System

Abstract

An object of a system according to an embodiment is to promote conversation with a dementia patient and activation of memory.SOLUTION: A system includes a collection part, an analysis part, an interaction part, and a provision part. The collection part collects information on hobbies or careers, photographs, favorite television programs or music of the patient. The analysis unit analyzes the information collected by the collection unit. The dialogue unit uses the story generated by the analysis unit for a dialogue with the patient. The providing unit provides a result of the story used by the dialogue unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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 technologies do not adequately provide effective means for communicating with dementia patients or activating their memories, and there is room for improvement.

[0005] The system according to the embodiment aims to promote dialogue with dementia patients and memory activation. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a dialogue unit, and a provision unit. The collection unit collects information such as a patient's hobbies or history, photos, and favorite TV programs or music. The analysis unit analyzes the information collected by the collection unit. The dialogue unit uses the story generated by the analysis unit in dialogue with the patient. The provision unit provides the results of the story used by the dialogue unit. [Effects of the Invention]

[0007] The system according to the embodiment can promote dialogue with dementia patients and memory activation. [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 inputs information about a dementia patient, such as their hobbies, career history, photos, and favorite television programs and music, into a generation AI, which then generates stories related to the patient's topics of interest and hobbies, thereby promoting dialogue with the dementia patient and activating their memory. For example, the system collects information about the patient's hobbies, career history, photos, favorite television programs and music, and inputs it into the generation AI. The generation AI then analyzes this information and generates stories related to the patient's topics of interest and hobbies. The generated stories are used in dialogue with the patient to promote memory activation. For example, the system collects information from the patient's family and caregivers, collecting information about the patient's favorite music, television programs, and hobbies from their youth. The collected information is then input into the generation AI, which then analyzes this information and generates stories related to the patient's topics of interest and hobbies. The generated stories are used in dialogue with the patient to promote memory activation. For example, a caregiver can use the generated stories to interact with the patient, thereby activating the patient's memory. This facilitates dialogue with the dementia patient and activates the patient's memory. This allows the system to facilitate smooth dialogue with dementia patients and activate their memories. For example, listening to a story related to the music the patient liked when they were younger can be expected to revive memories of that time and spark a lively conversation. Also, listening to anecdotes about hobbies can be expected to pique the patient's interest and lead to more lively conversations.

[0029] A dialogue support system according to an embodiment includes a collection unit, an analysis unit, a dialogue unit, and a provision unit. The collection unit collects information about the patient's hobbies or career, photos, and favorite television programs or music. The collection unit can collect information using, for example, interviews or questionnaires with family members or caregivers. The collection unit can also analyze the patient's past behavioral history and select an optimal information collection method. For example, based on the patient's favorite activities in the past, the collection unit creates related questions and collects information. The analysis unit uses a generation AI to analyze the information collected by the collection unit and generate a story related to the patient's topics of interest or hobbies. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and generates the story using these. For example, the generation AI may generate a story related to the music the patient liked when they were young or an episode related to their hobbies. The dialogue unit engages in a dialogue with the patient based on the generated story. The dialogue unit stimulates the patient's memory by, for example, reading the generated story aloud or asking related questions. The dialogue unit can also estimate the patient's emotions and adjust the progress of the dialogue based on the estimated patient's emotions. For example, if the patient is relaxed, the dialogue proceeds at a slow pace. The providing unit records the results of the dialogue and uses them for the next dialogue. The providing unit can, for example, analyze the results of the dialogue in real time and adjust the content of the next dialogue. As a result, the dialogue support system according to the embodiment facilitates dialogue with dementia patients and activates the patient's memory. For example, listening to a story related to music the patient liked when they were young can be expected to revive memories from that time and make the dialogue more lively. Furthermore, listening to anecdotes about hobbies can be expected to pique the patient's interest and make the dialogue more lively.

[0030] The collection unit can collect information using interviews or questionnaires from family members or caregivers. For example, the collection unit can conduct interviews with family members or caregivers to collect information such as the patient's hobbies, career, favorite television programs and music, etc. The collection unit can also use questionnaires to collect information about the patient's interests and concerns. For example, the collection unit can collect information by asking the patient's family members questions about the music, television programs, and hobbies the patient liked when they were younger. The collection unit can also collect information about the patient's daily life from the patient's caregivers. This allows for effective collection of information from family members and caregivers. Some or all of the above-mentioned processing in the collection unit can be performed using, or without, AI, for example. For example, the collection unit can input the results of interviews or questionnaires into a generation AI, which can then organize and analyze the information.

[0031] The analysis unit can analyze the collected information and generate a story related to a topic or hobby that the patient was interested in. The analysis unit can use, for example, a generation AI to analyze the collected information and generate a story related to a topic or hobby that the patient was interested in. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and generate a story using these. For example, the generation AI can generate a story related to the music the patient liked when they were young or an episode related to their hobbies. The analysis unit can also generate a story to pique the patient's interest based on the collected information. For example, the generation AI can generate an interesting episode based on the patient's hobbies and background. This piques the patient's interest and facilitates dialogue. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input the collected information into the generation AI, which can then generate a story.

[0032] The dialogue unit can engage in a dialogue with the patient based on the generated story. For example, the dialogue unit can stimulate the patient's memory by reading the generated story aloud or asking related questions. The dialogue unit can also estimate the patient's emotions and adjust the dialogue progression based on the estimated patient's emotions. For example, if the patient is relaxed, the dialogue proceeds at a slow pace. The dialogue unit can smoothly advance the dialogue with the patient based on the generated story. For example, by listening to a story related to music the patient liked when they were young, the dialogue unit can revive memories from that time and encourage a lively dialogue. Furthermore, by listening to anecdotes about hobbies, the dialogue can be expected to pique the patient's interest and make the dialogue more lively. Some or all of the above-described processing in the dialogue unit may be performed using, for example, AI, or may be performed without AI. For example, the dialogue unit can input the generated story into a generation AI, which can then adjust the dialogue progression.

[0033] The providing unit can record the results of the dialogue and use them in the next dialogue. For example, the providing unit can record the results of the dialogue and use them in the next dialogue. The providing unit can analyze the results of the dialogue in real time and adjust the content of the next dialogue. For example, the providing unit can select a topic for the next dialogue based on the results of the dialogue. The providing unit can also adjust how the next dialogue will proceed based on the results of the dialogue. By utilizing the results of the dialogue in the next dialogue, the accuracy of the dialogue can be improved. For example, by adjusting the content of the next dialogue based on the results of the dialogue, it is expected that the patient's interest will be piqued and the dialogue will proceed smoothly. Some or all of the above-mentioned processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input the results of the dialogue into a generating AI, which can adjust the content of the next dialogue.

[0034] The collection unit can analyze the patient's past behavioral history and select an appropriate information collection method. The collection unit, for example, analyzes the patient's past behavioral history and selects the optimal information collection method. The collection unit creates relevant questions based on the patient's past favorite activities and collects information. The collection unit can also collect information at specific time periods from the patient's past behavioral history. Furthermore, the collection unit can analyze the patient's past behavioral history and select the most effective information collection method (interview, questionnaire, etc.). This enables effective information collection by selecting the optimal information collection method based on the patient's past behavioral history. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the patient's past behavioral history data into a generation AI, which can select the optimal information collection method.

[0035] The collection unit can filter information based on the patient's current health condition or living situation when collecting information. For example, the collection unit collects detailed information when the patient's health condition is good. The collection unit can also select appropriate questions to collect information depending on the patient's living situation. Furthermore, the collection unit can ask simple questions and collect information when the patient's health condition is poor. This makes it possible to collect information according to the patient's health condition and living situation. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data on the patient's health condition and living situation into the generation AI, and the generation AI can filter the collected information.

[0036] When collecting information, the collection unit can select an appropriate collection means depending on the patient's input method. For example, if the patient prefers voice input, the collection unit can ask questions by voice and collect information. If the patient prefers text input, the collection unit can also ask questions by text and collect information. Furthermore, if the patient prefers images, the collection unit can also ask questions using images and collect information. This enables optimal information collection depending on the patient's input method. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the patient's input data into a generation AI, which can select the optimal collection means.

[0037] When collecting information, the collection unit can prioritize collecting highly relevant information based on the patient's geographical location information. For example, the collection unit prioritizes collecting information related to the area where the patient currently lives. The collection unit can also prioritize collecting information related to areas where the patient has lived in the past. The collection unit can also prioritize collecting information related to places the patient frequently visits. This enables effective information collection based on the patient's geographical location information. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the patient's geographical location information to the generation AI, and the generation AI can prioritize collecting highly relevant information.

[0038] When collecting information, the collection unit can analyze the patient's social media activities and collect relevant information. For example, the collection unit can collect relevant information based on photos and posts shared by the patient on social media. The collection unit can also collect relevant information by referring to the activities of the patient's friends on social media. The collection unit can also analyze the patient's interests on social media and collect relevant information. This enables effective information collection based on the patient's social media activities. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using AI or without AI. For example, the collection unit can input the patient's social media data into a generation AI, which can collect relevant information.

[0039] When collecting information, the collection unit can customize the collection method based on the patient's past feedback. For example, the collection unit selects the optimal collection method based on the patient's past preferred collection method. The collection unit can also adjust the content of questions by referring to the patient's past feedback. The collection unit can also select the collection means (audio, text, image, etc.) based on the patient's past feedback. This enables effective information collection based on the patient's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the patient's past feedback data into a generation AI and use the generation AI to customize the collection method.

[0040] During analysis, the analysis unit can adjust the level of detail of the story based on the importance of the information. For example, the analysis unit generates a detailed story based on important information. The analysis unit can also generate a concise story based on less important information. The analysis unit can also adjust the length of the story based on the importance of the information. This makes it possible to generate an optimal story based on the importance of the information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input information importance data to a generation AI, and the generation AI can adjust the level of detail of the story.

[0041] During analysis, the analysis unit can apply different analysis algorithms based on the category of information. For example, the analysis unit can apply a music analysis algorithm to information about music. The analysis unit can also apply an image analysis algorithm to information about photos. The analysis unit can also apply a video analysis algorithm to information about television programs. This enables optimal analysis according to the category of information. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input category data of the information into a generation AI, and the generation AI can apply different analysis algorithms.

[0042] During analysis, the analysis unit can improve the accuracy of the analysis based on the patient's past story generation results. The analysis unit improves the accuracy of the analysis based, for example, on the patient's preferred story patterns in the past. The analysis unit can also analyze the patient's past story generation results and select the optimal analysis algorithm. The analysis unit can also adjust the content of the story by referring to the patient's past story generation results. In this way, the accuracy of the analysis is improved by referring to the patient's past story generation results. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the patient's past story generation result data into the generation AI, and the generation AI can improve the accuracy of the analysis.

[0043] During analysis, the analysis unit can determine the priority of stories based on when information was collected. For example, the analysis unit generates stories with priority based on recently collected information. The analysis unit can also lower the priority of stories based on older information. The analysis unit can also adjust the order in which stories are generated depending on when information was collected. This makes it possible to generate optimal stories based on when information was collected. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on when information was collected into a generation AI, and the generation AI can determine the priority of stories.

[0044] The analysis unit can adjust the order of stories based on the relevance of information during analysis. For example, the analysis unit determines the order of stories based on highly relevant information. The analysis unit can also postpone the order of stories based on less relevant information. The analysis unit can also dynamically adjust the order of stories according to the relevance of information. This makes it possible to optimally order stories based on the relevance of information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input information relevance data into a generation AI, and the generation AI can adjust the order of stories.

[0045] During analysis, the analysis unit can adjust the use of technical terms in the story based on the patient's level of expertise. For example, if the patient has technical expertise, the analysis unit generates a story that uses a lot of technical terms. If the patient does not have technical expertise, the analysis unit can also generate a story in simple language. The analysis unit can also adjust the content of the story according to the patient's level of expertise. This makes it possible to generate an optimal story according to the patient's level of expertise. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the patient's level of expertise data into the generation AI, and the generation AI can adjust the use of technical terms in the story.

[0046] During the dialogue, the dialogue unit can adjust the level of detail of the dialogue based on the importance of the generated story. For example, the dialogue unit conducts a detailed dialogue based on an important story. The dialogue unit can also conduct a brief dialogue based on a less important story. The dialogue unit can also adjust the level of detail of the dialogue according to the importance of the story. This enables an optimal dialogue according to the importance of the generated story. Some or all of the above-mentioned processing in the dialogue unit may be performed using, for example, AI, or may be performed without using AI. For example, the dialogue unit can input importance data of the generated story to the generation AI, and the generation AI can adjust the level of detail of the dialogue.

[0047] The dialogue unit can analyze the patient's response in real time during the dialogue and dynamically change the content of the dialogue. For example, if the patient shows interest, the dialogue unit continues the dialogue related to that topic. If the patient does not show interest, the dialogue unit can also switch the dialogue to another topic. The dialogue unit can also adjust the content of the dialogue in real time depending on the patient's response. This makes it possible to have an optimal dialogue depending on the patient's response. Some or all of the above-mentioned processing in the dialogue unit may be performed using, for example, AI, or may be performed without using AI. For example, the dialogue unit can input patient response data into a generation AI, which can dynamically change the content of the dialogue.

[0048] During a dialogue, the dialogue unit can improve the accuracy of the dialogue based on the patient's past dialogue history. The dialogue unit improves the accuracy of the dialogue, for example, based on the patient's preferred dialogue patterns in the past. The dialogue unit can also analyze the patient's past dialogue history and select the optimal dialogue method. The dialogue unit can also adjust the content of the dialogue by referring to the patient's past dialogue history. This makes it possible to have an optimal dialogue based on the patient's past dialogue history. Some or all of the above-mentioned processing in the dialogue unit may be performed using, for example, AI, or may be performed without using AI. For example, the dialogue unit can input the patient's past dialogue history data into a generation AI, which can improve the accuracy of the dialogue.

[0049] The dialogue unit can adjust the order of dialogue based on the relevance of the generated stories during dialogue. For example, the dialogue unit prioritizes highly relevant stories in the dialogue. The dialogue unit can also postpone less relevant stories in the dialogue. The dialogue unit can also dynamically adjust the order of dialogue according to the relevance of the stories. This enables an optimal dialogue order according to the relevance of the generated stories. Some or all of the above-mentioned processing in the dialogue unit may be performed using, for example, AI, or may be performed without using AI. For example, the dialogue unit can input relevance data of the generated stories to a generation AI, and the generation AI can adjust the order of dialogue.

[0050] The dialogue unit can adjust the timing of the dialogue based on the patient's lifestyle rhythm during the dialogue. For example, if the patient is a morning person, the dialogue unit can conduct the dialogue in the morning. If the patient is a night owl, the dialogue unit can also conduct the dialogue in the evening. The dialogue unit can also dynamically adjust the timing of the dialogue according to the patient's lifestyle rhythm. This enables the optimal dialogue timing according to the patient's lifestyle rhythm. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI, for example, or may be performed without using AI. For example, the dialogue unit can input the patient's lifestyle rhythm data into the generation AI, and the generation AI can adjust the timing of the dialogue.

[0051] During the dialogue, the dialogue unit can adjust the use of technical terminology in the dialogue based on the patient's level of expertise. For example, if the patient has specialized knowledge, the dialogue unit can use a lot of technical terminology. If the patient does not have specialized knowledge, the dialogue unit can also use simple language. The dialogue unit can also adjust the content of the dialogue according to the patient's level of expertise. This enables an optimal dialogue according to the patient's level of expertise. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI, for example, or may be performed without using AI. For example, the dialogue unit can input the patient's level of expertise data into the generation AI, and the generation AI can adjust the use of technical terminology in the dialogue.

[0052] The providing unit can adjust the level of detail of the provided information based on the importance of the dialogue result when providing the information. The providing unit, for example, provides detailed information based on an important dialogue result. The providing unit can also provide concise information based on a less important dialogue result. The providing unit can also adjust the level of detail of the provided information based on the importance of the dialogue result. This enables optimal provision based on the importance of the dialogue result. Some or all of the above-described processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input importance data of the dialogue result to a generating AI, and the generating AI can adjust the level of detail of the provided information.

[0053] The providing unit can analyze the results of the dialogue in real time when providing the data and reflect them in the next dialogue. For example, the providing unit can analyze the results of the dialogue in real time and adjust the content of the next dialogue. The providing unit can also select a topic for the next dialogue based on the results of the dialogue. The providing unit can also analyze the results of the dialogue in real time and adjust how the next dialogue will proceed. This improves the accuracy of the dialogue by reflecting the results of the dialogue in the next dialogue. Some or all of the above-mentioned processing in the providing unit can be performed using AI, for example, or can be performed without using AI. For example, the providing unit can input dialogue result data to a generating AI, which can adjust the content of the next dialogue.

[0054] At the time of provision, the provision unit can improve the accuracy of provision based on the patient's past provision results. The provision unit improves the accuracy of provision, for example, based on the patient's past provision results. The provision unit can also analyze the patient's past provision results and select the optimal provision method. The provision unit can also adjust the content of provision by referring to the patient's past provision results. This enables optimal provision based on the patient's past provision results. Some or all of the above-mentioned processing in the provision unit may be performed, for example, using AI, or may be performed without using AI. For example, the provision unit can input the patient's past provision result data into a generation AI, and the generation AI can improve the accuracy of provision.

[0055] The providing unit can adjust the order of providing the dialogue results based on the relevance of the dialogue results when providing them. For example, the providing unit can prioritize providing dialogue results with high relevance. The providing unit can also provide dialogue results with low relevance at a later date. The providing unit can also dynamically adjust the order of providing the dialogue results based on the relevance of the dialogue results. This enables optimal provision based on the relevance of the dialogue results. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the providing unit can input relevance data of the dialogue results to a generation AI, and the generation AI can adjust the order of providing the dialogue results.

[0056] The providing unit can adjust the timing of providing the results based on the patient's lifestyle rhythm when providing the results. For example, if the patient is a morning person, the providing unit can provide the results in the morning hours. If the patient is a night owl, the providing unit can also provide the results in the evening hours. The providing unit can also dynamically adjust the timing of providing the results according to the patient's lifestyle rhythm. This enables the optimal timing of providing the results according to the patient's lifestyle rhythm. Some or all of the above-mentioned processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input the patient's lifestyle rhythm data into the generating AI, and the generating AI can adjust the timing of providing the results.

[0057] The providing unit can adjust the use of technical terminology in the provided results based on the patient's level of expertise when providing the results. For example, if the patient has technical expertise, the providing unit can provide results that use a lot of technical terminology. If the patient does not have technical expertise, the providing unit can also provide results in simple language. The providing unit can also adjust the content of the provided results according to the patient's level of expertise. This enables optimal provision according to the patient's level of expertise. Some or all of the above-mentioned processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input the patient's level of expertise data into the generating AI, and the generating AI can adjust the use of technical terminology in the provided results.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] When the dialogue unit engages in a dialogue with a patient based on the generated story, it can customize the content of the dialogue based on the patient's past dialogue history. For example, the dialogue unit can arouse interest in the dialogue by prioritizing topics and episodes that the patient liked in the past. The dialogue unit can also identify topics that the patient wants to avoid from the past dialogue history and avoid them to facilitate the dialogue. Furthermore, the dialogue unit can promote memory activation by analyzing the past dialogue history and revisiting episodes to which the patient particularly responded. This allows the dialogue unit to utilize the patient's past dialogue history to realize more effective dialogue.

[0060] The collection unit can analyze the patient's social media activity and collect related information. For example, the collection unit can collect related information based on photos and posts shared by the patient on social media. The collection unit can also collect related information by referring to the activities of the patient's friends on social media. Furthermore, the collection unit can analyze the patient's interests and concerns on social media and collect related information. This enables effective collection of information based on the patient's social media activity.

[0061] When analyzing collected information, the analysis unit can apply different analysis algorithms based on the category of the information. For example, a music analysis algorithm can be applied to information about music. An image analysis algorithm can be applied to information about photos. A video analysis algorithm can be applied to information about television programs. This allows for optimal analysis according to the category of information.

[0062] The dialogue unit can analyze the patient's response in real time during the dialogue and dynamically change the content of the dialogue. For example, if the patient shows interest, the dialogue can continue with a topic related to that. If the patient shows no interest, the dialogue can switch to a different topic. The dialogue unit can also adjust the content of the dialogue in real time according to the patient's response. This allows for optimal dialogue according to the patient's response.

[0063] The providing unit can adjust the level of detail of the provided information based on the importance of the dialogue result when providing the information. For example, detailed information can be provided based on an important dialogue result. Brief information can also be provided based on a less important dialogue result. The level of detail of the provided information can also be adjusted according to the importance of the dialogue result. This makes it possible to provide the most appropriate information according to the importance of the dialogue result.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The collection unit collects information about the patient's hobbies or career history, photos, and favorite TV programs or music. For example, the collection unit can collect information by using interviews or questionnaires with family members or caregivers. The collection unit can also analyze the patient's past behavioral history and select the optimal information collection method. For example, the collection unit can create related questions based on the patient's favorite activities in the past and collect information. Step 2: The analysis unit uses a generation AI to analyze the information collected by the collection unit and generate stories related to topics and hobbies that the patient was interested in. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and uses these to generate stories. For example, the generation AI may generate stories related to the music the patient liked when they were young or anecdotes about their hobbies. Step 3: The dialogue unit engages in a dialogue with the patient based on the generated story. For example, the dialogue unit stimulates the patient's memory by reading the generated story aloud or asking related questions. The dialogue unit can also estimate the patient's emotions and adjust the way the dialogue proceeds based on the estimated patient emotions. For example, if the patient is relaxed, the dialogue will proceed at a slower pace. Step 4: The providing unit records the results of the dialogue and uses them for the next dialogue. The providing unit can, for example, analyze the results of the dialogue in real time and adjust the content of the next dialogue. As a result, the dialogue support system according to the embodiment facilitates dialogue with dementia patients and activates the patients' memories.

[0066] (Example 2) A system according to an embodiment of the present invention inputs information about a dementia patient, such as their hobbies, career history, photos, and favorite television programs and music, into a generation AI, which then generates stories related to the patient's topics of interest and hobbies, thereby promoting dialogue with the dementia patient and activating their memory. For example, the system collects information about the patient's hobbies, career history, photos, favorite television programs and music, and inputs it into the generation AI. The generation AI then analyzes this information and generates stories related to the patient's topics of interest and hobbies. The generated stories are used in dialogue with the patient to promote memory activation. For example, the system collects information from the patient's family and caregivers, collecting information about the patient's favorite music, television programs, and hobbies from their youth. The collected information is then input into the generation AI, which then analyzes this information and generates stories related to the patient's topics of interest and hobbies. The generated stories are used in dialogue with the patient to promote memory activation. For example, a caregiver can use the generated stories to interact with the patient, thereby activating the patient's memory. This facilitates dialogue with the dementia patient and activates the patient's memory. This allows the system to facilitate smooth dialogue with dementia patients and activate their memories. For example, listening to a story related to the music the patient liked when they were younger can be expected to revive memories of that time and spark a lively conversation. Also, listening to anecdotes about hobbies can be expected to pique the patient's interest and lead to more lively conversations.

[0067] A dialogue support system according to an embodiment includes a collection unit, an analysis unit, a dialogue unit, and a provision unit. The collection unit collects information about the patient's hobbies or career, photos, and favorite television programs or music. The collection unit can collect information using, for example, interviews or questionnaires with family members or caregivers. The collection unit can also analyze the patient's past behavioral history and select an optimal information collection method. For example, based on the patient's favorite activities in the past, the collection unit creates related questions and collects information. The analysis unit uses a generation AI to analyze the information collected by the collection unit and generate a story related to the patient's topics of interest or hobbies. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and generates the story using these. For example, the generation AI may generate a story related to the music the patient liked when they were young or an episode related to their hobbies. The dialogue unit engages in a dialogue with the patient based on the generated story. The dialogue unit stimulates the patient's memory by, for example, reading the generated story aloud or asking related questions. The dialogue unit can also estimate the patient's emotions and adjust the progress of the dialogue based on the estimated patient's emotions. For example, if the patient is relaxed, the dialogue proceeds at a slow pace. The providing unit records the results of the dialogue and uses them for the next dialogue. The providing unit can, for example, analyze the results of the dialogue in real time and adjust the content of the next dialogue. As a result, the dialogue support system according to the embodiment facilitates dialogue with dementia patients and activates the patient's memory. For example, listening to a story related to music the patient liked when they were young can be expected to revive memories from that time and make the dialogue more lively. Furthermore, listening to anecdotes about hobbies can be expected to pique the patient's interest and make the dialogue more lively.

[0068] The collection unit can collect information using interviews or questionnaires from family members or caregivers. For example, the collection unit can conduct interviews with family members or caregivers to collect information such as the patient's hobbies, career, favorite television programs and music, etc. The collection unit can also use questionnaires to collect information about the patient's interests and concerns. For example, the collection unit can collect information by asking the patient's family members questions about the music, television programs, and hobbies the patient liked when they were younger. The collection unit can also collect information about the patient's daily life from the patient's caregivers. This allows for effective collection of information from family members and caregivers. Some or all of the above-mentioned processing in the collection unit can be performed using, or without, AI, for example. For example, the collection unit can input the results of interviews or questionnaires into a generation AI, which can then organize and analyze the information.

[0069] The analysis unit can analyze the collected information and generate a story related to a topic or hobby that the patient was interested in. The analysis unit can use, for example, a generation AI to analyze the collected information and generate a story related to a topic or hobby that the patient was interested in. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and generate a story using these. For example, the generation AI can generate a story related to the music the patient liked when they were young or an episode related to their hobbies. The analysis unit can also generate a story to pique the patient's interest based on the collected information. For example, the generation AI can generate an interesting episode based on the patient's hobbies and background. This piques the patient's interest and facilitates dialogue. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input the collected information into the generation AI, which can then generate a story.

[0070] The dialogue unit can engage in a dialogue with the patient based on the generated story. For example, the dialogue unit can stimulate the patient's memory by reading the generated story aloud or asking related questions. The dialogue unit can also estimate the patient's emotions and adjust the dialogue progression based on the estimated patient's emotions. For example, if the patient is relaxed, the dialogue proceeds at a slow pace. The dialogue unit can smoothly advance the dialogue with the patient based on the generated story. For example, by listening to a story related to music the patient liked when they were young, the dialogue unit can revive memories from that time and encourage a lively dialogue. Furthermore, by listening to anecdotes about hobbies, the dialogue can be expected to pique the patient's interest and make the dialogue more lively. Some or all of the above-described processing in the dialogue unit may be performed using, for example, AI, or may be performed without AI. For example, the dialogue unit can input the generated story into a generation AI, which can then adjust the dialogue progression.

[0071] The providing unit can record the results of the dialogue and use them in the next dialogue. For example, the providing unit can record the results of the dialogue and use them in the next dialogue. The providing unit can analyze the results of the dialogue in real time and adjust the content of the next dialogue. For example, the providing unit can select a topic for the next dialogue based on the results of the dialogue. The providing unit can also adjust how the next dialogue will proceed based on the results of the dialogue. By utilizing the results of the dialogue in the next dialogue, the accuracy of the dialogue can be improved. For example, by adjusting the content of the next dialogue based on the results of the dialogue, it is expected that the patient's interest will be piqued and the dialogue will proceed smoothly. Some or all of the above-mentioned processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input the results of the dialogue into a generating AI, which can adjust the content of the next dialogue.

[0072] The collection unit can estimate the patient's emotions and adjust the timing of information collection based on the estimated patient's emotions. For example, the collection unit estimates the patient's emotions and adjusts the timing of information collection based on the estimated patient's emotions. The collection unit collects information by interviewing family members or caregivers when the patient is relaxed. The collection unit can also temporarily suspend information collection when the patient is feeling stressed and resume it later. Furthermore, the collection unit can collect information by asking simple questions in a short time when the patient is excited. This enables more appropriate information collection by adjusting the timing of information collection according to the patient's emotions. 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-mentioned processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input patient emotion data into a generation AI and use the generation AI to adjust the timing of information collection.

[0073] The collection unit can analyze the patient's past behavioral history and select an appropriate information collection method. The collection unit, for example, analyzes the patient's past behavioral history and selects the optimal information collection method. The collection unit creates relevant questions based on the patient's past favorite activities and collects information. The collection unit can also collect information at specific time periods from the patient's past behavioral history. Furthermore, the collection unit can analyze the patient's past behavioral history and select the most effective information collection method (interview, questionnaire, etc.). This enables effective information collection by selecting the optimal information collection method based on the patient's past behavioral history. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the patient's past behavioral history data into a generation AI, which can select the optimal information collection method.

[0074] The collection unit can filter information based on the patient's current health condition or living situation when collecting information. For example, the collection unit collects detailed information when the patient's health condition is good. The collection unit can also select appropriate questions to collect information depending on the patient's living situation. Furthermore, the collection unit can ask simple questions and collect information when the patient's health condition is poor. This makes it possible to collect information according to the patient's health condition and living situation. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data on the patient's health condition and living situation into the generation AI, and the generation AI can filter the collected information.

[0075] When collecting information, the collection unit can select an appropriate collection means depending on the patient's input method. For example, if the patient prefers voice input, the collection unit can ask questions by voice and collect information. If the patient prefers text input, the collection unit can also ask questions by text and collect information. Furthermore, if the patient prefers images, the collection unit can also ask questions using images and collect information. This enables optimal information collection depending on the patient's input method. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the patient's input data into a generation AI, which can select the optimal collection means.

[0076] The collection unit can estimate the patient's emotions and determine the priority of information to be collected based on the estimated patient's emotions. For example, the collection unit can estimate the patient's emotions and determine the priority of information to be collected based on the estimated patient's emotions. The collection unit prioritizes collecting detailed information when the patient is relaxed. The collection unit can also prioritize collecting simple information when the patient is stressed. Furthermore, the collection unit can prioritize collecting interesting information when the patient is excited. This enables effective information collection by determining the priority of information according to the patient's emotions. 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-mentioned processing in the collection unit can be performed using AI, for example, or without AI. For example, the collection unit can input patient emotion data into a generation AI, which can then determine the priority of information.

[0077] When collecting information, the collection unit can prioritize collecting highly relevant information based on the patient's geographical location information. For example, the collection unit prioritizes collecting information related to the area where the patient currently lives. The collection unit can also prioritize collecting information related to areas where the patient has lived in the past. The collection unit can also prioritize collecting information related to places the patient frequently visits. This enables effective information collection based on the patient's geographical location information. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the patient's geographical location information to the generation AI, and the generation AI can prioritize collecting highly relevant information.

[0078] When collecting information, the collection unit can analyze the patient's social media activities and collect relevant information. For example, the collection unit can collect relevant information based on photos and posts shared by the patient on social media. The collection unit can also collect relevant information by referring to the activities of the patient's friends on social media. The collection unit can also analyze the patient's interests on social media and collect relevant information. This enables effective information collection based on the patient's social media activities. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using AI or without AI. For example, the collection unit can input the patient's social media data into a generation AI, which can collect relevant information.

[0079] When collecting information, the collection unit can customize the collection method based on the patient's past feedback. For example, the collection unit selects the optimal collection method based on the patient's past preferred collection method. The collection unit can also adjust the content of questions by referring to the patient's past feedback. The collection unit can also select the collection means (audio, text, image, etc.) based on the patient's past feedback. This enables effective information collection based on the patient's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the patient's past feedback data into a generation AI and use the generation AI to customize the collection method.

[0080] The analysis unit can estimate the patient's emotions and adjust the way the story is presented based on the estimated patient's emotions. For example, the analysis unit can estimate the patient's emotions and adjust the way the story is presented based on the estimated patient's emotions. If the patient is relaxed, the analysis unit can generate a story in a calm tone. If the patient is excited, the analysis unit can generate a story in a lively tone. If the patient is sad, the analysis unit can generate a story in a comforting tone. This enables the optimal story presentation according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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-mentioned processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input patient emotion data into the generation AI, and the generation AI can adjust the way the story is presented.

[0081] During analysis, the analysis unit can adjust the level of detail of the story based on the importance of the information. For example, the analysis unit generates a detailed story based on important information. The analysis unit can also generate a concise story based on less important information. The analysis unit can also adjust the length of the story based on the importance of the information. This makes it possible to generate an optimal story based on the importance of the information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input information importance data to a generation AI, and the generation AI can adjust the level of detail of the story.

[0082] During analysis, the analysis unit can apply different analysis algorithms based on the category of information. For example, the analysis unit can apply a music analysis algorithm to information about music. The analysis unit can also apply an image analysis algorithm to information about photos. The analysis unit can also apply a video analysis algorithm to information about television programs. This enables optimal analysis according to the category of information. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input category data of the information into a generation AI, and the generation AI can apply different analysis algorithms.

[0083] During analysis, the analysis unit can improve the accuracy of the analysis based on the patient's past story generation results. The analysis unit improves the accuracy of the analysis based, for example, on the patient's preferred story patterns in the past. The analysis unit can also analyze the patient's past story generation results and select the optimal analysis algorithm. The analysis unit can also adjust the content of the story by referring to the patient's past story generation results. In this way, the accuracy of the analysis is improved by referring to the patient's past story generation results. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the patient's past story generation result data into the generation AI, and the generation AI can improve the accuracy of the analysis.

[0084] The analysis unit can estimate the patient's emotions and adjust the length of the story based on the estimated patient's emotions. For example, the analysis unit can estimate the patient's emotions and adjust the length of the story based on the estimated patient's emotions. The analysis unit can generate a longer story if the patient is relaxed. The analysis unit can also generate a shorter story if the patient is in a hurry. Furthermore, the analysis unit can generate a story of an appropriate length if the patient is excited. This enables the optimal story length to be determined according to the patient's emotions. 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 analysis unit can be performed using AI, or can be performed without AI. For example, the analysis unit can input patient emotion data into the generation AI, and the generation AI can adjust the length of the story.

[0085] During analysis, the analysis unit can determine the priority of stories based on when information was collected. For example, the analysis unit generates stories with priority based on recently collected information. The analysis unit can also lower the priority of stories based on older information. The analysis unit can also adjust the order in which stories are generated depending on when information was collected. This makes it possible to generate optimal stories based on when information was collected. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on when information was collected into a generation AI, and the generation AI can determine the priority of stories.

[0086] The analysis unit can adjust the order of stories based on the relevance of information during analysis. For example, the analysis unit determines the order of stories based on highly relevant information. The analysis unit can also postpone the order of stories based on less relevant information. The analysis unit can also dynamically adjust the order of stories according to the relevance of information. This makes it possible to optimally order stories based on the relevance of information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input information relevance data into a generation AI, and the generation AI can adjust the order of stories.

[0087] During analysis, the analysis unit can adjust the use of technical terms in the story based on the patient's level of expertise. For example, if the patient has technical expertise, the analysis unit generates a story that uses a lot of technical terms. If the patient does not have technical expertise, the analysis unit can also generate a story in simple language. The analysis unit can also adjust the content of the story according to the patient's level of expertise. This makes it possible to generate an optimal story according to the patient's level of expertise. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the patient's level of expertise data into the generation AI, and the generation AI can adjust the use of technical terms in the story.

[0088] The dialogue unit can estimate the patient's emotions and adjust the dialogue progression method based on the estimated patient's emotions. For example, the dialogue unit can estimate the patient's emotions and adjust the dialogue progression method based on the estimated patient's emotions. If the patient is relaxed, the dialogue unit can proceed at a slow pace. If the patient is excited, the dialogue unit can proceed at a lively pace. If the patient is sad, the dialogue unit can proceed with the dialogue in a comforting tone. This enables the dialogue to proceed optimally according to the patient's emotions. 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-mentioned processing in the dialogue unit may be performed using AI, or may be performed without AI. For example, the dialogue unit can input patient emotion data into the generation AI and use the generation AI to adjust the dialogue progression method.

[0089] During the dialogue, the dialogue unit can adjust the level of detail of the dialogue based on the importance of the generated story. For example, the dialogue unit conducts a detailed dialogue based on an important story. The dialogue unit can also conduct a brief dialogue based on a less important story. The dialogue unit can also adjust the level of detail of the dialogue according to the importance of the story. This enables an optimal dialogue according to the importance of the generated story. Some or all of the above-mentioned processing in the dialogue unit may be performed using, for example, AI, or may be performed without using AI. For example, the dialogue unit can input importance data of the generated story to the generation AI, and the generation AI can adjust the level of detail of the dialogue.

[0090] The dialogue unit can analyze the patient's response in real time during the dialogue and dynamically change the content of the dialogue. For example, if the patient shows interest, the dialogue unit continues the dialogue related to that topic. If the patient does not show interest, the dialogue unit can also switch the dialogue to another topic. The dialogue unit can also adjust the content of the dialogue in real time depending on the patient's response. This makes it possible to have an optimal dialogue depending on the patient's response. Some or all of the above-mentioned processing in the dialogue unit may be performed using, for example, AI, or may be performed without using AI. For example, the dialogue unit can input patient response data into a generation AI, which can dynamically change the content of the dialogue.

[0091] During a dialogue, the dialogue unit can improve the accuracy of the dialogue based on the patient's past dialogue history. The dialogue unit improves the accuracy of the dialogue, for example, based on the patient's preferred dialogue patterns in the past. The dialogue unit can also analyze the patient's past dialogue history and select the optimal dialogue method. The dialogue unit can also adjust the content of the dialogue by referring to the patient's past dialogue history. This makes it possible to have an optimal dialogue based on the patient's past dialogue history. Some or all of the above-mentioned processing in the dialogue unit may be performed using, for example, AI, or may be performed without using AI. For example, the dialogue unit can input the patient's past dialogue history data into a generation AI, which can improve the accuracy of the dialogue.

[0092] The dialogue unit can estimate the patient's emotions and adjust the length of the dialogue based on the estimated patient's emotions. For example, the dialogue unit can estimate the patient's emotions and adjust the length of the dialogue based on the estimated patient's emotions. The dialogue unit can conduct a longer dialogue if the patient is relaxed. The dialogue unit can also conduct a shorter dialogue if the patient is in a hurry. Furthermore, the dialogue unit can conduct a dialogue of an appropriate length if the patient is excited. This enables the dialogue length to be optimized according to the patient's emotions. 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-mentioned processing in the dialogue unit can be performed using AI, for example, or without AI. For example, the dialogue unit can input patient emotion data into the generation AI and use the generation AI to adjust the length of the dialogue.

[0093] The dialogue unit can adjust the order of dialogue based on the relevance of the generated stories during dialogue. For example, the dialogue unit prioritizes highly relevant stories in the dialogue. The dialogue unit can also postpone less relevant stories in the dialogue. The dialogue unit can also dynamically adjust the order of dialogue according to the relevance of the stories. This enables an optimal dialogue order according to the relevance of the generated stories. Some or all of the above-mentioned processing in the dialogue unit may be performed using, for example, AI, or may be performed without using AI. For example, the dialogue unit can input relevance data of the generated stories to a generation AI, and the generation AI can adjust the order of dialogue.

[0094] The dialogue unit can adjust the timing of the dialogue based on the patient's lifestyle rhythm during the dialogue. For example, if the patient is a morning person, the dialogue unit can conduct the dialogue in the morning. If the patient is a night owl, the dialogue unit can also conduct the dialogue in the evening. The dialogue unit can also dynamically adjust the timing of the dialogue according to the patient's lifestyle rhythm. This enables the optimal dialogue timing according to the patient's lifestyle rhythm. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI, for example, or may be performed without using AI. For example, the dialogue unit can input the patient's lifestyle rhythm data into the generation AI, and the generation AI can adjust the timing of the dialogue.

[0095] During the dialogue, the dialogue unit can adjust the use of technical terminology in the dialogue based on the patient's level of expertise. For example, if the patient has specialized knowledge, the dialogue unit can use a lot of technical terminology. If the patient does not have specialized knowledge, the dialogue unit can also use simple language. The dialogue unit can also adjust the content of the dialogue according to the patient's level of expertise. This enables an optimal dialogue according to the patient's level of expertise. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI, for example, or may be performed without using AI. For example, the dialogue unit can input the patient's level of expertise data into the generation AI, and the generation AI can adjust the use of technical terminology in the dialogue.

[0096] The providing unit can estimate the patient's emotions and adjust the presentation method of the results to be provided based on the estimated patient's emotions. For example, the providing unit can estimate the patient's emotions and adjust the presentation method of the results to be provided based on the estimated patient's emotions. If the patient is relaxed, the providing unit can provide the results in a calm tone. If the patient is excited, the providing unit can provide the results in a lively tone. If the patient is sad, the providing unit can provide the results in a comforting tone. This enables the provision of optimal results according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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-mentioned processing in the providing unit can be performed using AI, for example, or without AI. For example, the providing unit can input patient emotion data into the generation AI, and the generation AI can adjust the presentation method of the results.

[0097] The providing unit can adjust the level of detail of the provided information based on the importance of the dialogue result when providing the information. The providing unit, for example, provides detailed information based on an important dialogue result. The providing unit can also provide concise information based on a less important dialogue result. The providing unit can also adjust the level of detail of the provided information based on the importance of the dialogue result. This enables optimal provision based on the importance of the dialogue result. Some or all of the above-described processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input importance data of the dialogue result to a generating AI, and the generating AI can adjust the level of detail of the provided information.

[0098] The providing unit can analyze the results of the dialogue in real time when providing the data and reflect them in the next dialogue. For example, the providing unit can analyze the results of the dialogue in real time and adjust the content of the next dialogue. The providing unit can also select a topic for the next dialogue based on the results of the dialogue. The providing unit can also analyze the results of the dialogue in real time and adjust how the next dialogue will proceed. This improves the accuracy of the dialogue by reflecting the results of the dialogue in the next dialogue. Some or all of the above-mentioned processing in the providing unit can be performed using AI, for example, or can be performed without using AI. For example, the providing unit can input dialogue result data to a generating AI, which can adjust the content of the next dialogue.

[0099] At the time of provision, the provision unit can improve the accuracy of provision based on the patient's past provision results. The provision unit improves the accuracy of provision, for example, based on the patient's past provision results. The provision unit can also analyze the patient's past provision results and select the optimal provision method. The provision unit can also adjust the content of provision by referring to the patient's past provision results. This enables optimal provision based on the patient's past provision results. Some or all of the above-mentioned processing in the provision unit may be performed, for example, using AI, or may be performed without using AI. For example, the provision unit can input the patient's past provision result data into a generation AI, and the generation AI can improve the accuracy of provision.

[0100] The providing unit can estimate the patient's emotions and determine the priority of results to be provided based on the estimated patient's emotions. For example, the providing unit can estimate the patient's emotions and determine the priority of results to be provided based on the estimated patient's emotions. The providing unit can prioritize providing detailed results when the patient is relaxed. The providing unit can also prioritize providing concise results when the patient is stressed. Furthermore, the providing unit can prioritize providing interesting results when the patient is excited. This makes it possible to provide optimal results according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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-mentioned processing in the providing unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the providing unit can input patient emotion data into the generation AI, and the generation AI can determine the priority of results.

[0101] The providing unit can adjust the order of providing the dialogue results based on the relevance of the dialogue results when providing them. For example, the providing unit can prioritize providing dialogue results with high relevance. The providing unit can also provide dialogue results with low relevance at a later date. The providing unit can also dynamically adjust the order of providing the dialogue results based on the relevance of the dialogue results. This enables optimal provision based on the relevance of the dialogue results. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the providing unit can input relevance data of the dialogue results to a generation AI, and the generation AI can adjust the order of providing the dialogue results.

[0102] The providing unit can adjust the timing of providing the results based on the patient's lifestyle rhythm when providing the results. For example, if the patient is a morning person, the providing unit can provide the results in the morning hours. If the patient is a night owl, the providing unit can also provide the results in the evening hours. The providing unit can also dynamically adjust the timing of providing the results according to the patient's lifestyle rhythm. This enables the optimal timing of providing the results according to the patient's lifestyle rhythm. Some or all of the above-mentioned processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input the patient's lifestyle rhythm data into the generating AI, and the generating AI can adjust the timing of providing the results.

[0103] The providing unit can adjust the use of technical terminology in the provided results based on the patient's level of expertise when providing the results. For example, if the patient has technical expertise, the providing unit can provide results that use a lot of technical terminology. If the patient does not have technical expertise, the providing unit can also provide results in simple language. The providing unit can also adjust the content of the provided results according to the patient's level of expertise. This enables optimal provision according to the patient's level of expertise. Some or all of the above-mentioned processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input the patient's level of expertise data into the generating AI, and the generating AI can adjust the use of technical terminology in the provided results. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, dialogue unit, and provision unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit uses the camera 42 and microphone 38B of the smart device 14 to collect information on the patient's hobbies, career, photos, and favorite television programs and music. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected information using a generation AI and generates a story related to the patient's topics of interest and hobbies. The dialogue unit, realized, for example, by the control unit 46A of the smart device 14, engages in a dialogue with the patient based on the generated story. The provision unit, realized, for example, by the specific processing unit 290 of the data processing device 12, records the results of the dialogue and uses them for the next dialogue. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, dialogue unit, and provision unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit uses the camera 42 and microphone 238 of the smart glasses 214 to collect information on the patient's hobbies, career, photos, and favorite television programs and music. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected information using a generation AI and generates a story related to the patient's topics of interest and hobbies. The dialogue unit, realized, for example, by the control unit 46A of the smart glasses 214, engages in a dialogue with the patient based on the generated story. The provision unit, realized, for example, by the specific processing unit 290 of the data processing device 12, records the results of the dialogue and uses them for the next dialogue. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, analysis unit, dialogue unit, and provision unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit uses the camera 42 and microphone 238 of the headset-type terminal 314 to collect information on the patient's hobbies, career, photos, and favorite television programs and music. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the collected information using a generation AI to generate a story related to the patient's topics of interest and hobbies. The dialogue unit is realized, for example, by the control unit 46A of the headset-type terminal 314 and engages in a dialogue with the patient based on the generated story. The provision unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and records the results of the dialogue to use in the next dialogue. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, analysis unit, dialogue unit, and provision unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit uses the camera 42 and microphone 238 of the robot 414 to collect information on the patient's hobbies, career, photos, and favorite television programs and music. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected information using a generation AI to generate a story related to the patient's topics of interest and hobbies. The dialogue unit is realized, for example, by the control unit 46A of the robot 414, and engages in a dialogue with the patient based on the generated story. The provision unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and records the results of the dialogue to use in the next dialogue.

[0104] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0105] When the dialogue unit engages in a dialogue with a patient based on the generated story, it can customize the content of the dialogue based on the patient's past dialogue history. For example, the dialogue unit can arouse interest in the dialogue by prioritizing topics and episodes that the patient liked in the past. The dialogue unit can also identify topics that the patient wants to avoid from the past dialogue history and avoid them to facilitate the dialogue. Furthermore, the dialogue unit can promote memory activation by analyzing the past dialogue history and revisiting episodes to which the patient particularly responded. This allows the dialogue unit to utilize the patient's past dialogue history to realize more effective dialogue.

[0106] The collection unit can analyze the patient's social media activity and collect related information. For example, the collection unit can collect related information based on photos and posts shared by the patient on social media. The collection unit can also collect related information by referring to the activities of the patient's friends on social media. Furthermore, the collection unit can analyze the patient's interests and concerns on social media and collect related information. This enables effective collection of information based on the patient's social media activity.

[0107] When analyzing collected information, the analysis unit can apply different analysis algorithms based on the category of the information. For example, a music analysis algorithm can be applied to information about music. An image analysis algorithm can be applied to information about photos. A video analysis algorithm can be applied to information about television programs. This allows for optimal analysis according to the category of information.

[0108] The dialogue unit can analyze the patient's response in real time during the dialogue and dynamically change the content of the dialogue. For example, if the patient shows interest, the dialogue can continue with a topic related to that. If the patient shows no interest, the dialogue can switch to a different topic. The dialogue unit can also adjust the content of the dialogue in real time according to the patient's response. This allows for optimal dialogue according to the patient's response.

[0109] The providing unit can adjust the level of detail of the provided information based on the importance of the dialogue result when providing the information. For example, detailed information can be provided based on an important dialogue result. Brief information can also be provided based on a less important dialogue result. The level of detail of the provided information can also be adjusted according to the importance of the dialogue result. This makes it possible to provide the most appropriate information according to the importance of the dialogue result.

[0110] The collection unit can estimate the patient's emotions and adjust the timing of information collection based on the estimated patient emotions. For example, when the patient is relaxed, interviews with family members or caregivers can be conducted to collect information. When the patient is feeling stressed, information collection can be temporarily suspended and resumed later. Furthermore, when the patient is excited, simple questions can be asked in a short period of time to collect information. This allows for more appropriate information collection by adjusting the timing of information collection according to the patient's emotions.

[0111] The analysis unit can estimate the patient's emotions and adjust the way the story is presented based on the estimated patient emotions. For example, if the patient is relaxed, the analysis unit can generate a story in a calm tone. If the patient is excited, the analysis unit can generate a story in a lively tone. Furthermore, if the patient is sad, the analysis unit can generate a story in a comforting tone. This makes it possible to present the optimal story according to the patient's emotions.

[0112] The dialogue unit can estimate the patient's emotions and adjust the dialogue progression based on the estimated patient's emotions. For example, if the patient is relaxed, the dialogue can proceed at a slow pace. If the patient is excited, the dialogue can proceed at a lively pace. Furthermore, if the patient is sad, the dialogue can proceed in a comforting tone. This makes it possible to optimally progress the dialogue according to the patient's emotions.

[0113] The dialogue unit can estimate the patient's emotions and adjust the length of the dialogue based on the estimated patient's emotions. For example, if the patient is relaxed, the dialogue can be longer. If the patient is in a hurry, the dialogue can be shorter. Furthermore, if the patient is excited, the dialogue can be of an appropriate length. This makes it possible to optimize the length of the dialogue according to the patient's emotions.

[0114] The providing unit can estimate the patient's emotions and adjust the way in which the results are presented based on the estimated patient's emotions. For example, if the patient is relaxed, the results can be presented in a calm tone. If the patient is excited, the results can be presented in a lively tone. Furthermore, if the patient is sad, the results can be presented in a comforting tone. This makes it possible to provide optimal results according to the patient's emotions.

[0115] The processing flow of the second embodiment will be briefly explained below.

[0116] Step 1: The collection unit collects information about the patient's hobbies or career history, photos, and favorite TV programs or music. For example, the collection unit can collect information by using interviews or questionnaires with family members or caregivers. The collection unit can also analyze the patient's past behavioral history and select the optimal information collection method. For example, the collection unit can create related questions based on the patient's favorite activities in the past and collect information. Step 2: The analysis unit uses a generation AI to analyze the information collected by the collection unit and generate stories related to topics and hobbies that the patient was interested in. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and uses these to generate stories. For example, the generation AI may generate stories related to the music the patient liked when they were young or anecdotes about their hobbies. Step 3: The dialogue unit engages in a dialogue with the patient based on the generated story. For example, the dialogue unit stimulates the patient's memory by reading the generated story aloud or asking related questions. The dialogue unit can also estimate the patient's emotions and adjust the way the dialogue proceeds based on the estimated patient emotions. For example, if the patient is relaxed, the dialogue will proceed at a slower pace. Step 4: The providing unit records the results of the dialogue and uses them for the next dialogue. The providing unit can, for example, analyze the results of the dialogue in real time and adjust the content of the next dialogue. As a result, the dialogue support system according to the embodiment facilitates dialogue with dementia patients and activates the patients' memories.

[0117] 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.

[0118] 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 generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. 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 a data format such as voice data and text data. 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0119] 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.

[0120] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0121] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text 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 model 58 includes AI 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] 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.

[0136] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0137] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0138] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text 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 model 58 includes AI 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] 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.

[0152] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0153] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text 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 model 58 includes AI 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0168] 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.

[0169] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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).

[0174] 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 expressed, and when they approach the ideal, a state of pleasure is expressed. 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 expressed, and when they approach the ideal, a state of pleasure is expressed. 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.

[0175] 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."

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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, in order to avoid confusion and to 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.

[0187] 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.

[0188] [Explanation of symbols]

[0189] 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 collection department that collects information on the patient's hobbies or career, photos, favorite TV shows or music; an analysis unit that analyzes the information collected by the collection unit; a dialogue unit that uses the story generated by the analysis unit in dialogue with a patient; a providing unit that provides the results of the story used by the dialogue unit A system characterized by:

2. The collecting unit Gather information using interviews or questionnaires from family members or caregivers 2. The system of claim 1.

3. The analysis unit Analyze the collected information and generate stories related to the patient's interests or hobbies 2. The system of claim 1.

4. The dialogue unit Engage in dialogue with patients based on the generated story 2. The system of claim 1.

5. The providing unit Record the results of the conversation and use them for the next conversation.

2. The system of claim 1.

6. The collecting unit Estimate the patient's emotions and adjust the timing of information collection based on the estimated patient emotions.

2. The system of claim 1.

7. The collecting unit Analyze the patient's past behavioral history and select the appropriate method of collecting information 2. The system of claim 1.

8. The collecting unit When collecting information, filter it based on the patient's current health or living situation.

2. The system of claim 1.

Images