using AI. For example, the processing unit can input related literature of the generating AI service into the AI ​​to improve the accuracy of the processing.

[0094] The providing unit can estimate the user's emotion and change the method of providing the generated result based on the estimated user's emotion. For example, when the user is relaxed, the providing unit provides a generated result including a detailed explanation. In addition, when the user is in a hurry, the providing unit can also provide a concise generated result. Furthermore, when the user is excited, the providing unit can also provide a visually stimulating generated result. This makes it possible to provide an appropriate generated result according to the user's situation by adjusting the method of providing the generated result based on the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the user's emotion data into the AI ​​and adjust the providing method.

[0095] When providing the generated result, the providing unit can select the optimal providing method by referring to the user's past usage history. For example, the providing unit preferentially selects a providing method that the user has used in the past. The providing unit can also prioritize providing in a specific format (text, image, etc.) from the user's past usage history. Furthermore, the providing unit can analyze the user's past usage history and select the most efficient providing method. In this way, the optimal providing method for the generated result can be selected by referring to the user's past usage history. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's past usage history into AI and select the optimal providing method.

[0096] The providing unit can perform filtering based on the user's current project or field of interest when providing the generation result. For example, the providing unit preferentially provides the generation result related to the project currently being carried out by the user. The providing unit can also filter and provide the related generation result based on the user's field of interest. Furthermore, the providing unit can also preferentially provide the generation result related to the field in which the user has shown interest in the past. Thereby, by filtering based on the user's current project or field of interest, it is possible to preferentially provide the highly relevant generation result. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's project information or field of interest into AI and perform filtering.

[0097] The providing unit can estimate the user's emotion and determine the priority of the generation results based on the estimated user's emotion. For example, when the user is feeling stressed, the providing unit provides important generation results with priority. In addition, when the user is relaxed, the providing unit can also provide urgent generation results with the highest priority when the user is in a hurry. In this way, by determining the priority of the generation results based on the user's emotion, important generation results can be provided with priority. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the user's emotion data into the AI ​​and determine the priority.

[0098] The providing unit can provide highly relevant results preferentially based on the geographical location information of the user when providing the generation results. For example, when the user is in a specific area, the providing unit can provide the generation results related to the area preferentially. In addition, when the user is moving, the providing unit can also suggest the optimal generation result based on the current location. Furthermore, when the user is in a specific location, the providing unit can also provide the generation results related to the location preferentially. As a result, by preferentially providing the highly relevant generation results based on the geographical location information of the user, it is possible to provide the appropriate generation results according to the user's situation. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the geographical location information of the user to AI and provide the highly relevant results preferentially.

[0099] The providing unit can analyze the user's social media activity and provide related results when providing the generated results. The providing unit can provide related generated results preferentially based on, for example, information shared by the user on social media. The providing unit can also suggest generated results related to the user's field of interest from the user's social media activity. Furthermore, the providing unit can provide related generated results based on accounts the user follows on social media. In this way, by analyzing the user's social media activity, it is possible to provide highly relevant generated results preferentially. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's social media activity data into AI and provide related results.

[0100] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0101] When accepting instructions from a user, the reception unit can analyze the user's past behavioral patterns and provide an optimal interface. For example, the reception unit can preferentially display input methods (text, voice, gestures, etc.) that the user has frequently used in the past. The reception unit can also present predicted instructions in advance based on instructions given by the user in a specific time period in the past. Furthermore, the reception unit can automatically select a specific generation AI service from the user's past behavioral patterns. This enables more efficient and personalized instruction acceptance by analyzing the user's past behavioral patterns.

[0102] The selection unit can take into consideration the progress of the user's current project when selecting a generating AI service. For example, the selection unit preferentially selects a generating AI service related to a project that the user is currently working on. The selection unit can also suggest a required generating AI service based on the progress of the user's project. Furthermore, the selection unit can dynamically change the selection criteria for the generating AI service according to the progress of the user's project. This makes it possible to select an optimal generating AI service based on the progress of the user's project.

[0103] When processing a prompt, the processing unit can select the optimal processing method by referring to the past performance data of the generation AI service. For example, the processing unit selects the processing method with the highest success rate from the past performance data. The processing unit can also analyze the past performance data and select the optimal processing method for a specific task. Furthermore, the processing unit can select a processing method that can provide stable results based on the past performance data. In this way, the optimal prompt processing method can be selected by referring to the past performance data of the generation AI service.

[0104] When providing the generation results, the providing unit can provide highly relevant results preferentially based on the geographical location information of the user. For example, when the user is in a specific area, the providing unit can provide generation results related to the area preferentially. In addition, when the user is moving, the providing unit can also suggest optimal generation results based on the current location. Furthermore, when the user is in a specific location, the providing unit can also provide generation results related to the location preferentially. This makes it possible to provide appropriate generation results according to the user's situation by preferentially providing highly relevant generation results based on the geographical location information of the user.

[0105] When providing the generated results, the providing unit can analyze the user's social media activity and provide related results. For example, based on information shared by the user on social media, the providing unit can provide related generated results preferentially. The providing unit can also suggest generated results related to the user's field of interest from the user's social media activity. Furthermore, the providing unit can provide related generated results based on accounts the user follows on social media. In this way, by analyzing the user's social media activity, it is possible to provide highly relevant generated results preferentially.

[0106] The reception unit can estimate the user's emotion and change the instruction reception method based on the estimated user's emotion. For example, when the user is stressed, a simple interface is provided to minimize input procedures. In addition, when the user is relaxed, the reception unit can provide detailed input options and suggest a customizable input method. Furthermore, when the user is in a hurry, the reception unit can prioritize voice input to enable the user to input instructions quickly. In this way, by adjusting the instruction reception method based on the user's emotion, it is possible to receive appropriate instructions according to the user's situation.

[0107] The selection unit can estimate the user's emotions and change the selection criteria of the generation AI service based on the estimated user's emotions. For example, when the user is relaxed, the selection unit selects a generation AI service with stable performance. In addition, when the user is in a hurry, the selection unit can also select a generation AI service that can provide results quickly. Furthermore, when the user is excited, the selection unit can also select a generation AI service that is visually stimulating. In this way, by adjusting the selection criteria of the generation AI service based on the user's emotions, it is possible to select the optimal generation AI service according to the user's situation.

[0108] The processing unit can estimate the user's emotion and change the prompt processing method based on the estimated user's emotion. For example, when the user is relaxed, detailed prompt processing is performed. Furthermore, when the user is in a hurry, the processing unit can also process prompts quickly. Furthermore, when the user is excited, the processing unit can also process visually stimulating prompt processing. In this way, by adjusting the prompt processing method based on the user's emotion, appropriate prompt processing according to the user's situation is possible.

[0109] The providing unit can estimate the user's emotion and change the method of providing the generated result based on the estimated user's emotion. For example, when the user is relaxed, the providing unit can provide a generated result including a detailed explanation. When the user is in a hurry, the providing unit can also provide a concise generated result. Furthermore, when the user is excited, the providing unit can also provide a visually stimulating generated result. In this way, by adjusting the method of providing the generated result based on the user's emotion, it is possible to provide an appropriate generated result according to the user's situation.

[0110] The providing unit can estimate the user's emotions and determine the priority order of the generation results based on the estimated user's emotions. For example, when the user is feeling stressed, important generation results are provided with priority. The providing unit can also provide generation results with normal priority order when the user is relaxed. Furthermore, the providing unit can provide urgent generation results with top priority order when the user is in a hurry. In this way, important generation results can be provided with priority order by determining the priority order of the generation results based on the user's emotions.

[0111] The process flow of the second embodiment will be briefly described below.

[0112] Step 1: The reception unit receives a user's instruction. The user's instruction includes text input, voice instruction, gesture, etc. For example, the user may input the instruction "create text" by text input, may give the instruction "create image" by voice, or may give an instruction by performing a specific gesture. Step 2: The selection unit centrally manages multiple generative AI services available on the market through API integration, and selects the optimal generative AI service based on the user's instructions. For example, if the user gives the instruction "generate text," the optimal one will be selected from multiple text generation AI services. The selection unit selects the optimal generative AI service using the evaluation criteria and algorithms of the generative AI services. Step 3: The processing unit processes the prompt using the selected generation AI service. The processing of the prompt may include natural language processing, image analysis, speech recognition, etc. For example, the selected sentence generation AI service processes the prompt and generates a sentence. Also, the selected image generation AI service may process the prompt and generate an image. Step 4: The providing unit provides the result generated by the processing unit to the user. The generated result includes text, images, audio, etc. For example, the generated text, image, and audio are provided to the user.

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0114] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0115] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0116] Each of the multiple elements including the above-mentioned reception unit, selection unit, processing unit, and provision unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the reception device 38 of the smart device 14 and receives text input and voice instructions from the user. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects the optimal generation AI service by API cooperation. The processing unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the selected generation AI service processes the prompt. The provision unit is realized, for example, by the output device 40 of the smart device 14 and provides the generated result to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0117] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0118] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0119] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0120] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0121] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0123] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0124] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0127] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0129] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0131] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0132] Each of the multiple elements including the above-mentioned reception unit, selection unit, processing unit, and provision unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the smart glasses 214 and receives a voice instruction from the user. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects the optimal generation AI service by API cooperation. The processing unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the selected generation AI service processes the prompt. The provision unit is realized, for example, by the speaker 240 of the smart glasses 214 and provides the generated result to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0133] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0134] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0135] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0136] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0137] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0140] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0141] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0142] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0143] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0144] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0145] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0146] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0147] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0148] Each of the multiple elements including the above-mentioned reception unit, selection unit, processing unit, and provision unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the headset type terminal 314 and receives a voice instruction from the user. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects the optimal generation AI service by API cooperation. The processing unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the selected generation AI service processes the prompt. The provision unit is realized, for example, by the display 343 of the headset type terminal 314 and provides the generated result to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0149] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0150] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0151] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0152] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0153] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0155] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0156] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0157] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0158] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0159] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0160] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0161] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0162] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0163] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0164] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0165] Each of the multiple elements including the above-mentioned reception unit, selection unit, processing unit, and provision unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the robot 414 and receives a voice instruction from the user. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects the optimal generation AI service by API cooperation. The processing unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the selected generation AI service processes the prompt. The provision unit is realized, for example, by the speaker 240 of the robot 414 and provides the generated result to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0166] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0167] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0168] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0169] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0170] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0171] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0172] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0173] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0174] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0175] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0176] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0177] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0178] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0179] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0180] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0181] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0182] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0183] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0184] (Appendix 1) A reception unit that receives an instruction from a user; A selection unit that selects a generation AI service based on the instruction received by the reception unit; a processor for processing the prompts by the selected generative AI service; a providing unit that provides a result generated by the processing unit to a user; A system characterized by: (Appendix 2) The reception unit is Accepts user instructions as specific content to be generated 2. The system of claim 1, (Appendix 3) The selection section is Through API integration, multiple generative AI services available on the market are centrally managed, and generative AI services are selected based on user instructions. 2. The system of claim 1, (Appendix 4) The processing unit includes: The selected generative AI service processes the prompt 2. The system of claim 1, (Appendix 5) The providing unit is Present the generated results to the user 2. The system of claim 1, (Appendix 6) The selection section is Select a generative AI service using generative AI service selection criteria and algorithms 2. The system of claim 1, (Appendix 7) The providing unit is Provide generated results in text and image formats 2. The system of claim 1, (Appendix 8) The reception department is To estimate a user's emotion and change a method of receiving an instruction based on the estimated user's emotion 2. The system of claim 1, (Appendix 9) The reception unit is Analyze the user's past instruction history and select the optimal reception method 2. The system of claim 1, (Appendix 10) The reception unit is Filter incoming orders based on the user's current projects and interests 2. The system of claim 1, (Appendix 11) The reception department is To estimate a user's emotion and determine a priority of an instruction based on the estimated user's emotion. 2. The system of claim 1, (Appendix 12) The reception unit is When receiving instructions, the system prioritizes receiving instructions that are more relevant based on the user's geographic location information. 2. The system of claim 1, (Appendix 13) The reception unit is Upon receiving an instruction, analyze the user's social media activity and receive relevant instructions. 2. The system of claim 1, (Appendix 14) The selection section is Estimate the user's emotions and change the selection criteria for generative AI services based on the estimated user emotions. 2. The system of claim 1, (Appendix 15) The selection unit is When selecting, the best service is selected by referencing the past performance data of the generative AI service. 2. The system of claim 1, (Appendix 16) The selection unit is During selection, different selection algorithms are applied for each category of generative AI services. 2. The system of claim 1, (Appendix 17) The selection section is Estimate user emotions and change the selection order of generative AI services based on the estimated user emotions 2. The system of claim 1, (Appendix 18) The selection unit is At the time of selection, the optimal service is selected based on the geographic distribution of the generative AI services. 2. The system of claim 1, (Appendix 19) The selection unit is When making a selection, the accuracy of the selection is improved by referring to related literature of the generative AI service. 2. The system of claim 1, (Appendix 20) The processing unit includes: Infer user sentiment and change how prompts are handled based on the inferred user sentiment 2. The system of claim 1, (Appendix 21) The processing unit includes: When processing a prompt, the optimal processing method is selected by referring to the past processing results of the generation AI service. 2. The system of claim 1, (Appendix 22) The processing unit includes: Apply different processing algorithms for each category of generative AI service when processing prompts 2. The system of claim 1, (Appendix 23) The processing unit includes: Infer user sentiment and change the order of prompt processing based on the inferred user sentiment 2. The system of claim 1, (Appendix 24) The processing unit includes: When processing a prompt, choose the best processing method based on the geographic distribution of the generating AI service 2. The system of claim 1, (Appendix 25) The processing unit includes: When processing prompts, the generative AI service will refer to relevant literature to improve the accuracy of the processing. 2. The system of claim 1, (Appendix 26) The provision department Inferring user emotion and changing the way in which generated results are provided based on the estimated user emotion 2. The system of claim 1, (Appendix 27) The providing unit is When providing the generated results, the optimal method of providing them is selected by referring to the user's past usage history. 2. The system of claim 1, (Appendix 28) The providing unit is Filter the generated results based on the user's current projects and interests 2. The system of claim 1, (Appendix 29) The provision department Estimate the user's emotions and prioritize the generated results based on the estimated user's emotions. 2. The system of claim 1, (Appendix 30) The providing unit is When providing generated results, the system prioritizes relevant results based on the user's geographic location. 2. The system of claim 1, (Appendix 31) The providing unit is When providing generated results, analyze your social media activity to provide you with relevant results 2. The system of claim 1, [Explanation of symbols]

[0185] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception unit that receives an instruction from a user; A selection unit that selects a generated AI service based on the instruction received by the reception unit; A processing unit that processes a prompt by the generated AI service selected by the selection unit; a providing unit that provides a result generated by the processing unit to a user. A system characterized by:

2. The reception unit is Accepts user instructions as specific content to be generated 2. The system of claim 1 .

3. The selection unit is Through API integration, multiple AI generation services available on the market are managed in a unified manner, and a generation AI service is selected based on user instructions.

2. The system of claim 1 .

4. The processing unit includes: The selected generating AI service processes the prompt.

2. The system of claim 1 .

5. The selection unit is Selecting a generating AI service using selection criteria and algorithms for the generating AI service 2. The system of claim 1 .

6. The providing unit is Provide generated results in text and image formats 2. The system of claim 1 .

7. The reception unit is To estimate a user's emotion and change a method of receiving an instruction based on the estimated user's emotion 2. The system of claim 1 .

Images