system

Abstract

The system according to the embodiment aims to generate highly reliable training data by effectively utilizing data held by a company. According to an embodiment, the system includes a collection unit, an analysis unit, and a generation unit. The collection unit collects company data. The analysis unit analyzes the data collected by the collection unit. The generation unit generates training data based on the data analyzed by the analysis unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have not been able to effectively utilize data held by companies to generate highly reliable training data, and there is room for improvement.

[0005] The system according to the embodiment aims to generate highly reliable training data by effectively utilizing data held by a company. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, and a generation unit. The collection unit collects company data. The analysis unit analyzes the data collected by the collection unit. The generation unit generates training data based on the data analyzed by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can effectively utilize data held by a company to generate highly reliable training data. [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 pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

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

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

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

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

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

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

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

[0028] (Example 1) A data management system according to an embodiment of the present invention is a system that enables organizations such as companies, local governments, schools, and hospitals to ensure reliable data required for their operations. This data management system aims to conduct business operations based on data held by the company itself, rather than on ambiguous information from the web. Specifically, it uses generative AI to regenerate training data to ensure reliability. The training data includes the following elements: 1. University-level knowledge of each country; 2. AI literacy, laws, and general knowledge of each country; 3. Multilingual support. In addition, training data is created by adding data from the company's industry and its own data. This allows the generative AI to learn reliable data specific to the company's operations. Furthermore, by contracting out the generation of training data, we aim to expand profits. Specifically, we provide a process for generating reliable training data based on data provided by companies and training the generative AI with this data. This system allows companies to conduct business using data optimized for their operations, which is expected to improve operational efficiency and ensure reliability. For example, the system collects financial data, customer data, marketing data, and other data held by the company and generates training data based on this data. Furthermore, the reliability of the collected data is evaluated, and only reliable data is used as training data. Furthermore, to support multiple languages, the system is equipped with a translation department and generates learning data that includes university-level knowledge, AI literacy, laws, and general knowledge from each country. This allows companies to operate using data optimized for their own business, which is expected to improve operational efficiency and ensure reliability. This allows the data management system to provide the highly reliable data required for corporate business operations.

[0029] A data management system according to an embodiment includes a collection unit, an analysis unit, and a generation unit. The collection unit collects corporate data. Corporate data includes, but is not limited to, financial data, customer data, and marketing data. The collection unit collects corporate data using, for example, an API. The collection unit can also collect data from the web using scraping technology. The collection unit can also obtain data directly from a corporate database. For example, the collection unit accesses the corporate database and extracts necessary data. The analysis unit analyzes the data collected by the collection unit. The analysis unit evaluates, for example, the reliability of the data. Evaluation of reliability includes, but is not limited to, the origin and consistency of the data. For example, the analysis unit verifies the origin of the data and selects only highly reliable data. The analysis unit can also evaluate the consistency of the data and select consistent data. The analysis unit can also evaluate the quality of the data and select only high-quality data. For example, the analysis unit detects missing values ​​and outliers in the data and removes them. The generation unit generates training data based on the data analyzed by the analysis unit. The generation unit generates training data including, for example, university-level knowledge of each country, AI literacy, laws, and general knowledge. The training data includes, for example, text data, numerical data, and image data, but is not limited to these examples. For example, the generation unit generates text data and trains an AI model. The generation unit can also generate numerical data and train an AI model. Furthermore, the generation unit can generate image data and train an AI model. For example, the generation unit generates text data based on university-level knowledge of each country and trains an AI model. This enables the data management system according to the embodiment to efficiently collect, analyze, and generate corporate data.

[0030] The collection unit can collect company industry data or company data. For example, the collection unit collects company industry data. Company industry data includes, but is not limited to, manufacturing, service, and IT industries. For example, the collection unit collects manufacturing industry data to acquire manufacturing process and product information. The collection unit can also collect service industry data to acquire service provision process and customer information. The collection unit can also collect IT industry data to acquire software development process and technical information. For example, the collection unit collects company industry data using an API and stores it in a database. The collection unit can also collect company industry data from the web using scraping technology. The collection unit can also acquire industry data directly from a company database. For example, the collection unit accesses a company database and extracts the necessary industry data. This allows for efficient collection of company industry data and company data.

[0031] The analysis unit may include an evaluation unit that evaluates the reliability of the collected data. The analysis unit, for example, evaluates the reliability of the collected data. The evaluation of reliability includes, but is not limited to, the origin and consistency of the data. For example, the analysis unit verifies the origin of the data and selects only highly reliable data. The analysis unit can also evaluate the consistency of the data and select consistent data. Furthermore, the analysis unit can evaluate the quality of the data and select only high-quality data. For example, the analysis unit detects missing values ​​and outliers in the data and removes them. This allows the reliability of the collected data to be evaluated. Some or all of the above-described processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit may input the collected data into a generation AI and have the generation AI perform a reliability evaluation.

[0032] The generation unit may include a translation unit that supports multiple languages. The generation unit may include, for example, a translation unit for supporting multiple languages. The translation unit translates the training data into multiple languages, for example, using a translation algorithm that supports the languages ​​of each country. For example, the translation unit uses a translation algorithm that supports languages ​​such as English, Japanese, and French. The translation unit may also perform real-time translation. For example, the translation unit translates the training data into the corresponding language as soon as it is input. Furthermore, the translation unit may have language experts review the training data to improve translation accuracy. For example, the translation unit may have experts review the translated training data and make corrections as necessary. This enables multilingual support. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit may input the training data into a generation AI and have the generation AI perform the translation.

[0033] The generation unit can generate training data including university-level knowledge of each country, AI literacy, laws, and general knowledge. For example, the generation unit generates training data including university-level knowledge of each country. University-level knowledge includes, but is not limited to, specific academic fields and specialized knowledge. For example, the generation unit generates training data including knowledge of academic fields such as physics, chemistry, and biology. The generation unit can also generate training data including AI literacy. AI literacy includes, but is not limited to, basic AI concepts and AI application methods. For example, the generation unit generates training data including AI concepts such as machine learning, deep learning, and natural language processing. The generation unit can also generate training data including laws. Examples of laws include, but are not limited to, data protection laws and intellectual property laws. For example, the generation unit generates training data including knowledge of data protection laws and intellectual property laws of each country. The generation unit can also generate training data including general knowledge. Examples of general knowledge include, but are not limited to, social etiquette and basic ethics. For example, the generation unit generates training data including knowledge on business etiquette and ethics. This makes it possible to generate training data including university-level knowledge from each country, AI literacy, law, and general knowledge. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may input university-level knowledge from each country into the generation AI and cause the generation AI to generate training data.

[0034] The collection unit can analyze the company's past data collection history and select an appropriate collection method. The collection unit, for example, analyzes the company's past data collection history. The past data collection history includes, for example, the collection date and time, the type of collected data, etc., but is not limited to these examples. For example, the collection unit analyzes the data collection methods used by the company in the past and selects the most effective method. The collection unit can also select a collection method that is effective at a specific time from the company's past data collection history. Furthermore, the collection unit can select the optimal data collection tool based on the company's past data collection history. For example, the collection unit analyzes the past data collection history and confirms that a specific tool is most effective. This allows the optimal collection method to be selected based on the company's past data collection history. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using a generation AI or without using a generation AI. For example, the collection unit can input the past data collection history into the generation AI and have the generation AI select the optimal collection method.

[0035] When collecting data, the collection unit may filter the data based on the company's current projects or areas of interest. For example, the collection unit may collect only data related to the company's current projects. Current projects include, but are not limited to, ongoing projects and planned projects. For example, the collection unit may collect data related to ongoing projects to understand the project's progress. The collection unit may also collect data related to planned projects to support project planning. Furthermore, the collection unit may preferentially collect relevant data based on the company's areas of interest. Areas of interest include, but are not limited to, specific technical fields or market segments. For example, the collection unit may collect data related to a specific technical field to understand technological advances. The collection unit may also collect data related to a specific market segment to understand market trends. This allows data to be filtered based on the company's current projects or areas of interest. Some or all of the above-described processing in the collection unit may be performed using, or without, the generation AI. For example, the collection unit may input the company's project information and areas of interest into the generation AI and have the generation AI perform the filtering.

[0036] When collecting data, the collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the company. For example, the collection unit prioritizes collecting data related to the company's location. Geographical location information includes, but is not limited to, countries, regions, cities, etc. For example, the collection unit collects data related to the company's location and acquires region-specific information. The collection unit can also collect region-specific data based on the company's geographical location information. Furthermore, the collection unit can select an optimal data collection method by taking into account the company's geographical location information. For example, the collection unit selects an optimal data collection method based on the company's location. This allows highly relevant data to be prioritized by taking into account the company's geographical location information. Some or all of the above-described processing by the collection unit may be performed using, or without, the generation AI. For example, the collection unit can input the company's geographical location information into the generation AI and cause the generation AI to collect highly relevant data.

[0037] During data collection, the collection unit may analyze the company's social media activities and collect related data. The collection unit may, for example, analyze the company's social media activities. Social media activities may include, but are not limited to, post content, engagement rates, etc. For example, the collection unit may analyze the company's social media posts and collect related data. The collection unit may also collect trend-related data from the company's social media activities. Furthermore, the collection unit may select the optimal data collection method based on the company's social media activities. For example, the collection unit may analyze the social media activities and confirm that a specific collection method is most effective. This allows the company's social media activities to be analyzed and related data to be collected. Some or all of the above-described processing in the collection unit may be performed, for example, using or without the generation AI. For example, the collection unit may input the company's social media data into the generation AI and have the generation AI collect related data.

[0038] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the data. The analysis unit adjusts the level of detail of the analysis based on, for example, the importance of the data. The importance of the data includes, for example, the impact on the business and the reliability of the data, but is not limited to these examples. For example, the analysis unit performs a detailed analysis on data with high importance. The analysis unit can also perform a concise analysis on data with low importance. Furthermore, the analysis unit can optimally allocate analysis resources according to the importance of the data. For example, the analysis unit allocates more resources to data with high importance and performs a detailed analysis. This makes it possible to adjust the level of detail of the analysis based on the importance of the data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the importance of the data to the generation AI and have the generation AI adjust the level of detail of the analysis.

[0039] During analysis, the analysis unit can apply different analysis algorithms depending on the data category. For example, the analysis unit applies different analysis algorithms depending on the data category. Data categories include, but are not limited to, text data, numerical data, and image data. For example, the analysis unit applies a natural language processing algorithm to text data. The analysis unit can also apply an image recognition algorithm to image data. The analysis unit can also apply a statistical analysis algorithm to numerical data. For example, the analysis unit can apply a clustering algorithm to text data to classify the data. The analysis unit can also apply an image recognition algorithm to image data to analyze the content of the image. This makes it possible to apply different analysis algorithms depending on the data category. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input the data category to the generation AI and have the generation AI select an analysis algorithm to apply.

[0040] During analysis, the analysis unit can determine the analysis priority based on the time of data submission. The analysis unit determines the analysis priority based on, for example, the time of data submission. The time of data submission includes, for example, the submission date and time and the submission frequency, but is not limited to these examples. For example, the analysis unit prioritizes analysis of the most recent data. The analysis unit can also postpone data that was submitted earlier. Furthermore, the analysis unit can optimize the analysis schedule based on the time of submission. For example, the analysis unit adjusts the analysis schedule based on the time of submission and performs analysis efficiently. This makes it possible to determine the analysis priority based on the time of data submission. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the time of data submission to the generation AI and have the generation AI determine the analysis priority.

[0041] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the data. The analysis unit adjusts the order of analysis based on, for example, the relevance of the data. Data relevance includes, for example, correlation between data and frequency of co-occurrence, but is not limited to such examples. For example, the analysis unit prioritizes analysis of highly relevant data. The analysis unit can also postpone analysis of less relevant data. Furthermore, the analysis unit can optimize the order of analysis based on the relevance of the data. For example, the analysis unit starts analysis with highly relevant data and performs analysis efficiently. This makes it possible to adjust the order of analysis based on the relevance of the data. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the relevance of the data into the generation AI and have the generation AI adjust the order of analysis.

[0042] The generation unit can improve the accuracy of the generation of training data by taking into account the interrelationships between data. The generation unit generates the training data, for example, by taking into account the interrelationships between data. Examples of the interrelationships between data include, but are not limited to, correlations between data and co-occurrence frequencies between data. For example, the generation unit analyzes the interrelationships between data and generates training data by combining highly related data. The generation unit can also improve the accuracy of the training data by taking into account the interrelationships between data. Furthermore, the generation unit can generate optimal training data based on the interrelationships between data. For example, the generation unit analyzes the correlations between data and generates training data by combining highly related data. This allows the accuracy of the training data to be improved by taking into account the interrelationships between data. Some or all of the above-described processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit may input the interrelationships between data into the generation AI and cause the generation AI to generate training data.

[0043] The generation unit can generate training data while taking into account attribute information of the data submitter. The generation unit generates training data, for example, by taking into account attribute information of the data submitter. The attribute information of the data submitter includes, but is not limited to, the submitter's occupation and expertise. For example, the generation unit generates training data by taking into account the expertise of the data submitter. The generation unit can also generate optimal training data based on the industry of the data submitter. Furthermore, the generation unit can improve the accuracy of the training data based on the attribute information of the data submitter. For example, the generation unit generates training data by taking into account the submitter's occupation and expertise. This makes it possible to improve the accuracy of the training data by taking into account the attribute information of the data submitter. Some or all of the above-described processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the submitter's attribute information into the generation AI and cause the generation AI to generate training data.

[0044] The generation unit may generate training data while taking into account the geographical distribution of the data. For example, the generation unit generates training data while taking into account the geographical distribution of the data. Examples of geographical distribution include, but are not limited to, countries, regions, and cities. For example, the generation unit generates region-specific training data while taking into account the geographical distribution of the data. The generation unit may also generate optimal training data based on the geographical distribution. Furthermore, the generation unit may improve the accuracy of the training data while taking into account the geographical distribution. For example, the generation unit analyzes the geographical distribution of the data and generates region-specific training data. This allows the accuracy of the training data to be improved while taking into account the geographical distribution of the data. Some or all of the above-described processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit may input the geographical distribution of the data into the generation AI and cause the generation AI to generate training data.

[0045] When generating training data, the generation unit can improve the accuracy of the generation by referring to literature related to the data. The generation unit generates training data by, for example, referring to literature related to the data. Related literature includes, for example, academic papers and technical reports, but is not limited to such examples. For example, the generation unit improves the accuracy of the training data by referring to literature related to the data. The generation unit can also generate optimal training data based on the related literature. Furthermore, the generation unit can improve the accuracy of the training data by taking into account literature related to the data. For example, the generation unit improves the accuracy of the training data by referring to the related literature. This makes it possible to improve the accuracy of the training data by referring to literature related to the data. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input related literature to the generation AI and cause the generation AI to generate training data.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] When collecting corporate data, the collection unit can evaluate the reliability of the data source in real time. For example, the collection unit can consider the past data provision history and the reputation of the data source to evaluate whether the data source is reliable. In addition, if the data source is not reliable, the collection unit can automatically select another reliable data source. Furthermore, if the data source is reliable, the collection unit can increase the frequency of data collection and collect more detailed data. This allows the collection unit to evaluate the reliability of the data source in real time and efficiently collect reliable data.

[0048] The collection unit can automatically optimize the data collection method when collecting company industry data or company data. For example, when collecting company industry data, the collection unit can consider past collection history and collection efficiency to select the optimal collection method. The collection unit can also consider the characteristics of the collection source and the type of data to automatically optimize the data collection method. Furthermore, the collection unit can also consider the network status of the collection source and the frequency of data updates to optimize the data collection method. This allows the collection unit to efficiently collect company industry data and company data.

[0049] When evaluating the reliability of collected data, the analysis unit can evaluate not only the origin and consistency of the data, but also the recency and relevance of the data. For example, the analysis unit can evaluate whether the collected data is up-to-date and exclude old data. The analysis unit can also evaluate whether the collected data is relevant to other data and exclude less relevant data. Furthermore, to evaluate the reliability of data, the analysis unit can evaluate not only the origin and consistency of the data, but also the quality and accuracy of the data. This allows the analysis unit to increase the reliability of the collected data.

[0050] When the generation unit includes a translation unit that supports multiple languages, it can take technical terms and industry-specific expressions into consideration to improve translation accuracy. For example, when using a translation algorithm that supports the languages ​​of each country, the translation unit can use a dictionary for accurately translating technical terms and industry-specific expressions. The translation unit can also conduct reviews by language experts in each country to improve translation accuracy. Furthermore, the translation unit can include technical terms and industry-specific expressions in the training data of the translation algorithm to improve translation accuracy. This allows the generation unit to improve translation accuracy when supporting multiple languages.

[0051] When generating training data including university-level knowledge of each country or AI literacy, law, and general knowledge, the generation unit can evaluate the origin and consistency of the data to improve the reliability of the data. For example, when generating training data including university-level knowledge of each country, the generation unit can evaluate whether the origin of the data is reliable. In addition, when generating training data including AI literacy, the generation unit can evaluate the consistency of the data and select consistent data. Furthermore, when generating training data including law, the generation unit can evaluate the quality of the data and select only high-quality data. This allows the generation unit to improve the reliability of training data including university-level knowledge of each country, AI literacy, law, and general knowledge.

[0052] The collection unit can analyze the company's past data collection history and automatically detect patterns in the collection history when selecting an appropriate collection method. For example, the collection unit can use a machine learning algorithm to analyze the past data collection history and detect specific patterns. The collection unit can also automatically select an optimal collection method based on the patterns in the collection history. Furthermore, the collection unit can evaluate the effectiveness of the collection method based on the patterns in the collection history and improve the collection method. In this way, the collection unit can select an optimal collection method based on the company's past data collection history and improve the efficiency of data collection.

[0053] When collecting data, the collection unit can take into account the progress and priority of projects when filtering based on the company's current projects and areas of interest. For example, the collection unit can grasp the progress of ongoing projects and prioritize collecting data related to high-priority projects. The collection unit can also consider the priority of planned projects and prioritize collecting data related to important projects. Furthermore, the collection unit can monitor changes in the areas of interest in real time when prioritizedly collecting highly relevant data based on the company's areas of interest. This allows the collection unit to efficiently filter and collect data based on the company's current projects and areas of interest.

[0054] When collecting data, the collection unit may take into account geographical trends and region-specific events when prioritizing the collection of highly relevant data by taking into account the geographical location information of the company. For example, the collection unit may analyze geographical trends related to the location of the company and prioritize the collection of data related to the trends. The collection unit may also prioritize the collection of data related to region-specific events and festivals. Furthermore, the collection unit may prioritize the collection of data related to region-specific regulations and laws based on the geographical location information of the company. This allows the collection unit to efficiently collect highly relevant data by taking into account the geographical location information of the company.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The collection unit collects company data. This data includes financial data, customer data, marketing data, etc. The collection unit can collect company data using APIs. It can also collect data from the web using scraping technology. It can also obtain data directly from the company's database, accessing the company's database and extracting the required data. Step 2: The analysis department analyzes the data collected by the collection department. The analysis department evaluates the reliability of the data and selects only reliable data. The analysis department checks the origin and consistency of the data and selects consistent data. The analysis department also evaluates the quality of the data and detects and removes missing values ​​and outliers. Step 3: The generation unit generates training data based on the data analyzed by the analysis unit. The generation unit generates training data that includes university-level knowledge from each country, AI literacy, laws, and general knowledge. The training data includes text data, numerical data, image data, etc. For example, the generation unit generates text data, numerical data, and image data and trains the AI ​​model.

[0057] (Example 2) A data management system according to an embodiment of the present invention is a system that enables organizations such as companies, local governments, schools, and hospitals to ensure reliable data required for their operations. This data management system aims to conduct business operations based on data held by the company itself, rather than on ambiguous information from the web. Specifically, it uses generative AI to regenerate training data to ensure reliability. The training data includes the following elements: 1. University-level knowledge of each country; 2. AI literacy, laws, and general knowledge of each country; 3. Multilingual support. In addition, training data is created by adding data from the company's industry and its own data. This allows the generative AI to learn reliable data specific to the company's operations. Furthermore, by contracting out the generation of training data, we aim to expand profits. Specifically, we provide a process for generating reliable training data based on data provided by companies and training the generative AI with this data. This system allows companies to conduct business using data optimized for their operations, which is expected to improve operational efficiency and ensure reliability. For example, the system collects financial data, customer data, marketing data, and other data held by the company and generates training data based on this data. Furthermore, the reliability of the collected data is evaluated, and only reliable data is used as training data. Furthermore, to support multiple languages, the system is equipped with a translation department and generates learning data that includes university-level knowledge, AI literacy, laws, and general knowledge from each country. This allows companies to operate using data optimized for their own business, which is expected to improve operational efficiency and ensure reliability. This allows the data management system to provide the highly reliable data required for corporate business operations.

[0058] A data management system according to an embodiment includes a collection unit, an analysis unit, and a generation unit. The collection unit collects corporate data. Corporate data includes, but is not limited to, financial data, customer data, and marketing data. The collection unit collects corporate data using, for example, an API. The collection unit can also collect data from the web using scraping technology. The collection unit can also obtain data directly from a corporate database. For example, the collection unit accesses the corporate database and extracts necessary data. The analysis unit analyzes the data collected by the collection unit. The analysis unit evaluates, for example, the reliability of the data. Evaluation of reliability includes, but is not limited to, the origin and consistency of the data. For example, the analysis unit verifies the origin of the data and selects only highly reliable data. The analysis unit can also evaluate the consistency of the data and select consistent data. The analysis unit can also evaluate the quality of the data and select only high-quality data. For example, the analysis unit detects missing values ​​and outliers in the data and removes them. The generation unit generates training data based on the data analyzed by the analysis unit. The generation unit generates training data including, for example, university-level knowledge of each country, AI literacy, laws, and general knowledge. The training data includes, for example, text data, numerical data, and image data, but is not limited to these examples. For example, the generation unit generates text data and trains an AI model. The generation unit can also generate numerical data and train an AI model. Furthermore, the generation unit can generate image data and train an AI model. For example, the generation unit generates text data based on university-level knowledge of each country and trains an AI model. This enables the data management system according to the embodiment to efficiently collect, analyze, and generate corporate data.

[0059] The collection unit can collect company industry data or company data. For example, the collection unit collects company industry data. Company industry data includes, but is not limited to, manufacturing, service, and IT industries. For example, the collection unit collects manufacturing industry data to acquire manufacturing process and product information. The collection unit can also collect service industry data to acquire service provision process and customer information. The collection unit can also collect IT industry data to acquire software development process and technical information. For example, the collection unit collects company industry data using an API and stores it in a database. The collection unit can also collect company industry data from the web using scraping technology. The collection unit can also acquire industry data directly from a company database. For example, the collection unit accesses a company database and extracts the necessary industry data. This allows for efficient collection of company industry data and company data.

[0060] The analysis unit may include an evaluation unit that evaluates the reliability of the collected data. The analysis unit, for example, evaluates the reliability of the collected data. The evaluation of reliability includes, but is not limited to, the origin and consistency of the data. For example, the analysis unit verifies the origin of the data and selects only highly reliable data. The analysis unit can also evaluate the consistency of the data and select consistent data. Furthermore, the analysis unit can evaluate the quality of the data and select only high-quality data. For example, the analysis unit detects missing values ​​and outliers in the data and removes them. This allows the reliability of the collected data to be evaluated. Some or all of the above-described processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit may input the collected data into a generation AI and have the generation AI perform a reliability evaluation.

[0061] The generation unit may include a translation unit that supports multiple languages. The generation unit may include, for example, a translation unit for supporting multiple languages. The translation unit translates the training data into multiple languages, for example, using a translation algorithm that supports the languages ​​of each country. For example, the translation unit uses a translation algorithm that supports languages ​​such as English, Japanese, and French. The translation unit may also perform real-time translation. For example, the translation unit translates the training data into the corresponding language as soon as it is input. Furthermore, the translation unit may have language experts review the training data to improve translation accuracy. For example, the translation unit may have experts review the translated training data and make corrections as necessary. This enables multilingual support. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit may input the training data into a generation AI and have the generation AI perform the translation.

[0062] The generation unit can generate training data including university-level knowledge of each country, AI literacy, laws, and general knowledge. For example, the generation unit generates training data including university-level knowledge of each country. University-level knowledge includes, but is not limited to, specific academic fields and specialized knowledge. For example, the generation unit generates training data including knowledge of academic fields such as physics, chemistry, and biology. The generation unit can also generate training data including AI literacy. AI literacy includes, but is not limited to, basic AI concepts and AI application methods. For example, the generation unit generates training data including AI concepts such as machine learning, deep learning, and natural language processing. The generation unit can also generate training data including laws. Examples of laws include, but are not limited to, data protection laws and intellectual property laws. For example, the generation unit generates training data including knowledge of data protection laws and intellectual property laws of each country. The generation unit can also generate training data including general knowledge. Examples of general knowledge include, but are not limited to, social etiquette and basic ethics. For example, the generation unit generates training data including knowledge on business etiquette and ethics. This makes it possible to generate training data including university-level knowledge from each country, AI literacy, law, and general knowledge. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may input university-level knowledge from each country into the generation AI and cause the generation AI to generate training data.

[0063] The collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated user's emotions. The collection unit, for example, estimates the user's emotions. To estimate the emotions, for example, an emotion estimation algorithm is used. The emotion estimation algorithm can use technologies such as facial expression recognition, voice analysis, and text analysis. For example, the collection unit can capture the user's facial expressions with a camera and estimate the emotions using a facial expression recognition algorithm. The collection unit can also record the user's voice and estimate the emotions using a voice analysis algorithm. Furthermore, the collection unit can analyze the user's text data and estimate the emotions using a text analysis algorithm. For example, the collection unit can analyze the user's chat log to estimate the emotions. Based on the estimated user's emotions, the collection unit adjusts the timing of data collection. For example, if the user is feeling stressed, the collection unit can reduce the frequency of data collection to reduce the user's burden. Also, if the user is relaxed, the collection unit can increase the frequency of data collection and collect more detailed data. Furthermore, if the user is in a hurry, the collection unit can shorten the timing of data collection to quickly collect necessary data. This allows the timing of data collection to be adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, or without, the generation AI. For example, the collection unit may input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0064] The collection unit can analyze the company's past data collection history and select an appropriate collection method. The collection unit, for example, analyzes the company's past data collection history. The past data collection history includes, for example, the collection date and time, the type of collected data, etc., but is not limited to these examples. For example, the collection unit analyzes the data collection methods used by the company in the past and selects the most effective method. The collection unit can also select a collection method that is effective at a specific time from the company's past data collection history. Furthermore, the collection unit can select the optimal data collection tool based on the company's past data collection history. For example, the collection unit analyzes the past data collection history and confirms that a specific tool is most effective. This allows the optimal collection method to be selected based on the company's past data collection history. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using a generation AI or without using a generation AI. For example, the collection unit can input the past data collection history into the generation AI and have the generation AI select the optimal collection method.

[0065] When collecting data, the collection unit may filter the data based on the company's current projects or areas of interest. For example, the collection unit may collect only data related to the company's current projects. Current projects include, but are not limited to, ongoing projects and planned projects. For example, the collection unit may collect data related to ongoing projects to understand the project's progress. The collection unit may also collect data related to planned projects to support project planning. Furthermore, the collection unit may preferentially collect relevant data based on the company's areas of interest. Areas of interest include, but are not limited to, specific technical fields or market segments. For example, the collection unit may collect data related to a specific technical field to understand technological advances. The collection unit may also collect data related to a specific market segment to understand market trends. This allows data to be filtered based on the company's current projects or areas of interest. Some or all of the above-described processing in the collection unit may be performed using, or without, the generation AI. For example, the collection unit may input the company's project information and areas of interest into the generation AI and have the generation AI perform the filtering.

[0066] The collection unit can estimate the user's emotions and determine the priority of data to be collected based on the estimated user's emotions. The collection unit, for example, estimates the user's emotions. To estimate the emotions, for example, an emotion estimation algorithm is used. The emotion estimation algorithm can use technologies such as facial expression recognition, voice analysis, and text analysis. For example, the collection unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The collection unit can also record the user's voice and estimate the emotions using a voice analysis algorithm. Furthermore, the collection unit can analyze the user's text data and estimate the emotions using a text analysis algorithm. For example, the collection unit analyzes the user's chat log to estimate the emotions. Based on the estimated user's emotions, the collection unit determines the priority of data to be collected. For example, if the user is feeling stressed, the collection unit can prioritize collecting data of high importance. Also, if the user is relaxed, the collection unit can prioritize collecting detailed data. Furthermore, if the user is in a hurry, the collection unit can prioritize collecting data that can be collected quickly. This makes it possible to determine the priority of data to be collected according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, or without, the generation AI. For example, the collection unit may input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0067] When collecting data, the collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the company. For example, the collection unit prioritizes collecting data related to the company's location. Geographical location information includes, but is not limited to, countries, regions, cities, etc. For example, the collection unit collects data related to the company's location and acquires region-specific information. The collection unit can also collect region-specific data based on the company's geographical location information. Furthermore, the collection unit can select an optimal data collection method by taking into account the company's geographical location information. For example, the collection unit selects an optimal data collection method based on the company's location. This allows highly relevant data to be prioritized by taking into account the company's geographical location information. Some or all of the above-described processing by the collection unit may be performed using, or without, the generation AI. For example, the collection unit can input the company's geographical location information into the generation AI and cause the generation AI to collect highly relevant data.

[0068] During data collection, the collection unit may analyze the company's social media activities and collect related data. The collection unit may, for example, analyze the company's social media activities. Social media activities may include, but are not limited to, post content, engagement rates, etc. For example, the collection unit may analyze the company's social media posts and collect related data. The collection unit may also collect trend-related data from the company's social media activities. Furthermore, the collection unit may select the optimal data collection method based on the company's social media activities. For example, the collection unit may analyze the social media activities and confirm that a specific collection method is most effective. This allows the company's social media activities to be analyzed and related data to be collected. Some or all of the above-described processing in the collection unit may be performed, for example, using or without the generation AI. For example, the collection unit may input the company's social media data into the generation AI and have the generation AI collect related data.

[0069] The analysis unit can estimate the user's emotion and adjust the data analysis method based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion. To estimate the emotion, for example, an emotion estimation algorithm is used. The emotion estimation algorithm can use technologies such as facial expression recognition, voice analysis, and text analysis. For example, the analysis unit can capture the user's facial expression with a camera and estimate the emotion using a facial expression recognition algorithm. The analysis unit can also record the user's voice and estimate the emotion using a voice analysis algorithm. Furthermore, the analysis unit can analyze the user's text data and estimate the emotion using a text analysis algorithm. For example, the analysis unit can analyze the user's chat log to estimate the emotion. Based on the estimated user's emotion, the analysis unit adjusts the data analysis method. For example, if the user is stressed, the analysis unit can provide a concise and to-the-point analysis method. On the other hand, if the user is relaxed, the analysis unit can provide a detailed analysis method. Furthermore, if the user is in a hurry, the analysis unit can select a method that quickly provides analysis results. This makes it possible to adjust the data analysis method according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit may input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0070] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the data. The analysis unit adjusts the level of detail of the analysis based on, for example, the importance of the data. The importance of the data includes, for example, the impact on the business and the reliability of the data, but is not limited to these examples. For example, the analysis unit performs a detailed analysis on data with high importance. The analysis unit can also perform a concise analysis on data with low importance. Furthermore, the analysis unit can optimally allocate analysis resources according to the importance of the data. For example, the analysis unit allocates more resources to data with high importance and performs a detailed analysis. This makes it possible to adjust the level of detail of the analysis based on the importance of the data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the importance of the data to the generation AI and have the generation AI adjust the level of detail of the analysis.

[0071] During analysis, the analysis unit can apply different analysis algorithms depending on the data category. For example, the analysis unit applies different analysis algorithms depending on the data category. Data categories include, but are not limited to, text data, numerical data, and image data. For example, the analysis unit applies a natural language processing algorithm to text data. The analysis unit can also apply an image recognition algorithm to image data. The analysis unit can also apply a statistical analysis algorithm to numerical data. For example, the analysis unit can apply a clustering algorithm to text data to classify the data. The analysis unit can also apply an image recognition algorithm to image data to analyze the content of the image. This makes it possible to apply different analysis algorithms depending on the data category. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input the data category to the generation AI and have the generation AI select an analysis algorithm to apply.

[0072] The analysis unit can estimate the user's emotion and adjust the display method of the analysis results based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion. To estimate the emotion, for example, an emotion estimation algorithm is used. The emotion estimation algorithm can use technologies such as facial expression recognition, voice analysis, and text analysis. For example, the analysis unit can capture the user's facial expression with a camera and estimate the emotion using a facial expression recognition algorithm. The analysis unit can also record the user's voice and estimate the emotion using a voice analysis algorithm. Furthermore, the analysis unit can analyze the user's text data and estimate the emotion using a text analysis algorithm. For example, the analysis unit can analyze the user's chat log and estimate the emotion. Based on the estimated user's emotion, the analysis unit adjusts the display method of the analysis results. For example, if the user is feeling stressed, the analysis unit can provide a simple, highly visible display method. If the user is relaxed, the analysis unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a display method that focuses on the main points. This makes it possible to adjust the display method of the analysis results according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit may input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0073] During analysis, the analysis unit can determine the analysis priority based on the time of data submission. The analysis unit determines the analysis priority based on, for example, the time of data submission. The time of data submission includes, for example, the submission date and time and the submission frequency, but is not limited to these examples. For example, the analysis unit prioritizes analysis of the most recent data. The analysis unit can also postpone data that was submitted earlier. Furthermore, the analysis unit can optimize the analysis schedule based on the time of submission. For example, the analysis unit adjusts the analysis schedule based on the time of submission and performs analysis efficiently. This makes it possible to determine the analysis priority based on the time of data submission. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the time of data submission to the generation AI and have the generation AI determine the analysis priority.

[0074] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the data. The analysis unit adjusts the order of analysis based on, for example, the relevance of the data. Data relevance includes, for example, correlation between data and frequency of co-occurrence, but is not limited to such examples. For example, the analysis unit prioritizes analysis of highly relevant data. The analysis unit can also postpone analysis of less relevant data. Furthermore, the analysis unit can optimize the order of analysis based on the relevance of the data. For example, the analysis unit starts analysis with highly relevant data and performs analysis efficiently. This makes it possible to adjust the order of analysis based on the relevance of the data. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the relevance of the data into the generation AI and have the generation AI adjust the order of analysis.

[0075] The generation unit can estimate the user's emotion and adjust the training data generation method based on the estimated user's emotion. The generation unit, for example, estimates the user's emotion. To estimate the emotion, for example, an emotion estimation algorithm is used. The emotion estimation algorithm can use technologies such as facial expression recognition, voice analysis, and text analysis. For example, the generation unit captures the user's facial expression with a camera and estimates the emotion using a facial expression recognition algorithm. The generation unit can also record the user's voice and estimate the emotion using a voice analysis algorithm. Furthermore, the generation unit can analyze the user's text data and estimate the emotion using a text analysis algorithm. For example, the generation unit analyzes the user's chat log to estimate the emotion. Based on the estimated user's emotion, the generation unit adjusts the training data generation method. For example, if the user is stressed, the generation unit generates concise and to-the-point training data. On the other hand, if the user is relaxed, the generation unit can generate detailed training data. Furthermore, if the user is in a hurry, the generation unit can provide training data that can be generated quickly. This makes it possible to adjust the training data generation method according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit may input user facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0076] The generation unit can improve the accuracy of the generation of training data by taking into account the interrelationships between data. The generation unit generates the training data, for example, by taking into account the interrelationships between data. Examples of the interrelationships between data include, but are not limited to, correlations between data and co-occurrence frequencies between data. For example, the generation unit analyzes the interrelationships between data and generates training data by combining highly related data. The generation unit can also improve the accuracy of the training data by taking into account the interrelationships between data. Furthermore, the generation unit can generate optimal training data based on the interrelationships between data. For example, the generation unit analyzes the correlations between data and generates training data by combining highly related data. This allows the accuracy of the training data to be improved by taking into account the interrelationships between data. Some or all of the above-described processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit may input the interrelationships between data into the generation AI and cause the generation AI to generate training data.

[0077] The generation unit can generate training data while taking into account attribute information of the data submitter. The generation unit generates training data, for example, by taking into account attribute information of the data submitter. The attribute information of the data submitter includes, but is not limited to, the submitter's occupation and expertise. For example, the generation unit generates training data by taking into account the expertise of the data submitter. The generation unit can also generate optimal training data based on the industry of the data submitter. Furthermore, the generation unit can improve the accuracy of the training data based on the attribute information of the data submitter. For example, the generation unit generates training data by taking into account the submitter's occupation and expertise. This makes it possible to improve the accuracy of the training data by taking into account the attribute information of the data submitter. Some or all of the above-described processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the submitter's attribute information into the generation AI and cause the generation AI to generate training data.

[0078] The generation unit can estimate the user's emotion and adjust the display method of the generated training data based on the estimated user's emotion. The generation unit, for example, estimates the user's emotion. To estimate the emotion, for example, an emotion estimation algorithm is used. The emotion estimation algorithm can use technologies such as facial expression recognition, voice analysis, and text analysis. For example, the generation unit captures the user's facial expression with a camera and estimates the emotion using a facial expression recognition algorithm. The generation unit can also record the user's voice and estimate the emotion using a voice analysis algorithm. Furthermore, the generation unit can analyze the user's text data and estimate the emotion using a text analysis algorithm. For example, the generation unit analyzes the user's chat log and estimates the emotion. Based on the estimated user's emotion, the generation unit adjusts the display method of the generated training data. For example, if the user is feeling stressed, the generation unit provides a simple, highly visible display method. If the user is relaxed, the generation unit can provide a display method including detailed information. Furthermore, if the user is in a hurry, the generation unit can provide a display method that focuses on the main points. This allows the display method of the learning data to be adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit may input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0079] The generation unit may generate training data while taking into account the geographical distribution of the data. For example, the generation unit generates training data while taking into account the geographical distribution of the data. Examples of geographical distribution include, but are not limited to, countries, regions, and cities. For example, the generation unit generates region-specific training data while taking into account the geographical distribution of the data. The generation unit may also generate optimal training data based on the geographical distribution. Furthermore, the generation unit may improve the accuracy of the training data while taking into account the geographical distribution. For example, the generation unit analyzes the geographical distribution of the data and generates region-specific training data. This allows the accuracy of the training data to be improved while taking into account the geographical distribution of the data. Some or all of the above-described processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit may input the geographical distribution of the data into the generation AI and cause the generation AI to generate training data.

[0080] When generating training data, the generation unit can improve the accuracy of the generation by referring to literature related to the data. The generation unit generates training data by, for example, referring to literature related to the data. Related literature includes, for example, academic papers and technical reports, but is not limited to such examples. For example, the generation unit improves the accuracy of the training data by referring to literature related to the data. The generation unit can also generate optimal training data based on the related literature. Furthermore, the generation unit can improve the accuracy of the training data by taking into account literature related to the data. For example, the generation unit improves the accuracy of the training data by referring to the related literature. This makes it possible to improve the accuracy of the training data by referring to literature related to the data. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input related literature to the generation AI and cause the generation AI to generate training data. === Hard Collateral 1-1 === Each of the multiple elements including the collection unit, analysis unit, and generation unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the smart device 14 and collects company data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the reliability of the collected data. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates training data based on the analyzed data. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, and generation unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the smart glasses 214 and collects company data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the reliability of the collected data. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates training data based on the analyzed data. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, analysis unit, and generation unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the headset type terminal 314 and collects company data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the reliability of the collected data. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates training data based on the analyzed data. === Hard Collateral 1-4 === Each of the multiple elements described above, including the collection unit, analysis unit, and generation unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the robot 414 and collects corporate data. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and evaluates the reliability of the collected data. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and generates training data based on the analyzed data.

[0081] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0082] The data collection unit can evaluate the reliability of data sources in real time when collecting corporate data. For example, the collection unit can consider past data provision history and the provider's reputation to assess whether a data source is reliable. Furthermore, if a data source is unreliable, the collection unit can automatically select other reliable sources. In addition, if a data source is reliable, the collection unit can increase the data collection frequency to collect more detailed data. This allows the collection unit to evaluate the reliability of data sources in real time and efficiently collect reliable data.

[0083] The data collection unit can automatically optimize the data collection method when collecting industry data or company data. For example, when collecting industry data, the collection unit can consider past collection history and collection efficiency to select the optimal collection method. Furthermore, the collection unit can consider the characteristics of the data source and the type of data to automatically optimize the data collection method. In addition, the collection unit can consider the network conditions of the data source and the frequency of data updates to optimize the data collection method. This allows the collection unit to efficiently collect industry data and company data.

[0084] When evaluating the reliability of collected data, the analysis unit can evaluate not only the origin and consistency of the data, but also the recency and relevance of the data. For example, the analysis unit can evaluate whether the collected data is up-to-date and exclude old data. The analysis unit can also evaluate whether the collected data is relevant to other data and exclude less relevant data. Furthermore, to evaluate the reliability of data, the analysis unit can evaluate not only the origin and consistency of the data, but also the quality and accuracy of the data. This allows the analysis unit to increase the reliability of the collected data.

[0085] When the generation unit includes a translation unit that supports multiple languages, it can take technical terms and industry-specific expressions into consideration to improve translation accuracy. For example, when using a translation algorithm that supports the languages ​​of each country, the translation unit can use a dictionary for accurately translating technical terms and industry-specific expressions. The translation unit can also conduct reviews by language experts in each country to improve translation accuracy. Furthermore, the translation unit can include technical terms and industry-specific expressions in the training data of the translation algorithm to improve translation accuracy. This allows the generation unit to improve translation accuracy when supporting multiple languages.

[0086] When generating training data including university-level knowledge of each country or AI literacy, law, and general knowledge, the generation unit can evaluate the origin and consistency of the data to improve the reliability of the data. For example, when generating training data including university-level knowledge of each country, the generation unit can evaluate whether the origin of the data is reliable. In addition, when generating training data including AI literacy, the generation unit can evaluate the consistency of the data and select consistent data. Furthermore, when generating training data including law, the generation unit can evaluate the quality of the data and select only high-quality data. This allows the generation unit to improve the reliability of training data including university-level knowledge of each country, AI literacy, law, and general knowledge.

[0087] The collection unit can monitor changes in the user's emotions in real time when estimating the user's emotions and adjusting the timing of data collection based on the estimated user emotions. For example, the collection unit can capture the user's facial expressions with a camera and estimate the emotions in real time using a facial expression recognition algorithm. The collection unit can also record the user's voice and estimate the emotions in real time using a voice analysis algorithm. Furthermore, the collection unit can analyze the user's text data and estimate the emotions in real time using a text analysis algorithm. This allows the collection unit to monitor changes in the user's emotions in real time and appropriately adjust the timing of data collection.

[0088] The collection unit can analyze the company's past data collection history and automatically detect patterns in the collection history when selecting an appropriate collection method. For example, the collection unit can use a machine learning algorithm to analyze the past data collection history and detect specific patterns. The collection unit can also automatically select an optimal collection method based on the patterns in the collection history. Furthermore, the collection unit can evaluate the effectiveness of the collection method based on the patterns in the collection history and improve the collection method. In this way, the collection unit can select an optimal collection method based on the company's past data collection history and improve the efficiency of data collection.

[0089] When collecting data, the collection unit can take into account the progress and priority of projects when filtering based on the company's current projects and areas of interest. For example, the collection unit can grasp the progress of ongoing projects and prioritize collecting data related to high-priority projects. The collection unit can also consider the priority of planned projects and prioritize collecting data related to important projects. Furthermore, the collection unit can monitor changes in the areas of interest in real time when prioritizedly collecting highly relevant data based on the company's areas of interest. This allows the collection unit to efficiently filter and collect data based on the company's current projects and areas of interest.

[0090] The collection unit can estimate a user's emotion and consider the intensity of the emotion when determining the priority of data to be collected based on the estimated user's emotion. For example, the collection unit can capture the user's facial expression with a camera and estimate the intensity of the emotion using a facial expression recognition algorithm. The collection unit can also record the user's voice and estimate the intensity of the emotion using a voice analysis algorithm. Furthermore, the collection unit can analyze the user's text data and estimate the intensity of the emotion using a text analysis algorithm. This allows the collection unit to appropriately determine the priority of data to be collected based on the intensity of the user's emotion.

[0091] When collecting data, the collection unit may take into account geographical trends and region-specific events when prioritizing the collection of highly relevant data by taking into account the geographical location information of the company. For example, the collection unit may analyze geographical trends related to the location of the company and prioritize the collection of data related to the trends. The collection unit may also prioritize the collection of data related to region-specific events and festivals. Furthermore, the collection unit may prioritize the collection of data related to region-specific regulations and laws based on the geographical location information of the company. This allows the collection unit to efficiently collect highly relevant data by taking into account the geographical location information of the company.

[0092] The processing flow of the second embodiment will be briefly explained below.

[0093] Step 1: The data collection unit collects company data. This data includes financial data, customer data, marketing data, etc. The data collection unit can collect company data using APIs. It can also collect data from the web using scraping techniques. Furthermore, it can directly obtain data from company databases, accessing the databases and extracting the necessary data. Step 2: The analysis department analyzes the data collected by the collection department. The analysis department evaluates the reliability of the data and selects only reliable data. The analysis department checks the origin and consistency of the data and selects consistent data. The analysis department also evaluates the quality of the data and detects and removes missing values ​​and outliers. Step 3: The generation unit generates training data based on the data analyzed by the analysis unit. The generation unit generates training data that includes university-level knowledge, AI literacy, laws, and general knowledge from various countries. The training data includes text data, numerical data, and image data. For example, the generation unit generates text data, numerical data, and image data to train the AI ​​model.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0098] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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).

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0114] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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).

[0120] 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.

[0121] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0130] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0131] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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."

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] [Explanation of symbols]

[0166] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection department that collects data from companies; an analysis unit that analyzes the data collected by the collection unit; a generation unit that generates learning data based on the data analyzed by the analysis unit. A system characterized by:

2. The collecting unit Collect company industry or company data 2. The system of claim 1.

3. The analysis unit Equipped with an evaluation unit that evaluates the reliability of collected data 2. The system of claim 1.

4. The generation unit Equipped with a translation department that handles multiple languages 2. The system of claim 1.

5. The generation unit Generate learning data including university-level knowledge or AI literacy, law, and general knowledge from each country 2. The system of claim 1.

6. The collecting unit Inferring user emotions and adjusting the timing of data collection based on the estimated user emotions 2. The system of claim 1.

7. The collecting unit Analyze the company's past data collection history and select the appropriate collection method 2. The system of claim 1.

8. The collecting unit As data is collected, filtering is performed based on the company's current projects and areas of interest.

2. The system of claim 1.

Images