system

Abstract

An object of a system according to an embodiment is to facilitate communication in collaboration between different cultures.SOLUTION: A system includes a holding unit, a generation unit, and a provision unit. The holding unit holds information of each individual. The generation unit generates a group LLM on the basis of the information held by the holding unit. The provider provides a chat based on the group LLM generated by the generator.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] With conventional technology, there was a communication skill barrier when collaborating with people from different cultures, and interactions between people meeting for the first time were mentally stressful.

[0005] The system according to the embodiment aims to facilitate communication in cross-cultural collaboration. [Means for solving the problem]

[0006] The system according to the embodiment includes a storage unit, a generation unit, and a provision unit. The storage unit stores information about each individual. The generation unit generates a group LLM based on the information stored by the storage unit. The provision unit provides chat based on the group LLM generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can facilitate communication in cross-cultural collaboration. [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 communication support system according to an embodiment of the present invention generates a group LLM based on individual information and provides casual conversation. The communication support system maintains a large-scale language model (LLM) for each individual, which represents their own understanding. It then merges these LLMs to generate a new LLM that represents a group. This group LLM retains all the characteristics of each individual's LLM and generates casual conversations that satisfy the group's interests and preferences. This lowers the barriers to communication between people meeting for the first time and reduces mental stress. For example, the communication support system maintains an LLM for each individual, which represents their own understanding. This LLM learns each individual's hobbies, preferences, past conversation history, and other information, providing a good understanding of each individual's characteristics. Next, when multiple individuals gather, the LLMs of each individual are merged to generate a group LLM. This group LLM retains all the characteristics of each individual's LLM and understands the hobbies and preferences of the entire group. The generated group LLM generates casual conversations that satisfy the group's interests and preferences. This facilitates smooth communication between people meeting for the first time and reduces mental stress. This communication support system can invigorate cross-cultural collaboration and promote the creation of new value. This allows the communication support system to facilitate cross-cultural collaboration. For example, in international conferences or project teams where people from different countries and cultures come together, the Group LLM can act as a communication intermediary, enabling smooth dialogue and facilitating collaboration.

[0029] A communication support system according to an embodiment includes a storage unit, a generation unit, and a providing unit. The storage unit stores information about each individual. The information about each individual includes, for example, name, age, hobbies, preferences, and past dialogue history, but is not limited to these examples. The storage unit learns, for example, the individual's hobbies, preferences, and past dialogue history. The generation unit generates a group LLM based on the information stored by the storage unit. For example, the generation unit merges the LLMs of each individual to generate the group LLM. The generation unit can use a generation AI to integrate the LLMs of each individual to generate the group LLM. The providing unit provides small talk based on the group LLM generated by the generation unit. For example, the providing unit generates small talk that satisfies the hobbies and preferences of the group. The providing unit can use a generation AI to generate small talk based on the group LLM. As a result, the communication support system according to an embodiment generates a group LLM based on the information of each individual and provides small talk, thereby facilitating collaboration between people of different cultures.

[0030] The storage unit can learn an individual's hobbies and preferences, and past dialogue history. Hobbies and preferences include, but are not limited to, music genres, types of sports, and food preferences. The storage unit, for example, learns an individual's hobbies and preferences. The storage unit can also learn past dialogue history. Past dialogue history includes, but is not limited to, the duration of dialogue and the format of data to be stored. The storage unit, for example, learns past dialogue history. By learning an individual's hobbies and preferences and past dialogue history, more accurate personal information can be retained. Some or all of the above-described processing in the storage unit may be performed, for example, using AI, or may be performed without using AI. For example, the storage unit can input an individual's hobbies and preferences and past dialogue history into the generation AI and cause the generation AI to perform learning.

[0031] The generation unit can merge the LLMs of each individual to generate a collective LLM. Merging includes, for example, an algorithm for integrating the LLMs of each individual, but is not limited to such an example. The generation unit can, for example, merge the LLMs of each individual to generate a collective LLM. When merging, the generation unit can also weight each individual's LLM. For example, the generation unit weights each individual's LLM based on the importance of each individual's LLM. The generation unit can use a generation AI to integrate each individual's LLM and generate a collective LLM. In this way, by merging each individual's LLM, a collective LLM that understands the hobbies and preferences of the entire group can be generated. Some or all of the above-described processing in the generation unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the generation unit can input each individual's LLM into the generation AI and cause the generation AI to generate a collective LLM.

[0032] The providing unit can generate chatter that satisfies the hobbies and preferences of the group. Satisfying the hobbies and preferences includes, but is not limited to, providing topics and content that match the hobbies and preferences of the group. For example, the providing unit can generate chatter that satisfies the hobbies and preferences of the group. The providing unit can generate chatter based on the group LLM using a generation AI. The providing unit can also evaluate the quality of the generated chatter. For example, the providing unit can evaluate the naturalness and accuracy of the information in the generated chatter. This allows for smooth communication between people who have just met by generating chatter that satisfies the hobbies and preferences of the group. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input the group LLM into the generation AI and cause the generation AI to generate chatter.

[0033] The providing unit can evaluate the quality of the generated chat. Examples of evaluating the quality include, but are not limited to, user feedback, naturalness of the dialogue, and accuracy of the information. The providing unit can evaluate the quality of the generated chat, for example. The providing unit can evaluate the quality of the generated chat using a generation AI. For example, the providing unit evaluates the quality of the chat based on user feedback. The providing unit can also evaluate the quality of the chat based on the naturalness of the dialogue. The providing unit can also evaluate the quality of the chat based on the accuracy of the information. In this way, by evaluating the quality of the generated chat, higher quality chat can be provided. 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 generated chat to the generation AI and cause the generation AI to evaluate the quality.

[0034] The storage unit can detect changes in an individual's hobbies and preferences in real time and automatically update the stored information. Real-time detection can be achieved, for example, by using a sensor, an algorithm, and detection accuracy, but is not limited to these examples. The storage unit, for example, detects changes in an individual's hobbies and preferences in real time. The storage unit automatically updates the stored information based on the detected information. For example, if a user starts a new hobby, the storage unit can detect the information in real time and add it to the stored information. If a user loses interest in a particular hobby, the storage unit can also detect the information in real time and delete it from the stored information. If a user takes an action that indicates a new preference, the storage unit can also detect the information in real time and reflect it in the stored information. This allows changes in an individual's hobbies and preferences to be detected in real time and automatically update the stored information, thereby always maintaining the latest information. Some or all of the above-described processing in the storage unit can be performed using, for example, AI, or without AI. For example, the storage unit can input changes in an individual's hobbies and preferences into a generation AI and have the generation AI update the information.

[0035] The storage unit can analyze an individual's dialogue history and classify hobbies and preferences in detail based on the frequency of appearance of specific keywords and phrases. Specific keywords and phrases include, but are not limited to, frequency of appearance and co-occurrence relationships. The storage unit, for example, analyzes the individual's dialogue history. The storage unit classifies hobbies and preferences in detail based on the frequency of appearance of specific keywords and phrases. For example, the storage unit can analyze the frequency of appearance of keywords related to a specific music genre from the user's dialogue history and classify them as hobbies. The storage unit can also analyze the frequency of appearance of phrases related to a specific sport from the user's dialogue history and classify them as preferences. The storage unit can also analyze the frequency of appearance of keywords related to a specific dish from the user's dialogue history and classify them as hobbies. In this way, by analyzing an individual's dialogue history, hobbies and preferences can be classified in detail and more accurate information can be stored. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or without AI. For example, the storage unit can input the individual's dialogue history into a generation AI and cause the generation AI to classify hobbies and preferences.

[0036] The storage unit can learn an individual's lifestyle rhythm and activity patterns and acquire and update information at appropriate times. Life rhythms and activity patterns include, but are not limited to, daily behavior and activities by time period. The storage unit, for example, learns an individual's lifestyle rhythm and activity patterns. The storage unit acquires and updates information at appropriate times based on the learned information. For example, if a user is more active in the morning, the storage unit acquires and updates information in the morning. If a user is more active in the evening, the storage unit can also acquire and update information in the evening. If a user is more active on weekends, the storage unit can also acquire and update information on weekends. This allows information to be acquired and updated based on an individual's lifestyle rhythm and activity patterns, enabling information to be managed at more appropriate times. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without AI. For example, the storage unit may input an individual's lifestyle rhythm and activity patterns into a generation AI and cause the generation AI to acquire and update information.

[0037] The storage unit can analyze the individual's social media activity and supplement information about hobbies and preferences. Social media activity includes, but is not limited to, post content, number of likes, and comments. The storage unit, for example, analyzes the individual's social media activity. The storage unit supplements information about hobbies and preferences. For example, the storage unit analyzes content frequently posted by the user on social media and supplements information about hobbies and preferences. The storage unit can also analyze accounts the user follows on social media and supplement information about hobbies and preferences. The storage unit can also analyze groups the user participates in on social media and supplement information about hobbies and preferences. In this way, by analyzing social media activity, information about hobbies and preferences can be supplemented and more accurate information can be retained. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the individual's social media activity into a generation AI and cause the generation AI to supplement information about hobbies and preferences.

[0038] The storage unit can add region-specific hobbies and preferences to the retained information based on the individual's geographical location information. Geographical location information includes, but is not limited to, GPS data and location information services. The storage unit, for example, considers the individual's geographical location information. The storage unit adds region-specific hobbies and preferences to the retained information. For example, if the user lives in a specific region, the storage unit adds region-specific hobbies and preferences to the retained information. If the user frequently visits a specific region, the storage unit can also add region-specific hobbies and preferences to the retained information. If the user is often active in a specific region, the storage unit can also add region-specific hobbies and preferences to the retained information. By taking geographical location information into consideration, region-specific hobbies and preferences can be added to the retained information, thereby enabling more accurate information to be retained. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or without AI. For example, the storage unit can input the individual's geographical location information to the generation AI and cause the generation AI to add region-specific hobbies and preferences.

[0039] The storage unit can improve the accuracy of the retained information by reflecting the individual's past feedback. Past feedback includes, for example, user ratings, comments, survey results, etc., but is not limited to these examples. The storage unit, for example, reflects the individual's past feedback. The storage unit improves the accuracy of the retained information. The storage unit, for example, improves the accuracy of the retained information based on feedback provided by the user in the past. The storage unit can also improve the accuracy of the retained information based on information evaluated by the user in the past. The storage unit can also improve the accuracy of the retained information based on comments provided by the user in the past. In this way, the accuracy of the retained information can be improved by reflecting the past feedback. Some or all of the above-mentioned processing in the storage unit may be performed using AI, for example, or may be performed without using AI. For example, the storage unit can input the individual's past feedback into the generation AI and cause the generation AI to improve the accuracy of the information.

[0040] The generation unit can improve the accuracy of generating the group LLM by taking into account the interrelationships between each individual's LLM. Consideration of the interrelationships includes, for example, the strength of relationships, common hobbies and preferences, etc., but is not limited to these examples. The generation unit, for example, considers the interrelationships between each individual's LLM. The generation unit improves the accuracy of generating the group LLM. For example, the generation unit extracts commonalities between each individual's LLM to improve the accuracy of generating the group LLM. The generation unit can also improve the accuracy of generating the group LLM by taking into account differences between each individual's LLM. The generation unit can also analyze the interrelationships between each individual's LLM to improve the accuracy of generating the group LLM. In this way, by taking into account the interrelationships between each individual's LLM, the accuracy of generating the group LLM can be improved. Some or all of the above-described processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the interrelationships between each individual's LLM into the generation AI and cause the generation AI to improve the generation accuracy.

[0041] The generation unit can adjust the generation algorithm taking into account individual attribute information when generating the collective LLM. Attribute information includes, but is not limited to, age, occupation, and gender. For example, the generation unit can consider individual attribute information when generating the collective LLM. The generation unit adjusts the generation algorithm. For example, the generation unit can optimize the generation algorithm taking into account the individual's age when generating the collective LLM. The generation unit can also optimize the generation algorithm taking into account the individual's occupation when generating the collective LLM. The generation unit can also optimize the generation algorithm taking into account the individual's interests and concerns when generating the collective LLM. This allows for the generation of a more appropriate collective LLM by taking into account individual attribute information. Some or all of the above-described processing in the generation unit can be performed using, or without, a generation AI. For example, the generation unit can input individual attribute information into the generation AI and cause the generation AI to adjust the generation algorithm.

[0042] The generation unit may weight the individual's dialogue history based on its importance when generating the collective LLM. Examples of weighting include, but are not limited to, the importance, frequency, and content relevance of the dialogue history. For example, the generation unit may weight the individual's dialogue history based on its importance when generating the collective LLM. For example, the generation unit may weight the individual's dialogue history based on its frequency when generating the collective LLM. For example, the generation unit may weight the individual's dialogue history based on its content when generating the collective LLM. For example, the generation unit may weight the individual's dialogue history based on its length when generating the collective LLM. Thus, weighting the individual's dialogue history based on its importance allows for the generation of a more appropriate collective LLM. Some or all of the above-described processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit may input the individual's dialogue history into the generation AI and cause the generation AI to perform weighting.

[0043] The generation unit can adjust the generation algorithm taking into account the geographic distribution of individuals when generating the group LLM. Geographic distribution includes, but is not limited to, regional population distribution, cultural background, etc. For example, the generation unit can adjust the generation algorithm taking into account the geographic distribution of individuals when generating the group LLM. For example, the generation unit can adjust the generation algorithm taking into account the geographic distribution of individuals when generating the group LLM. The generation unit can also generate region-specific topics based on the geographic distribution of individuals when generating the group LLM. The generation unit can also reflect cultural background by taking into account the geographic distribution of individuals when generating the group LLM. In this way, by taking into account the geographic distribution of individuals, a group LLM that reflects region-specific topics can be generated. Some or all of the above-described processing in the generation unit can be performed using, or without, a generation AI. For example, the generation unit can input the geographic distribution of individuals into the generation AI and cause the generation AI to adjust the generation algorithm.

[0044] The generation unit can improve the generation accuracy by referring to related literature and data when generating the collective LLM. Examples of related literature and data include, but are not limited to, academic papers, databases, and statistical data. For example, the generation unit can refer to related literature and data when generating the collective LLM. The generation unit improves the generation accuracy. For example, the generation unit can improve the generation accuracy by referring to related literature when generating the collective LLM. The generation unit can also improve the generation accuracy by referring to related data when generating the collective LLM. The generation unit can also improve the generation accuracy by referring to related research results when generating the collective LLM. In this way, by referring to related literature and data, the generation accuracy of the collective LLM can be improved. Some or all of the above-described processing in the generation unit can be performed using, or without, a generation AI. For example, the generation unit can input related literature and data into the generation AI and cause the generation AI to improve the generation accuracy.

[0045] When generating a population LLM, the generation unit can optimize the generation algorithm taking into account the market value and business needs of the population. Market value and business needs include, but are not limited to, market research results, business models, and customer needs. For example, when generating a population LLM, the generation unit considers the market value and business needs of the population. The generation unit optimizes the generation algorithm. For example, when generating a population LLM, the generation unit optimizes the generation algorithm taking into account the market value of the population. When generating a population LLM, the generation unit can also optimize the generation algorithm taking into account the business needs of the population. When generating a population LLM, the generation unit can also optimize the generation algorithm taking into account the economic background of the population. In this way, by taking into account the market value and business needs, a population LLM suitable for business can be generated. Some or all of the above-described processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the market value and business needs of the population into the generation AI and cause the generation AI to optimize the generation algorithm.

[0046] The providing unit can customize the content of the chat to be provided based on the past dialogue history of the group. The past dialogue history includes, for example, the duration of the dialogue and the format of the data to be saved, but is not limited to these examples. The providing unit, for example, customizes the content of the chat to be provided based on the past dialogue history of the group. The providing unit, for example, extracts common topics from the past dialogue history of the group and provides the chat. The providing unit can also extract interesting topics from the past dialogue history of the group and provide the chat. The providing unit can also provide the chat based on common hobbies and preferences from the past dialogue history of the group. In this way, by customizing the content of the chat based on the past dialogue history, more relevant topics can be provided. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the past dialogue history of the group to a generation AI and cause the generation AI to customize the chat.

[0047] The providing unit can associate the content of the chat to the group's current activities or projects. Current activities and projects include, but are not limited to, ongoing projects, team goals, etc. For example, the providing unit associates the content of the chat to the group's current activities or projects. For example, the providing unit can provide topics related to the group's current projects to promote communication between members. The providing unit can also provide topics related to the group's current activities to help members find common interests. The providing unit can also provide topics related to the group's current goals to raise awareness toward goal achievement. In this way, providing topics related to the current activities or projects can promote communication between members. Some or all of the above-described processing in the providing unit may be performed using, or without, AI. For example, the providing unit can input information about the group's current activities and projects into the generation AI and cause the generation AI to execute the content of the chat.

[0048] The providing unit can continuously improve the content of the chat to be provided by reflecting group feedback. Feedback includes, for example, user ratings, comments, survey results, etc., but is not limited to these examples. The providing unit, for example, continuously improves the content of the chat to be provided by reflecting group feedback. For example, the providing unit improves the content of the chat based on group feedback and provides more interesting topics. The providing unit can also adjust the tone of the chat based on group feedback to achieve more appropriate communication. The providing unit can also adjust the frequency of the chat and provide topics at appropriate times based on group feedback. In this way, more interesting topics can be provided by reflecting the feedback. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input group feedback to a generation AI and cause the generation AI to improve the chat.

[0049] The providing unit can customize the content of the chat to be provided by taking into account the geographical location information of the group. Geographical location information includes, but is not limited to, GPS data, location information services, etc. For example, the providing unit customizes the content of the chat to be provided by taking into account the geographical location information of the group. For example, the providing unit provides topics specific to a region based on the geographical location information of the group. The providing unit can also provide topics related to local events and news based on the geographical location information of the group. The providing unit can also provide topics related to local culture and customs based on the geographical location information of the group. In this way, by taking the geographical location information into account, it is possible to provide topics specific to a region. Some or all of the above-described processing in the providing unit may be performed using, or without using, AI. For example, the providing unit can input the geographical location information of the group to a generating AI and cause the generating AI to customize the chat.

[0050] The providing unit can analyze the social media activity of the group to increase the relevance of the content of the chat to be provided. Social media activity includes, but is not limited to, for example, the content of posts, the number of likes, and comments. For example, the providing unit analyzes the social media activity of the group to increase the relevance of the content of the chat to be provided. For example, the providing unit analyzes the social media activity of the group to provide common topics. The providing unit can also analyze the social media activity of the group to provide interesting topics. The providing unit can also analyze the social media activity of the group to provide topics based on common hobbies and preferences. In this way, more relevant topics can be provided by analyzing the social media activity. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the social media activity of the group to a generation AI and cause the generation AI to execute the content of the chat.

[0051] The providing unit can improve the accuracy of the content of the chat to be provided by reflecting past feedback from the group. Past feedback includes, for example, user ratings, comments, survey results, etc., but is not limited to these examples. For example, the providing unit improves the accuracy of the content of the chat to be provided by reflecting past feedback from the group. For example, the providing unit improves the content of the chat and provides more interesting topics based on the past feedback from the group. The providing unit can also adjust the tone of the chat based on the past feedback from the group to achieve more appropriate communication. The providing unit can also adjust the frequency of the chat and provide topics at appropriate times based on the past feedback from the group. In this way, by reflecting past feedback, more accurate topics can be provided. Some or all of the above-mentioned processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the past feedback of the group into the generation AI and cause the generation AI to improve the accuracy of the chat.

[0052] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0053] The storage unit can acquire the user's health data and reflect it in the personal information. For example, it acquires health data such as the user's heart rate, sleep patterns, and amount of exercise to understand the individual's health condition. The storage unit can also estimate the user's stress level and fatigue level based on the user's health data and reflect this in the personal information. This enables more appropriate communication support based on the user's health condition. Some or all of the above-mentioned processing in the storage unit may be performed using, for example, a sensor or application that acquires health data, or may be performed without using AI. For example, the storage unit can input the user's health data into a generation AI and have the generation AI estimate the health condition.

[0054] The generation unit can analyze the user's past dialogue history and adjust the population LLM generation algorithm based on the frequency of occurrence of specific keywords and phrases. For example, the generation unit can analyze the frequency of occurrence of keywords related to a specific music genre from the user's dialogue history and reflect this in the population LLM generation algorithm. The generation unit can also analyze the frequency of occurrence of phrases related to a specific sport from the user's dialogue history and reflect this in the population LLM generation algorithm. This allows for the generation of a more accurate population LLM based on the user's dialogue history. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or can be performed without using AI. For example, the generation unit can input the user's dialogue history into the generation AI and cause the generation AI to adjust the generation algorithm.

[0055] The storage unit can analyze the user's social media activity and supplement information about hobbies and preferences. For example, it can analyze content that the user frequently posts on social media and supplement information about hobbies and preferences. The storage unit can also analyze accounts that the user follows on social media and supplement information about hobbies and preferences. The storage unit can also analyze groups that the user participates in on social media and supplement information about hobbies and preferences. In this way, by analyzing social media activity, information about hobbies and preferences can be supplemented and more accurate information can be retained. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input an individual's social media activity into a generation AI and cause the generation AI to supplement information about hobbies and preferences.

[0056] The providing unit can customize the content of the chat to be provided based on the past dialogue history of the group. For example, the providing unit can extract common topics from the past dialogue history of the group and provide the chat. The providing unit can also extract interesting topics from the past dialogue history of the group and provide the chat. The providing unit can also provide the chat based on common hobbies and preferences from the past dialogue history of the group. In this way, by customizing the content of the chat based on the past dialogue history, more relevant topics can be provided. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the past dialogue history of the group into a generating AI and cause the generating AI to customize the chat.

[0057] The storage unit can add region-specific hobbies and preferences to the retained information based on the individual's geographical location information. For example, if a user lives in a specific region, the storage unit can add region-specific hobbies and preferences to the retained information. If a user frequently visits a specific region, the storage unit can also add region-specific hobbies and preferences to the retained information. If a user is often active in a specific region, the storage unit can also add region-specific hobbies and preferences to the retained information. This allows region-specific hobbies and preferences to be added to the retained information by taking geographical location information into consideration, thereby enabling more accurate information to be retained. Some or all of the above-described processing in the storage unit may be performed using AI, for example, or may be performed without using AI. For example, the storage unit can input the individual's geographical location information to the generation AI and cause the generation AI to add region-specific hobbies and preferences.

[0058] The generation unit can improve the generation accuracy by referring to related literature and data when generating the collective LLM. For example, the generation accuracy can be improved by referring to related literature when generating the collective LLM. The generation unit can also improve the generation accuracy by referring to related data when generating the collective LLM. The generation unit can also improve the generation accuracy by referring to related research results when generating the collective LLM. In this way, by referring to related literature and data, the generation accuracy of the collective LLM can be improved. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit can input related literature and data into the generation AI and cause the generation AI to improve the generation accuracy.

[0059] The providing unit can associate the content of the chat to be provided with the group's current activities or projects. For example, it can provide topics related to the group's current projects to promote communication between members. The providing unit can also provide topics related to the group's current activities to help members find common interests. The providing unit can also provide topics related to the group's current goals to raise awareness toward goal achievement. In this way, providing topics related to the current activities or projects can promote communication between members. Some or all of the above-described processing in the providing unit may be performed using, or without, AI, for example. For example, the providing unit can input information about the group's current activities or projects into the generating AI and have the generating AI execute the content of the chat.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The storage unit stores information about each individual. This information includes the individual's name, age, hobbies, preferences, and past interaction history. The storage unit learns the individual's hobbies, preferences, and past interaction history. Step 2: The generation unit generates a population LLM based on the information stored by the storage unit. The generation unit merges the LLMs of each individual to generate a population LLM, and integrates the LLMs of each individual using the generation AI. Step 3: The provider provides chats based on the group LLM generated by the generator. The provider generates chats that satisfy the hobbies and preferences of the group, and generates chats based on the group LLM using a generation AI.

[0062] (Example 2) A communication support system according to an embodiment of the present invention generates a group LLM based on individual information and provides casual conversation. The communication support system maintains a large-scale language model (LLM) for each individual, which represents their own understanding. It then merges these LLMs to generate a new LLM that represents a group. This group LLM retains all the characteristics of each individual's LLM and generates casual conversations that satisfy the group's interests and preferences. This lowers the barriers to communication between people meeting for the first time and reduces mental stress. For example, the communication support system maintains an LLM for each individual, which represents their own understanding. This LLM learns each individual's hobbies, preferences, past conversation history, and other information, providing a good understanding of each individual's characteristics. Next, when multiple individuals gather, the LLMs of each individual are merged to generate a group LLM. This group LLM retains all the characteristics of each individual's LLM and understands the hobbies and preferences of the entire group. The generated group LLM generates casual conversations that satisfy the group's interests and preferences. This facilitates smooth communication between people meeting for the first time and reduces mental stress. This communication support system can invigorate cross-cultural collaboration and promote the creation of new value. This allows the communication support system to facilitate cross-cultural collaboration. For example, in international conferences or project teams where people from different countries and cultures come together, the Group LLM can act as a communication intermediary, enabling smooth dialogue and facilitating collaboration.

[0063] A communication support system according to an embodiment includes a storage unit, a generation unit, and a providing unit. The storage unit stores information about each individual. The information about each individual includes, for example, name, age, hobbies, preferences, and past dialogue history, but is not limited to these examples. The storage unit learns, for example, the individual's hobbies, preferences, and past dialogue history. The generation unit generates a group LLM based on the information stored by the storage unit. For example, the generation unit merges the LLMs of each individual to generate the group LLM. The generation unit can use a generation AI to integrate the LLMs of each individual to generate the group LLM. The providing unit provides small talk based on the group LLM generated by the generation unit. For example, the providing unit generates small talk that satisfies the hobbies and preferences of the group. The providing unit can use a generation AI to generate small talk based on the group LLM. As a result, the communication support system according to an embodiment generates a group LLM based on the information of each individual and provides small talk, thereby facilitating collaboration between people of different cultures.

[0064] The storage unit can learn an individual's hobbies and preferences, and past dialogue history. Hobbies and preferences include, but are not limited to, music genres, types of sports, and food preferences. The storage unit, for example, learns an individual's hobbies and preferences. The storage unit can also learn past dialogue history. Past dialogue history includes, but is not limited to, the duration of dialogue and the format of data to be stored. The storage unit, for example, learns past dialogue history. By learning an individual's hobbies and preferences and past dialogue history, more accurate personal information can be retained. Some or all of the above-described processing in the storage unit may be performed, for example, using AI, or may be performed without using AI. For example, the storage unit can input an individual's hobbies and preferences and past dialogue history into the generation AI and cause the generation AI to perform learning.

[0065] The generation unit can merge the LLMs of each individual to generate a collective LLM. Merging includes, for example, an algorithm for integrating the LLMs of each individual, but is not limited to such an example. The generation unit can, for example, merge the LLMs of each individual to generate a collective LLM. When merging, the generation unit can also weight each individual's LLM. For example, the generation unit weights each individual's LLM based on the importance of each individual's LLM. The generation unit can use a generation AI to integrate each individual's LLM and generate a collective LLM. In this way, by merging each individual's LLM, a collective LLM that understands the hobbies and preferences of the entire group can be generated. Some or all of the above-described processing in the generation unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the generation unit can input each individual's LLM into the generation AI and cause the generation AI to generate a collective LLM.

[0066] The providing unit can generate chatter that satisfies the hobbies and preferences of the group. Satisfying the hobbies and preferences includes, but is not limited to, providing topics and content that match the hobbies and preferences of the group. For example, the providing unit can generate chatter that satisfies the hobbies and preferences of the group. The providing unit can generate chatter based on the group LLM using a generation AI. The providing unit can also evaluate the quality of the generated chatter. For example, the providing unit can evaluate the naturalness and accuracy of the information in the generated chatter. This allows for smooth communication between people who have just met by generating chatter that satisfies the hobbies and preferences of the group. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input the group LLM into the generation AI and cause the generation AI to generate chatter.

[0067] The providing unit can evaluate the quality of the generated chat. Examples of evaluating the quality include, but are not limited to, user feedback, naturalness of the dialogue, and accuracy of the information. The providing unit can evaluate the quality of the generated chat, for example. The providing unit can evaluate the quality of the generated chat using a generation AI. For example, the providing unit evaluates the quality of the chat based on user feedback. The providing unit can also evaluate the quality of the chat based on the naturalness of the dialogue. The providing unit can also evaluate the quality of the chat based on the accuracy of the information. In this way, by evaluating the quality of the generated chat, higher quality chat can be provided. 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 generated chat to the generation AI and cause the generation AI to evaluate the quality.

[0068] The storage unit can estimate the user's emotions and adjust the update frequency of the personal information based on the estimated user emotions. Estimating emotions can include, but is not limited to, the algorithm used, the type of emotion, and the accuracy of estimation. The storage unit estimates the user's emotions. The storage unit adjusts the update frequency of the personal information based on the estimated user emotions. Adjusting the update frequency can include, but is not limited to, an update interval depending on changes in emotions and trigger conditions for updates. For example, if the user is feeling stressed, the storage unit can set the update frequency low to minimize changes to the information. If the user is relaxed, the storage unit can also set the update frequency high to reflect the latest information. If the user is excited, the storage unit can also set the update frequency to a medium level to update the information appropriately. This enables more appropriate information management by adjusting the update frequency of the personal information according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit may input user emotion data to the generation AI and cause the generation AI to estimate the emotion.

[0069] The storage unit can detect changes in an individual's hobbies and preferences in real time and automatically update the stored information. Real-time detection can be achieved, for example, by using a sensor, an algorithm, and detection accuracy, but is not limited to these examples. The storage unit, for example, detects changes in an individual's hobbies and preferences in real time. The storage unit automatically updates the stored information based on the detected information. For example, if a user starts a new hobby, the storage unit can detect the information in real time and add it to the stored information. If a user loses interest in a particular hobby, the storage unit can also detect the information in real time and delete it from the stored information. If a user takes an action that indicates a new preference, the storage unit can also detect the information in real time and reflect it in the stored information. This allows changes in an individual's hobbies and preferences to be detected in real time and automatically update the stored information, thereby always maintaining the latest information. Some or all of the above-described processing in the storage unit can be performed using, for example, AI, or without AI. For example, the storage unit can input changes in an individual's hobbies and preferences into a generation AI and have the generation AI update the information.

[0070] The storage unit can analyze an individual's dialogue history and classify hobbies and preferences in detail based on the frequency of appearance of specific keywords and phrases. Specific keywords and phrases include, but are not limited to, frequency of appearance and co-occurrence relationships. The storage unit, for example, analyzes the individual's dialogue history. The storage unit classifies hobbies and preferences in detail based on the frequency of appearance of specific keywords and phrases. For example, the storage unit can analyze the frequency of appearance of keywords related to a specific music genre from the user's dialogue history and classify them as hobbies. The storage unit can also analyze the frequency of appearance of phrases related to a specific sport from the user's dialogue history and classify them as preferences. The storage unit can also analyze the frequency of appearance of keywords related to a specific dish from the user's dialogue history and classify them as hobbies. In this way, by analyzing an individual's dialogue history, hobbies and preferences can be classified in detail and more accurate information can be stored. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or without AI. For example, the storage unit can input the individual's dialogue history into a generation AI and cause the generation AI to classify hobbies and preferences.

[0071] The storage unit can learn an individual's lifestyle rhythm and activity patterns and acquire and update information at appropriate times. Life rhythms and activity patterns include, but are not limited to, daily behavior and activities by time period. The storage unit, for example, learns an individual's lifestyle rhythm and activity patterns. The storage unit acquires and updates information at appropriate times based on the learned information. For example, if a user is more active in the morning, the storage unit acquires and updates information in the morning. If a user is more active in the evening, the storage unit can also acquire and update information in the evening. If a user is more active on weekends, the storage unit can also acquire and update information on weekends. This allows information to be acquired and updated based on an individual's lifestyle rhythm and activity patterns, enabling information to be managed at more appropriate times. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without AI. For example, the storage unit may input an individual's lifestyle rhythm and activity patterns into a generation AI and cause the generation AI to acquire and update information.

[0072] The storage unit can estimate the user's emotions and determine the priority of information to be stored based on the estimated user emotions. Information priority includes, but is not limited to, the importance of the emotions and the urgency of the information. The storage unit, for example, estimates the user's emotions. The storage unit determines the priority of information to be stored based on the estimated user emotions. For example, if the user is feeling stressed, the storage unit prioritizes and stores relaxing information. If the user is relaxed, the storage unit can also prioritize and store interesting information. If the user is excited, the storage unit can also prioritize and store stimulating information. This enables more appropriate information management by determining the priority of information based on the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the storage unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the storage unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0073] The storage unit can analyze the individual's social media activity and supplement information about hobbies and preferences. Social media activity includes, but is not limited to, post content, number of likes, and comments. The storage unit, for example, analyzes the individual's social media activity. The storage unit supplements information about hobbies and preferences. For example, the storage unit analyzes content frequently posted by the user on social media and supplements information about hobbies and preferences. The storage unit can also analyze accounts the user follows on social media and supplement information about hobbies and preferences. The storage unit can also analyze groups the user participates in on social media and supplement information about hobbies and preferences. In this way, by analyzing social media activity, information about hobbies and preferences can be supplemented and more accurate information can be retained. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the individual's social media activity into a generation AI and cause the generation AI to supplement information about hobbies and preferences.

[0074] The storage unit can add region-specific hobbies and preferences to the retained information based on the individual's geographical location information. Geographical location information includes, but is not limited to, GPS data and location information services. The storage unit, for example, considers the individual's geographical location information. The storage unit adds region-specific hobbies and preferences to the retained information. For example, if the user lives in a specific region, the storage unit adds region-specific hobbies and preferences to the retained information. If the user frequently visits a specific region, the storage unit can also add region-specific hobbies and preferences to the retained information. If the user is often active in a specific region, the storage unit can also add region-specific hobbies and preferences to the retained information. By taking geographical location information into consideration, region-specific hobbies and preferences can be added to the retained information, thereby enabling more accurate information to be retained. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or without AI. For example, the storage unit can input the individual's geographical location information to the generation AI and cause the generation AI to add region-specific hobbies and preferences.

[0075] The storage unit can improve the accuracy of the retained information by reflecting the individual's past feedback. Past feedback includes, for example, user ratings, comments, survey results, etc., but is not limited to these examples. The storage unit, for example, reflects the individual's past feedback. The storage unit improves the accuracy of the retained information. The storage unit, for example, improves the accuracy of the retained information based on feedback provided by the user in the past. The storage unit can also improve the accuracy of the retained information based on information evaluated by the user in the past. The storage unit can also improve the accuracy of the retained information based on comments provided by the user in the past. In this way, the accuracy of the retained information can be improved by reflecting the past feedback. Some or all of the above-mentioned processing in the storage unit may be performed using AI, for example, or may be performed without using AI. For example, the storage unit can input the individual's past feedback into the generation AI and cause the generation AI to improve the accuracy of the information.

[0076] The generation unit can estimate the user's emotion and adjust the generation algorithm of the collective LLM based on the estimated user's emotion. Adjusting the generation algorithm includes, but is not limited to, weighting the emotion and adjusting the parameters of the algorithm. The generation unit, for example, estimates the user's emotion. The generation unit adjusts the generation algorithm of the collective LLM based on the estimated user's emotion. For example, if the user is relaxed, the generation unit adjusts the algorithm to generate relaxed chat. If the user is excited, the generation unit can also adjust the algorithm to generate chat that allows the user to share their excitement. If the user is stressed, the generation unit can also adjust the algorithm to generate chat that reduces stress. In this way, by adjusting the generation algorithm based on the user's emotion, a more appropriate collective LLM can be generated. Emotion estimation is realized using an emotion estimation function, for example, using 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 generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can input user emotion data into the generation AI and cause the generation AI to adjust the generation algorithm.

[0077] The generation unit can improve the accuracy of generating the group LLM by taking into account the interrelationships between each individual's LLM. Consideration of the interrelationships includes, for example, the strength of relationships, common hobbies and preferences, etc., but is not limited to these examples. The generation unit, for example, considers the interrelationships between each individual's LLM. The generation unit improves the accuracy of generating the group LLM. For example, the generation unit extracts commonalities between each individual's LLM to improve the accuracy of generating the group LLM. The generation unit can also improve the accuracy of generating the group LLM by taking into account differences between each individual's LLM. The generation unit can also analyze the interrelationships between each individual's LLM to improve the accuracy of generating the group LLM. In this way, by taking into account the interrelationships between each individual's LLM, the accuracy of generating the group LLM can be improved. Some or all of the above-described processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the interrelationships between each individual's LLM into the generation AI and cause the generation AI to improve the generation accuracy.

[0078] The generation unit can adjust the generation algorithm taking into account individual attribute information when generating the collective LLM. Attribute information includes, but is not limited to, age, occupation, and gender. For example, the generation unit can consider individual attribute information when generating the collective LLM. The generation unit adjusts the generation algorithm. For example, the generation unit can optimize the generation algorithm taking into account the individual's age when generating the collective LLM. The generation unit can also optimize the generation algorithm taking into account the individual's occupation when generating the collective LLM. The generation unit can also optimize the generation algorithm taking into account the individual's interests and concerns when generating the collective LLM. This allows for the generation of a more appropriate collective LLM by taking into account individual attribute information. Some or all of the above-described processing in the generation unit can be performed using, or without, a generation AI. For example, the generation unit can input individual attribute information into the generation AI and cause the generation AI to adjust the generation algorithm.

[0079] The generation unit may weight the individual's dialogue history based on its importance when generating the collective LLM. Examples of weighting include, but are not limited to, the importance, frequency, and content relevance of the dialogue history. For example, the generation unit may weight the individual's dialogue history based on its importance when generating the collective LLM. For example, the generation unit may weight the individual's dialogue history based on its frequency when generating the collective LLM. For example, the generation unit may weight the individual's dialogue history based on its content when generating the collective LLM. For example, the generation unit may weight the individual's dialogue history based on its length when generating the collective LLM. Thus, weighting the individual's dialogue history based on its importance allows for the generation of a more appropriate collective LLM. Some or all of the above-described processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit may input the individual's dialogue history into the generation AI and cause the generation AI to perform weighting.

[0080] The generation unit can estimate the user's emotions and adjust the generation order of the collective LLMs based on the estimated user's emotions. Adjusting the generation order includes, but is not limited to, ordering the LLMs according to changes in emotions or generating them from information with higher priority. The generation unit, for example, estimates the user's emotions. The generation unit adjusts the generation order of the collective LLMs based on the estimated user's emotions. For example, if the user is relaxed, the generation unit can prioritize generating casual conversations with a relaxed atmosphere. If the user is excited, the generation unit can also prioritize generating casual conversations that allow the user to share their excitement. If the user is stressed, the generation unit can also prioritize generating casual conversations that help reduce stress. By adjusting the generation order based on the user's emotions, a more appropriate collective LLM can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., an LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may input user emotion data into the generation AI and have the generation AI adjust the generation order.

[0081] The generation unit can adjust the generation algorithm taking into account the geographic distribution of individuals when generating the group LLM. Geographic distribution includes, but is not limited to, regional population distribution, cultural background, etc. For example, the generation unit can adjust the generation algorithm taking into account the geographic distribution of individuals when generating the group LLM. For example, the generation unit can adjust the generation algorithm taking into account the geographic distribution of individuals when generating the group LLM. The generation unit can also generate region-specific topics based on the geographic distribution of individuals when generating the group LLM. The generation unit can also reflect cultural background by taking into account the geographic distribution of individuals when generating the group LLM. In this way, by taking into account the geographic distribution of individuals, a group LLM that reflects region-specific topics can be generated. Some or all of the above-described processing in the generation unit can be performed using, or without, a generation AI. For example, the generation unit can input the geographic distribution of individuals into the generation AI and cause the generation AI to adjust the generation algorithm.

[0082] The generation unit can improve the generation accuracy by referring to related literature and data when generating the collective LLM. Examples of related literature and data include, but are not limited to, academic papers, databases, and statistical data. For example, the generation unit can refer to related literature and data when generating the collective LLM. The generation unit improves the generation accuracy. For example, the generation unit can improve the generation accuracy by referring to related literature when generating the collective LLM. The generation unit can also improve the generation accuracy by referring to related data when generating the collective LLM. The generation unit can also improve the generation accuracy by referring to related research results when generating the collective LLM. In this way, by referring to related literature and data, the generation accuracy of the collective LLM can be improved. Some or all of the above-described processing in the generation unit can be performed using, or without, a generation AI. For example, the generation unit can input related literature and data into the generation AI and cause the generation AI to improve the generation accuracy.

[0083] When generating a population LLM, the generation unit can optimize the generation algorithm taking into account the market value and business needs of the population. Market value and business needs include, but are not limited to, market research results, business models, and customer needs. For example, when generating a population LLM, the generation unit considers the market value and business needs of the population. The generation unit optimizes the generation algorithm. For example, when generating a population LLM, the generation unit optimizes the generation algorithm taking into account the market value of the population. When generating a population LLM, the generation unit can also optimize the generation algorithm taking into account the business needs of the population. When generating a population LLM, the generation unit can also optimize the generation algorithm taking into account the economic background of the population. In this way, by taking into account the market value and business needs, a population LLM suitable for business can be generated. Some or all of the above-described processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the market value and business needs of the population into the generation AI and cause the generation AI to optimize the generation algorithm.

[0084] The providing unit can estimate the user's emotions and adjust the content and tone of the chat based on the estimated user's emotions. The content and tone of the chat include, but are not limited to, the type of emotion, the purpose of the conversation, and the user's reaction. The providing unit, for example, estimates the user's emotions. The providing unit adjusts the content and tone of the chat based on the estimated user's emotions. For example, if the user is relaxed, the providing unit provides the chat in a relaxed tone. If the user is excited, the providing unit can also provide the chat in a tone that allows the user to share the excitement. If the user is stressed, the providing unit can also provide the chat in a tone that reduces the stress. This allows for more appropriate communication by adjusting the content and tone of the chat based on the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the user's emotional data into the generating AI and have the generating AI adjust the content and tone of the chat.

[0085] The providing unit can customize the content of the chat to be provided based on the past dialogue history of the group. The past dialogue history includes, for example, the duration of the dialogue and the format of the data to be saved, but is not limited to these examples. The providing unit, for example, customizes the content of the chat to be provided based on the past dialogue history of the group. The providing unit, for example, extracts common topics from the past dialogue history of the group and provides the chat. The providing unit can also extract interesting topics from the past dialogue history of the group and provide the chat. The providing unit can also provide the chat based on common hobbies and preferences from the past dialogue history of the group. In this way, by customizing the content of the chat based on the past dialogue history, more relevant topics can be provided. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the past dialogue history of the group to a generation AI and cause the generation AI to customize the chat.

[0086] The providing unit can associate the content of the chat to the group's current activities or projects. Current activities and projects include, but are not limited to, ongoing projects, team goals, etc. For example, the providing unit associates the content of the chat to the group's current activities or projects. For example, the providing unit can provide topics related to the group's current projects to promote communication between members. The providing unit can also provide topics related to the group's current activities to help members find common interests. The providing unit can also provide topics related to the group's current goals to raise awareness toward goal achievement. In this way, providing topics related to the current activities or projects can promote communication between members. Some or all of the above-described processing in the providing unit may be performed using, or without, AI. For example, the providing unit can input information about the group's current activities and projects into the generation AI and cause the generation AI to execute the content of the chat.

[0087] The providing unit can continuously improve the content of the chat to be provided by reflecting group feedback. Feedback includes, for example, user ratings, comments, survey results, etc., but is not limited to these examples. The providing unit, for example, continuously improves the content of the chat to be provided by reflecting group feedback. For example, the providing unit improves the content of the chat based on group feedback and provides more interesting topics. The providing unit can also adjust the tone of the chat based on group feedback to achieve more appropriate communication. The providing unit can also adjust the frequency of the chat and provide topics at appropriate times based on group feedback. In this way, more interesting topics can be provided by reflecting the feedback. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input group feedback to a generation AI and cause the generation AI to improve the chat.

[0088] The providing unit can estimate the user's emotions and determine the priority of chats based on the estimated user's emotions. The priority of chats includes, for example, the importance of the emotion and the urgency of the topic, but is not limited to these examples. The providing unit, for example, estimates the user's emotions. The providing unit determines the priority of chats based on the estimated user's emotions. For example, if the user is relaxed, the providing unit can prioritize relaxing topics. If the user is excited, the providing unit can also prioritize topics that allow the user to share the excitement. If the user is stressed, the providing unit can also prioritize topics that reduce stress. Thus, by determining the priority of chats based on the user's emotions, more appropriate topics can be provided. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the user's emotional data into the generating AI and have the generating AI determine the priority of the chat.

[0089] The providing unit can customize the content of the chat to be provided by taking into account the geographical location information of the group. Geographical location information includes, but is not limited to, GPS data, location information services, etc. For example, the providing unit customizes the content of the chat to be provided by taking into account the geographical location information of the group. For example, the providing unit provides topics specific to a region based on the geographical location information of the group. The providing unit can also provide topics related to local events and news based on the geographical location information of the group. The providing unit can also provide topics related to local culture and customs based on the geographical location information of the group. In this way, by taking the geographical location information into account, it is possible to provide topics specific to a region. Some or all of the above-described processing in the providing unit may be performed using, or without using, AI. For example, the providing unit can input the geographical location information of the group to a generating AI and cause the generating AI to customize the chat.

[0090] The providing unit can analyze the social media activity of the group to increase the relevance of the content of the chat to be provided. Social media activity includes, but is not limited to, for example, the content of posts, the number of likes, and comments. For example, the providing unit analyzes the social media activity of the group to increase the relevance of the content of the chat to be provided. For example, the providing unit analyzes the social media activity of the group to provide common topics. The providing unit can also analyze the social media activity of the group to provide interesting topics. The providing unit can also analyze the social media activity of the group to provide topics based on common hobbies and preferences. In this way, more relevant topics can be provided by analyzing the social media activity. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the social media activity of the group to a generation AI and cause the generation AI to execute the content of the chat.

[0091] The providing unit can improve the accuracy of the content of the chat to be provided by reflecting past feedback from the group. Past feedback includes, for example, user ratings, comments, survey results, etc., but is not limited to these examples. For example, the providing unit improves the accuracy of the content of the chat to be provided by reflecting past feedback from the group. For example, the providing unit improves the content of the chat and provides more interesting topics based on the past feedback from the group. The providing unit can also adjust the tone of the chat based on the past feedback from the group to achieve more appropriate communication. The providing unit can also adjust the frequency of the chat and provide topics at appropriate times based on the past feedback from the group. In this way, by reflecting past feedback, more accurate topics can be provided. Some or all of the above-mentioned processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the past feedback of the group into the generation AI and cause the generation AI to improve the accuracy of the chat. === Hard Collateral 1-1 === Each of the multiple elements including the storage unit, generation 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 storage unit is realized by the storage 50 of the smart device 14 or the database 24 of the data processing device 12. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and merges the LLMs of each individual to generate a collective LLM. The provision unit is realized, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and provides chat based on the generated collective LLM. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned storage unit, generation unit, and provision unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the storage unit is realized by the storage 50 of the smart glasses 214 or the database 24 of the data processing device 12. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and merges the LLMs of each individual to generate a collective LLM. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and provides chat based on the generated collective LLM. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned storage unit, generation unit, and provision unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the storage unit is realized by the storage 50 of the headset type terminal 314 or the database 24 of the data processing device 12. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and merges the LLMs of each individual to generate a collective LLM. The provision unit is realized, for example, by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and provides chat based on the generated collective LLM. === Hard Collateral 1-4 === Each of the multiple elements including the storage unit, generation 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 storage unit is realized by the storage 50 of the robot 414 or the database 24 of the data processing device 12. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a group LLM by merging the LLMs of each individual. The provision unit is realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and provides chat based on the generated group LLM.

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

[0093] The storage unit can acquire the user's health data and reflect it in the personal information. For example, it acquires health data such as the user's heart rate, sleep patterns, and amount of exercise to understand the individual's health condition. The storage unit can also estimate the user's stress level and fatigue level based on the user's health data and reflect this in the personal information. This enables more appropriate communication support based on the user's health condition. Some or all of the above-mentioned processing in the storage unit may be performed using, for example, a sensor or application that acquires health data, or may be performed without using AI. For example, the storage unit can input the user's health data into a generation AI and have the generation AI estimate the health condition.

[0094] The generation unit can analyze the user's past dialogue history and adjust the population LLM generation algorithm based on the frequency of occurrence of specific keywords and phrases. For example, the generation unit can analyze the frequency of occurrence of keywords related to a specific music genre from the user's dialogue history and reflect this in the population LLM generation algorithm. The generation unit can also analyze the frequency of occurrence of phrases related to a specific sport from the user's dialogue history and reflect this in the population LLM generation algorithm. This allows for the generation of a more accurate population LLM based on the user's dialogue history. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or can be performed without using AI. For example, the generation unit can input the user's dialogue history into the generation AI and cause the generation AI to adjust the generation algorithm.

[0095] The providing unit can estimate the user's emotions and adjust the content and tone of the chat based on the estimated user's emotions. For example, if the user is relaxed, the providing unit can provide the chat in a relaxed tone. If the user is excited, the providing unit can also provide the chat in a tone that allows the user to share the excitement. If the user is stressed, the providing unit can also provide the chat in a tone that reduces the stress. This allows for more appropriate communication by adjusting the content and tone of the chat based on the user'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 the user's emotion data into the generation AI and cause the generation AI to adjust the content and tone of the chat.

[0096] The storage unit can analyze the user's social media activity and supplement information about hobbies and preferences. For example, it can analyze content that the user frequently posts on social media and supplement information about hobbies and preferences. The storage unit can also analyze accounts that the user follows on social media and supplement information about hobbies and preferences. The storage unit can also analyze groups that the user participates in on social media and supplement information about hobbies and preferences. In this way, by analyzing social media activity, information about hobbies and preferences can be supplemented and more accurate information can be retained. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input an individual's social media activity into a generation AI and cause the generation AI to supplement information about hobbies and preferences.

[0097] The generation unit can estimate the user's emotions and adjust the generation algorithm of the collective LLM based on the estimated user's emotions. For example, if the user is relaxed, the generation unit can adjust the algorithm to generate chatter with a relaxed atmosphere. If the user is excited, the generation unit can also adjust the algorithm to generate chatter that allows the user to share their excitement. If the user is stressed, the generation unit can also adjust the algorithm to generate chatter that reduces stress. In this way, by adjusting the generation algorithm based on the user's emotions, a more appropriate collective LLM can be generated. Emotion estimation is realized 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., an LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the generation unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the generation algorithm.

[0098] The providing unit can customize the content of the chat to be provided based on the past dialogue history of the group. For example, the providing unit can extract common topics from the past dialogue history of the group and provide the chat. The providing unit can also extract interesting topics from the past dialogue history of the group and provide the chat. The providing unit can also provide the chat based on common hobbies and preferences from the past dialogue history of the group. In this way, by customizing the content of the chat based on the past dialogue history, more relevant topics can be provided. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the past dialogue history of the group into a generating AI and cause the generating AI to customize the chat.

[0099] The storage unit can add region-specific hobbies and preferences to the retained information based on the individual's geographical location information. For example, if a user lives in a specific region, the storage unit can add region-specific hobbies and preferences to the retained information. If a user frequently visits a specific region, the storage unit can also add region-specific hobbies and preferences to the retained information. If a user is often active in a specific region, the storage unit can also add region-specific hobbies and preferences to the retained information. This allows region-specific hobbies and preferences to be added to the retained information by taking geographical location information into consideration, thereby enabling more accurate information to be retained. Some or all of the above-described processing in the storage unit may be performed using AI, for example, or may be performed without using AI. For example, the storage unit can input the individual's geographical location information to the generation AI and cause the generation AI to add region-specific hobbies and preferences.

[0100] The providing unit can estimate the user's emotions and determine the priority of chat topics based on the estimated user emotions. For example, if the user is relaxed, the providing unit can prioritize relaxing topics. If the user is excited, the providing unit can also prioritize topics that allow the user to share their excitement. If the user is stressed, the providing unit can also prioritize topics that will reduce stress. This allows for more appropriate topics to be provided by determining the priority of chat topics based on the user'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 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 the user's emotion data into the generation AI and have the generation AI determine the priority of chat topics.

[0101] The generation unit can improve the generation accuracy by referring to related literature and data when generating the collective LLM. For example, the generation accuracy can be improved by referring to related literature when generating the collective LLM. The generation unit can also improve the generation accuracy by referring to related data when generating the collective LLM. The generation unit can also improve the generation accuracy by referring to related research results when generating the collective LLM. In this way, by referring to related literature and data, the generation accuracy of the collective LLM can be improved. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit can input related literature and data into the generation AI and cause the generation AI to improve the generation accuracy.

[0102] The providing unit can associate the content of the chat to be provided with the group's current activities or projects. For example, it can provide topics related to the group's current projects to promote communication between members. The providing unit can also provide topics related to the group's current activities to help members find common interests. The providing unit can also provide topics related to the group's current goals to raise awareness toward goal achievement. In this way, providing topics related to the current activities or projects can promote communication between members. Some or all of the above-described processing in the providing unit may be performed using, or without, AI, for example. For example, the providing unit can input information about the group's current activities or projects into the generating AI and have the generating AI execute the content of the chat.

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

[0104] Step 1: The storage unit stores information about each individual. This information includes the individual's name, age, hobbies, preferences, and past interaction history. The storage unit learns the individual's hobbies, preferences, and past interaction history. Step 2: The generation unit generates a population LLM based on the information stored by the storage unit. The generation unit merges the LLMs of each individual to generate a population LLM, and integrates the LLMs of each individual using the generation AI. Step 3: The provider provides chats based on the group LLM generated by the generator. The provider generates chats that satisfy the hobbies and preferences of the group, and generates chats based on the group LLM using a generation AI.

[0105] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0106] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of 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.

[0107] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

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

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

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

[0111] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0112] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0113] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0114] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0115] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0116] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0117] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0118] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0119] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

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

[0121] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0122] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt 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.

[0123] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

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

[0126] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0127] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0128] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0129] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0130] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0131] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0132] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0133] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0134] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0135] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

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

[0137] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0138] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt 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.

[0139] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

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

[0142] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0143] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0144] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0145] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

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

[0147] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0148] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0149] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0150] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0151] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0152] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

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

[0154] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0155] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt 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.

[0156] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

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

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

[0160] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

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

[0162] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0163] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0164] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0165] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0166] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0167] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0168] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

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

[0170] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0171] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

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

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

[0174] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

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

[0176] [Explanation of symbols]

[0177] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a storage unit for storing information about each individual; a generating unit that generates a collective LLM based on the information held by the holding unit; a providing unit that provides chat based on the group LLM generated by the generating unit; A system characterized by:

2. The holding portion is Learn about personal hobbies, preferences, and past conversation history 2. The system of claim 1.

3. The generation unit Merging each individual's LLM to generate a collective LLM 2. The system of claim 1.

4. The providing unit Generate chats that satisfy the hobbies and preferences of a group 2. The system of claim 1.

5. The providing unit Evaluate the quality of the generated chat 2. The system of claim 1.

6. The holding portion is Estimate user emotions and adjust the frequency of updating personal information based on the estimated user emotions 2. The system of claim 1.

7. The holding portion is Detect changes in personal tastes and preferences in real time and automatically update retained information 2. The system of claim 1.

8. The holding portion is Analyzing an individual's conversation history and classifying their hobbies and preferences in detail based on the frequency of specific keywords and phrases 2. The system of claim 1.

Images