system

Abstract

The system according to the embodiment aims to systematize interactions with the generation AI and reduce the burden on the user. [Solution] A system according to an embodiment includes a sending unit, a receiving unit, and a re-requesting unit. The sending unit sends a request. The receiving unit receives a code generated based on the request sent by the sending unit. The re-requesting unit makes a request again if the code received by the receiving unit does not produce the desired result.

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 an instruction sentence related to a description of 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology had the problem that interacting with the generative AI placed a heavy burden on the user, and it took a long time to obtain the desired results.

[0005] The system according to the embodiment aims to systematize interactions with the generation AI and reduce the burden on the user. [Means for solving the problem]

[0006] The system according to the embodiment includes a transmitting unit, a receiving unit, and a re-requesting unit. The transmitting unit transmits a request. The receiving unit receives a code generated based on the request transmitted by the transmitting unit. The re-requesting unit transmits a request again if the code received by the receiving unit does not produce the desired result. [Effects of the Invention]

[0007] The system according to the embodiment systemizes the interaction with the generation AI, thereby reducing the burden on the user. [Brief explanation 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. [Figure 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. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 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. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 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 INVENTION

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

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

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single 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 coded 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, 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 symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and 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. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "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, RAM 30, and 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 (for example, 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., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with 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 CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. 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 process 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.

[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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 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 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. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A system according to an embodiment of the present invention addresses the problem of the generation AI often generating hallucinations for requests that are difficult to interpret, resulting in a long wait time for the desired results. This system aims to systematize the interaction (trial and error) with the generation AI, reducing the burden on the user. First, the user makes a request to the generation AI. The request is entered in natural language. Next, the system sends the request to the generation AI and receives the generated code. If the generated code does not produce the desired result, the system automatically requests the generation AI again and attempts to correct it. By repeating this process, the desired result can be achieved without any user intervention. For example, when a user makes a request to the generation AI, the system sends the request to the generation AI and receives the generated code. If the generated code does not produce the desired result, the system automatically requests the AI ​​again and attempts to correct it. This significantly reduces the time and effort required for users to interact with the generation AI. It also prevents the generation AI from generating erroneous information due to hallucinations, thereby obtaining accurate results. This reduces the burden on the user and streamlines interaction with the generation AI.

[0029] The system according to the embodiment includes a transmitting unit, a receiving unit, and a re-requesting unit. When a user makes a request to the generation AI, the transmitting unit transmits the request to the generation AI. For example, the transmitting unit can transmit the request content input by the user in natural language to the generation AI. The receiving unit receives the code generated by the generation AI. For example, the receiving unit can receive the code transmitted from the generation AI and analyze the code. The re-requesting unit makes a request again if the code received by the receiving unit does not produce the desired result. For example, the re-requesting unit can make a request to the generation AI again if the generated code contains an error or does not produce the expected output. This enables the system to reduce the burden on the user and streamline interactions with the generation AI.

[0030] The system includes a detection unit that detects hallucination in the generation AI. The detection unit has the function of detecting hallucination in code and information generated by the generation AI. For example, the detection unit can use an algorithm that determines whether the generated code contains information that is not based on facts. The detection unit can analyze the context and content of the code generated by the generation AI and detect information that is not factual or that does not fit the context. This allows the system to prevent the generation of erroneous information due to hallucination in the generation AI. For example, the detection unit can detect hallucination when the generated code does not meet certain conditions or does not match the expected output. This allows the system to detect hallucination in the generation AI and provide accurate information.

[0031] The system includes a correction unit that attempts to correct the generation AI. The correction unit has the function of attempting to correct the code and information generated by the generation AI. For example, if the generated code contains an error or does not generate the expected output, the correction unit can request the generation AI again. The correction unit can analyze the content of the code generated by the generation AI and make any necessary corrections. For example, the correction unit can correct part of the generated code and request the generation AI again. This allows the system to correct the results generated by the generation AI and obtain accurate results. For example, the correction unit can attempt to correct the generated code if it does not satisfy certain conditions or does not match the expected output. This allows the system to correct the results generated by the generation AI and provide accurate information.

[0032] The transmission unit can transmit the user's request to the generation AI. For example, the transmission unit can transmit the request content input by the user in natural language to the generation AI. The transmission unit can analyze the user's request content and transmit it to the generation AI in an appropriate format. For example, the transmission unit can convert the text input by the user into a format understandable by the generation AI and transmit it. This allows the system to accurately transmit the user's request to the generation AI. Some or all of the above-mentioned processing in the transmission unit may be performed using AI, for example, or may be performed without using AI. For example, the transmission unit can input the user's request content to the generation AI and have the generation AI analyze the request content.

[0033] The receiving unit can receive the code generated by the generation AI. For example, the receiving unit can receive a code sent from the generation AI and analyze the code. The receiving unit can analyze the content of the code generated by the generation AI and provide it to the user. For example, the receiving unit can determine whether the generated code contains an error and notify the user. This allows the system to accurately receive the code from the generation AI. Some or all of the above-mentioned processing in the receiving unit may be performed, for example, using AI or may be performed without using AI. For example, the receiving unit can input the code received from the generation AI into the generation AI and have the generation AI analyze the code.

[0034] The re-request unit can make a request again if the generated code does not produce the desired result. For example, if the generated code contains an error or does not produce the expected output, the re-request unit can make a request to the generation AI again. The re-request unit can analyze the contents of the code generated by the generation AI and make any necessary corrections. For example, the re-request unit can correct part of the generated code and make a request to the generation AI again. This allows the system to automatically make re-requests until the desired result is obtained. Some or all of the above-mentioned processing in the re-request unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the re-request unit can input the code received from the generation AI into the generation AI and have the generation AI execute the code corrections.

[0035] When transmitting a request, the transmission unit can select the optimal transmission timing by referring to past request history. The transmission unit can, for example, analyze the time periods in which the user made past requests and transmit the request during those time periods. The transmission unit can also select the timing with the highest success rate from the user's past request history and transmit the request. Furthermore, the transmission unit can optimize the request transmission interval based on the user's past request history. This allows the system to select the optimal transmission timing based on the past request history. Some or all of the above-described processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input past request history data into a generation AI and have the generation AI select the optimal transmission timing.

[0036] When sending a request, the sending unit can change the sending method depending on the complexity of the request content. For example, if the request content is simple, the sending unit can send it in a text-based format. In addition, if the request content is complex, the sending unit can send it by attaching a document containing a detailed explanation. Furthermore, if the request content is very complex, the sending unit can send it using a voice message or a video message. This allows the system to provide a sending method depending on the complexity of the request content. Some or all of the above-mentioned processing in the sending unit may be performed using AI, for example, or may be performed without using AI. For example, the sending unit can input complexity data of the request content to the generating AI and have the generating AI change the sending method.

[0037] When transmitting a request, the transmission unit can prioritize transmitting highly relevant requests based on the user's geographical location information. For example, when the user is in a specific area, the transmission unit can prioritize transmitting requests related to that area. Furthermore, when the user is traveling, the transmission unit can prioritize transmitting requests related to the user's destination. Furthermore, when the user is in a specific facility, the transmission unit can prioritize transmitting requests related to the facility. This allows the system to transmit requests based on the user's geographical location information. Some or all of the above-described processing in the transmission unit may be performed using, or without, AI. For example, the transmission unit can input the user's geographical location information data into a generation AI and cause the generation AI to select highly relevant requests.

[0038] When sending a request, the sending unit can analyze the user's social media activity and send a relevant request. For example, if the user posts about a specific topic on social media, the sending unit can send a request related to that topic. Also, if the user is participating in a specific event on social media, the sending unit can send a request related to the event. Furthermore, if the user belongs to a specific group on social media, the sending unit can send a request related to the group. This allows the system to send requests based on the user's social media activity. Some or all of the above-mentioned processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can input the user's social media activity data into a generation AI and cause the generation AI to select a relevant request.

[0039] At the time of reception, the receiving unit can select an appropriate reception method by referring to past reception history. For example, the receiving unit can select the optimal reception method based on reception methods used by the user in the past. The receiving unit can also select the most efficient reception method from the user's past reception history. Furthermore, the receiving unit can analyze the user's past reception history and select the reception method with the highest success rate. This allows the system to select the optimal reception method based on the past reception history. Some or all of the above-described processing in the receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the receiving unit can input past reception history data into a generation AI and have the generation AI select the optimal reception method.

[0040] The receiving unit can change the receiving method depending on the complexity of the code when receiving it. For example, in the case of a simple code, the receiving unit can receive it text-based. In the case of a complex code, the receiving unit can also receive it with a document containing a detailed explanation attached. Furthermore, in the case of a very complex code, the receiving unit can also receive it using a voice message or a video message. This allows the system to provide a receiving method depending on the complexity of the code. Some or all of the above-mentioned processing in the receiving unit may be performed using AI, for example, or may be performed without using AI. For example, the receiving unit can input code complexity data to the generating AI and have the generating AI change the receiving method.

[0041] Upon receiving the codes, the receiving unit can prioritize receiving codes that are highly relevant based on the user's geographical location information. For example, if the user is in a specific area, the receiving unit can prioritize receiving codes related to that area. Furthermore, if the user is traveling, the receiving unit can prioritize receiving codes related to the user's destination. Furthermore, if the user is in a specific facility, the receiving unit can prioritize receiving codes related to the facility. This allows the system to provide code reception based on the user's geographical location information. Some or all of the above-described processing in the receiving unit may be performed using, or without, AI. For example, the receiving unit can input the user's geographical location information data into a generation AI and cause the generation AI to select highly relevant codes.

[0042] Upon receiving the code, the receiving unit can analyze the user's social media activity and receive a relevant code. For example, if the user posts about a specific topic on social media, the receiving unit can receive a code related to that topic. Furthermore, if the user participates in a specific event on social media, the receiving unit can receive a code related to that event. Furthermore, if the user belongs to a specific group on social media, the receiving unit can receive a code related to that group. This allows the system to provide code reception based on the user's social media activity. Some or all of the above-described processing in the receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the receiving unit can input the user's social media activity data into a generation AI and cause the generation AI to select a relevant code.

[0043] When re-requesting, the re-request unit can select an appropriate re-request method by referring to past re-request history. For example, the re-request unit can select the optimal re-request method based on re-request methods used by the user in the past. The re-request unit can also select the most efficient re-request method from the user's past re-request history. Furthermore, the re-request unit can analyze the user's past re-request history and select the re-request method with the highest success rate. This allows the system to select the optimal re-request method based on the past re-request history. Some or all of the above-described processing in the re-request unit may be performed using, for example, AI, or may be performed without using AI. For example, the re-request unit can input past re-request history data into the generation AI and cause the generation AI to select the optimal re-request method.

[0044] When making a re-request, the re-request unit can change the re-request method depending on the complexity of the request content. For example, if the request content is simple, the re-request unit can make a text-based re-request. In addition, if the request content is complex, the re-request unit can make a re-request by attaching a document containing a detailed explanation. Furthermore, if the request content is very complex, the re-request unit can make a re-request using a voice message or a video message. This allows the system to provide a re-request method depending on the complexity of the request content. Some or all of the above-mentioned processing in the re-request unit may be performed using, for example, AI, or may be performed without using AI. For example, the re-request unit can input complexity data of the request content to the generation AI and cause the generation AI to change the re-request method.

[0045] When making a re-request, the re-request unit can prioritize highly relevant re-requests based on the user's geographical location information. For example, if the user is in a specific area, the re-request unit can prioritize re-requests related to that area. Furthermore, if the user is traveling, the re-request unit can prioritize re-requests related to the user's destination. Furthermore, if the user is in a specific facility, the re-request unit can prioritize re-requests related to the facility. This allows the system to provide re-requests based on the user's geographical location information. Some or all of the above-described processing in the re-request unit may be performed using, for example, AI, or may be performed without using AI. For example, the re-request unit can input the user's geographical location information data into the generation AI and cause the generation AI to select highly relevant re-requests.

[0046] At the time of re-request, the re-request unit can analyze the user's social media activity and make a related re-request. For example, if the user posts about a specific topic on social media, the re-request unit can make a re-request related to that topic. Also, if the user is participating in a specific event on social media, the re-request unit can make a re-request related to that event. Furthermore, if the user belongs to a specific group on social media, the re-request unit can make a re-request related to that group. This allows the system to provide a re-request based on the user's social media activity. Some or all of the above-described processing in the re-request unit may be performed using, for example, AI, or may be performed without using AI. For example, the re-request unit can input the user's social media activity data into the generation AI and cause the generation AI to select a related re-request.

[0047] When detecting hallucination, the detection unit can select an appropriate detection method by referring to past detection history. For example, the detection unit can select the optimal detection method based on detection methods used by the user in the past. The detection unit can also select the most efficient detection method from the user's past detection history. Furthermore, the detection unit can analyze the user's past detection history and select the detection method with the highest success rate. This allows the system to select the optimal hallucination detection method based on the past detection history. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input past detection history data into the generation AI and have the generation AI select the optimal detection method.

[0048] When detecting hallucinations, the detection unit can prioritize highly relevant detections based on the user's geographical location information. For example, if the user is in a specific area, the detection unit can prioritize detection of hallucinations related to that area. Furthermore, if the user is traveling, the detection unit can prioritize detection of hallucinations related to the user's destination. Furthermore, if the user is in a specific facility, the detection unit can prioritize detection of hallucinations related to that facility. This allows the system to provide hallucination detection based on the user's geographical location information. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the user's geographical location information data into the generation AI and cause the generation AI to detect highly relevant hallucinations.

[0049] When making corrections, the correction unit can select an appropriate correction method by referring to past correction history. For example, the correction unit can select the optimal correction method based on correction methods used by the user in the past. The correction unit can also select the most efficient correction method from the user's past correction history. Furthermore, the correction unit can analyze the user's past correction history and select the correction method with the highest success rate. This allows the system to select the optimal correction method based on the past correction history. Some or all of the above-mentioned processing in the correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the correction unit can input past correction history data into a generation AI and have the generation AI select the optimal correction method.

[0050] When making corrections, the correction unit can prioritize highly relevant corrections based on the user's geographical location information. For example, if the user is in a specific area, the correction unit can prioritize corrections related to that area. Furthermore, if the user is traveling, the correction unit can prioritize corrections related to the user's destination. Furthermore, if the user is in a specific facility, the correction unit can prioritize corrections related to the facility. This allows the system to provide corrections based on the user's geographical location information. Some or all of the above-described processing in the correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the correction unit can input the user's geographical location information data into the generation AI and cause the generation AI to select highly relevant corrections.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The system may include an analysis unit that analyzes the user's request. The analysis unit can analyze the request in natural language entered by the user and perform preprocessing to send it to the generation AI in an appropriate format. For example, the analysis unit can extract keywords from the request and convert it into a format that is easy for the generation AI to understand. The analysis unit can also understand the context of the request and generate appropriate instructions for the generation AI. Furthermore, the analysis unit can clarify ambiguous parts of the request and send specific instructions to the generation AI. This allows the system to more accurately convey the user's request to the generation AI.

[0053] The system can be equipped with a prevention unit for preventing hallucination in the generation AI. The prevention unit can take measures in advance to prevent the generation AI from generating hallucination. For example, the prevention unit can provide learning data to the generation AI in advance to suppress the occurrence of hallucination. The prevention unit can also monitor the output of the generation AI in real time and issue a warning if signs of hallucination are detected. Furthermore, the prevention unit can optimize the generation AI's algorithm to minimize the occurrence of hallucination. This allows the system to prevent hallucination in the generation AI before it occurs.

[0054] The system can include a support unit that supports the generation AI in correcting code and information generated by the generation AI. The support unit can provide support when correcting code and information generated by the generation AI. For example, the support unit can identify errors in the generated code and suggest correction methods. The support unit can also evaluate the quality of the generated code and indicate areas for improvement. Furthermore, the support unit can test the code generated by the generation AI to confirm whether the corrections were made correctly. This allows the system to streamline the generation AI's correction work and obtain accurate results.

[0055] The system may include a storage unit that stores user requests. The storage unit can store requests made by the user to the generation AI so that they can be referenced later. For example, the storage unit can store requests made by the user in chronological order so that they can be searched as needed. The storage unit can also store requests made by the user in association with their results so that they can be compared later. Furthermore, the storage unit can analyze the history of requests made by the user and refer to it for the next request. This allows the system to efficiently manage and reuse user requests.

[0056] The system can include an evaluation unit that evaluates the output of the generative AI. The evaluation unit can evaluate the quality of the code or information generated by the generative AI and provide feedback to the user. For example, the evaluation unit can evaluate the accuracy and efficiency of the generated code and assign a score. The evaluation unit can also evaluate the readability and maintainability of the generated code and indicate areas for improvement. Furthermore, the evaluation unit can evaluate the execution results of the generated code and confirm whether they match the expected output. This allows the system to objectively evaluate the output of the generative AI and provide useful feedback to the user.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: When a user makes a request to the generation AI, the transmission unit transmits the request to the generation AI. For example, the transmission unit can transmit the request content entered by the user in natural language to the generation AI. Step 2: The receiving unit receives the code generated by the generating AI. For example, the receiving unit can receive the code sent from the generating AI and analyze the code. Step 3: The re-request unit resubmits a request if the code received by the receiving unit does not produce the desired result. For example, the re-request unit can resubmit a request to the generating AI if the generated code contains an error or does not produce the expected output.

[0059] (Example 2) A system according to an embodiment of the present invention addresses the problem of the generation AI often generating hallucinations for requests that are difficult to interpret, resulting in a long wait time for the desired results. This system aims to systematize the interaction (trial and error) with the generation AI, reducing the burden on the user. First, the user makes a request to the generation AI. The request is entered in natural language. Next, the system sends the request to the generation AI and receives the generated code. If the generated code does not produce the desired result, the system automatically requests the generation AI again and attempts to correct it. By repeating this process, the desired result can be achieved without any user intervention. For example, when a user makes a request to the generation AI, the system sends the request to the generation AI and receives the generated code. If the generated code does not produce the desired result, the system automatically requests the AI ​​again and attempts to correct it. This significantly reduces the time and effort required for users to interact with the generation AI. It also prevents the generation AI from generating erroneous information due to hallucinations, thereby obtaining accurate results. This reduces the burden on the user and streamlines interaction with the generation AI.

[0060] The system according to the embodiment includes a transmitting unit, a receiving unit, and a re-requesting unit. When a user makes a request to the generation AI, the transmitting unit transmits the request to the generation AI. For example, the transmitting unit can transmit the request content input by the user in natural language to the generation AI. The receiving unit receives the code generated by the generation AI. For example, the receiving unit can receive the code transmitted from the generation AI and analyze the code. The re-requesting unit makes a request again if the code received by the receiving unit does not produce the desired result. For example, the re-requesting unit can make a request to the generation AI again if the generated code contains an error or does not produce the expected output. This enables the system to reduce the burden on the user and streamline interactions with the generation AI.

[0061] The system includes a detection unit that detects hallucination in the generation AI. The detection unit has the function of detecting hallucination in code and information generated by the generation AI. For example, the detection unit can use an algorithm that determines whether the generated code contains information that is not based on facts. The detection unit can analyze the context and content of the code generated by the generation AI and detect information that is not factual or that does not fit the context. This allows the system to prevent the generation of erroneous information due to hallucination in the generation AI. For example, the detection unit can detect hallucination when the generated code does not meet certain conditions or does not match the expected output. This allows the system to detect hallucination in the generation AI and provide accurate information.

[0062] The system includes a correction unit that attempts to correct the generation AI. The correction unit has the function of attempting to correct the code and information generated by the generation AI. For example, if the generated code contains an error or does not generate the expected output, the correction unit can request the generation AI again. The correction unit can analyze the content of the code generated by the generation AI and make any necessary corrections. For example, the correction unit can correct part of the generated code and request the generation AI again. This allows the system to correct the results generated by the generation AI and obtain accurate results. For example, the correction unit can attempt to correct the generated code if it does not satisfy certain conditions or does not match the expected output. This allows the system to correct the results generated by the generation AI and provide accurate information.

[0063] The transmission unit can transmit the user's request to the generation AI. For example, the transmission unit can transmit the request content input by the user in natural language to the generation AI. The transmission unit can analyze the user's request content and transmit it to the generation AI in an appropriate format. For example, the transmission unit can convert the text input by the user into a format understandable by the generation AI and transmit it. This allows the system to accurately transmit the user's request to the generation AI. Some or all of the above-mentioned processing in the transmission unit may be performed using AI, for example, or may be performed without using AI. For example, the transmission unit can input the user's request content to the generation AI and have the generation AI analyze the request content.

[0064] The receiving unit can receive the code generated by the generation AI. For example, the receiving unit can receive a code sent from the generation AI and analyze the code. The receiving unit can analyze the content of the code generated by the generation AI and provide it to the user. For example, the receiving unit can determine whether the generated code contains an error and notify the user. This allows the system to accurately receive the code from the generation AI. Some or all of the above-mentioned processing in the receiving unit may be performed, for example, using AI or may be performed without using AI. For example, the receiving unit can input the code received from the generation AI into the generation AI and have the generation AI analyze the code.

[0065] The re-request unit can make a request again if the generated code does not produce the desired result. For example, if the generated code contains an error or does not produce the expected output, the re-request unit can make a request to the generation AI again. The re-request unit can analyze the contents of the code generated by the generation AI and make any necessary corrections. For example, the re-request unit can correct part of the generated code and make a request to the generation AI again. This allows the system to automatically make re-requests until the desired result is obtained. Some or all of the above-mentioned processing in the re-request unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the re-request unit can input the code received from the generation AI into the generation AI and have the generation AI execute the code corrections.

[0066] The transmission unit can estimate the user's emotions and adjust the way the request is expressed based on the estimated user's emotions. For example, if the user is feeling stressed, the transmission unit can transmit concise and clear request content to the generation AI. Furthermore, if the user is relaxed, the transmission unit can transmit detailed request content to the generation AI. Furthermore, if the user is in a hurry, the transmission unit can simplify the request content and transmit it to the generation AI so that it can be processed quickly. This allows the system to provide a way to express the request content according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the transmission unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the transmission unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the way the request is expressed.

[0067] When transmitting a request, the transmission unit can select the optimal transmission timing by referring to past request history. The transmission unit can, for example, analyze the time periods in which the user made past requests and transmit the request during those time periods. The transmission unit can also select the timing with the highest success rate from the user's past request history and transmit the request. Furthermore, the transmission unit can optimize the request transmission interval based on the user's past request history. This allows the system to select the optimal transmission timing based on the past request history. Some or all of the above-described processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input past request history data into a generation AI and have the generation AI select the optimal transmission timing.

[0068] When sending a request, the sending unit can change the sending method depending on the complexity of the request content. For example, if the request content is simple, the sending unit can send it in a text-based format. In addition, if the request content is complex, the sending unit can send it by attaching a document containing a detailed explanation. Furthermore, if the request content is very complex, the sending unit can send it using a voice message or a video message. This allows the system to provide a sending method depending on the complexity of the request content. Some or all of the above-mentioned processing in the sending unit may be performed using AI, for example, or may be performed without using AI. For example, the sending unit can input complexity data of the request content to the generating AI and have the generating AI change the sending method.

[0069] The transmission unit can estimate the user's emotions and determine the priority of requests based on the estimated user emotions. For example, if the user is feeling stressed, the transmission unit can set the priority of requests to high. If the user is relaxed, the transmission unit can also set the priority of requests to normal. If the user is in a hurry, the transmission unit can also set the priority of requests to highest. This allows the system to provide priority of requests according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the transmission unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the transmission unit can input the user's emotion data into the generation AI and have the generation AI determine the priority of requests.

[0070] When transmitting a request, the transmission unit can prioritize transmitting highly relevant requests based on the user's geographical location information. For example, when the user is in a specific area, the transmission unit can prioritize transmitting requests related to that area. Furthermore, when the user is traveling, the transmission unit can prioritize transmitting requests related to the user's destination. Furthermore, when the user is in a specific facility, the transmission unit can prioritize transmitting requests related to the facility. This allows the system to transmit requests based on the user's geographical location information. Some or all of the above-described processing in the transmission unit may be performed using, or without, AI. For example, the transmission unit can input the user's geographical location information data into a generation AI and cause the generation AI to select highly relevant requests.

[0071] When sending a request, the sending unit can analyze the user's social media activity and send a relevant request. For example, if the user posts about a specific topic on social media, the sending unit can send a request related to that topic. Also, if the user is participating in a specific event on social media, the sending unit can send a request related to the event. Furthermore, if the user belongs to a specific group on social media, the sending unit can send a request related to the group. This allows the system to send requests based on the user's social media activity. Some or all of the above-mentioned processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can input the user's social media activity data into a generation AI and cause the generation AI to select a relevant request.

[0072] The receiving unit can estimate the user's emotion and adjust the display method of the received code based on the estimated user emotion. For example, if the user is feeling stressed, the receiving unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the receiving unit can provide a display method including detailed information. Furthermore, if the user is in a hurry, the receiving unit can provide a display method that focuses on the main points. This allows the system to provide a code display method that corresponds to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the receiving unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the receiving unit can input the user's emotion data into the generation AI and have the generation AI adjust the display method.

[0073] At the time of reception, the receiving unit can select an appropriate reception method by referring to past reception history. For example, the receiving unit can select the optimal reception method based on reception methods used by the user in the past. The receiving unit can also select the most efficient reception method from the user's past reception history. Furthermore, the receiving unit can analyze the user's past reception history and select the reception method with the highest success rate. This allows the system to select the optimal reception method based on the past reception history. Some or all of the above-described processing in the receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the receiving unit can input past reception history data into a generation AI and have the generation AI select the optimal reception method.

[0074] The receiving unit can change the receiving method depending on the complexity of the code when receiving it. For example, in the case of a simple code, the receiving unit can receive it text-based. In the case of a complex code, the receiving unit can also receive it with a document containing a detailed explanation attached. Furthermore, in the case of a very complex code, the receiving unit can also receive it using a voice message or a video message. This allows the system to provide a receiving method depending on the complexity of the code. Some or all of the above-mentioned processing in the receiving unit may be performed using AI, for example, or may be performed without using AI. For example, the receiving unit can input code complexity data to the generating AI and have the generating AI change the receiving method.

[0075] The receiving unit can estimate the user's emotions and determine the priority of received codes based on the estimated user emotions. For example, if the user is feeling stressed, the receiving unit can set the priority of the received code to high. Furthermore, if the user is relaxed, the receiving unit can set the priority of the received code to normal. Furthermore, if the user is in a hurry, the receiving unit can set the priority of the received code to highest. This allows the system to provide code priorities according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the receiving unit can be performed using, for example, an AI, or without an AI. For example, the receiving unit can input the user's emotion data into the generation AI and have the generation AI determine the priority.

[0076] Upon receiving the codes, the receiving unit can prioritize receiving codes that are highly relevant based on the user's geographical location information. For example, if the user is in a specific area, the receiving unit can prioritize receiving codes related to that area. Furthermore, if the user is traveling, the receiving unit can prioritize receiving codes related to the user's destination. Furthermore, if the user is in a specific facility, the receiving unit can prioritize receiving codes related to the facility. This allows the system to provide code reception based on the user's geographical location information. Some or all of the above-described processing in the receiving unit may be performed using, or without, AI. For example, the receiving unit can input the user's geographical location information data into a generation AI and cause the generation AI to select highly relevant codes.

[0077] Upon receiving the code, the receiving unit can analyze the user's social media activity and receive a relevant code. For example, if the user posts about a specific topic on social media, the receiving unit can receive a code related to that topic. Furthermore, if the user participates in a specific event on social media, the receiving unit can receive a code related to that event. Furthermore, if the user belongs to a specific group on social media, the receiving unit can receive a code related to that group. This allows the system to provide code reception based on the user's social media activity. Some or all of the above-described processing in the receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the receiving unit can input the user's social media activity data into a generation AI and cause the generation AI to select a relevant code.

[0078] The re-request unit can estimate the user's emotions and adjust the timing of the re-request based on the estimated user emotions. For example, if the user is feeling stressed, the re-request unit can quickly make a re-request. Furthermore, if the user is relaxed, the re-request unit can also make a re-request at a normal timing. Furthermore, if the user is in a hurry, the re-request unit can also make a re-request with top priority. This allows the system to provide the timing of the re-request according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the re-request unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the re-request unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the timing of the re-request.

[0079] When re-requesting, the re-request unit can select an appropriate re-request method by referring to past re-request history. For example, the re-request unit can select the optimal re-request method based on re-request methods used by the user in the past. The re-request unit can also select the most efficient re-request method from the user's past re-request history. Furthermore, the re-request unit can analyze the user's past re-request history and select the re-request method with the highest success rate. This allows the system to select the optimal re-request method based on the past re-request history. Some or all of the above-described processing in the re-request unit may be performed using, for example, AI, or may be performed without using AI. For example, the re-request unit can input past re-request history data into the generation AI and cause the generation AI to select the optimal re-request method.

[0080] When making a re-request, the re-request unit can change the re-request method depending on the complexity of the request content. For example, if the request content is simple, the re-request unit can make a text-based re-request. In addition, if the request content is complex, the re-request unit can make a re-request by attaching a document containing a detailed explanation. Furthermore, if the request content is very complex, the re-request unit can make a re-request using a voice message or a video message. This allows the system to provide a re-request method depending on the complexity of the request content. Some or all of the above-mentioned processing in the re-request unit may be performed using, for example, AI, or may be performed without using AI. For example, the re-request unit can input complexity data of the request content to the generation AI and cause the generation AI to change the re-request method.

[0081] The re-request unit can estimate the user's emotions and determine the priority of re-requests based on the estimated user emotions. For example, if the user is feeling stressed, the re-request unit can set the priority of re-requests to high. Furthermore, if the user is relaxed, the re-request unit can also set the priority of re-requests to normal. Furthermore, if the user is in a hurry, the re-request unit can also set the priority of re-requests to highest. This allows the system to provide a priority of re-requests according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the re-request unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the re-request unit can input the user's emotion data into the generation AI and have the generation AI determine the priority of re-requests.

[0082] When making a re-request, the re-request unit can prioritize highly relevant re-requests based on the user's geographical location information. For example, if the user is in a specific area, the re-request unit can prioritize re-requests related to that area. Furthermore, if the user is traveling, the re-request unit can prioritize re-requests related to the user's destination. Furthermore, if the user is in a specific facility, the re-request unit can prioritize re-requests related to the facility. This allows the system to provide re-requests based on the user's geographical location information. Some or all of the above-described processing in the re-request unit may be performed using, for example, AI, or may be performed without using AI. For example, the re-request unit can input the user's geographical location information data into the generation AI and cause the generation AI to select highly relevant re-requests.

[0083] At the time of re-request, the re-request unit can analyze the user's social media activity and make a related re-request. For example, if the user posts about a specific topic on social media, the re-request unit can make a re-request related to that topic. Also, if the user is participating in a specific event on social media, the re-request unit can make a re-request related to that event. Furthermore, if the user belongs to a specific group on social media, the re-request unit can make a re-request related to that group. This allows the system to provide a re-request based on the user's social media activity. Some or all of the above-described processing in the re-request unit may be performed using, for example, AI, or may be performed without using AI. For example, the re-request unit can input the user's social media activity data into the generation AI and cause the generation AI to select a related re-request.

[0084] The detection unit can estimate the user's emotion and adjust the hallucination detection method based on the estimated user emotion. For example, if the user is stressed, the detection unit can adopt a quick hallucination detection method. Furthermore, if the user is relaxed, the detection unit can adopt a detailed detection method. Furthermore, if the user is in a hurry, the detection unit can adopt a simplified detection method. This allows the system to provide a hallucination detection method that corresponds to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the detection unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the detection unit can input the user's emotion data into the generation AI and have the generation AI adjust the hallucination detection method.

[0085] When detecting hallucination, the detection unit can select an appropriate detection method by referring to past detection history. For example, the detection unit can select the optimal detection method based on detection methods used by the user in the past. The detection unit can also select the most efficient detection method from the user's past detection history. Furthermore, the detection unit can analyze the user's past detection history and select the detection method with the highest success rate. This allows the system to select the optimal hallucination detection method based on the past detection history. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input past detection history data into the generation AI and have the generation AI select the optimal detection method.

[0086] The detection unit can estimate the user's emotion and determine the hallucination detection priority based on the estimated user's emotion. For example, if the user is feeling stressed, the detection unit can set the hallucination detection priority to high. Furthermore, if the user is relaxed, the detection unit can also set the hallucination detection priority to normal. Furthermore, if the user is in a hurry, the detection unit can also set the hallucination detection priority to highest priority. This allows the system to provide hallucination detection priority according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the detection unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the detection unit can input the user's emotion data into the generation AI and have the generation AI determine the hallucination detection priority.

[0087] When detecting hallucinations, the detection unit can prioritize highly relevant detections based on the user's geographical location information. For example, if the user is in a specific area, the detection unit can prioritize detection of hallucinations related to that area. Furthermore, if the user is traveling, the detection unit can prioritize detection of hallucinations related to the user's destination. Furthermore, if the user is in a specific facility, the detection unit can prioritize detection of hallucinations related to that facility. This allows the system to provide hallucination detection based on the user's geographical location information. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the user's geographical location information data into the generation AI and cause the generation AI to detect highly relevant hallucinations.

[0088] The correction unit can estimate the user's emotion and adjust the correction method based on the estimated user's emotion. For example, the correction unit can adopt a quick correction method when the user is stressed. The correction unit can also adopt a detailed correction method when the user is relaxed. Furthermore, the correction unit can also adopt a simplified correction method when the user is in a hurry. This allows the system to provide a correction method that corresponds to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the correction unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the correction unit can input the user's emotion data into the generation AI and have the generation AI adjust the correction method.

[0089] When making corrections, the correction unit can select an appropriate correction method by referring to past correction history. For example, the correction unit can select the optimal correction method based on correction methods used by the user in the past. The correction unit can also select the most efficient correction method from the user's past correction history. Furthermore, the correction unit can analyze the user's past correction history and select the correction method with the highest success rate. This allows the system to select the optimal correction method based on the past correction history. Some or all of the above-mentioned processing in the correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the correction unit can input past correction history data into a generation AI and have the generation AI select the optimal correction method.

[0090] The correction unit can estimate the user's emotions and determine the priority of corrections based on the estimated user emotions. For example, if the user is feeling stressed, the correction unit can set the priority of corrections to high. Furthermore, if the user is relaxed, the correction unit can set the priority of corrections to normal. Furthermore, if the user is in a hurry, the correction unit can set the priority of corrections to highest. This allows the system to provide a priority of corrections according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the correction unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the correction unit can input the user's emotion data into the generation AI and have the generation AI determine the priority of corrections.

[0091] When making corrections, the correction unit can prioritize highly relevant corrections based on the user's geographical location information. For example, if the user is in a specific area, the correction unit can prioritize corrections related to that area. Furthermore, if the user is traveling, the correction unit can prioritize corrections related to the user's destination. Furthermore, if the user is in a specific facility, the correction unit can prioritize corrections related to the facility. This allows the system to provide corrections based on the user's geographical location information. Some or all of the above-described processing in the correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the correction unit can input the user's geographical location information data into the generation AI and cause the generation AI to select highly relevant corrections. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned transmitting unit, receiving unit, re-requesting unit, detecting unit, and correcting unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the transmitting unit is realized by the control unit 46A of the smart device 14 and transmits the request content entered by the user in natural language to the generation AI. The receiving unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and receives and analyzes the code transmitted from the generation AI. The re-requesting unit is realized, for example, by the control unit 46A of the smart device 14 and makes a re-request if the generated code does not produce the desired result. The detecting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and determines whether the generated code contains information that is not based on fact. The correcting unit is realized, for example, by the control unit 46A of the smart device 14 and corrects part of the generated code and makes a re-request to the generation AI. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned transmitter, receiver, re-requester, detector, and corrector, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the transmitter is realized by the control unit 46A of the smart glasses 214 and transmits the request content entered by the user in natural language to the generation AI. The receiver is realized, for example, by the specific processing unit 290 of the data processing device 12 and receives and analyzes the code transmitted from the generation AI. The re-requester is realized, for example, by the control unit 46A of the smart glasses 214 and makes a re-request if the generated code does not produce the desired result. The detector is realized, for example, by the specific processing unit 290 of the data processing device 12 and determines whether the generated code contains information that is not based on fact. The corrector is realized, for example, by the control unit 46A of the smart glasses 214 and corrects part of the generated code and makes a re-request to the generation AI. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned transmitter, receiver, re-requester, detector, and corrector, is implemented, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the transmitter is implemented by the control unit 46A of the headset-type terminal 314 and transmits the request entered by the user in natural language to the generation AI. The receiver is implemented, for example, by the specific processing unit 290 of the data processing device 12 and receives and analyzes the code sent from the generation AI. The re-requester is implemented, for example, by the control unit 46A of the headset-type terminal 314 and makes a re-request if the generated code does not produce the desired result. The detector is implemented, for example, by the specific processing unit 290 of the data processing device 12 and determines whether the generated code contains information that is not based on fact. The corrector is implemented, for example, by the control unit 46A of the headset-type terminal 314 and corrects part of the generated code and makes a re-request to the generation AI. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned transmitting unit, receiving unit, re-requesting unit, detecting unit, and correcting unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the transmitting unit is realized by the control unit 46A of the robot 414 and transmits the request content entered by the user in natural language to the generation AI. The receiving unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and receives and analyzes the code transmitted from the generation AI. The re-requesting unit is realized, for example, by the control unit 46A of the robot 414 and makes a re-request if the generated code does not produce the desired result. The detecting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and determines whether the generated code contains information that is not based on fact. The correcting unit is realized, for example, by the control unit 46A of the robot 414 and corrects part of the generated code and makes a re-request to the generation AI.

[0092] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0093] The system may include an analysis unit that analyzes the user's request. The analysis unit can analyze the request in natural language entered by the user and perform preprocessing to send it to the generation AI in an appropriate format. For example, the analysis unit can extract keywords from the request and convert it into a format that is easy for the generation AI to understand. The analysis unit can also understand the context of the request and generate appropriate instructions for the generation AI. Furthermore, the analysis unit can clarify ambiguous parts of the request and send specific instructions to the generation AI. This allows the system to more accurately convey the user's request to the generation AI.

[0094] The system can be equipped with a prevention unit for preventing hallucination in the generation AI. The prevention unit can take measures in advance to prevent the generation AI from generating hallucination. For example, the prevention unit can provide learning data to the generation AI in advance to suppress the occurrence of hallucination. The prevention unit can also monitor the output of the generation AI in real time and issue a warning if signs of hallucination are detected. Furthermore, the prevention unit can optimize the generation AI's algorithm to minimize the occurrence of hallucination. This allows the system to prevent hallucination in the generation AI before it occurs.

[0095] The system can include a support unit that supports the generation AI in correcting code and information generated by the generation AI. The support unit can provide support when correcting code and information generated by the generation AI. For example, the support unit can identify errors in the generated code and suggest correction methods. The support unit can also evaluate the quality of the generated code and indicate areas for improvement. Furthermore, the support unit can test the code generated by the generation AI to confirm whether the corrections were made correctly. This allows the system to streamline the generation AI's correction work and obtain accurate results.

[0096] The system may include a storage unit that stores user requests. The storage unit can store requests made by the user to the generation AI so that they can be referenced later. For example, the storage unit can store requests made by the user in chronological order so that they can be searched as needed. The storage unit can also store requests made by the user in association with their results so that they can be compared later. Furthermore, the storage unit can analyze the history of requests made by the user and refer to it for the next request. This allows the system to efficiently manage and reuse user requests.

[0097] The system can include an evaluation unit that evaluates the output of the generative AI. The evaluation unit can evaluate the quality of the code or information generated by the generative AI and provide feedback to the user. For example, the evaluation unit can evaluate the accuracy and efficiency of the generated code and assign a score. The evaluation unit can also evaluate the readability and maintainability of the generated code and indicate areas for improvement. Furthermore, the evaluation unit can evaluate the execution results of the generated code and confirm whether they match the expected output. This allows the system to objectively evaluate the output of the generative AI and provide useful feedback to the user.

[0098] The system can include an adjustment unit that estimates the user's emotions and adjusts the output of the generation AI based on the estimated emotions. If the user is feeling stressed, the adjustment unit can simplify the output of the generation AI and provide it in an easy-to-understand format. If the user is relaxed, the adjustment unit can also provide output containing detailed information. Furthermore, if the user is in a hurry, the adjustment unit can simplify the output so that it can be processed quickly. This allows the system to provide output of the generation AI that corresponds to the user's emotions. Emotion estimation is achieved using an emotion engine and the generation AI.

[0099] The system may include a priority determination unit that estimates the user's emotions and determines the priority of requests based on the estimated emotions. The priority determination unit can set a high priority for a request if the user is feeling stressed. Also, it can set a normal priority for a request if the user is relaxed. Furthermore, it can set a top priority for a request if the user is in a hurry. This allows the system to provide a priority for requests according to the user's emotions. Emotion estimation is achieved using an emotion engine or a generation AI.

[0100] The system can include an expression adjustment unit that estimates the user's emotions and adjusts the way the request is expressed based on the estimated emotions. If the user is feeling stressed, the expression adjustment unit can send a concise and clear request to the generation AI. If the user is relaxed, the expression adjustment unit can also send a detailed request to the generation AI. Furthermore, if the user is in a hurry, the request can be simplified and sent to the generation AI so that it can be processed quickly. This allows the system to provide a way to express the request based on the user's emotions. Emotion estimation is achieved using an emotion engine and the generation AI.

[0101] The system can include a display adjustment unit that estimates the user's emotions and adjusts the display method of the generation AI's output based on the estimated emotions. The display adjustment unit can provide a simple, highly visible display method when the user is feeling stressed. It can also provide a display method that includes detailed information when the user is relaxed. It can also provide a display method that focuses on the main points when the user is in a hurry. This allows the system to provide a display method of the generation AI's output that corresponds to the user's emotions. Emotion estimation is achieved using an emotion engine and the generation AI.

[0102] The system can include a priority determination unit that estimates the user's emotions and determines the priority of the generation AI's output based on the estimated emotions. The priority determination unit can set the priority of the generation AI's output to high if the user is feeling stressed. Also, if the user is relaxed, the priority of the generation AI's output can be set to normal. Furthermore, if the user is in a hurry, the priority of the generation AI's output can be set to highest priority. This allows the system to provide a priority of the generation AI's output according to the user's emotions. Emotion estimation is achieved using an emotion engine and the generation AI.

[0103] The processing flow of the second embodiment will be briefly explained below.

[0104] Step 1: When a user makes a request to the generation AI, the transmission unit transmits the request to the generation AI. For example, the transmission unit can transmit the request content entered by the user in natural language to the generation AI. Step 2: The receiving unit receives the code generated by the generating AI. For example, the receiving unit can receive the code sent from the generating AI and analyze the code. Step 3: The re-request unit resubmits a request if the code received by the receiving unit does not produce the desired result. For example, the re-request unit can resubmit a request to the generating AI if the generated code contains an error or does not produce the expected output.

[0105] 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 audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0106] 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 engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0107] Furthermore, the processing by the data processing system 10 described above 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 necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0108] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0109] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0110] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0111] 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, RAM 30, and 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.

[0112] 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.

[0113] 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 audio according to instructions from the processor 46.

[0114] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and 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 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0115] 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 carried out in a secure state.

[0116] Fig. 4 shows an example of the 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.

[0117] 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.

[0118] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0119] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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. The smart glasses 214 also 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 perform processing similar to that of the specific processing unit 290 using these models.

[0120] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0121] 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 audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0122] 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. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0123] 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 also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, 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, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0124] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0125] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0126] 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.

[0127] 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, RAM 30, and 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.

[0128] 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.

[0129] 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 audio according to instructions from the processor 46.

[0130] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and 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 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0131] 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 carried out in a secure state.

[0132] 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.

[0133] 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.

[0134] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0135] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification 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.

[0136] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0137] 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 audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0138] 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. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0139] 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 also 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. Furthermore, 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, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0140] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0141] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0142] 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.

[0143] 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, RAM 30, and 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.

[0144] 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. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0145] 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 audio according to instructions from the processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0147] 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 carried out in a secure state.

[0148] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. 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.

[0149] 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.

[0150] 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.

[0151] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0152] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also 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 perform the same process as the identification processing unit 290 using these models.

[0153] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0154] 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 voice indicating a user input regarding 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.

[0155] 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. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0156] 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 also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, 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.

[0157] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0158] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0159] FIG. 9 illustrates 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. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0160] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically 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.

[0161] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0162] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0163] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0164] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of 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, "relieved," "calm," and "reassuring," have similar emotion values.

[0165] 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.

[0166] 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 USB (Universal Serial Bus) 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.

[0167] Alternatively, 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 in response to a request from the data processing device 12.

[0168] 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.

[0169] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0170] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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.

[0171] As an example of a system configured with a single 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 system that uses a processor that realizes the functions of an 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.

[0172] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0173] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0174] The above-described description and illustrations are a detailed explanation 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, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects 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 replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0175] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0176] [Explanation of symbols]

[0177] 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 sending unit that sends a request; a receiving unit that receives a code generated based on the request transmitted by the transmitting unit; a re-request unit that makes a re-request if the code received by the receiving unit does not produce a desired result; Equipped with A system characterized by:

2. Equipped with a detection unit that detects hallucination of the generated AI 2. The system of claim 1.

3. Equipped with a correction unit that attempts to correct the generated AI 2. The system of claim 1.

4. The transmission unit A part that sends user requests to the generation AI 2. The system of claim 1.

5. The receiving unit Receive the code generated by the generation AI 2. The system of claim 1.

6. The re-request unit A part that requests retry if the generated code does not produce the desired results 2. The system of claim 1.

7. The transmission unit Estimate the user's emotions and adjust the way the request is expressed based on the estimated user emotions.

2. The system of claim 1.

8. The transmission unit When sending a request, refer to past request history to select the appropriate sending timing.

2. The system of claim 1.

Images