system

Abstract

The system according to the embodiment aims to efficiently provide answers by utilizing past input tasks. [Solution] A system according to an embodiment includes a recording unit, an analysis unit, a comparison unit, and a providing unit. The recording unit records input tasks of a user. The analysis unit analyzes the input tasks recorded by the recording unit. The comparison unit compares the input tasks analyzed by the analysis unit with past input tasks. When a similar task is found by the comparison unit, the providing unit provides an answer by referring to past answers.

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has the problem that the power consumption of LLM increases, making it difficult to provide efficient answers.

[0005] The system according to the embodiment aims to efficiently provide answers by utilizing past input tasks. [Means for solving the problem]

[0006] The system according to the embodiment includes a recording unit, an analysis unit, a comparison unit, and a provision unit. The recording unit records input tasks of a user. The analysis unit analyzes the input tasks recorded by the recording unit. The comparison unit compares the input tasks analyzed by the analysis unit with past input tasks. When a similar task is found by the comparison unit, the provision unit provides an answer by referring to past answers. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently provide answers by utilizing past input tasks. [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 of form 1) The system according to an embodiment of the present invention is a system for solving the power consumption problem of LLMs (Large-Scale Language Models). This system records user input tasks, compares new input tasks with past input tasks when they are submitted, and provides answers by referring to past answers if similar tasks are found. This allows for fast and high-quality answers to be obtained without directly running the LLM. For example, when a user submits an input task to the system, this input task is recorded in memory or a database. Next, when a new input task is submitted, the system compares it with past input tasks. This comparison is performed by analyzing the content and context of the task. For example, if there was a past input such as "a task to provide information," then a new input that is "a task to provide similar information" will be judged as a similar task. If a similar task is found, the system refers to past answers and provides a similar answer. This allows for fast and high-quality answers to be obtained without directly running the LLM. This mechanism can significantly reduce the power consumption of the LLM. Since there is no need to directly run the LLM, power consumption is reduced, and the load on the data center is also reduced. In addition, by providing fast and high-quality answers, user satisfaction is also improved. Furthermore, this system can also be used as training data for the LLM. The accuracy of the LLM can be improved by feeding back the matching results of new input tasks with past input tasks. For example, if the matching accuracy for similar tasks is low, it can be fed back as training data for the LLM to improve the matching accuracy for subsequent tasks. In this way, the present invention solves the power consumption problem of LLMs and contributes to the realization of a society where LLMs and humanity can coexist. As a result, the system can significantly reduce the power consumption of the LLM and alleviate the load on the data center. Furthermore, by providing fast and high-quality answers, user satisfaction can be improved. Moreover, the system can be used as training data for the LLM, further improving the accuracy of the LLM.

[0029] The system according to the embodiment includes a recording unit, an analysis unit, a comparison unit, and a provision unit. The recording unit records a user's input task. Examples of the user's input task include, but are not limited to, text input, voice input, and image input. The recording unit records the user's input task in a memory or a database. The memory includes, for example, a RAM or a HDD, and the database includes, for example, an SQL database or a NoSQL database. The analysis unit analyzes the new input task and identifies the content and context of the task. The analysis unit analyzes the content and context of the task using, for example, natural language processing technology. Examples of natural language processing technology include morphological analysis, grammatical analysis, and semantic analysis. The comparison unit compares a previous input task with a new input task. The comparison unit compares the previous input task with a new input task using, for example, a similarity calculation algorithm. Examples of similarity calculation algorithms include cosine similarity and Euclidean distance. When a similar task is found, the provision unit provides an answer by referring to previous answers. The providing unit references past answers using, for example, a database search technique, such as an SQL query or a full-text search engine. This allows the system according to the embodiment to efficiently record, analyze, and compare user input tasks, and provide high-quality answers quickly when similar tasks are found.

[0030] The recording unit can record the user's input tasks in a memory or a database. For example, the recording unit records the user's input tasks in a memory. The memory includes, for example, a RAM or a HDD. The recording unit can also record the user's input tasks in a database. The database includes, for example, an SQL database or a NoSQL database. This allows the recording unit to efficiently record the user's input tasks. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input the user's input tasks into AI and have the AI ​​perform recording optimization.

[0031] The analysis unit can analyze a new input task and identify its content and context. For example, the analysis unit can analyze a new input task using natural language processing techniques. Natural language processing techniques include, for example, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit can analyze the content of the task using morphological analysis. The analysis unit can also identify the context of the task using grammatical analysis. Furthermore, the analysis unit can identify the meaning of the task using semantic analysis. This allows the analysis unit to accurately identify the content and context of a new input task. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input a new input task into an AI and have the AI ​​perform the task content and context identification.

[0032] The comparison unit can compare past input tasks with new input tasks. For example, the comparison unit compares past input tasks with new input tasks using a similarity calculation algorithm. Similarity calculation algorithms include, for example, cosine similarity and Euclidean distance. For example, the comparison unit compares past input tasks with new input tasks using cosine similarity. The comparison unit can also calculate task similarity using Euclidean distance. Furthermore, the comparison unit can also calculate task similarity using TF-IDF. This allows the comparison unit to accurately compare past input tasks with new input tasks. Some or all of the above processing in the comparison unit may be performed using, for example, AI, or not using AI. For example, the comparison unit can input past input tasks and new input tasks into AI and have the AI ​​perform the similarity calculation.

[0033] When a similar task is found, the providing unit can provide an answer by referring to past answers. The providing unit, for example, refers to past answers using a database search technology. Database search technology includes, for example, an SQL query or a full-text search engine. The providing unit, for example, refers to past answers using an SQL query. The providing unit can also search past answers using a full-text search engine. Furthermore, the providing unit can quickly search past answers using an index. This allows the providing unit to quickly provide a high-quality answer when a similar task is found. 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 past answers to an AI and have the AI ​​select an optimal answer.

[0034] The analysis unit can use natural language processing technology to analyze the content and context of a task. The analysis unit analyzes the content and context of a task using, for example, natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, and semantic analysis. The analysis unit analyzes the content of a task using, for example, morphological analysis. The analysis unit can also identify the context of a task using grammatical analysis. Furthermore, the analysis unit can also identify the meaning of a task using semantic analysis. This allows the analysis unit to analyze the content and context of a task more accurately. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can cause AI to analyze the content and context of a task.

[0035] The comparison unit can use a similarity calculation algorithm to compare past input tasks with new input tasks. For example, the comparison unit compares past input tasks with new input tasks using a similarity calculation algorithm. Similarity calculation algorithms include, for example, cosine similarity and Euclidean distance. For example, the comparison unit compares past input tasks with new input tasks using cosine similarity. The comparison unit can also calculate task similarity using Euclidean distance. Furthermore, the comparison unit can also calculate task similarity using TF-IDF. This allows the comparison unit to improve the accuracy of task comparison. Some or all of the above processing in the comparison unit may be performed using, for example, AI, or not using AI. For example, the comparison unit can have AI execute the similarity calculation algorithm.

[0036] The service provider can use database search techniques to refer to past answers. For example, the service provider can refer to past answers using database search techniques. Database search techniques include, for example, SQL queries and full-text search engines. For example, the service provider can refer to past answers using SQL queries. The service provider can also search for past answers using full-text search engines. Furthermore, the service provider can also use indexes to quickly search for past answers. This allows the service provider to quickly refer to past answers. Some or all of the above processing in the service provider may be performed using, for example, AI, or not using AI. For example, the service provider can input past answers into AI and have the AI ​​select the optimal answer.

[0037] The recording unit can analyze the user's past input task history and select the optimal recording method. For example, the recording unit may use data mining techniques to analyze the user's past input task history. Data mining techniques include, for example, clustering, association rules, and decision trees. For example, the recording unit may use clustering to classify the user's past input tasks. The recording unit may also use association rules to analyze the relationships between input tasks. Furthermore, the recording unit may use decision trees to identify patterns in input tasks. After analyzing the user's past input task history, the recording unit selects the optimal recording method. For example, it may automatically record tasks that the user has frequently entered in the past. It may also prioritize recording input methods that the user has used in the past (voice, text, etc.). Furthermore, it may predict the input method to be used during specific time periods based on the user's past input history and select the optimal recording method. In this way, the recording unit can select the optimal recording method by analyzing the user's past input task history. Some or all of the above processing in the recording unit may be performed using, for example, AI, or not using AI. For example, the recording unit can input the user's past input task history into the AI ​​and have the AI ​​select the optimal recording method.

[0038] The recording unit can filter data based on the user's current projects and areas of interest during recording. For example, the recording unit may use project management tools or social media analytics techniques to identify the user's current projects and areas of interest. Project management tools include, for example, task management software and project management platforms. Social media analytics techniques include, for example, analysis of post content and activity frequency. The recording unit may, for example, use project management tools to identify the user's current projects. It can also use social media analytics techniques to identify the user's areas of interest. After identifying the user's current projects and areas of interest, the recording unit performs filtering. For example, it may record only tasks related to the project the user is currently working on. It can also prioritize recording tasks that are highly relevant based on the user's areas of interest. Furthermore, it can record only specific tasks based on filter conditions set by the user. This allows the recording unit to prioritize recording tasks that are highly relevant by filtering based on the user's current projects and areas of interest. Some or all of the above processing in the recording unit may be performed using, for example, AI, or not using AI. For example, the recording unit can input data on the user's projects and areas of interest into the AI, allowing the AI ​​to optimize the filtering process.

[0039] During recording, the recording unit can prioritize recording highly relevant tasks in consideration of the user's geographical location information. The recording unit, for example, uses GPS data or a location information service to acquire the user's geographical location information. The GPS data includes, for example, latitude and longitude information. The location information service includes, for example, Wi-Fi location information and mobile phone base station information. The recording unit, for example, uses GPS data to identify the user's current location. The recording unit can also identify the user's location using a location information service. After identifying the user's geographical location information, the recording unit prioritizes recording highly relevant tasks. For example, when the user is in a specific location, the recording unit prioritizes recording tasks related to that location. Furthermore, when the user is traveling, the recording unit can prioritize recording tasks related to the user's destination. Furthermore, when the user is at home, the recording unit can prioritize recording tasks to be performed at home. This allows the recording unit to prioritize recording highly relevant tasks in consideration of the user's geographical location information. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input the user's geographical location information into the AI ​​and allow the AI ​​to optimize task priorities.

[0040] The recording unit can analyze the user's social media activity and record related tasks during recording. The recording unit, for example, uses social media analysis technology to analyze the user's social media activity. Social media analysis technology includes, for example, analyzing the content of posts and the frequency of activity. The recording unit, for example, analyzes the content of posts to identify the user's areas of interest. The recording unit can also analyze the frequency of activity to identify the user's activity patterns. The recording unit records related tasks after analyzing the user's social media activity. For example, the recording unit can automatically record tasks mentioned by the user on social media. The recording unit can also prioritize recording related tasks based on the content of the user's social media posts. Furthermore, the recording unit can record tasks mentioned by the user's social media followers and friends. In this way, the recording unit can prioritize recording related tasks by analyzing the user's social media activity. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input the user's social media data into AI to optimize task recording.

[0041] The analysis unit can adjust the level of detail of the analysis based on the importance of the tasks during the analysis. For example, the analysis unit uses an importance evaluation algorithm to assess the importance of tasks. The importance evaluation algorithm may include, for example, the scope of impact, urgency, and dependencies of the tasks. For example, the analysis unit may determine the importance by evaluating the scope of impact of the tasks. The analysis unit may also determine the importance by evaluating the urgency of the tasks. Furthermore, the analysis unit may also determine the importance by evaluating the dependencies of the tasks. After evaluating the importance of the tasks, the analysis unit adjusts the level of detail of the analysis based on the importance. For example, a detailed analysis may be performed for tasks with high importance. A simplified analysis may be performed for tasks with low importance. Furthermore, the analysis priority may be determined according to the importance of the tasks. In this way, the analysis unit can provide more appropriate analysis results by adjusting the level of detail of the analysis based on the importance of the tasks. Some or all of the above processes in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit may input task importance data into AI and have the AI ​​perform the optimization of the level of detail of the analysis.

[0042] During analysis, the analysis unit can apply different analysis algorithms depending on the task category. The analysis unit, for example, uses a category classification algorithm to identify the task category. Examples of category classification algorithms include business tasks, personal tasks, information provision tasks, problem-solving tasks, and data analysis tasks. The analysis unit, for example, uses a business task classification algorithm to identify business tasks. The analysis unit can also use a personal task classification algorithm to identify personal tasks. The analysis unit can also use an information provision task classification algorithm to identify information provision tasks. After identifying the task category, the analysis unit applies different analysis algorithms depending on the category. For example, an information extraction algorithm can be applied to information provision tasks. A problem-solving algorithm can be applied to problem-solving tasks. A data mining algorithm can also be applied to data analysis tasks. This allows the analysis unit to improve analysis accuracy by applying an appropriate analysis algorithm depending on the task category. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input task category data into AI and have the AI ​​select an analysis algorithm.

[0043] During analysis, the analysis unit can determine the analysis priority based on the submission time of the task. The analysis unit, for example, uses a record of the submission date and time to identify the submission time of the task. The record of the submission date and time includes, for example, a timestamp of the submission date and time. The analysis unit, for example, uses the timestamp of the submission date and time to identify the submission time of the task. After identifying the submission time of the task, the analysis unit determines the analysis priority based on the submission time. For example, it can prioritize analysis of tasks with high urgency. It can also prioritize analysis of tasks with an approaching submission deadline. Furthermore, it can adjust the analysis priority according to the submission time. In this way, the analysis unit can prioritize analysis of tasks with high urgency by determining the analysis priority based on the submission time of the task. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input task submission time data into AI and cause the AI ​​to optimize the analysis priority.

[0044] The analysis unit can adjust the order of analysis based on the relevance of tasks during the analysis process. For example, the analysis unit uses a relevance evaluation algorithm to assess the relevance of tasks. This relevance evaluation algorithm may include, for example, dependencies between tasks, common themes, and interrelationships between tasks. For example, the analysis unit can determine relevance by evaluating dependencies between tasks. It can also determine relevance by evaluating common themes. Furthermore, it can determine relevance by evaluating interrelationships between tasks. After evaluating the relevance of tasks, the analysis unit adjusts the order of analysis based on the relevance. For example, it can prioritize the analysis of highly relevant tasks. It can also postpone the analysis of less relevant tasks. Furthermore, it can adjust the order of analysis according to the relevance of tasks. In this way, the analysis unit can prioritize the analysis of highly relevant tasks by adjusting the order of analysis based on the relevance of tasks. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input task relevance data into AI and have the AI ​​perform the optimization of the analysis order.

[0045] The comparison unit may improve the accuracy of the comparison by taking into account the interrelationships between tasks. The comparison unit may use, for example, an interrelationship evaluation algorithm to evaluate the interrelationships between tasks. The interrelationship evaluation algorithm may include, for example, inter-task dependency, common themes, task relevance, etc. The comparison unit may, for example, evaluate the interrelationships between tasks to determine the interrelationships. The comparison unit may also evaluate common themes to determine the interrelationships. The comparison unit may also evaluate task relevance to determine the interrelationships. After evaluating the interrelationships between tasks, the comparison unit may improve the accuracy of the comparison based on the interrelationships. For example, the comparison unit may analyze the interrelationships between tasks and prioritize comparison of highly related tasks. The comparison unit may also improve the accuracy of the comparison based on the interrelationships between tasks. Furthermore, the comparison unit may adjust the order of comparison by taking into account the interrelationships between tasks. In this way, the comparison unit may improve the accuracy of the comparison by taking into account the interrelationships between tasks, thereby providing more appropriate comparison results. Some or all of the above-described processing in the comparison unit may be performed using, for example, AI, or may be performed without using AI. For example, the comparison unit can input task interrelationship data into the AI ​​and cause the AI ​​to optimize the accuracy of the comparison.

[0046] The comparison unit can perform comparisons while considering the attribute information of the task submitter. For example, the comparison unit uses an attribute information acquisition algorithm to obtain the attribute information of the task submitter. The attribute information acquisition algorithm may include, for example, age, occupation, field of expertise, and past performance. For example, the comparison unit can obtain the submitter's age to identify attribute information. The comparison unit can also obtain the submitter's occupation to identify attribute information. Furthermore, the comparison unit can obtain the submitter's field of expertise to identify attribute information. After identifying the submitter's attribute information, the comparison unit performs a comparison based on the attribute information. For example, it can compare tasks based on the submitter's expertise. It can also compare tasks based on the submitter's past performance. Furthermore, it can compare tasks while considering the submitter's attribute information. In this way, the comparison unit can provide more appropriate comparison results by considering the attribute information of the task submitter when performing comparisons. Some or all of the above processing in the comparison unit may be performed using, for example, AI, or not using AI. For example, the comparison unit can input the submitter's attribute information into AI and have the AI ​​perform the optimization of the comparison.

[0047] The comparison unit can take into account the geographic distribution of tasks when making the comparison. The comparison unit, for example, uses a geographic information system (GIS) to evaluate the geographic distribution of tasks. The geographic information system includes, for example, geographic location information, distribution by region, distribution by country, etc. The comparison unit, for example, identifies the geographic distribution of tasks using geographic location information. The comparison unit can also identify the geographic distribution of tasks by evaluating the distribution by region. Furthermore, the comparison unit can identify the geographic distribution of tasks by evaluating the distribution by country. After identifying the geographic distribution of tasks, the comparison unit performs comparison based on the geographic distribution. For example, geographically close tasks can be compared preferentially. Geographically distant tasks can also be postponed. Furthermore, the comparison order can be adjusted taking into account the geographic distribution of tasks. In this way, the comparison unit can provide more appropriate comparison results by making the comparison taking into account the geographic distribution of tasks. Some or all of the above-described processing in the comparison unit may be performed using, for example, AI, or may be performed without AI. For example, the comparison unit can input geographical distribution data of tasks into the AI ​​and have the AI ​​perform the optimization of the comparison.

[0048] The comparison unit can improve the accuracy of the comparison by referring to task-related literature during the comparison. The comparison unit, for example, uses a literature database to refer to task-related literature. The literature database includes, for example, academic papers, technical reports, patent documents, etc. The comparison unit can identify task-related literature by referring to academic papers, for example. The comparison unit can also identify task-related literature by referring to technical reports. Furthermore, the comparison unit can identify task-related literature by referring to patent documents. After identifying task-related literature, the comparison unit can improve the accuracy of the comparison by referring to the relevant literature. For example, the comparison unit can improve the accuracy of task comparison by referring to the relevant literature. The comparison unit can also adjust task comparison criteria based on the relevant literature. Furthermore, the comparison result of the task can be displayed taking the relevant literature into consideration. In this way, the comparison unit can improve the accuracy of the comparison by referring to task-related literature, thereby providing more appropriate comparison results. Some or all of the above-described processing in the comparison unit can be performed using, for example, AI, or without AI. For example, the comparison unit can input task-related literature data into AI and cause the AI ​​to optimize the accuracy of the comparison.

[0049] The providing unit can adjust the level of detail to be provided based on the importance of past answers when providing the answers. The providing unit, for example, uses an importance evaluation algorithm to evaluate the importance of past answers. The importance evaluation algorithm includes, for example, the scope of influence of the answer, the accuracy of the answer, and the relevance of the answer. The providing unit, for example, determines the importance by evaluating the scope of influence of the answer. The providing unit can also determine the importance by evaluating the accuracy of the answer. Furthermore, the providing unit can determine the importance by evaluating the relevance of the answer. After evaluating the importance of past answers, the providing unit adjusts the level of detail to be provided based on the importance. For example, detailed information can be provided for answers with high importance. Furthermore, simplified information can be provided for answers with low importance. Furthermore, the providing unit can adjust the level of detail to be provided depending on the importance of past answers. As a result, the providing unit can provide a more appropriate answer by adjusting the level of detail to be provided based on the importance of past answers. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input the importance data of past answers into the AI ​​and have the AI ​​optimize the level of detail provided.

[0050] The providing unit can apply different provision algorithms depending on the task category when providing the data. The providing unit, for example, uses a category classification algorithm to identify the task category. Category classification algorithms include, for example, business tasks, personal tasks, information provision tasks, problem-solving tasks, and data analysis tasks. The providing unit, for example, uses a business task classification algorithm to identify business tasks. The providing unit can also use a personal task classification algorithm to identify personal tasks. Furthermore, the providing unit can also use an information provision task classification algorithm to identify information provision tasks. After identifying the task category, the providing unit applies different provision algorithms depending on the category. For example, an information extraction algorithm can be applied to an information provision task. A problem-solving algorithm can be applied to a problem-solving task. Furthermore, a data mining algorithm can be applied to a data analysis task. In this way, the providing unit can improve provision accuracy by applying an appropriate provision algorithm depending on the task category. 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 task category data into AI and cause the AI ​​to select a provision algorithm.

[0051] The providing unit can determine the priority of providing answers based on the submission dates of past answers when providing answers. The providing unit, for example, uses records of submission dates and times to identify the submission dates of past answers. The records of submission dates and times include, for example, timestamps of the submission dates. The providing unit, for example, uses the timestamps of the submission dates and times to identify the submission dates of past answers. After identifying the submission dates of past answers, the providing unit determines the priority of providing answers based on the submission dates. For example, answers with high urgency can be provided preferentially. Also, answers with an approaching submission deadline can be provided preferentially. Furthermore, the priority of providing answers can be adjusted depending on the submission dates. In this way, the providing unit can determine the priority of providing answers based on the submission dates of past answers, thereby providing answers with high urgency preferentially. 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 data on the submission dates of past answers into AI and cause the AI ​​to optimize the priority of providing answers.

[0052] The providing unit can adjust the order of providing answers based on the relevance of past answers when providing answers. The providing unit, for example, uses a relevance assessment algorithm to evaluate the relevance of past answers. The relevance assessment algorithm includes, for example, dependencies between answers, common themes, and interrelationships between answers. The providing unit, for example, determines the relevance by evaluating dependencies between answers. The providing unit can also determine the relevance by evaluating common themes. Furthermore, the providing unit can determine the relevance by evaluating interrelationships between answers. After evaluating the relevance of past answers, the providing unit adjusts the order of providing answers based on the relevance. For example, highly relevant answers can be provided preferentially. Also, less relevant answers can be postponed. Furthermore, the providing unit can adjust the order of providing answers according to the relevance of past answers. In this way, the providing unit can prioritize providing highly relevant answers by adjusting the order of providing answers based on the relevance of past answers. 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 relevance data of past answers into AI and cause the AI ​​to optimize the order of providing answers.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] When recording tasks input by a user, the recording unit can determine the priority of recording based on the importance of the task. For example, it can record urgent tasks first and postpone less important tasks. It can also adjust the order of recording taking into account the scope of impact and dependencies of tasks. This allows the recording unit to quickly record important tasks and achieve efficient task management. Furthermore, the recording unit can input task importance data into AI and have the AI ​​optimize the priority of recording.

[0055] When comparing past input tasks with new input tasks, the comparison unit can apply different comparison algorithms depending on the task category. For example, a comparison algorithm dedicated to business tasks can be applied to business tasks, and a comparison algorithm dedicated to personal tasks can be applied to personal tasks. It is also possible to apply a comparison algorithm dedicated to information provision tasks to information provision tasks. This allows the comparison unit to apply an appropriate comparison algorithm depending on the task category, thereby improving comparison accuracy. Some or all of the above-mentioned processing in the comparison unit may be performed using AI, or may be performed without using AI.

[0056] The recording unit can analyze the user's past input task history and select the optimal recording method. For example, it can classify the user's past input tasks using clustering and automatically record frequently input tasks. It can also analyze the relevance of input tasks using association rules and prioritize recording of highly relevant tasks. It can also identify input task patterns using a decision tree and predict the input method to be used during a specific time period to select the optimal recording method. In this way, the recording unit can select the optimal recording method by analyzing the user's past input task history. Some or all of the above-mentioned processing in the recording unit may be performed using AI, or may be performed without using AI.

[0057] When analyzing the content and context of a task, the analysis unit can take into account the attribute information of the task submitter. For example, the analysis unit can adjust the level of detail based on the submitter's expertise and past performance. The analysis unit can also adjust the way the analysis is presented based on the submitter's age and occupation. This allows the analysis unit to provide more appropriate analysis results by taking into account the submitter's attribute information. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI.

[0058] The providing unit can adjust the level of detail to be provided based on the importance of past answers when providing the answers. For example, detailed information is provided for answers with high importance, and simplified information is provided for answers with low importance. The providing unit can also adjust the level of detail to be provided by evaluating the scope of influence and accuracy of past answers. This allows the providing unit to adjust the level of detail to be provided based on the importance of past answers, and provide more appropriate answers. Some or all of the above-mentioned processing in the providing unit may be performed using AI, or may be performed without using AI.

[0059] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the task. For example, a detailed analysis is performed for a task with high importance, and a simplified analysis is performed for a task with low importance. The analysis unit can also determine the priority of the analysis by evaluating the scope of impact and urgency of the task. This allows the analysis unit to adjust the level of detail of the analysis based on the importance of the task and provide more appropriate analysis results. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without using AI.

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

[0061] Step 1: The recording unit records the user's input tasks. The user's input tasks include text input, voice input, image input, etc. The recording unit records these input tasks in memory or a database. Memory includes RAM and HDD, and databases include SQL databases and NoSQL databases. Step 2: The analyzer analyzes the new input task and identifies the task content and context. The analyzer analyzes the task content and context using natural language processing techniques, which include morphological analysis, grammatical analysis, and semantic analysis. Step 3: The comparison unit compares past input tasks with new input tasks. The comparison unit compares past input tasks with new input tasks using a similarity calculation algorithm. Similarity calculation algorithms include cosine similarity and Euclidean distance. Step 4: The provider will provide answers by referring to past answers if similar tasks are found. The provider will refer to past answers using database search techniques. Database search techniques include SQL queries and full-text search engines.

[0062] (Example 2) The system according to an embodiment of the present invention is a system for solving the power consumption problem of LLMs (Large-Scale Language Models). This system records user input tasks, compares new input tasks with past input tasks when they are submitted, and provides answers by referring to past answers if similar tasks are found. This allows for fast and high-quality answers to be obtained without directly running the LLM. For example, when a user submits an input task to the system, this input task is recorded in memory or a database. Next, when a new input task is submitted, the system compares it with past input tasks. This comparison is performed by analyzing the content and context of the task. For example, if there was a past input such as "a task to provide information," then a new input that is "a task to provide similar information" will be judged as a similar task. If a similar task is found, the system refers to past answers and provides a similar answer. This allows for fast and high-quality answers to be obtained without directly running the LLM. This mechanism can significantly reduce the power consumption of the LLM. Since there is no need to directly run the LLM, power consumption is reduced, and the load on the data center is also reduced. In addition, by providing fast and high-quality answers, user satisfaction is also improved. Furthermore, this system can also be used as training data for the LLM. The accuracy of the LLM can be improved by feeding back the matching results of new input tasks with past input tasks. For example, if the matching accuracy for similar tasks is low, it can be fed back as training data for the LLM to improve the matching accuracy for subsequent tasks. In this way, the present invention solves the power consumption problem of LLMs and contributes to the realization of a society where LLMs and humanity can coexist. As a result, the system can significantly reduce the power consumption of the LLM and alleviate the load on the data center. Furthermore, by providing fast and high-quality answers, user satisfaction can be improved. Moreover, the system can be used as training data for the LLM, further improving the accuracy of the LLM.

[0063] The system according to the embodiment includes a recording unit, an analysis unit, a comparison unit, and a provision unit. The recording unit records a user's input task. Examples of the user's input task include, but are not limited to, text input, voice input, and image input. The recording unit records the user's input task in a memory or a database. The memory includes, for example, a RAM or a HDD, and the database includes, for example, an SQL database or a NoSQL database. The analysis unit analyzes the new input task and identifies the content and context of the task. The analysis unit analyzes the content and context of the task using, for example, natural language processing technology. Examples of natural language processing technology include morphological analysis, grammatical analysis, and semantic analysis. The comparison unit compares a previous input task with a new input task. The comparison unit compares the previous input task with a new input task using, for example, a similarity calculation algorithm. Examples of similarity calculation algorithms include cosine similarity and Euclidean distance. When a similar task is found, the provision unit provides an answer by referring to previous answers. The providing unit references past answers using, for example, a database search technique, such as an SQL query or a full-text search engine. This allows the system according to the embodiment to efficiently record, analyze, and compare user input tasks, and provide high-quality answers quickly when similar tasks are found.

[0064] The recording unit can record the user's input tasks in a memory or a database. For example, the recording unit records the user's input tasks in a memory. The memory includes, for example, a RAM or a HDD. The recording unit can also record the user's input tasks in a database. The database includes, for example, an SQL database or a NoSQL database. This allows the recording unit to efficiently record the user's input tasks. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input the user's input tasks into AI and have the AI ​​perform recording optimization.

[0065] The analysis unit can analyze a new input task and identify its content and context. For example, the analysis unit can analyze a new input task using natural language processing techniques. Natural language processing techniques include, for example, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit can analyze the content of the task using morphological analysis. The analysis unit can also identify the context of the task using grammatical analysis. Furthermore, the analysis unit can identify the meaning of the task using semantic analysis. This allows the analysis unit to accurately identify the content and context of a new input task. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input a new input task into an AI and have the AI ​​perform the task content and context identification.

[0066] The comparison unit can compare past input tasks with new input tasks. For example, the comparison unit compares past input tasks with new input tasks using a similarity calculation algorithm. Similarity calculation algorithms include, for example, cosine similarity and Euclidean distance. For example, the comparison unit compares past input tasks with new input tasks using cosine similarity. The comparison unit can also calculate task similarity using Euclidean distance. Furthermore, the comparison unit can also calculate task similarity using TF-IDF. This allows the comparison unit to accurately compare past input tasks with new input tasks. Some or all of the above processing in the comparison unit may be performed using, for example, AI, or not using AI. For example, the comparison unit can input past input tasks and new input tasks into AI and have the AI ​​perform the similarity calculation.

[0067] When a similar task is found, the providing unit can provide an answer by referring to past answers. The providing unit, for example, refers to past answers using a database search technology. Database search technology includes, for example, an SQL query or a full-text search engine. The providing unit, for example, refers to past answers using an SQL query. The providing unit can also search past answers using a full-text search engine. Furthermore, the providing unit can quickly search past answers using an index. This allows the providing unit to quickly provide a high-quality answer when a similar task is found. 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 past answers to an AI and have the AI ​​select an optimal answer.

[0068] The analysis unit can use natural language processing technology to analyze the content and context of a task. The analysis unit analyzes the content and context of a task using, for example, natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, and semantic analysis. The analysis unit analyzes the content of a task using, for example, morphological analysis. The analysis unit can also identify the context of a task using grammatical analysis. Furthermore, the analysis unit can also identify the meaning of a task using semantic analysis. This allows the analysis unit to analyze the content and context of a task more accurately. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can cause AI to analyze the content and context of a task.

[0069] The comparison unit can use a similarity calculation algorithm to compare past input tasks with new input tasks. For example, the comparison unit compares past input tasks with new input tasks using a similarity calculation algorithm. Similarity calculation algorithms include, for example, cosine similarity and Euclidean distance. For example, the comparison unit compares past input tasks with new input tasks using cosine similarity. The comparison unit can also calculate task similarity using Euclidean distance. Furthermore, the comparison unit can also calculate task similarity using TF-IDF. This allows the comparison unit to improve the accuracy of task comparison. Some or all of the above processing in the comparison unit may be performed using, for example, AI, or not using AI. For example, the comparison unit can have AI execute the similarity calculation algorithm.

[0070] The service provider can use database search techniques to refer to past answers. For example, the service provider can refer to past answers using database search techniques. Database search techniques include, for example, SQL queries and full-text search engines. For example, the service provider can refer to past answers using SQL queries. The service provider can also search for past answers using full-text search engines. Furthermore, the service provider can also use indexes to quickly search for past answers. This allows the service provider to quickly refer to past answers. Some or all of the above processing in the service provider may be performed using, for example, AI, or not using AI. For example, the service provider can input past answers into AI and have the AI ​​select the optimal answer.

[0071] The recording unit can estimate the user's emotions and adjust the recording timing of input tasks based on the estimated emotions. For example, the recording unit uses emotion analysis algorithms to estimate the user's emotions. These algorithms include, for example, facial recognition, speech analysis, and text analysis. For instance, the recording unit can use facial recognition to estimate the user's emotions. It can also use speech analysis to estimate the user's emotions. Furthermore, it can use text analysis to estimate the user's emotions. After estimating the user's emotions, the recording unit adjusts the recording timing of input tasks based on the estimated emotions. For example, if the user is stressed, the recording unit delays recording the input task, waiting until the user is relaxed. If the user is relaxed, the recording unit can immediately record the input task for faster processing. Furthermore, if the user is in a hurry, the recording unit prioritizes recording the input task, processing it faster than other tasks. This allows the recording unit to record tasks at a more appropriate time by adjusting the recording timing according to the user's emotions. Some or all of the above-described processes in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input user emotion data into the AI ​​and have the AI ​​optimize the recording timing.

[0072] The recording unit can analyze the user's past input task history and select the optimal recording method. For example, the recording unit may use data mining techniques to analyze the user's past input task history. Data mining techniques include, for example, clustering, association rules, and decision trees. For example, the recording unit may use clustering to classify the user's past input tasks. The recording unit may also use association rules to analyze the relationships between input tasks. Furthermore, the recording unit may use decision trees to identify patterns in input tasks. After analyzing the user's past input task history, the recording unit selects the optimal recording method. For example, it may automatically record tasks that the user has frequently entered in the past. It may also prioritize recording input methods that the user has used in the past (voice, text, etc.). Furthermore, it may predict the input method to be used during specific time periods based on the user's past input history and select the optimal recording method. In this way, the recording unit can select the optimal recording method by analyzing the user's past input task history. Some or all of the above processing in the recording unit may be performed using, for example, AI, or not using AI. For example, the recording unit can input the user's past input task history into the AI ​​and have the AI ​​select the optimal recording method.

[0073] The recording unit can filter data based on the user's current projects and areas of interest during recording. For example, the recording unit may use project management tools or social media analytics techniques to identify the user's current projects and areas of interest. Project management tools include, for example, task management software and project management platforms. Social media analytics techniques include, for example, analysis of post content and activity frequency. The recording unit may, for example, use project management tools to identify the user's current projects. It can also use social media analytics techniques to identify the user's areas of interest. After identifying the user's current projects and areas of interest, the recording unit performs filtering. For example, it may record only tasks related to the project the user is currently working on. It can also prioritize recording tasks that are highly relevant based on the user's areas of interest. Furthermore, it can record only specific tasks based on filter conditions set by the user. This allows the recording unit to prioritize recording tasks that are highly relevant by filtering based on the user's current projects and areas of interest. Some or all of the above processing in the recording unit may be performed using, for example, AI, or not using AI. For example, the recording unit can input data on the user's projects and areas of interest into the AI, allowing the AI ​​to optimize the filtering process.

[0074] The recording unit can estimate the user's emotions and determine the priority of input tasks to be recorded based on the estimated user's emotions. The recording unit, for example, uses an emotion analysis algorithm to estimate the user's emotions. Emotion analysis algorithms include, for example, facial expression recognition, voice analysis, and text analysis. The recording unit, for example, estimates the user's emotions using facial expression recognition. The recording unit can also estimate the user's emotions using voice analysis. Furthermore, the recording unit can estimate the user's emotions using text analysis. After estimating the user's emotions, the recording unit determines the priority of input tasks to be recorded based on the estimated emotions. For example, if the user is stressed, the recording unit can postpone less important tasks. Furthermore, if the user is relaxed, the recording unit can prioritize recording more important tasks. Furthermore, if the user is in a hurry, the recording unit can prioritize recording more urgent tasks. In this way, the recording unit can record tasks in a more appropriate order by determining the priority of input tasks according to the user's emotions. Some or all of the above-described processing in the recording unit may be performed using, for example, AI or without AI. For example, the recording unit can input user emotion data into the AI ​​and have the AI ​​optimize priorities.

[0075] During recording, the recording unit can prioritize recording highly relevant tasks in consideration of the user's geographical location information. The recording unit, for example, uses GPS data or a location information service to acquire the user's geographical location information. The GPS data includes, for example, latitude and longitude information. The location information service includes, for example, Wi-Fi location information and mobile phone base station information. The recording unit, for example, uses GPS data to identify the user's current location. The recording unit can also identify the user's location using a location information service. After identifying the user's geographical location information, the recording unit prioritizes recording highly relevant tasks. For example, when the user is in a specific location, the recording unit prioritizes recording tasks related to that location. Furthermore, when the user is traveling, the recording unit can prioritize recording tasks related to the user's destination. Furthermore, when the user is at home, the recording unit can prioritize recording tasks to be performed at home. This allows the recording unit to prioritize recording highly relevant tasks in consideration of the user's geographical location information. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input the user's geographical location information into the AI ​​and allow the AI ​​to optimize task priorities.

[0076] The recording unit can analyze the user's social media activity and record related tasks during recording. The recording unit, for example, uses social media analysis technology to analyze the user's social media activity. Social media analysis technology includes, for example, analyzing the content of posts and the frequency of activity. The recording unit, for example, analyzes the content of posts to identify the user's areas of interest. The recording unit can also analyze the frequency of activity to identify the user's activity patterns. The recording unit records related tasks after analyzing the user's social media activity. For example, the recording unit can automatically record tasks mentioned by the user on social media. The recording unit can also prioritize recording related tasks based on the content of the user's social media posts. Furthermore, the recording unit can record tasks mentioned by the user's social media followers and friends. In this way, the recording unit can prioritize recording related tasks by analyzing the user's social media activity. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input the user's social media data into AI to optimize task recording.

[0077] The analysis unit can estimate the user's emotions and adjust the presentation method of the analysis based on the estimated user's emotions. The analysis unit, for example, uses an emotion analysis algorithm to estimate the user's emotions. Emotion analysis algorithms include, for example, facial expression recognition, voice analysis, and text analysis. The analysis unit, for example, estimates the user's emotions using facial expression recognition. The analysis unit can also estimate the user's emotions using voice analysis. Furthermore, the analysis unit can estimate the user's emotions using text analysis. After estimating the user's emotions, the analysis unit adjusts the presentation method of the analysis based on the estimated emotions. For example, if the user is nervous, the analysis unit can provide a simple, highly visible analysis result. On the other hand, if the user is relaxed, the analysis unit can provide a detailed analysis result. Furthermore, if the user is in a hurry, the analysis unit can provide a summary analysis result. In this way, the analysis unit can provide a more appropriate analysis result by adjusting the presentation method of the analysis according to the user's emotions. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI or without AI. For example, the analysis unit can input user emotion data into the AI ​​and have the AI ​​optimize the way the analysis is presented.

[0078] The analysis unit can adjust the level of detail of the analysis based on the importance of the tasks during the analysis. For example, the analysis unit uses an importance evaluation algorithm to assess the importance of tasks. The importance evaluation algorithm may include, for example, the scope of impact, urgency, and dependencies of the tasks. For example, the analysis unit may determine the importance by evaluating the scope of impact of the tasks. The analysis unit may also determine the importance by evaluating the urgency of the tasks. Furthermore, the analysis unit may also determine the importance by evaluating the dependencies of the tasks. After evaluating the importance of the tasks, the analysis unit adjusts the level of detail of the analysis based on the importance. For example, a detailed analysis may be performed for tasks with high importance. A simplified analysis may be performed for tasks with low importance. Furthermore, the analysis priority may be determined according to the importance of the tasks. In this way, the analysis unit can provide more appropriate analysis results by adjusting the level of detail of the analysis based on the importance of the tasks. Some or all of the above processes in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit may input task importance data into AI and have the AI ​​perform the optimization of the level of detail of the analysis.

[0079] During analysis, the analysis unit can apply different analysis algorithms depending on the task category. The analysis unit, for example, uses a category classification algorithm to identify the task category. Examples of category classification algorithms include business tasks, personal tasks, information provision tasks, problem-solving tasks, and data analysis tasks. The analysis unit, for example, uses a business task classification algorithm to identify business tasks. The analysis unit can also use a personal task classification algorithm to identify personal tasks. The analysis unit can also use an information provision task classification algorithm to identify information provision tasks. After identifying the task category, the analysis unit applies different analysis algorithms depending on the category. For example, an information extraction algorithm can be applied to information provision tasks. A problem-solving algorithm can be applied to problem-solving tasks. A data mining algorithm can also be applied to data analysis tasks. This allows the analysis unit to improve analysis accuracy by applying an appropriate analysis algorithm depending on the task category. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input task category data into AI and have the AI ​​select an analysis algorithm.

[0080] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated emotions. For example, the analysis unit uses an emotion analysis algorithm to estimate the user's emotions. Emotion analysis algorithms include, for example, facial recognition, voice analysis, and text analysis. For example, the analysis unit uses facial recognition to estimate the user's emotions. The analysis unit can also estimate the user's emotions using voice analysis. Furthermore, the analysis unit can also estimate the user's emotions using text analysis. After estimating the user's emotions, the analysis unit adjusts the length of the analysis based on the estimated emotions. For example, if the user is in a hurry, the analysis unit provides a short, concise analysis result. If the user is relaxed, the analysis unit can provide a detailed analysis result. Furthermore, if the user is excited, the analysis unit can provide a visually stimulating analysis result. In this way, the analysis unit can provide more appropriate analysis results by adjusting the length of the analysis according to the user's emotions. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input user emotional data into the AI ​​and have the AI ​​optimize the length of the analysis.

[0081] During analysis, the analysis unit can determine the analysis priority based on the submission time of the task. The analysis unit, for example, uses a record of the submission date and time to identify the submission time of the task. The record of the submission date and time includes, for example, a timestamp of the submission date and time. The analysis unit, for example, uses the timestamp of the submission date and time to identify the submission time of the task. After identifying the submission time of the task, the analysis unit determines the analysis priority based on the submission time. For example, it can prioritize analysis of tasks with high urgency. It can also prioritize analysis of tasks with an approaching submission deadline. Furthermore, it can adjust the analysis priority according to the submission time. In this way, the analysis unit can prioritize analysis of tasks with high urgency by determining the analysis priority based on the submission time of the task. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input task submission time data into AI and cause the AI ​​to optimize the analysis priority.

[0082] The analysis unit can adjust the order of analysis based on the relevance of tasks during the analysis process. For example, the analysis unit uses a relevance evaluation algorithm to assess the relevance of tasks. This relevance evaluation algorithm may include, for example, dependencies between tasks, common themes, and interrelationships between tasks. For example, the analysis unit can determine relevance by evaluating dependencies between tasks. It can also determine relevance by evaluating common themes. Furthermore, it can determine relevance by evaluating interrelationships between tasks. After evaluating the relevance of tasks, the analysis unit adjusts the order of analysis based on the relevance. For example, it can prioritize the analysis of highly relevant tasks. It can also postpone the analysis of less relevant tasks. Furthermore, it can adjust the order of analysis according to the relevance of tasks. In this way, the analysis unit can prioritize the analysis of highly relevant tasks by adjusting the order of analysis based on the relevance of tasks. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input task relevance data into AI and have the AI ​​perform the optimization of the analysis order.

[0083] The comparison unit can estimate the user's emotions and adjust the comparison criteria based on the estimated emotions. For example, the comparison unit may use an emotion analysis algorithm to estimate the user's emotions. Emotion analysis algorithms include, for example, facial recognition, speech analysis, and text analysis. For example, the comparison unit may use facial recognition to estimate the user's emotions. It can also use speech analysis to estimate the user's emotions. Furthermore, it can use text analysis to estimate the user's emotions. After estimating the user's emotions, the comparison unit adjusts the comparison criteria based on the estimated emotions. For example, if the user is nervous, the comparison unit provides simple and easily understandable comparison criteria. If the user is relaxed, the comparison unit can provide detailed comparison criteria. Furthermore, if the user is in a hurry, the comparison unit can provide concise comparison criteria. This allows the comparison unit to provide more appropriate comparison results by adjusting the comparison criteria according to the user's emotions. Some or all of the above processing in the comparison unit may be performed using, for example, AI, or not using AI. For example, the comparison unit can input user emotional data into the AI ​​and have the AI ​​optimize the comparison criteria.

[0084] The comparison unit may improve the accuracy of the comparison by taking into account the interrelationships between tasks. The comparison unit may use, for example, an interrelationship evaluation algorithm to evaluate the interrelationships between tasks. The interrelationship evaluation algorithm may include, for example, inter-task dependency, common themes, task relevance, etc. The comparison unit may, for example, evaluate the interrelationships between tasks to determine the interrelationships. The comparison unit may also evaluate common themes to determine the interrelationships. The comparison unit may also evaluate task relevance to determine the interrelationships. After evaluating the interrelationships between tasks, the comparison unit may improve the accuracy of the comparison based on the interrelationships. For example, the comparison unit may analyze the interrelationships between tasks and prioritize comparison of highly related tasks. The comparison unit may also improve the accuracy of the comparison based on the interrelationships between tasks. Furthermore, the comparison unit may adjust the order of comparison by taking into account the interrelationships between tasks. In this way, the comparison unit may improve the accuracy of the comparison by taking into account the interrelationships between tasks, thereby providing more appropriate comparison results. Some or all of the above-described processing in the comparison unit may be performed using, for example, AI, or may be performed without using AI. For example, the comparison unit can input task interrelationship data into the AI ​​and cause the AI ​​to optimize the accuracy of the comparison.

[0085] The comparison unit can perform comparisons while considering the attribute information of the task submitter. For example, the comparison unit uses an attribute information acquisition algorithm to obtain the attribute information of the task submitter. The attribute information acquisition algorithm may include, for example, age, occupation, field of expertise, and past performance. For example, the comparison unit can obtain the submitter's age to identify attribute information. The comparison unit can also obtain the submitter's occupation to identify attribute information. Furthermore, the comparison unit can obtain the submitter's field of expertise to identify attribute information. After identifying the submitter's attribute information, the comparison unit performs a comparison based on the attribute information. For example, it can compare tasks based on the submitter's expertise. It can also compare tasks based on the submitter's past performance. Furthermore, it can compare tasks while considering the submitter's attribute information. In this way, the comparison unit can provide more appropriate comparison results by considering the attribute information of the task submitter when performing comparisons. Some or all of the above processing in the comparison unit may be performed using, for example, AI, or not using AI. For example, the comparison unit can input the submitter's attribute information into AI and have the AI ​​perform the optimization of the comparison.

[0086] The comparison unit can estimate the user's emotion and adjust the order in which the comparison results are displayed based on the estimated user's emotion. The comparison unit, for example, uses an emotion analysis algorithm to estimate the user's emotion. The emotion analysis algorithm can include, for example, facial expression recognition, voice analysis, and text analysis. The comparison unit can estimate the user's emotion using, for example, facial expression recognition. The comparison unit can also estimate the user's emotion using voice analysis. Furthermore, the comparison unit can estimate the user's emotion using text analysis. After estimating the user's emotion, the comparison unit adjusts the order in which the comparison results are displayed based on the estimated emotion. For example, if the user is nervous, the comparison unit can display the results in a simple, highly visible order. Alternatively, if the user is relaxed, the comparison unit can display the results in a detailed order. Furthermore, if the user is in a hurry, the comparison unit can display the results in an order that emphasizes the main points. Thus, the comparison unit can provide the results in a more appropriate order by adjusting the order in which the comparison results are displayed based on the user's emotion. Some or all of the above-described processing in the comparison unit may be performed using, for example, AI, or without AI. For example, the comparison unit can input user emotion data into the AI ​​and have the AI ​​optimize the order in which the results are displayed.

[0087] The comparison unit can take into account the geographic distribution of tasks when making the comparison. The comparison unit, for example, uses a geographic information system (GIS) to evaluate the geographic distribution of tasks. The geographic information system includes, for example, geographic location information, distribution by region, distribution by country, etc. The comparison unit, for example, identifies the geographic distribution of tasks using geographic location information. The comparison unit can also identify the geographic distribution of tasks by evaluating the distribution by region. Furthermore, the comparison unit can identify the geographic distribution of tasks by evaluating the distribution by country. After identifying the geographic distribution of tasks, the comparison unit performs comparison based on the geographic distribution. For example, geographically close tasks can be compared preferentially. Geographically distant tasks can also be postponed. Furthermore, the comparison order can be adjusted taking into account the geographic distribution of tasks. In this way, the comparison unit can provide more appropriate comparison results by making the comparison taking into account the geographic distribution of tasks. Some or all of the above-described processing in the comparison unit may be performed using, for example, AI, or may be performed without AI. For example, the comparison unit can input geographical distribution data of tasks into the AI ​​and have the AI ​​perform the optimization of the comparison.

[0088] The comparison unit can improve the accuracy of the comparison by referring to task-related literature during the comparison. The comparison unit, for example, uses a literature database to refer to task-related literature. The literature database includes, for example, academic papers, technical reports, patent documents, etc. The comparison unit can identify task-related literature by referring to academic papers, for example. The comparison unit can also identify task-related literature by referring to technical reports. Furthermore, the comparison unit can identify task-related literature by referring to patent documents. After identifying task-related literature, the comparison unit can improve the accuracy of the comparison by referring to the relevant literature. For example, the comparison unit can improve the accuracy of task comparison by referring to the relevant literature. The comparison unit can also adjust task comparison criteria based on the relevant literature. Furthermore, the comparison result of the task can be displayed taking the relevant literature into consideration. In this way, the comparison unit can improve the accuracy of the comparison by referring to task-related literature, thereby providing more appropriate comparison results. Some or all of the above-described processing in the comparison unit can be performed using, for example, AI, or without AI. For example, the comparison unit can input task-related literature data into AI and cause the AI ​​to optimize the accuracy of the comparison.

[0089] The service provider can estimate the user's emotions and adjust the way it presents its responses based on those estimated emotions. For example, the service provider might use an emotion analysis algorithm to estimate the user's emotions. These algorithms could include, for example, facial recognition, speech analysis, or text analysis. For instance, the service provider might use facial recognition to estimate the user's emotions. It could also use speech analysis to estimate the user's emotions. Furthermore, it could use text analysis to estimate the user's emotions. After estimating the user's emotions, the service provider adjusts the way it presents its responses based on those estimated emotions. For example, if the user is nervous, the service provider might provide a simple and easily understandable response. If the user is relaxed, the service provider might provide a more detailed response. Furthermore, if the user is in a hurry, the service provider might provide a concise response. This allows the service provider to provide more appropriate responses by adjusting the way it presents its responses according to the user's emotions. Some or all of the above-described processes in the service provider may be performed using, for example, AI, or not using AI. For example, the providing unit can input the user's emotional data into the AI ​​and have the AI ​​optimize the way the answer is expressed.

[0090] The providing unit can adjust the level of detail to be provided based on the importance of past answers when providing the answers. The providing unit, for example, uses an importance evaluation algorithm to evaluate the importance of past answers. The importance evaluation algorithm includes, for example, the scope of influence of the answer, the accuracy of the answer, and the relevance of the answer. The providing unit, for example, determines the importance by evaluating the scope of influence of the answer. The providing unit can also determine the importance by evaluating the accuracy of the answer. Furthermore, the providing unit can determine the importance by evaluating the relevance of the answer. After evaluating the importance of past answers, the providing unit adjusts the level of detail to be provided based on the importance. For example, detailed information can be provided for answers with high importance. Furthermore, simplified information can be provided for answers with low importance. Furthermore, the providing unit can adjust the level of detail to be provided depending on the importance of past answers. As a result, the providing unit can provide a more appropriate answer by adjusting the level of detail to be provided based on the importance of past answers. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input the importance data of past answers into the AI ​​and have the AI ​​optimize the level of detail provided.

[0091] The providing unit can apply different provision algorithms depending on the task category when providing the data. The providing unit, for example, uses a category classification algorithm to identify the task category. Category classification algorithms include, for example, business tasks, personal tasks, information provision tasks, problem-solving tasks, and data analysis tasks. The providing unit, for example, uses a business task classification algorithm to identify business tasks. The providing unit can also use a personal task classification algorithm to identify personal tasks. Furthermore, the providing unit can also use an information provision task classification algorithm to identify information provision tasks. After identifying the task category, the providing unit applies different provision algorithms depending on the category. For example, an information extraction algorithm can be applied to an information provision task. A problem-solving algorithm can be applied to a problem-solving task. Furthermore, a data mining algorithm can be applied to a data analysis task. In this way, the providing unit can improve provision accuracy by applying an appropriate provision algorithm depending on the task category. 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 task category data into AI and cause the AI ​​to select a provision algorithm.

[0092] The providing unit can estimate the user's emotion and adjust the length of the answer to be provided based on the estimated user's emotion. The providing unit, for example, uses an emotion analysis algorithm to estimate the user's emotion. Emotion analysis algorithms include, for example, facial expression recognition, voice analysis, and text analysis. The providing unit, for example, estimates the user's emotion using facial expression recognition. The providing unit can also estimate the user's emotion using voice analysis. Furthermore, the providing unit can estimate the user's emotion using text analysis. After estimating the user's emotion, the providing unit adjusts the length of the answer to be provided based on the estimated emotion. For example, if the user is in a hurry, the providing unit can provide a short and to-the-point answer. On the other hand, if the user is relaxed, the providing unit can provide a detailed answer. Furthermore, if the user is excited, the providing unit can provide a visually stimulating answer. In this way, the providing unit can adjust the length of the answer to be provided according to the user's emotion, thereby providing a more appropriate answer. 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 user's emotional data into the AI ​​and have the AI ​​optimize the length of the answer.

[0093] The providing unit can determine the priority of providing answers based on the submission dates of past answers when providing answers. The providing unit, for example, uses records of submission dates and times to identify the submission dates of past answers. The records of submission dates and times include, for example, timestamps of the submission dates. The providing unit, for example, uses the timestamps of the submission dates and times to identify the submission dates of past answers. After identifying the submission dates of past answers, the providing unit determines the priority of providing answers based on the submission dates. For example, answers with high urgency can be provided preferentially. Also, answers with an approaching submission deadline can be provided preferentially. Furthermore, the priority of providing answers can be adjusted depending on the submission dates. In this way, the providing unit can determine the priority of providing answers based on the submission dates of past answers, thereby providing answers with high urgency preferentially. 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 data on the submission dates of past answers into AI and cause the AI ​​to optimize the priority of providing answers.

[0094] The providing unit can adjust the order of providing answers based on the relevance of past answers when providing answers. The providing unit, for example, uses a relevance assessment algorithm to evaluate the relevance of past answers. The relevance assessment algorithm includes, for example, dependencies between answers, common themes, and interrelationships between answers. The providing unit, for example, determines the relevance by evaluating dependencies between answers. The providing unit can also determine the relevance by evaluating common themes. Furthermore, the providing unit can determine the relevance by evaluating interrelationships between answers. After evaluating the relevance of past answers, the providing unit adjusts the order of providing answers based on the relevance. For example, highly relevant answers can be provided preferentially. Also, less relevant answers can be postponed. Furthermore, the providing unit can adjust the order of providing answers according to the relevance of past answers. In this way, the providing unit can prioritize providing highly relevant answers by adjusting the order of providing answers based on the relevance of past answers. 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 relevance data of past answers into AI and cause the AI ​​to optimize the order of providing answers. === Hard Collateral 1-1 === Each of the multiple elements described above, including the recording unit, analysis unit, comparison unit, and provision unit, is implemented in, for example, at least one of the smart device 14 and the data processing unit 12. For example, the recording unit records the user's input tasks in the memory or database of the smart device 14. The analysis unit analyzes the new input task using the identification processing unit 290 of the data processing unit 12 to identify the content and context of the task. The comparison unit compares past input tasks with the new input task using the identification processing unit 290 of the data processing unit 12. The provision unit provides answers by referring to past answers when similar tasks are found using the identification processing unit 290 of the data processing unit 12. The recording unit can, for example, estimate the user's emotions using the control unit 46A of the smart device 14 and adjust the timing of recording input tasks based on the estimated emotions. === Hard Collateral 1-2 === Each of the multiple elements described above, including the recording unit, analysis unit, comparison unit, and providing unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the recording unit records the user's input tasks in the memory or database of the smart glasses 214. The analysis unit analyzes new input tasks using the identification processing unit 290 of the data processing unit 12 to identify the content and context of the tasks. The comparison unit compares past input tasks with new input tasks using the identification processing unit 290 of the data processing unit 12. The providing unit provides answers by referring to past answers when similar tasks are found using the identification processing unit 290 of the data processing unit 12. The recording unit can, for example, estimate the user's emotions using the control unit 46A of the smart glasses 214 and adjust the timing of recording input tasks based on the estimated emotions. === Hard Collateral 1-3 === Each of the multiple elements described above, including the recording unit, analysis unit, comparison unit, and provision unit, is implemented in, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the recording unit records the user's input tasks in the memory or database of the headset terminal 314. The analysis unit analyzes new input tasks using the identification processing unit 290 of the data processing unit 12 and identifies the content and context of the tasks. The comparison unit compares past input tasks with new input tasks using the identification processing unit 290 of the data processing unit 12. The provision unit provides answers by referring to past answers when similar tasks are found using the identification processing unit 290 of the data processing unit 12. The recording unit can, for example, estimate the user's emotions using the control unit 46A of the headset terminal 314 and adjust the timing of recording input tasks based on the estimated emotions. === Hard Collateral 1-4 === Each of the multiple elements described above, including the recording unit, analysis unit, comparison unit, and providing unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the recording unit records the user's input tasks in the robot 414's memory or database. The analysis unit analyzes the new input task using the identification processing unit 290 of the data processing unit 12 to identify the task's content and context. The comparison unit compares past input tasks with the new input task using the identification processing unit 290 of the data processing unit 12. The providing unit provides answers by referring to past answers when similar tasks are found using the identification processing unit 290 of the data processing unit 12. The recording unit can, for example, estimate the user's emotions using the control unit 46A of the robot 414 and adjust the timing of recording input tasks based on the estimated emotions.

[0095] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0096] When recording tasks input by a user, the recording unit can determine the priority of recording based on the importance of the task. For example, it can record urgent tasks first and postpone less important tasks. It can also adjust the order of recording taking into account the scope of impact and dependencies of tasks. This allows the recording unit to quickly record important tasks and achieve efficient task management. Furthermore, the recording unit can input task importance data into AI and have the AI ​​optimize the priority of recording.

[0097] The analysis unit can estimate the user's emotions and adjust the level of detail of the analysis based on the estimated user's emotions. For example, if the user is feeling stressed, the analysis unit can provide a simplified analysis result, and if the user is relaxed, it can provide a detailed analysis result. Also, if the user is in a hurry, it can provide an analysis result that focuses on the main points. In this way, the analysis unit can adjust the level of detail of the analysis according to the user's emotions and provide more appropriate analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI.

[0098] When comparing past input tasks with new input tasks, the comparison unit can apply different comparison algorithms depending on the task category. For example, a comparison algorithm dedicated to business tasks can be applied to business tasks, and a comparison algorithm dedicated to personal tasks can be applied to personal tasks. It is also possible to apply a comparison algorithm dedicated to information provision tasks to information provision tasks. This allows the comparison unit to apply an appropriate comparison algorithm depending on the task category, thereby improving comparison accuracy. Some or all of the above-mentioned processing in the comparison unit may be performed using AI, or may be performed without using AI.

[0099] The providing unit can estimate the user's emotions and adjust the way the answer is presented based on the estimated user's emotions. For example, if the user is nervous, the providing unit can provide a simple, highly visible answer, and if the user is relaxed, the providing unit can provide a detailed answer. Also, if the user is in a hurry, the providing unit can provide an answer that focuses on the main points. This allows the providing unit to adjust the way the answer is presented in accordance with the user's emotions and provide a more appropriate answer. Some or all of the above-mentioned processing in the providing unit may be performed using AI, or may be performed without using AI.

[0100] The recording unit can analyze the user's past input task history and select the optimal recording method. For example, it can classify the user's past input tasks using clustering and automatically record frequently input tasks. It can also analyze the relevance of input tasks using association rules and prioritize recording of highly relevant tasks. It can also identify input task patterns using a decision tree and predict the input method to be used during a specific time period to select the optimal recording method. In this way, the recording unit can select the optimal recording method by analyzing the user's past input task history. Some or all of the above-mentioned processing in the recording unit may be performed using AI, or may be performed without using AI.

[0101] When analyzing the content and context of a task, the analysis unit can take into account the attribute information of the task submitter. For example, the analysis unit can adjust the level of detail based on the submitter's expertise and past performance. The analysis unit can also adjust the way the analysis is presented based on the submitter's age and occupation. This allows the analysis unit to provide more appropriate analysis results by taking into account the submitter's attribute information. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI.

[0102] The comparison unit can estimate the user's emotions and adjust the comparison criteria based on those emotions. For example, if the user is nervous, the comparison unit provides simple and easily understandable comparison criteria, while if the user is relaxed, it provides detailed comparison criteria. It can also provide concise comparison criteria if the user is in a hurry. This allows the comparison unit to adjust the comparison criteria according to the user's emotions and provide more appropriate comparison results. Some or all of the above processing in the comparison unit may be performed using AI or not.

[0103] The providing unit can adjust the level of detail to be provided based on the importance of past answers when providing the answers. For example, detailed information is provided for answers with high importance, and simplified information is provided for answers with low importance. The providing unit can also adjust the level of detail to be provided by evaluating the scope of influence and accuracy of past answers. This allows the providing unit to adjust the level of detail to be provided based on the importance of past answers, and provide more appropriate answers. Some or all of the above-mentioned processing in the providing unit may be performed using AI, or may be performed without using AI.

[0104] The recording unit can estimate the user's emotions and adjust the timing of recording input tasks based on the estimated emotions. For example, if the user is stressed, the recording unit will delay recording the input task and wait until the user is relaxed. If the user is relaxed, the recording unit will immediately record the input task for faster processing. Furthermore, if the user is in a hurry, the recording unit will prioritize recording the input task and process it faster than other tasks. In this way, the recording unit can adjust the timing of recording input tasks according to the user's emotions, recording tasks at a more appropriate time. Some or all of the above processing in the recording unit may be performed using AI or not.

[0105] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the task. For example, a detailed analysis is performed for a task with high importance, and a simplified analysis is performed for a task with low importance. The analysis unit can also determine the priority of the analysis by evaluating the scope of impact and urgency of the task. This allows the analysis unit to adjust the level of detail of the analysis based on the importance of the task and provide more appropriate analysis results. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without using AI.

[0106] The processing flow of the second embodiment will be briefly explained below.

[0107] Step 1: The recording unit records the user's input tasks. The user's input tasks include text input, voice input, image input, etc. The recording unit records these input tasks in memory or a database. Memory includes RAM and HDD, and databases include SQL databases and NoSQL databases. Step 2: The analyzer analyzes the new input task and identifies the task content and context. The analyzer analyzes the task content and context using natural language processing techniques, which include morphological analysis, grammatical analysis, and semantic analysis. Step 3: The comparison unit compares past input tasks with new input tasks. The comparison unit compares past input tasks with new input tasks using a similarity calculation algorithm. Similarity calculation algorithms include cosine similarity and Euclidean distance. Step 4: The provider will provide answers by referring to past answers if similar tasks are found. The provider will refer to past answers using database search techniques. Database search techniques include SQL queries and full-text search engines.

[0108] 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.

[0109] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0110] 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.

[0111] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0112] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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).

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0126] 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.

[0127] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0128] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0142] 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.

[0143] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0144] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0145] 7, the 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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).

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0159] 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.

[0160] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0166] 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."

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] [Explanation of symbols]

[0180] 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 recording unit for recording a user's input task; an analysis unit that analyzes the input task recorded by the recording unit; a comparison unit that compares the input task analyzed by the analysis unit with past input tasks; a providing unit that provides an answer by referring to past answers when a similar task is found by the comparing unit. A system characterized by:

2. The recording unit Recording user input tasks in memory or a database 2. The system of claim 1.

3. The analysis unit Analyze new input tasks to identify task content and context 2. The system of claim 1.

4. The comparison unit Compare past and new input tasks 2. The system of claim 1.

5. The providing unit If a similar task is found, provide an answer by referencing previous answers 2. The system of claim 1.

6. The analysis unit Use natural language processing techniques to analyze task content and context 2. The system of claim 1.

7. The comparison unit Use a similarity calculation algorithm to compare past input tasks with new input tasks 2. The system of claim 1.

8. The providing unit Use database search techniques to reference past answers 2. The system of claim 1.

Images