system

Abstract

The system according to this embodiment aims to provide specific answers to questions. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, an acquisition unit, a rules analysis unit, a generation unit, and a provision unit. The reception unit receives a question. The analysis unit analyzes the question received by the reception unit. The acquisition unit obtains the URL of the relevant rules based on the question analyzed by the analysis unit. The rules analysis unit analyzes the rules of the destination URL obtained by the acquisition unit. The generation unit generates a specific answer based on the rules analyzed by the rules analysis unit. The provision unit provides the answer generated by the generation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, a URL of a regulation is provided as an answer to a question, but there is a problem that it takes time for a user to search for the information they need.

[0005] The system according to the embodiment aims to provide a specific answer to a question.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, an analysis unit, an acquisition unit, a rules analysis unit, a generation unit, and a provision unit. The reception unit receives a question. The analysis unit analyzes the question received by the reception unit. The acquisition unit obtains the URL of the relevant rules based on the question analyzed by the analysis unit. The rules analysis unit analyzes the rules of the destination URL obtained by the acquisition unit. The generation unit generates a specific answer based on the rules analyzed by the rules analysis unit. The provision unit provides the answer generated by the generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can provide specific answers to questions. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An embodiment of the present invention provides an administrative procedure support system that efficiently provides answers to questions regarding internal administrative procedures using AI. The system works as follows: The user inputs a question about internal administrative procedures, the AI ​​analyzes the question, and obtains a URL to the relevant regulations. The AI ​​interprets the regulations at the destination of the obtained URL and generates a specific answer to the question in text form. This answer is then provided to the user. For example, the user might input a question such as, "How do I apply for leave?" This question is input to the AI. Next, the AI ​​analyzes the input question. The AI ​​understands the content of the question and obtains a URL to the relevant regulations. For example, it might obtain a URL to the regulations regarding "leave applications." The AI ​​interprets the regulations at the destination of the obtained URL. The AI ​​analyzes the content of the regulations and generates a specific answer to the question in text form. For example, it might generate an answer such as, "To apply for leave, you must first obtain approval from your supervisor, and then submit an application form to the Human Resources Department." The generated answer is then provided to the user. By reviewing the specific answer generated by the AI, the user can efficiently obtain information regarding administrative procedures. This eliminates the need for users to review each rule individually and allows them to receive quick and accurate answers to questions regarding administrative procedures. For example, in response to a question about the leave application process, the AI ​​can provide a detailed written explanation of the procedure, enabling users to proceed with the process quickly. This allows the administrative support system to provide prompt and accurate answers to user questions.

[0029] The administrative procedure support system according to this embodiment comprises a reception unit, an analysis unit, an acquisition unit, a rules analysis unit, a generation unit, and a provision unit. The reception unit receives questions from users regarding internal administrative procedures. The reception unit provides, for example, an interface for users to input questions in text format. The reception unit can also support voice input and image input. The analysis unit analyzes the questions received by the reception unit. The analysis unit understands the content of the questions using, for example, natural language processing technology. The analysis unit can also analyze the intent of the questions using machine learning algorithms. The analysis unit obtains the URL of the relevant rules based on the content of the questions. The acquisition unit obtains the URL of the relevant rules based on the questions analyzed by the analysis unit. The acquisition unit searches for the URL of the relevant rules from a database, for example. The acquisition unit can also obtain the URL of the relevant rules using a search engine. The rules analysis unit analyzes the rules that the URLs obtained by the acquisition unit redirect to. The rules analysis unit analyzes the content of the rules and generates specific answers to the questions. The rules analysis unit can also analyze the content of the rules using machine learning algorithms. The generation unit generates specific answers based on the rules analyzed by the rule analysis unit. The generation unit generates answers using, for example, a template-based generation algorithm. The generation unit can also generate answers using a machine learning algorithm. The provision unit provides the answers generated by the generation unit to the user. The provision unit displays the generated answers in, for example, text format. The provision unit can also provide answers in audio or image format. As a result, the administrative procedure support system according to this embodiment can provide quick and accurate answers to user questions.

[0030] The reception desk allows users to input questions regarding internal administrative procedures. The reception desk provides an interface for users to input questions in text format, for example. Specifically, it designs an intuitive user interface to make it easy for users to input questions. For instance, it uses text boxes and dropdown menus to provide an environment that facilitates question input. It also supports voice input, allowing users to input questions by voice using a microphone. In the case of voice input, speech recognition technology is used to convert the voice into text and send it to the analysis unit. Furthermore, it supports image input; users can upload images, and the text within the image can be analyzed and accepted as a question. This allows the reception desk to provide a flexible interface that allows users to input questions in various formats, improving user convenience.

[0031] The analysis unit analyzes the questions received by the reception unit. The analysis unit understands the content of the questions, for example, using natural language processing technology. Specifically, it uses natural language processing technology to analyze the grammatical structure and meaning of the questions and grasp the intent of the questions. For example, it performs morphological analysis to divide the question sentence into individual words and identifies the part of speech of each word. Next, it performs dependency structure analysis to clarify the relationships between words. This allows it to grasp the structure of the question, such as the subject, predicate, and object, and understand the meaning of the question. It can also analyze the intent of the questions using machine learning algorithms. For example, it can classify the intent of the questions using a model that has been trained in advance using a large amount of question data. As a result, the analysis unit can provide information to obtain URLs of relevant regulations based on the content of the questions.

[0032] The acquisition unit retrieves the URLs of relevant regulations based on the questions analyzed by the analysis unit. For example, the acquisition unit searches for relevant regulation URLs in a database. Specifically, it accesses a database where internal regulations are stored and searches for relevant regulation URLs based on keywords and categories provided by the analysis unit. It can also retrieve relevant regulation URLs using a search engine. For example, it searches for regulations published on the company's intranet using a search engine and retrieves the relevant URLs. This allows the acquisition unit to quickly and accurately retrieve relevant regulation URLs and provide the information necessary for subsequent processing.

[0033] The rules analysis unit analyzes the rules of the destination URL obtained by the acquisition unit. For example, the rules analysis unit analyzes the content of the rules and generates specific answers to questions. Specifically, it analyzes the text of the acquired rules and extracts the parts relevant to the questions. For example, it uses text mining technology to extract keywords and phrases related to the questions from the rules and generates answers based on them. It can also analyze the content of the rules using machine learning algorithms. For example, it uses a pre-trained model to classify the content of the rules and generate the optimal answer to the question. In this way, the rules analysis unit can quickly and accurately analyze the content of the acquired rules and provide specific answers to questions.

[0034] The generation unit generates specific answers based on the rules analyzed by the rules analysis unit. The generation unit generates answers using, for example, a template-based generation algorithm. Specifically, it quickly generates answers by embedding the information provided by the rules analysis unit into a pre-prepared answer template. For example, it embeds the analyzed answer content into a template such as "The answer to the question is as follows: {Answer content}". It can also generate answers using machine learning algorithms. For example, it generates the optimal answer to a question using a pre-trained model. This allows the generation unit to quickly and accurately generate specific answers and provide them to the user.

[0035] The providing unit provides the user with the answers generated by the generating unit. For example, the providing unit displays the generated answers in text format. Specifically, it displays the generated answers on the interface where the user entered the question. It can also provide answers in audio or image format. For example, it can use speech synthesis technology to read the generated answers aloud. It can also provide answers in a format that is easy for the user to understand by illustrating the content. This allows the providing unit to provide users with quick and accurate answers, improving user convenience. Furthermore, the providing unit can collect feedback from users and use it to improve the system. For example, it can collect feedback on satisfaction with and understanding of the answers and provide this feedback to the analysis and generation units. This allows the providing unit to improve the overall performance of the system and provide better service to users.

[0036] The analysis unit can understand the content of the question and obtain the URL of the relevant regulations. The analysis unit understands the content of the question using, for example, natural language processing technology. The analysis unit can also analyze the intent of the question using machine learning algorithms. The analysis unit obtains the URL of the relevant regulations based on the content of the question. For example, the analysis unit analyzes the content of the question and obtains the URL of the regulations regarding "leave of absence applications". The analysis unit uses natural language processing technology to understand the content of the question. For example, the analysis unit analyzes the content of the question and extracts relevant keywords. The analysis unit can also analyze the intent of the question using machine learning algorithms. For example, the analysis unit learns a model to analyze the content of the question and obtain the URL of the relevant regulations. This allows the analysis unit to obtain the URL of the appropriate regulations based on the content of the question.

[0037] The rules analysis unit can analyze the rules of the destination URL accessed by the acquired URL and generate specific answers to questions. For example, the rules analysis unit can analyze the content of the rules and generate specific answers to questions. The rules analysis unit can also analyze the content of the rules using machine learning algorithms. For example, the rules analysis unit can analyze the rules of the destination URL accessed by the acquired URL and generate specific answers such as, "To apply for leave, you must first obtain approval from your supervisor and then submit the application form to the Human Resources Department." The rules analysis unit uses natural language processing technology to analyze the content of the rules. For example, the rules analysis unit analyzes the content of the rules and extracts relevant information. The rules analysis unit can also analyze the content of the rules using machine learning algorithms. For example, the rules analysis unit can analyze the content of the rules and train a model to generate specific answers to questions. This allows the rules analysis unit to analyze the content of the rules and generate specific answers.

[0038] The generation unit can be equipped with a mechanism to verify the accuracy of the generated answers. For example, the generation unit can perform feedback evaluation to verify the accuracy of the generated answers. The generation unit can also perform cross-checking to verify the accuracy of the generated answers. For example, the generation unit can perform cross-checking using multiple AI models to verify the accuracy of the generated answers. The generation unit can collect feedback from users to verify the accuracy of the generated answers. For example, the generation unit can evaluate the accuracy of the generated answers based on user feedback. The generation unit can also perform periodic evaluations to verify the accuracy of the generated answers. For example, the generation unit can periodically evaluate the accuracy of the generated answers and make improvements as needed. This allows the generation unit to verify the accuracy of the generated answers.

[0039] The service provider can provide the generated answers to the user. For example, the service provider can display the generated answers in text format. The service provider can also provide answers in audio or image format. For example, the service provider can provide the generated answers in audio format using speech synthesis technology. The service provider can also use image generation technology to provide the generated answers in image format. For example, the service provider can display the generated answers in image format, providing them in a visually easy-to-understand format. The service provider can also use email or a chatbot to provide the generated answers to the user. For example, the service provider can send the generated answers to the user via email. The service provider can also provide the generated answers to the user through a chatbot. In this way, the service provider can provide the generated answers to the user.

[0040] The reception system can include a mechanism for users to select a question category when entering a question. For example, the reception system can provide an interface for users to select a question category when entering a question. By allowing users to select a question category, the reception system can streamline the question reception process. For example, the reception system can make it easier to identify the content of the question by allowing users to select a category such as "leave request" or "expense reimbursement." The reception system can also use dropdown menus or checkboxes to allow users to select a question category. For example, the reception system can provide an interface for users to select a question category from a dropdown menu. By allowing users to select a question category, the reception system can streamline the question analysis and answer generation process. For example, by allowing users to select a question category, the reception system can make it easier for the analysis and generation units to identify the content of the question. As a result, by allowing users to select a question category, the reception system can streamline the question reception process.

[0041] The reception desk can analyze a user's past question history and select the optimal reception method. For example, the reception desk can suggest the optimal reception method based on the questions the user has frequently asked in the past. The reception desk can also prioritize receiving questions asked during specific time periods based on the user's past question history. For example, the reception desk can analyze a user's past question history and select the most efficient reception method. The reception desk can use machine learning algorithms to analyze a user's past question history. For example, the reception desk can retrieve a user's past question history from a database and analyze it using a machine learning algorithm. This allows the reception desk to select the optimal reception method by analyzing the user's past question history.

[0042] The reception desk can filter questions based on the user's current work situation and areas of interest when receiving them. For example, the reception desk can consider the user's current work situation and prioritize receiving relevant questions. The reception desk can also filter relevant questions based on the user's areas of interest. For example, the reception desk can analyze the user's work situation and areas of interest and receive the most relevant questions. The reception desk can use machine learning algorithms to analyze the user's work situation and areas of interest. For example, the reception desk can retrieve the user's work situation and areas of interest from a database and analyze it using a machine learning algorithm. This allows the reception desk to filter questions based on the user's current work situation and areas of interest, thereby prioritizing the receipt of highly relevant questions.

[0043] The reception desk can prioritize receiving questions that are highly relevant, taking into account the user's geographical location. For example, the reception desk can prioritize receiving relevant questions based on the user's geographical location. The reception desk can also prioritize receiving questions related to a specific region if the user is in that region. For example, the reception desk can analyze the user's geographical location and prioritize receiving the most relevant questions. The reception desk can use GPS data or IP addresses to obtain the user's geographical location. For example, the reception desk can obtain the user's geographical location and prioritize receiving relevant questions. This allows the reception desk to prioritize receiving highly relevant questions by taking the user's geographical location into consideration.

[0044] The reception desk can analyze the user's social media activity when receiving a question and accept relevant questions. For example, the reception desk can accept relevant questions based on the user's social media activity. The reception desk can also accept relevant questions based on what the user has mentioned on social media. For example, the reception desk can analyze the user's social media activity and accept the most relevant questions. The reception desk can use machine learning algorithms to analyze the user's social media activity. For example, the reception desk can retrieve the user's social media activity from a database and analyze it using a machine learning algorithm. This allows the reception desk to accept highly relevant questions by analyzing the user's social media activity.

[0045] The analysis unit can adjust the level of detail of the analysis based on the importance of the question. For example, the analysis unit will perform a detailed analysis for high-importance questions. The analysis unit can also perform a concise analysis for low-importance questions. For example, the analysis unit will analyze the importance of the question and adjust the level of detail to the optimal level. The analysis unit can use machine learning algorithms to evaluate the importance of the question. For example, the analysis unit will evaluate the impact and urgency of the question and adjust the level of detail. This allows the analysis unit to analyze questions in a more appropriate way by adjusting the level of detail based on the importance of the question.

[0046] The analysis unit can apply different analysis algorithms depending on the category of the question when analyzing it. For example, if the question is about human resources, the analysis unit will apply a human resources-related analysis algorithm. If the question is about accounting, the analysis unit can also apply an accounting-related analysis algorithm. For example, the analysis unit analyzes the category of the question and applies the most suitable analysis algorithm. The analysis unit can use machine learning algorithms to identify the category of the question. For example, the analysis unit can learn a model that analyzes the content of the question and identifies the category. This allows the analysis unit to analyze questions in a more appropriate way by applying different analysis algorithms depending on the category of the question.

[0047] The analysis unit can determine the priority of analysis based on when the questions were submitted. For example, the analysis unit can determine the priority of analysis based on the time period in which the questions were submitted. The analysis unit can also determine the priority of analysis based on the date in which the questions were submitted. For example, the analysis unit can analyze the timing of question submissions and determine the optimal analysis priority. The analysis unit can use machine learning algorithms to evaluate the timing of question submissions. For example, the analysis unit can evaluate the date and time of question submissions and the frequency of submissions to determine the analysis priority. This allows the analysis unit to analyze questions in a more appropriate order by determining the priority of analysis based on the timing of question submissions.

[0048] The analysis unit can adjust the order of analysis based on the relevance of the questions. For example, the analysis unit can analyze the relevance of the questions and prioritize the analysis of the most relevant questions. The analysis unit can also adjust the order of analysis based on the relevance of the questions. For example, the analysis unit can evaluate the relevance of the questions and determine the optimal order of analysis. The analysis unit can use machine learning algorithms to evaluate the relevance of the questions. For example, the analysis unit can evaluate the similarity of the question content and related topics and adjust the order of analysis. In this way, the analysis unit can analyze questions in a more appropriate order by adjusting the order of analysis based on the relevance of the questions.

[0049] The retrieval unit can analyze the user's past question history to select the optimal retrieval method when obtaining the URL of the terms and conditions. For example, the retrieval unit can obtain the optimal terms and conditions URL based on the user's past question history. The retrieval unit can also prioritize obtaining the URL of the relevant terms and conditions from the user's past question history. For example, the retrieval unit analyzes the user's past question history and selects the most efficient method for obtaining the terms and conditions URL. The retrieval unit can use machine learning algorithms to analyze the user's past question history. For example, the retrieval unit retrieves the user's past question history from a database and analyzes it using a machine learning algorithm. As a result, the retrieval unit can select the optimal method for obtaining the terms and conditions URL by analyzing the user's past question history.

[0050] The retrieval unit can filter the URLs of the terms and conditions based on the user's current work situation and areas of interest when retrieving them. For example, the retrieval unit can consider the user's current work situation and prioritize retrieving URLs of relevant terms and conditions. The retrieval unit can also filter URLs of relevant terms and conditions based on the user's areas of interest. For example, the retrieval unit can analyze the user's work situation and areas of interest and retrieve the most relevant URLs. The retrieval unit can use machine learning algorithms to analyze the user's work situation and areas of interest. For example, the retrieval unit can retrieve the user's work situation and areas of interest from a database and analyze them using a machine learning algorithm. As a result, the retrieval unit can filter the URLs of the terms and conditions based on the user's current work situation and areas of interest, thereby prioritizing the retrieval of URLs of highly relevant terms and conditions.

[0051] The retrieval unit can prioritize retrieving URLs of terms and conditions that are highly relevant, taking into account the user's geographical location information when retrieving URLs of terms and conditions. For example, the retrieval unit can prioritize retrieving URLs of relevant terms and conditions based on the user's geographical location information. The retrieval unit can also prioritize retrieving URLs of terms and conditions related to a specific region if the user is in that region. For example, the retrieval unit can analyze the user's geographical location information and prioritize retrieving the URL of the most relevant terms and conditions. The retrieval unit can use GPS data or IP addresses to obtain the user's geographical location information. For example, the retrieval unit can obtain the user's geographical location information and prioritize retrieving URLs of relevant terms and conditions. In this way, the retrieval unit can prioritize retrieving URLs of highly relevant terms and conditions by taking the user's geographical location information into consideration.

[0052] The retrieval unit can analyze the user's social media activity and retrieve relevant URLs when retrieving terms and conditions URLs. For example, the retrieval unit can retrieve relevant terms and conditions URLs based on the user's social media activity. The retrieval unit can also retrieve relevant terms and conditions URLs based on what the user has mentioned on social media. For example, the retrieval unit can analyze the user's social media activity and retrieve the most relevant terms and conditions URL. The retrieval unit can use machine learning algorithms to analyze the user's social media activity. For example, the retrieval unit can retrieve the user's social media activity from a database and analyze it using a machine learning algorithm. This allows the retrieval unit to retrieve highly relevant terms and conditions URLs by analyzing the user's social media activity.

[0053] The rules analysis unit can adjust the level of detail of the analysis based on the importance of the rules. For example, the rules analysis unit will perform a detailed analysis for rules with high importance. The rules analysis unit can also perform a concise analysis for rules with low importance. For example, the rules analysis unit will analyze the importance of the rules and adjust the level of detail to the optimal level. The rules analysis unit can use machine learning algorithms to evaluate the importance of the rules. For example, the rules analysis unit will evaluate the impact and urgency of the rules and adjust the level of detail of the analysis. In this way, the rules analysis unit can analyze rules in a more appropriate way by adjusting the level of detail of the analysis based on the importance of the rules.

[0054] The regulations analysis unit can apply different analysis algorithms depending on the category of the regulations when analyzing them. For example, if the regulations concern human resources, the regulations analysis unit will apply a human resources-related analysis algorithm. If the regulations concern accounting, the regulations analysis unit can also apply an accounting-related analysis algorithm. For example, the regulations analysis unit analyzes the category of the regulations and applies the most appropriate analysis algorithm. The regulations analysis unit can use machine learning algorithms to identify the category of the regulations. For example, the regulations analysis unit can learn a model that analyzes the content of the regulations and identifies the category. This allows the regulations analysis unit to analyze the regulations in a more appropriate way by applying different analysis algorithms depending on the category of the regulations.

[0055] The rules analysis unit can determine the priority of analysis based on when the rules were submitted. For example, the rules analysis unit can determine the priority of analysis based on the time period in which the rules were submitted. The rules analysis unit can also determine the priority of analysis based on the date in which the rules were submitted. For example, the rules analysis unit can analyze the submission timing of the rules and determine the optimal analysis priority. The rules analysis unit can use machine learning algorithms to evaluate the submission timing of the rules. For example, the rules analysis unit can evaluate the submission date and time and submission frequency of the rules and determine the analysis priority. This allows the rules analysis unit to analyze the rules in a more appropriate order by determining the analysis priority based on the submission timing of the rules.

[0056] The rules analysis unit can adjust the order of analysis based on the relevance of the rules during analysis. For example, the rules analysis unit can analyze the relevance of the rules and prioritize the analysis of the most relevant rules. The rules analysis unit can also adjust the order of analysis based on the relevance of the rules. For example, the rules analysis unit can evaluate the relevance of the rules and determine the optimal analysis order. The rules analysis unit can use machine learning algorithms to evaluate the relevance of the rules. For example, the rules analysis unit can evaluate the similarity of the rules' content and related topics and adjust the analysis order. In this way, the rules analysis unit can analyze rules in a more appropriate order by adjusting the order of analysis based on the relevance of the rules.

[0057] The generator can adjust the level of detail in the response based on the importance of the question when generating the answer. For example, the generator will generate a detailed answer for a high-importance question. The generator can also generate a concise answer for a low-importance question. For example, the generator can analyze the importance of the question and adjust the level of detail to the optimal level. The generator can use machine learning algorithms to evaluate the importance of the question. For example, the generator can evaluate the impact and urgency of the question and adjust the level of detail in the answer. This allows the generator to generate answers in a more appropriate way by adjusting the level of detail in the answer based on the importance of the question.

[0058] The generation unit can apply different generation algorithms depending on the question category when generating answers. For example, if the question is about human resources, the generation unit will apply a human resources-related generation algorithm. If the question is about accounting, the generation unit can also apply an accounting-related generation algorithm. For example, the generation unit can analyze the question category and apply the most suitable generation algorithm. The generation unit can use machine learning algorithms to identify the question category. For example, the generation unit can learn a model that analyzes the content of the question and identifies the category. This allows the generation unit to generate answers in a more appropriate way by applying different generation algorithms depending on the question category.

[0059] The generation unit can determine the priority of answers based on when the questions were submitted. For example, the generation unit can determine the priority of answers based on the time period in which the questions were submitted. The generation unit can also determine the priority of answers based on the date in which the questions were submitted. For example, the generation unit can analyze the timing of question submissions and determine the optimal priority of answers. The generation unit can use machine learning algorithms to evaluate the timing of question submissions. For example, the generation unit can evaluate the date and time of question submissions and the frequency of submissions to determine the priority of answers. This allows the generation unit to generate answers in a more appropriate order by determining the priority of answers based on the timing of question submissions.

[0060] The generation unit can adjust the order of answers based on the relevance of the questions when generating responses. For example, the generation unit can analyze the relevance of the questions and prioritize generating answers to the most relevant questions. The generation unit can also adjust the order of answers based on the relevance of the questions. For example, the generation unit can evaluate the relevance of the questions and determine the optimal order of answers. The generation unit can use machine learning algorithms to evaluate the relevance of the questions. For example, the generation unit can evaluate the similarity of the question content and related topics and adjust the order of answers. This allows the generation unit to generate answers in a more appropriate order by adjusting the order of answers based on the relevance of the questions.

[0061] The service provider can select the optimal delivery method by referring to the user's past question history when providing answers. For example, the service provider can select the optimal delivery method based on the user's past question history. The service provider can also prioritize providing relevant answers from the user's past question history. For example, the service provider can analyze the user's past question history and select the most efficient delivery method. The service provider can use machine learning algorithms to analyze the user's past question history. For example, the service provider can retrieve the user's past question history from a database and analyze it using a machine learning algorithm. This allows the service provider to select the optimal delivery method by referring to the user's past question history.

[0062] The service provider can select the optimal delivery method when providing responses, taking into account the user's device information. For example, if the user is using a smartphone, the service provider will apply a delivery method that matches the screen size. If the user is using a tablet, the service provider can also apply a delivery method optimized for a larger screen. For example, if the user is using a desktop, the service provider will apply a delivery method that includes detailed information. The service provider can consider the type and usage of the device in order to obtain the user's device information. For example, the service provider can obtain the user's device information and select the optimal delivery method. This allows the service provider to provide responses in the most optimal way by taking the user's device information into consideration.

[0063] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0064] The reception system can include a mechanism for users to select a category when entering their questions. For example, users can select categories such as "leave request" or "expense reimbursement" to make it easier to identify the content of their questions. The reception system can also use dropdown menus or checkboxes for selecting question categories. This streamlines the analysis of questions and the generation of answers.

[0065] The analysis unit can adjust the level of detail in its analysis based on the importance of each question. For example, it can perform a detailed analysis on high-importance questions and a concise analysis on low-importance questions. This allows the analysis unit to analyze questions in a more appropriate way by adjusting the level of detail based on their importance.

[0066] The regulations analysis unit can apply different analysis algorithms depending on the category of the regulations. For example, if the regulations concern human resources, it can apply a human resources-related analysis algorithm, and if they concern accounting, it can apply an accounting-related analysis algorithm. This allows the regulations analysis unit to analyze regulations in a more appropriate way by applying different analysis algorithms depending on the category of the regulations.

[0067] The generation unit can determine the priority of answers based on when the questions were submitted. For example, it can determine the priority of answers based on the time of day or date the questions were submitted. This allows the generation unit to generate answers in a more appropriate order by determining the priority of answers based on when the questions were submitted.

[0068] The service provider can select the optimal delivery method when providing responses, taking into account the user's device information. For example, if the user is using a smartphone, the service provider can apply a delivery method that matches the screen size, and if the user is using a tablet, it can apply a delivery method optimized for a larger screen. This allows the service provider to deliver responses in the most optimal way by considering the user's device information.

[0069] The following briefly describes the processing flow for example form 1.

[0070] Step 1: The reception desk receives user input regarding internal administrative procedures. The reception desk provides an interface that supports text, voice, and image input. Step 2: The analysis unit analyzes the questions received by the reception unit. The analysis unit uses natural language processing techniques and machine learning algorithms to understand the content and intent of the questions. Step 3: The acquisition unit retrieves the URL of the relevant regulations based on the question analyzed by the analysis unit. The acquisition unit searches for the URL of the relevant regulations using a database or search engine. Step 4: The rules analysis unit analyzes the rules of the destination URL obtained by the acquisition unit. The rules analysis unit can also use machine learning algorithms to analyze the content of the rules and generate specific answers to questions. Step 5: The generation unit generates specific answers based on the rules analyzed by the rule analysis unit. The generation unit generates answers using template-based generation algorithms or machine learning algorithms. Step 6: The providing unit provides the user with the answers generated by the generating unit. The providing unit displays the generated answers in text, audio, and image formats.

[0071] (Example of form 2) An embodiment of the present invention provides an administrative procedure support system that efficiently provides answers to questions regarding internal administrative procedures using AI. The system works as follows: The user inputs a question about internal administrative procedures, the AI ​​analyzes the question, and obtains a URL to the relevant regulations. The AI ​​interprets the regulations at the destination of the obtained URL and generates a specific answer to the question in text form. This answer is then provided to the user. For example, the user might input a question such as, "How do I apply for leave?" This question is input to the AI. Next, the AI ​​analyzes the input question. The AI ​​understands the content of the question and obtains a URL to the relevant regulations. For example, it might obtain a URL to the regulations regarding "leave applications." The AI ​​interprets the regulations at the destination of the obtained URL. The AI ​​analyzes the content of the regulations and generates a specific answer to the question in text form. For example, it might generate an answer such as, "To apply for leave, you must first obtain approval from your supervisor, and then submit an application form to the Human Resources Department." The generated answer is then provided to the user. By reviewing the specific answer generated by the AI, the user can efficiently obtain information regarding administrative procedures. This eliminates the need for users to review each rule individually and allows them to receive quick and accurate answers to questions regarding administrative procedures. For example, in response to a question about the leave application process, the AI ​​can provide a detailed written explanation of the procedure, enabling users to proceed with the process quickly. This allows the administrative support system to provide prompt and accurate answers to user questions.

[0072] The administrative procedure support system according to this embodiment comprises a reception unit, an analysis unit, an acquisition unit, a rules analysis unit, a generation unit, and a provision unit. The reception unit receives questions from users regarding internal administrative procedures. The reception unit provides, for example, an interface for users to input questions in text format. The reception unit can also support voice input and image input. The analysis unit analyzes the questions received by the reception unit. The analysis unit understands the content of the questions using, for example, natural language processing technology. The analysis unit can also analyze the intent of the questions using machine learning algorithms. The analysis unit obtains the URL of the relevant rules based on the content of the questions. The acquisition unit obtains the URL of the relevant rules based on the questions analyzed by the analysis unit. The acquisition unit searches for the URL of the relevant rules from a database, for example. The acquisition unit can also obtain the URL of the relevant rules using a search engine. The rules analysis unit analyzes the rules that the URLs obtained by the acquisition unit redirect to. The rules analysis unit analyzes the content of the rules and generates specific answers to the questions. The rules analysis unit can also analyze the content of the rules using machine learning algorithms. The generation unit generates specific answers based on the rules analyzed by the rule analysis unit. The generation unit generates answers using, for example, a template-based generation algorithm. The generation unit can also generate answers using a machine learning algorithm. The provision unit provides the answers generated by the generation unit to the user. The provision unit displays the generated answers in, for example, text format. The provision unit can also provide answers in audio or image format. As a result, the administrative procedure support system according to this embodiment can provide quick and accurate answers to user questions.

[0073] The reception desk allows users to input questions regarding internal administrative procedures. The reception desk provides an interface for users to input questions in text format, for example. Specifically, it designs an intuitive user interface to make it easy for users to input questions. For instance, it uses text boxes and dropdown menus to provide an environment that facilitates question input. It also supports voice input, allowing users to input questions by voice using a microphone. In the case of voice input, speech recognition technology is used to convert the voice into text and send it to the analysis unit. Furthermore, it supports image input; users can upload images, and the text within the image can be analyzed and accepted as a question. This allows the reception desk to provide a flexible interface that allows users to input questions in various formats, improving user convenience.

[0074] The analysis unit analyzes the questions received by the reception unit. The analysis unit understands the content of the questions, for example, using natural language processing technology. Specifically, it uses natural language processing technology to analyze the grammatical structure and meaning of the questions and grasp the intent of the questions. For example, it performs morphological analysis to divide the question sentence into individual words and identifies the part of speech of each word. Next, it performs dependency structure analysis to clarify the relationships between words. This allows it to grasp the structure of the question, such as the subject, predicate, and object, and understand the meaning of the question. It can also analyze the intent of the questions using machine learning algorithms. For example, it can classify the intent of the questions using a model that has been trained in advance using a large amount of question data. As a result, the analysis unit can provide information to obtain URLs of relevant regulations based on the content of the questions.

[0075] The acquisition unit retrieves the URLs of relevant regulations based on the questions analyzed by the analysis unit. For example, the acquisition unit searches for relevant regulation URLs in a database. Specifically, it accesses a database where internal regulations are stored and searches for relevant regulation URLs based on keywords and categories provided by the analysis unit. It can also retrieve relevant regulation URLs using a search engine. For example, it searches for regulations published on the company's intranet using a search engine and retrieves the relevant URLs. This allows the acquisition unit to quickly and accurately retrieve relevant regulation URLs and provide the information necessary for subsequent processing.

[0076] The rules analysis unit analyzes the rules of the destination URL obtained by the acquisition unit. For example, the rules analysis unit analyzes the content of the rules and generates specific answers to questions. Specifically, it analyzes the text of the acquired rules and extracts the parts relevant to the questions. For example, it uses text mining technology to extract keywords and phrases related to the questions from the rules and generates answers based on them. It can also analyze the content of the rules using machine learning algorithms. For example, it uses a pre-trained model to classify the content of the rules and generate the optimal answer to the question. In this way, the rules analysis unit can quickly and accurately analyze the content of the acquired rules and provide specific answers to questions.

[0077] The generation unit generates specific answers based on the rules analyzed by the rules analysis unit. The generation unit generates answers using, for example, a template-based generation algorithm. Specifically, it quickly generates answers by embedding the information provided by the rules analysis unit into a pre-prepared answer template. For example, it embeds the analyzed answer content into a template such as "The answer to the question is as follows: {Answer content}". It can also generate answers using machine learning algorithms. For example, it generates the optimal answer to a question using a pre-trained model. This allows the generation unit to quickly and accurately generate specific answers and provide them to the user.

[0078] The providing unit provides the user with the answers generated by the generating unit. For example, the providing unit displays the generated answers in text format. Specifically, it displays the generated answers on the interface where the user entered the question. It can also provide answers in audio or image format. For example, it can use speech synthesis technology to read the generated answers aloud. It can also provide answers in a format that is easy for the user to understand by illustrating the content. This allows the providing unit to provide users with quick and accurate answers, improving user convenience. Furthermore, the providing unit can collect feedback from users and use it to improve the system. For example, it can collect feedback on satisfaction with and understanding of the answers and provide this feedback to the analysis and generation units. This allows the providing unit to improve the overall performance of the system and provide better service to users.

[0079] The analysis unit can understand the content of the question and obtain the URL of the relevant regulations. The analysis unit understands the content of the question using, for example, natural language processing technology. The analysis unit can also analyze the intent of the question using machine learning algorithms. The analysis unit obtains the URL of the relevant regulations based on the content of the question. For example, the analysis unit analyzes the content of the question and obtains the URL of the regulations regarding "leave of absence applications". The analysis unit uses natural language processing technology to understand the content of the question. For example, the analysis unit analyzes the content of the question and extracts relevant keywords. The analysis unit can also analyze the intent of the question using machine learning algorithms. For example, the analysis unit learns a model to analyze the content of the question and obtain the URL of the relevant regulations. This allows the analysis unit to obtain the URL of the appropriate regulations based on the content of the question.

[0080] The rules analysis unit can analyze the rules of the destination URL accessed by the acquired URL and generate specific answers to questions. For example, the rules analysis unit can analyze the content of the rules and generate specific answers to questions. The rules analysis unit can also analyze the content of the rules using machine learning algorithms. For example, the rules analysis unit can analyze the rules of the destination URL accessed by the acquired URL and generate specific answers such as, "To apply for leave, you must first obtain approval from your supervisor and then submit the application form to the Human Resources Department." The rules analysis unit uses natural language processing technology to analyze the content of the rules. For example, the rules analysis unit analyzes the content of the rules and extracts relevant information. The rules analysis unit can also analyze the content of the rules using machine learning algorithms. For example, the rules analysis unit can analyze the content of the rules and train a model to generate specific answers to questions. This allows the rules analysis unit to analyze the content of the rules and generate specific answers.

[0081] The generation unit can be equipped with a mechanism to verify the accuracy of the generated answers. For example, the generation unit can perform feedback evaluation to verify the accuracy of the generated answers. The generation unit can also perform cross-checking to verify the accuracy of the generated answers. For example, the generation unit can perform cross-checking using multiple AI models to verify the accuracy of the generated answers. The generation unit can collect feedback from users to verify the accuracy of the generated answers. For example, the generation unit can evaluate the accuracy of the generated answers based on user feedback. The generation unit can also perform periodic evaluations to verify the accuracy of the generated answers. For example, the generation unit can periodically evaluate the accuracy of the generated answers and make improvements as needed. This allows the generation unit to verify the accuracy of the generated answers.

[0082] The service provider can provide the generated answers to the user. For example, the service provider can display the generated answers in text format. The service provider can also provide answers in audio or image format. For example, the service provider can provide the generated answers in audio format using speech synthesis technology. The service provider can also use image generation technology to provide the generated answers in image format. For example, the service provider can display the generated answers in image format, providing them in a visually easy-to-understand format. The service provider can also use email or a chatbot to provide the generated answers to the user. For example, the service provider can send the generated answers to the user via email. The service provider can also provide the generated answers to the user through a chatbot. In this way, the service provider can provide the generated answers to the user.

[0083] The reception system can include a mechanism for users to select a question category when entering a question. For example, the reception system can provide an interface for users to select a question category when entering a question. By allowing users to select a question category, the reception system can streamline the question reception process. For example, the reception system can make it easier to identify the content of the question by allowing users to select a category such as "leave request" or "expense reimbursement." The reception system can also use dropdown menus or checkboxes to allow users to select a question category. For example, the reception system can provide an interface for users to select a question category from a dropdown menu. By allowing users to select a question category, the reception system can streamline the question analysis and answer generation process. For example, by allowing users to select a question category, the reception system can make it easier for the analysis and generation units to identify the content of the question. As a result, by allowing users to select a question category, the reception system can streamline the question reception process.

[0084] The reception desk can estimate the user's emotions and adjust the timing of question reception based on the estimated emotions. For example, if the user is stressed, the reception desk will quickly receive questions and respond immediately. If the user is relaxed, the reception desk can also receive questions at a normal time. For example, if the user is in a hurry, the reception desk will prioritize receiving questions and process them quickly. To estimate the user's emotions, the reception desk uses emotion estimation functions, such as an emotion engine or generative AI. For example, the reception desk can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The reception desk can also record the user's voice and estimate their emotions using voice analysis technology. For example, the reception desk can analyze the tone and speed of the user's voice and calculate an emotion score. This allows the reception desk to adjust the timing of question reception according to the user's emotions.

[0085] The reception desk can analyze a user's past question history and select the optimal reception method. For example, the reception desk can suggest the optimal reception method based on the questions the user has frequently asked in the past. The reception desk can also prioritize receiving questions asked during specific time periods based on the user's past question history. For example, the reception desk can analyze a user's past question history and select the most efficient reception method. The reception desk can use machine learning algorithms to analyze a user's past question history. For example, the reception desk can retrieve a user's past question history from a database and analyze it using a machine learning algorithm. This allows the reception desk to select the optimal reception method by analyzing the user's past question history.

[0086] The reception desk can filter questions based on the user's current work situation and areas of interest when receiving them. For example, the reception desk can consider the user's current work situation and prioritize receiving relevant questions. The reception desk can also filter relevant questions based on the user's areas of interest. For example, the reception desk can analyze the user's work situation and areas of interest and receive the most relevant questions. The reception desk can use machine learning algorithms to analyze the user's work situation and areas of interest. For example, the reception desk can retrieve the user's work situation and areas of interest from a database and analyze it using a machine learning algorithm. This allows the reception desk to filter questions based on the user's current work situation and areas of interest, thereby prioritizing the receipt of highly relevant questions.

[0087] The reception desk can estimate the user's emotions and determine the priority of questions to answer based on the estimated emotions. For example, if the user is stressed, the reception desk will set a higher priority for the questions. If the user is relaxed, the reception desk can set the priority of the questions to a normal level. For example, if the user is in a hurry, the reception desk will set the priority of the questions to the highest level. To estimate the user's emotions, the reception desk uses emotion estimation functions, such as an emotion engine or generative AI. For example, the reception desk can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The reception desk can also record the user's voice and estimate their emotions using voice analysis technology. For example, the reception desk can analyze the tone and speed of the user's voice and calculate an emotion score. This allows the reception desk to answer questions in a more appropriate order by determining the priority of questions according to the user's emotions.

[0088] The reception desk can prioritize receiving questions that are highly relevant, taking into account the user's geographical location. For example, the reception desk can prioritize receiving relevant questions based on the user's geographical location. The reception desk can also prioritize receiving questions related to a specific region if the user is in that region. For example, the reception desk can analyze the user's geographical location and prioritize receiving the most relevant questions. The reception desk can use GPS data or IP addresses to obtain the user's geographical location. For example, the reception desk can obtain the user's geographical location and prioritize receiving relevant questions. This allows the reception desk to prioritize receiving highly relevant questions by taking the user's geographical location into consideration.

[0089] The reception desk can analyze the user's social media activity when receiving a question and accept relevant questions. For example, the reception desk can accept relevant questions based on the user's social media activity. The reception desk can also accept relevant questions based on what the user has mentioned on social media. For example, the reception desk can analyze the user's social media activity and accept the most relevant questions. The reception desk can use machine learning algorithms to analyze the user's social media activity. For example, the reception desk can retrieve the user's social media activity from a database and analyze it using a machine learning algorithm. This allows the reception desk to accept highly relevant questions by analyzing the user's social media activity.

[0090] The analysis unit can estimate the user's emotions and adjust the question analysis method based on the estimated emotions. For example, if the user is stressed, the analysis unit will apply a quick and concise analysis method. If the user is relaxed, the analysis unit can also apply a detailed analysis method. For example, if the user is in a hurry, the analysis unit will apply a method that performs the analysis in the shortest possible time. To estimate the user's emotions, the analysis unit uses emotion estimation functions, such as an emotion engine or generative AI. For example, the analysis unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The analysis unit can also record the user's voice and estimate their emotions using voice analysis technology. For example, the analysis unit can analyze the tone and speed of the user's voice and calculate an emotion score. This allows the analysis unit to analyze questions in a more appropriate way by adjusting the question analysis method according to the user's emotions.

[0091] The analysis unit can adjust the level of detail of the analysis based on the importance of the question. For example, the analysis unit will perform a detailed analysis for high-importance questions. The analysis unit can also perform a concise analysis for low-importance questions. For example, the analysis unit will analyze the importance of the question and adjust the level of detail to the optimal level. The analysis unit can use machine learning algorithms to evaluate the importance of the question. For example, the analysis unit will evaluate the impact and urgency of the question and adjust the level of detail. This allows the analysis unit to analyze questions in a more appropriate way by adjusting the level of detail based on the importance of the question.

[0092] The analysis unit can apply different analysis algorithms depending on the category of the question when analyzing it. For example, if the question is about human resources, the analysis unit will apply a human resources-related analysis algorithm. If the question is about accounting, the analysis unit can also apply an accounting-related analysis algorithm. For example, the analysis unit analyzes the category of the question and applies the most suitable analysis algorithm. The analysis unit can use machine learning algorithms to identify the category of the question. For example, the analysis unit can learn a model that analyzes the content of the question and identifies the category. This allows the analysis unit to analyze questions in a more appropriate way by applying different analysis algorithms depending on the category of the question.

[0093] The analysis unit can estimate the user's emotions and determine the priority of analysis based on the estimated emotions. For example, if the user is stressed, the analysis unit will set a higher priority. If the user is relaxed, the analysis unit can set the priority to normal. For example, if the user is in a hurry, the analysis unit will set the priority to the highest priority. To estimate the user's emotions, the analysis unit uses emotion estimation functions, such as an emotion engine or generative AI. For example, the analysis unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The analysis unit can also record the user's voice and estimate their emotions using voice analysis technology. For example, the analysis unit can analyze the tone and speed of the user's voice and calculate an emotion score. This allows the analysis unit to determine the priority of analysis according to the user's emotions, enabling it to analyze questions in a more appropriate order.

[0094] The analysis unit can determine the priority of analysis based on when the questions were submitted. For example, the analysis unit can determine the priority of analysis based on the time period in which the questions were submitted. The analysis unit can also determine the priority of analysis based on the date in which the questions were submitted. For example, the analysis unit can analyze the timing of question submissions and determine the optimal analysis priority. The analysis unit can use machine learning algorithms to evaluate the timing of question submissions. For example, the analysis unit can evaluate the date and time of question submissions and the frequency of submissions to determine the analysis priority. This allows the analysis unit to analyze questions in a more appropriate order by determining the priority of analysis based on the timing of question submissions.

[0095] The analysis unit can adjust the order of analysis based on the relevance of the questions. For example, the analysis unit can analyze the relevance of the questions and prioritize the analysis of the most relevant questions. The analysis unit can also adjust the order of analysis based on the relevance of the questions. For example, the analysis unit can evaluate the relevance of the questions and determine the optimal order of analysis. The analysis unit can use machine learning algorithms to evaluate the relevance of the questions. For example, the analysis unit can evaluate the similarity of the question content and related topics and adjust the order of analysis. In this way, the analysis unit can analyze questions in a more appropriate order by adjusting the order of analysis based on the relevance of the questions.

[0096] The acquisition unit can estimate the user's emotions and adjust the timing of acquiring the terms and conditions URL based on the estimated emotions. For example, if the user is stressed, the acquisition unit will acquire the terms and conditions URL quickly. If the user is relaxed, the acquisition unit can also acquire the terms and conditions URL at a normal time. For example, if the user is in a hurry, the acquisition unit will prioritize acquiring the terms and conditions URL. To estimate the user's emotions, the acquisition unit uses an emotion estimation function, such as an emotion engine or generative AI. For example, the acquisition unit can capture the user's facial expression with a camera and estimate the emotion using an emotion estimation algorithm. The acquisition unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the acquisition unit can analyze the tone and speed of the user's voice and calculate an emotion score. As a result, the acquisition unit can acquire the terms and conditions URL at a more appropriate time by adjusting the timing of acquisition according to the user's emotions.

[0097] The retrieval unit can analyze the user's past question history to select the optimal retrieval method when obtaining the URL of the terms and conditions. For example, the retrieval unit can obtain the optimal terms and conditions URL based on the user's past question history. The retrieval unit can also prioritize obtaining the URL of the relevant terms and conditions from the user's past question history. For example, the retrieval unit analyzes the user's past question history and selects the most efficient method for obtaining the terms and conditions URL. The retrieval unit can use machine learning algorithms to analyze the user's past question history. For example, the retrieval unit retrieves the user's past question history from a database and analyzes it using a machine learning algorithm. As a result, the retrieval unit can select the optimal method for obtaining the terms and conditions URL by analyzing the user's past question history.

[0098] The retrieval unit can filter the URLs of the terms and conditions based on the user's current work situation and areas of interest when retrieving them. For example, the retrieval unit can consider the user's current work situation and prioritize retrieving URLs of relevant terms and conditions. The retrieval unit can also filter URLs of relevant terms and conditions based on the user's areas of interest. For example, the retrieval unit can analyze the user's work situation and areas of interest and retrieve the most relevant URLs. The retrieval unit can use machine learning algorithms to analyze the user's work situation and areas of interest. For example, the retrieval unit can retrieve the user's work situation and areas of interest from a database and analyze them using a machine learning algorithm. As a result, the retrieval unit can filter the URLs of the terms and conditions based on the user's current work situation and areas of interest, thereby prioritizing the retrieval of URLs of highly relevant terms and conditions.

[0099] The retrieval unit can estimate the user's emotions and determine the priority of the terms and conditions URLs to retrieve based on the estimated emotions. For example, if the user is stressed, the retrieval unit will set a higher priority for the terms and conditions URLs. If the user is relaxed, the retrieval unit can set the priority of the terms and conditions URLs to a normal level. For example, if the user is in a hurry, the retrieval unit will set the priority of the terms and conditions URLs to the highest priority. To estimate the user's emotions, the retrieval unit uses an emotion estimation function, such as an emotion engine or generative AI. For example, the retrieval unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The retrieval unit can also record the user's voice and estimate their emotions using voice analysis technology. For example, the retrieval unit can analyze the tone and speed of the user's voice and calculate an emotion score. As a result, the retrieval unit can retrieve the terms and conditions URLs in a more appropriate order by determining the priority of the terms and conditions URLs according to the user's emotions.

[0100] The retrieval unit can prioritize retrieving URLs of terms and conditions that are highly relevant, taking into account the user's geographical location information when retrieving URLs of terms and conditions. For example, the retrieval unit can prioritize retrieving URLs of relevant terms and conditions based on the user's geographical location information. The retrieval unit can also prioritize retrieving URLs of terms and conditions related to a specific region if the user is in that region. For example, the retrieval unit can analyze the user's geographical location information and prioritize retrieving the URL of the most relevant terms and conditions. The retrieval unit can use GPS data or IP addresses to obtain the user's geographical location information. For example, the retrieval unit can obtain the user's geographical location information and prioritize retrieving URLs of relevant terms and conditions. In this way, the retrieval unit can prioritize retrieving URLs of highly relevant terms and conditions by taking the user's geographical location information into consideration.

[0101] The retrieval unit can analyze the user's social media activity and retrieve relevant URLs when retrieving terms and conditions URLs. For example, the retrieval unit can retrieve relevant terms and conditions URLs based on the user's social media activity. The retrieval unit can also retrieve relevant terms and conditions URLs based on what the user has mentioned on social media. For example, the retrieval unit can analyze the user's social media activity and retrieve the most relevant terms and conditions URL. The retrieval unit can use machine learning algorithms to analyze the user's social media activity. For example, the retrieval unit can retrieve the user's social media activity from a database and analyze it using a machine learning algorithm. This allows the retrieval unit to retrieve highly relevant terms and conditions URLs by analyzing the user's social media activity.

[0102] The rules analysis unit can estimate the user's emotions and adjust the rules analysis method based on the estimated user emotions. For example, if the user is stressed, the rules analysis unit will apply a quick and concise analysis method. If the user is relaxed, the rules analysis unit can also apply a detailed analysis method. For example, if the user is in a hurry, the rules analysis unit will apply a method that performs the analysis in the shortest possible time. To estimate the user's emotions, the rules analysis unit uses emotion estimation functions, such as an emotion engine or generative AI. For example, the rules analysis unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The rules analysis unit can also record the user's voice and estimate their emotions using voice analysis technology. For example, the rules analysis unit can analyze the tone and speed of the user's voice and calculate an emotion score. This allows the rules analysis unit to analyze the rules in a more appropriate way by adjusting the rules analysis method according to the user's emotions.

[0103] The rules analysis unit can adjust the level of detail of the analysis based on the importance of the rules. For example, the rules analysis unit will perform a detailed analysis for rules with high importance. The rules analysis unit can also perform a concise analysis for rules with low importance. For example, the rules analysis unit will analyze the importance of the rules and adjust the level of detail to the optimal level. The rules analysis unit can use machine learning algorithms to evaluate the importance of the rules. For example, the rules analysis unit will evaluate the impact and urgency of the rules and adjust the level of detail of the analysis. In this way, the rules analysis unit can analyze rules in a more appropriate way by adjusting the level of detail of the analysis based on the importance of the rules.

[0104] The regulations analysis unit can apply different analysis algorithms depending on the category of the regulations when analyzing them. For example, if the regulations concern human resources, the regulations analysis unit will apply a human resources-related analysis algorithm. If the regulations concern accounting, the regulations analysis unit can also apply an accounting-related analysis algorithm. For example, the regulations analysis unit analyzes the category of the regulations and applies the most appropriate analysis algorithm. The regulations analysis unit can use machine learning algorithms to identify the category of the regulations. For example, the regulations analysis unit can learn a model that analyzes the content of the regulations and identifies the category. This allows the regulations analysis unit to analyze the regulations in a more appropriate way by applying different analysis algorithms depending on the category of the regulations.

[0105] The convention analysis unit can estimate the user's emotions and determine the priority of analysis based on the estimated emotions. For example, if the user is stressed, the convention analysis unit will set a high priority for analysis. If the user is relaxed, the convention analysis unit can set the priority of analysis to normal. For example, if the user is in a hurry, the convention analysis unit will set the priority of analysis to the highest priority. To estimate the user's emotions, the convention analysis unit uses emotion estimation functions, such as an emotion engine or generative AI. For example, the convention analysis unit can capture the user's facial expressions with a camera and estimate emotions using an emotion estimation algorithm. The convention analysis unit can also record the user's voice and estimate emotions using voice analysis technology. For example, the convention analysis unit can analyze the tone and speed of the user's voice and calculate an emotion score. This allows the convention analysis unit to analyze conventions in a more appropriate order by determining the priority of analysis according to the user's emotions.

[0106] The rules analysis unit can determine the priority of analysis based on when the rules were submitted. For example, the rules analysis unit can determine the priority of analysis based on the time period in which the rules were submitted. The rules analysis unit can also determine the priority of analysis based on the date in which the rules were submitted. For example, the rules analysis unit can analyze the submission timing of the rules and determine the optimal analysis priority. The rules analysis unit can use machine learning algorithms to evaluate the submission timing of the rules. For example, the rules analysis unit can evaluate the submission date and time and submission frequency of the rules and determine the analysis priority. This allows the rules analysis unit to analyze the rules in a more appropriate order by determining the analysis priority based on the submission timing of the rules.

[0107] The rules analysis unit can adjust the order of analysis based on the relevance of the rules during analysis. For example, the rules analysis unit can analyze the relevance of the rules and prioritize the analysis of the most relevant rules. The rules analysis unit can also adjust the order of analysis based on the relevance of the rules. For example, the rules analysis unit can evaluate the relevance of the rules and determine the optimal analysis order. The rules analysis unit can use machine learning algorithms to evaluate the relevance of the rules. For example, the rules analysis unit can evaluate the similarity of the rules' content and related topics and adjust the analysis order. In this way, the rules analysis unit can analyze rules in a more appropriate order by adjusting the order of analysis based on the relevance of the rules.

[0108] The generation unit can estimate the user's emotions and adjust the way it expresses the generated response based on the estimated emotions. For example, if the user is stressed, the generation unit will apply a concise and clear expression. If the user is relaxed, the generation unit may also apply an expression that includes detailed explanations. For example, if the user is in a hurry, the generation unit will apply an expression that can be quickly understood. To estimate the user's emotions, the generation unit uses emotion estimation capabilities, such as an emotion engine or generative AI. For example, the generation unit may capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The generation unit may also record the user's voice and estimate their emotions using voice analysis technology. For example, the generation unit may analyze the tone and speed of the user's voice and calculate an emotion score. This allows the generation unit to generate responses in a more appropriate way by adjusting the way it expresses the generated response according to the user's emotions.

[0109] The generator can adjust the level of detail in the response based on the importance of the question when generating the answer. For example, the generator will generate a detailed answer for a high-importance question. The generator can also generate a concise answer for a low-importance question. For example, the generator can analyze the importance of the question and adjust the level of detail to the optimal level. The generator can use machine learning algorithms to evaluate the importance of the question. For example, the generator can evaluate the impact and urgency of the question and adjust the level of detail in the answer. This allows the generator to generate answers in a more appropriate way by adjusting the level of detail in the answer based on the importance of the question.

[0110] The generation unit can apply different generation algorithms depending on the question category when generating answers. For example, if the question is about human resources, the generation unit will apply a human resources-related generation algorithm. If the question is about accounting, the generation unit can also apply an accounting-related generation algorithm. For example, the generation unit can analyze the question category and apply the most suitable generation algorithm. The generation unit can use machine learning algorithms to identify the question category. For example, the generation unit can learn a model that analyzes the content of the question and identifies the category. This allows the generation unit to generate answers in a more appropriate way by applying different generation algorithms depending on the question category.

[0111] The generation unit can estimate the user's emotions and adjust the length of the responses it generates based on those emotions. For example, if the user is stressed, the generation unit will generate short, to-the-point responses. If the user is relaxed, the generation unit can also generate longer responses that include more detailed explanations. For example, if the user is in a hurry, the generation unit will generate short responses that can be quickly understood. To estimate the user's emotions, the generation unit uses emotion estimation capabilities, such as an emotion engine or generative AI. For example, the generation unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The generation unit can also record the user's voice and estimate their emotions using voice analysis technology. For example, the generation unit can analyze the tone and speed of the user's voice and calculate an emotion score. This allows the generation unit to generate responses in a more appropriate way by adjusting the length of the responses it generates according to the user's emotions.

[0112] The generation unit can determine the priority of answers based on when the questions were submitted. For example, the generation unit can determine the priority of answers based on the time period in which the questions were submitted. The generation unit can also determine the priority of answers based on the date in which the questions were submitted. For example, the generation unit can analyze the timing of question submissions and determine the optimal priority of answers. The generation unit can use machine learning algorithms to evaluate the timing of question submissions. For example, the generation unit can evaluate the date and time of question submissions and the frequency of submissions to determine the priority of answers. This allows the generation unit to generate answers in a more appropriate order by determining the priority of answers based on the timing of question submissions.

[0113] The generation unit can adjust the order of answers based on the relevance of the questions when generating responses. For example, the generation unit can analyze the relevance of the questions and prioritize generating answers to the most relevant questions. The generation unit can also adjust the order of answers based on the relevance of the questions. For example, the generation unit can evaluate the relevance of the questions and determine the optimal order of answers. The generation unit can use machine learning algorithms to evaluate the relevance of the questions. For example, the generation unit can evaluate the similarity of the question content and related topics and adjust the order of answers. This allows the generation unit to generate answers in a more appropriate order by adjusting the order of answers based on the relevance of the questions.

[0114] The service provider can estimate the user's emotions and adjust the way it delivers responses based on those emotions. For example, if the user is stressed, the service provider will apply a quick and concise delivery method. If the user is relaxed, the service provider may also apply a delivery method that includes detailed explanations. For example, if the user is in a hurry, the service provider will apply a delivery method that is easy to understand quickly. To estimate the user's emotions, the service provider uses emotion estimation capabilities, such as an emotion engine or generative AI. For example, the service provider may capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The service provider may also record the user's voice and estimate their emotions using voice analysis technology. For example, the service provider may analyze the tone and speed of the user's voice and calculate an emotion score. This allows the service provider to deliver responses in a more appropriate way by adjusting the delivery method according to the user's emotions.

[0115] The service provider can select the optimal delivery method by referring to the user's past question history when providing answers. For example, the service provider can select the optimal delivery method based on the user's past question history. The service provider can also prioritize providing relevant answers from the user's past question history. For example, the service provider can analyze the user's past question history and select the most efficient delivery method. The service provider can use machine learning algorithms to analyze the user's past question history. For example, the service provider can retrieve the user's past question history from a database and analyze it using a machine learning algorithm. This allows the service provider to select the optimal delivery method by referring to the user's past question history.

[0116] The service provider can estimate the user's emotions and adjust the timing of response delivery based on the estimated emotions. For example, if the user is stressed, the service provider will provide a response quickly. If the user is relaxed, the service provider can also provide a response at a normal time. For example, if the user is in a hurry, the service provider will provide a response as a top priority. To estimate the user's emotions, the service provider uses emotion estimation functions, such as an emotion engine or generative AI. For example, the service provider can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The service provider can also record the user's voice and estimate their emotions using voice analysis technology. For example, the service provider can analyze the tone and speed of the user's voice and calculate an emotion score. This allows the service provider to provide responses at a more appropriate time by adjusting the timing of response delivery according to the user's emotions.

[0117] The service provider can select the optimal delivery method when providing responses, taking into account the user's device information. For example, if the user is using a smartphone, the service provider will apply a delivery method that matches the screen size. If the user is using a tablet, the service provider can also apply a delivery method optimized for a larger screen. For example, if the user is using a desktop, the service provider will apply a delivery method that includes detailed information. The service provider can consider the type and usage of the device in order to obtain the user's device information. For example, the service provider can obtain the user's device information and select the optimal delivery method. This allows the service provider to provide responses in the most optimal way by taking the user's device information into consideration.

[0118] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0119] The reception system can include a mechanism for users to select a category when entering their questions. For example, users can select categories such as "leave request" or "expense reimbursement" to make it easier to identify the content of their questions. The reception system can also use dropdown menus or checkboxes for selecting question categories. This streamlines the analysis of questions and the generation of answers.

[0120] The analysis unit can adjust the level of detail in its analysis based on the importance of each question. For example, it can perform a detailed analysis on high-importance questions and a concise analysis on low-importance questions. This allows the analysis unit to analyze questions in a more appropriate way by adjusting the level of detail based on their importance.

[0121] The regulations analysis unit can apply different analysis algorithms depending on the category of the regulations. For example, if the regulations concern human resources, it can apply a human resources-related analysis algorithm, and if they concern accounting, it can apply an accounting-related analysis algorithm. This allows the regulations analysis unit to analyze regulations in a more appropriate way by applying different analysis algorithms depending on the category of the regulations.

[0122] The generation unit can determine the priority of answers based on when the questions were submitted. For example, it can determine the priority of answers based on the time of day or date the questions were submitted. This allows the generation unit to generate answers in a more appropriate order by determining the priority of answers based on when the questions were submitted.

[0123] The service provider can select the optimal delivery method when providing responses, taking into account the user's device information. For example, if the user is using a smartphone, the service provider can apply a delivery method that matches the screen size, and if the user is using a tablet, it can apply a delivery method optimized for a larger screen. This allows the service provider to deliver responses in the most optimal way by considering the user's device information.

[0124] The reception desk can estimate the user's emotions and adjust the timing of question reception based on those estimates. For example, if a user is feeling stressed, the reception desk can quickly process the question and respond immediately. This allows the reception desk to adjust the timing of question reception according to the user's emotions.

[0125] The analysis unit can estimate the user's emotions and adjust the question analysis method based on the estimated user emotions. For example, if the user is stressed, a quick and concise analysis method can be applied, while if the user is relaxed, a detailed analysis method can be applied. In this way, the analysis unit can adjust the question analysis method according to the user's emotions.

[0126] The acquisition unit can estimate the user's emotions and adjust the timing of acquiring the terms and conditions URL based on the estimated emotions. For example, if the user is feeling stressed, the terms and conditions URL can be acquired quickly, while if the user is relaxed, it can be acquired at the normal timing. In this way, the acquisition unit can adjust the timing of acquiring the terms and conditions URL according to the user's emotions.

[0127] The terms analysis unit can estimate the user's emotions and adjust the terms analysis method based on the estimated user emotions. For example, if the user is stressed, a quick and concise analysis method can be applied, while if the user is relaxed, a detailed analysis method can be applied. In this way, the terms analysis unit can adjust the terms analysis method according to the user's emotions.

[0128] The generation unit can estimate the user's emotions and adjust the way the generated responses are expressed based on the estimated emotions. For example, if the user is stressed, a concise and clear expression can be applied, while if the user is relaxed, an expression that includes detailed explanations can be applied. In this way, the generation unit can adjust the way the generated responses are expressed according to the user's emotions.

[0129] The following briefly describes the processing flow for example form 2.

[0130] Step 1: The reception desk receives user input regarding internal administrative procedures. The reception desk provides an interface that supports text, voice, and image input. Step 2: The analysis unit analyzes the questions received by the reception unit. The analysis unit uses natural language processing techniques and machine learning algorithms to understand the content and intent of the questions. Step 3: The acquisition unit retrieves the URL of the relevant regulations based on the question analyzed by the analysis unit. The acquisition unit searches for the URL of the relevant regulations using a database or search engine. Step 4: The rules analysis unit analyzes the rules of the destination URL obtained by the acquisition unit. The rules analysis unit can also use machine learning algorithms to analyze the content of the rules and generate specific answers to questions. Step 5: The generation unit generates specific answers based on the rules analyzed by the rule analysis unit. The generation unit generates answers using template-based generation algorithms or machine learning algorithms. Step 6: The providing unit provides the user with the answers generated by the generating unit. The providing unit displays the generated answers in text, audio, and image formats.

[0131] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0132] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, 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), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0133] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0134] Each of the multiple elements described above, including the reception unit, analysis unit, acquisition unit, convention analysis unit, generation unit, and provision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and provides an interface for the user to input a question in text format. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and understands the content of the question using natural language processing technology. The acquisition unit is implemented by the specific processing unit 290 of the data processing unit 12 and searches the database 24 for the URL of the relevant convention. The convention analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the convention of the destination of the acquired URL. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates an answer using a template-based generation algorithm. The provision unit is implemented by the control unit 46A of the smart device 14 and displays the generated answer in text format. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0135] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0136] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0137] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0138] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0139] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0141] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0142] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0143] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0144] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0145] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0146] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0147] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0148] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0149] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0150] Each of the multiple elements described above, including the reception unit, analysis unit, acquisition unit, convention analysis unit, generation unit, and provision unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and provides an interface for the user to input a question in text format. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and understands the content of the question using natural language processing technology. The acquisition unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and searches the database 24 for the URL of the relevant convention. The convention analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and analyzes the convention of the destination of the acquired URL. The generation unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and generates an answer using a template-based generation algorithm. The provision unit is implemented, for example, by the control unit 46A of the smart glasses 214 and displays the generated answer in text format. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0151] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0152] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0153] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0154] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0155] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0156] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0157] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0158] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0159] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0160] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0161] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0162] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0163] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0164] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0165] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0166] Each of the multiple elements described above, including the reception unit, analysis unit, acquisition unit, rule analysis unit, generation unit, and provision unit, is implemented, for example, in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and provides an interface for the user to input a question in text format. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and understands the content of the question using natural language processing technology. The acquisition unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and searches the database 24 for the URL of the relevant rule. The rule analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and analyzes the rule of the destination of the acquired URL. The generation unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and generates an answer using a template-based generation algorithm. The provision unit is implemented, for example, by the control unit 46A of the headset terminal 314 and displays the generated answer in text format. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0167] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0168] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0169] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0170] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0171] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0172] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0173] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0174] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0175] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0176] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0177] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0178] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0179] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0180] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0181] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0182] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0183] Each of the multiple elements described above, including the reception unit, analysis unit, acquisition unit, convention analysis unit, generation unit, and provision unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and provides an interface for the user to input a question in text format. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and understands the content of the question using natural language processing technology. The acquisition unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and searches the database 24 for the URL of the relevant convention. The convention analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the convention of the destination of the acquired URL. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and generates an answer using a template-based generation algorithm. The provision unit is implemented, for example, by the control unit 46A of the robot 414 and displays the generated answer in text format. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0184] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0185] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0186] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0187] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0188] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0189] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0190] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0191] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0192] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0193] 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.

[0194] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0195] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0196] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0197] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0198] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0199] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0200] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0201] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0202] (Note 1) The reception desk that takes questions, An analysis unit that analyzes the questions received by the reception unit, An acquisition unit that obtains the URL of the relevant regulations based on the question analyzed by the aforementioned analysis unit, A rules analysis unit analyzes the rules of the destination URL obtained by the acquisition unit, A generation unit that generates a specific answer based on the rules analyzed by the aforementioned rule analysis unit, The system includes a providing unit that provides the answer generated by the generation unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Understand the question and obtain the URL of the relevant terms and conditions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned protocol analysis unit, The system analyzes the terms of service of the destination URL obtained and generates specific answers to the questions. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is It includes a mechanism to verify the accuracy of the generated responses. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, Provide the generated response to the user. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is The system includes a mechanism for users to select a question category when entering their question. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of question submissions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is Analyze the user's past question history and select the most suitable method of handling inquiries. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When receiving questions, filtering is performed based on the user's current work situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is The system estimates the user's emotions and prioritizes the questions to be asked based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When receiving questions, the system prioritizes accepting questions that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When receiving a question, the system analyzes the user's social media activity and selects relevant questions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, We estimate the user's emotions and adjust the question analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, When analyzing questions, adjust the level of detail based on the importance of the questions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, When analyzing a question, different analysis algorithms are applied depending on the question category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, The system estimates the user's emotions and determines the priority of analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, When analyzing questions, we prioritize the analysis based on when the questions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, When analyzing questions, the order of analysis is adjusted based on the relevance of the questions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The acquisition unit is, The system estimates the user's sentiment and adjusts the timing of obtaining the terms of service URL based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 20) The acquisition unit is, When retrieving the URL for the terms of service, the system analyzes the user's past question history to select the most suitable retrieval method. The system described in Appendix 1, characterized by the features described herein. (Note 21) The acquisition unit is, When retrieving URLs for terms of service, filtering is performed based on the user's current work situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 22) The acquisition unit is, It estimates the user's sentiment and determines the priority of URLs for terms of service to retrieve based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The acquisition unit is, When retrieving URLs for terms of service, the system prioritizes retrieving URLs that are more relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The acquisition unit is, When obtaining the URL for the terms of service, the system analyzes the user's social media activity and retrieves relevant URLs. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned protocol analysis unit, We estimate user sentiment and adjust the terms of service analysis method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned protocol analysis unit, When analyzing the terms and conditions, adjust the level of detail of the analysis based on the importance of the terms and conditions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned protocol analysis unit, When analyzing the terms and conditions, different analysis algorithms are applied depending on the category of the terms and conditions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned protocol analysis unit, The system estimates the user's emotions and determines the priority of analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned protocol analysis unit, When analyzing the terms and conditions, the priority of the analysis is determined based on when the terms and conditions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned protocol analysis unit, When analyzing the rules, the order of analysis is adjusted based on the relevance of the rules. The system described in Appendix 1, characterized by the features described herein. (Note 31) The generating unit is It estimates the user's emotions and adjusts how the generated responses are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The generating unit is When generating answers, adjust the level of detail in the answers based on the importance of the question. The system described in Appendix 1, characterized by the features described herein. (Note 33) The generating unit is When generating answers, different generation algorithms are applied depending on the question category. The system described in Appendix 1, characterized by the features described herein. (Note 34) The generating unit is It estimates the user's emotions and adjusts the length of the response generated based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The generating unit is When generating answers, we prioritize them based on when the questions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 36) The generating unit is When generating answers, the order of answers is adjusted based on the relevance of the questions. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned supply unit is, The system estimates the user's emotions and adjusts how responses are provided based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned supply unit is, When providing answers, the system will refer to the user's past question history to select the most appropriate method of delivery. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned supply unit is, The system estimates the user's emotions and adjusts the timing of response delivery based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned supply unit is, When providing responses, the optimal delivery method will be selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0203] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The reception desk that takes questions, An analysis unit that analyzes the questions received by the reception unit, An acquisition unit that obtains the URL of the relevant regulations based on the question analyzed by the aforementioned analysis unit, A rules analysis unit analyzes the rules of the destination URL obtained by the acquisition unit, A generation unit that generates a specific answer based on the rules analyzed by the aforementioned rule analysis unit, The system includes a providing unit that provides the answer generated by the generation unit. A system characterized by the following features.

2. The aforementioned analysis unit, Understand the question and obtain the URL of the relevant terms and conditions. The system according to feature 1.

3. The aforementioned protocol analysis unit, The system analyzes the terms of service of the destination URL obtained and generates specific answers to the questions. The system according to feature 1.

4. The generating unit is It includes a mechanism to verify the accuracy of the generated responses. The system according to feature 1.

5. The aforementioned supply unit is, Provide the generated response to the user. The system according to feature 1.

6. The aforementioned reception unit is The system includes a mechanism for users to select a question category when entering their question. The system according to feature 1.

7. The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of question submissions based on those estimated emotions. The system according to feature 1.

8. The aforementioned reception unit is Analyze the user's past question history and select the most suitable method of handling inquiries. The system according to feature 1.

9. The aforementioned reception unit is When receiving questions, filtering is performed based on the user's current work situation and areas of interest. The system according to feature 1.

Images