system

Abstract

The system according to this embodiment aims to efficiently prepare chatbot question and answer data. [Solution] The system according to the embodiment comprises a collection unit, a question processing unit, a generation unit, and a provision unit. The collection unit collects questions. The question processing unit processes the questions collected by the collection unit. The generation unit generates answers based on the processing results by the question processing unit. The provision unit provides the answers generated by the generation unit.

Description

Technical Field

[0006]

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot 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 as a 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 prior art, there is a problem that it takes a great deal of time and effort to prepare question - and - answer data for chatbots.

[0005] The system according to the embodiment aims to efficiently prepare question - and - answer data for chatbots.

Means for Solving the Problems

[0006] The system according to the embodiment includes a collection unit, a question processing unit, a generation unit, and a provision unit. The collection unit collects questions. The question processing unit processes the questions collected by the collection unit. The generation unit generates answers based on the processing results of the question processing unit. The provision unit provides the answers generated by the generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently prepare chatbot question and answer data. [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 signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface 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 �2. 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 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are 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) The business support system according to an embodiment of the present invention is a system for streamlining business support for questions and answers (QA) using a chatbot. This business support system includes a collection unit for collecting questions, a question processing unit for processing questions, a generation unit for generating answers, and a provision unit for providing the generated answers. First, the collection unit sets predetermined keywords and scrapes questions from websites and databases. Next, the collected questions are processed by the question processing unit. The question processing unit corrects inconsistencies in the wording of the questions and automatically creates variations of question data for training using a generation AI. Furthermore, based on the processing results by the question processing unit, the generation unit generates answers. The generated answers are provided by the provision unit. This system makes it possible to make the chatbot usable with minimal human intervention. For example, the collection unit sets predetermined keywords and scrapes questions from websites and databases. Next, the collected questions are processed by the question processing unit. The question processing unit corrects inconsistencies in the wording of the questions and automatically creates variations of question data for training using a generation AI. Furthermore, based on the processing results by the question processing unit, the generation unit generates answers. The generated answers are provided by the provision unit. This system makes it possible to make chatbots available with minimal human intervention. As a result, business support systems can efficiently handle everything from collecting questions to providing answers.

[0029] The business support system according to this embodiment comprises a collection unit, a question processing unit, a generation unit, and a provision unit. The collection unit collects questions. The collection unit scrapes questions from websites and databases by setting predetermined keywords, for example. The collection unit can set keywords to collect questions related to a specific topic, for example. The collection unit can analyze the HTML structure of a website and extract questions, for example. The collection unit can obtain questions that match specific conditions from a database using queries, for example. The question processing unit processes the questions collected by the collection unit. The question processing unit can correct inconsistencies in the wording of questions, for example. The question processing unit can unify synonyms and correct spelling mistakes, for example. The question processing unit can analyze and standardize the grammatical structure of questions, for example. The question processing unit can generate variations of questions, for example. The question processing unit can ensure diversity in training data by performing synonym substitutions and grammatical structure changes, for example. The question processing unit can automatically generate variations of questions using a generation AI, for example. The generation unit generates answers based on the processing results of the question processing unit. The generation unit generates appropriate answers to questions, for example, using generation AI. The generation unit can, for example, search for relevant information based on the content of the question and generate answers. The generation unit can, for example, understand the context of the question and generate appropriate answers. The provision unit provides the answers generated by the generation unit. The provision unit can, for example, provide answers through web applications or mobile applications. The provision unit can, for example, provide answers using email or messaging apps. The provision unit can, for example, save answers in a database for later reference. As a result, the business support system according to the embodiment can efficiently perform tasks from question collection to answer provision.

[0030] The data collection unit collects questions. For example, the data collection unit scrapes questions from websites and databases by setting predetermined keywords. Specifically, the data collection unit analyzes the HTML structure of websites and extracts questions based on specific tags and class names. For example, if an element containing a question has a specific class name, the question can be extracted based on that class name. The data collection unit can also obtain questions using website APIs. By using APIs, data can be collected more efficiently and necessary information can be obtained quickly. Furthermore, the data collection unit can retrieve questions that match specific conditions from databases using queries. For example, it can use SQL queries to search for and retrieve questions containing specific keywords. By combining these methods, the data collection unit can collect questions from diverse sources and increase data comprehensiveness. The data collection unit centrally manages the collected questions and stores them in a database. This allows subsequent processing units to efficiently access and process the data. In addition, the data collection unit cleans and filters the collected data to ensure its quality. For example, it can improve data quality by deleting duplicate questions and excluding inappropriate questions. This enables the data collection unit to achieve efficient and high-quality data collection, thereby improving the overall system performance.

[0031] The question processing unit processes the questions collected by the collection unit. For example, the question processing unit corrects inconsistencies in question notation. Specifically, it uses natural language processing techniques to unify synonyms and correct spelling errors. For instance, it can maintain question consistency by referring to a dictionary database and unifying synonyms and related words. It can also automatically correct spelling errors using a spell checker. The question processing unit also analyzes and standardizes the grammatical structure of questions. For example, it uses dependency structure analysis to analyze the grammatical structure of questions and converts it into a standard format. This allows for an accurate understanding of the meaning of the questions and facilitates subsequent processing. Furthermore, the question processing unit generates variations of questions. For example, it can perform synonym substitutions and grammatical structure modifications to ensure diversity in training data. This enables the generative AI to handle a variety of questions. The question processing unit can also automatically generate variations of questions using the generative AI. For example, the generative AI uses a transformer model to generate diverse variations based on the input questions. This allows the question processing unit to process questions efficiently and with high accuracy, improving the overall system performance.

[0032] The generation unit generates answers based on the processing results from the question processing unit. The generation unit generates appropriate answers to questions, for example, using a generation AI. Specifically, the generation AI uses a transformer model or a large-scale language model (LLM) to understand the content of the question and generate an appropriate answer. For example, if the question is "What are the latest technology trends?", the generation AI searches for information on the latest technology trends and generates an appropriate answer. The generation unit uses information retrieval techniques to understand the context of the question and search for relevant information. For example, it searches relevant literature and databases based on the keywords of the question and obtains appropriate information. The generation unit generates an appropriate answer to the question based on the obtained information. The generation unit evaluates the quality of the generated answer and makes corrections as necessary. For example, if the generated answer is inappropriate, it runs the generation AI again to generate a more appropriate answer. In this way, the generation unit can provide high-quality answers to questions. Furthermore, the generation unit saves the generated answers to a database so that they can be referenced later. This allows for quick answers to the same question. Through these processes, the generation unit can achieve efficient and high-quality answer generation and improve the overall system performance.

[0033] The provider unit provides answers generated by the generator unit. The provider unit can provide answers through, for example, web applications or mobile applications. Specifically, when a user enters a question, the provider unit displays the answer retrieved from the generator unit in real time. In web applications, the answer is displayed visually through the user interface, making it easy for the user to understand. In mobile applications, answers can be provided quickly to the user using push notifications or in-app notifications. The provider unit can also provide answers via email or messaging apps. For example, when a user submits a question, the provider unit sends the answer retrieved from the generator unit to the user via email or messaging app. This allows the user to receive answers anytime, anywhere. The provider unit can also store answers in a database for later reference. For example, past questions and answers can be stored in a database for later reference. This allows for quicker responses to the same questions. Through these processes, the provider unit can provide users with quick and appropriate answers, improving the overall system performance. Furthermore, the provider unit can collect user feedback and continuously improve the quality and delivery method of the answers. For example, users can evaluate the responses provided, and the quality of the responses can be improved based on those evaluations. Furthermore, the service provider can reliably transmit information using multiple communication methods. This allows the service provider to provide responses to users quickly and reliably, improving the overall reliability of the system and user satisfaction.

[0034] The question processing unit can correct inconsistencies in the spelling of questions collected by the collection unit. For example, the question processing unit can unify synonyms and correct spelling errors. The question processing unit can also analyze and standardize the grammatical structure of questions. The question processing unit can also automatically correct inconsistencies in the spelling of questions using natural language processing techniques. This ensures consistency in the question data by correcting inconsistencies in the spelling of questions. Some or all of the above-described processes in the question processing unit may be performed using AI, for example, or without AI. For example, the question processing unit can input the collected question data into a generating AI and have the generating AI perform the correction of inconsistencies in spelling.

[0035] The question processing unit can generate variations of questions collected by the collection unit. The question processing unit can ensure diversity in the training data by, for example, substituting synonyms or changing grammatical structures. The question processing unit can also automatically generate variations of questions using, for example, a generative AI. The question processing unit can also generate variations of different expressions based on the content of the question. In this way, diversity in the training data can be ensured by generating variations of questions. Some or all of the above processing in the question processing unit may be performed using, for example, an AI, or without an AI. For example, the question processing unit can input the collected question data into a generative AI and have the generative AI perform the generation of variations.

[0036] The collection unit can set predetermined keywords and scrape questions from at least one website. The collection unit can set keywords, for example, to collect questions related to a specific topic. The collection unit can also, for example, analyze the HTML structure of a website and extract questions. The collection unit can also, for example, retrieve questions that match specific conditions from a database using queries. This allows for efficient question collection by setting predetermined keywords. Some or all of the above processing in the collection unit may be performed using AI, for example, or not using AI. For example, the collection unit can input predetermined keywords into a generating AI and have the generating AI perform question scraping.

[0037] The collection unit can analyze the user's past question history when collecting questions and select an appropriate collection method. For example, the collection unit may prioritize collecting topics that the user has frequently asked about in the past. The collection unit can also select a method for collecting questions at a specific time period based on the user's past question history. The collection unit can also analyze the user's past question history and suggest the most efficient collection method. This allows the optimal collection method to be selected by analyzing the user's past question history. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's past question history data into a generating AI and have the generating AI select the optimal collection method.

[0038] The collection unit can filter questions based on the user's current areas of interest when collecting them. For example, the collection unit can prioritize collecting questions related to topics the user is currently interested in. The collection unit can also filter out unnecessary questions based on the user's current areas of interest. The collection unit can also analyze the user's areas of interest in real time and collect the most relevant questions. This allows for the collection of highly relevant questions by filtering questions based on the user's current areas of interest. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input user area of ​​interest data into a generating AI and have the generating AI perform the filtering.

[0039] The collection unit can prioritize collecting questions that are highly relevant based on the user's geographical location information when collecting questions. For example, if the user is in a specific region, the collection unit will prioritize collecting questions related to that region. The collection unit can also filter region-specific questions based on the user's geographical location information. The collection unit can also collect the most relevant questions based on the user's current location. This allows for the priority collection of highly relevant questions by considering the user's geographical location information. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's geographical location data into a generating AI and have the generating AI collect highly relevant questions.

[0040] The collection unit can analyze the user's social media activity and collect relevant questions when collecting questions. For example, the collection unit can collect questions related to topics the user has shown interest in on social media. The collection unit can also analyze the user's social media activity and collect the most relevant questions. For example, the collection unit can collect the most relevant questions based on the user's social media posts. This allows for the collection of highly relevant questions by analyzing the user's social media activity. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's social media activity data into a generating AI and have the generating AI collect relevant questions.

[0041] The question processing unit can adjust the level of detail in processing questions based on their importance. For example, it may perform detailed processing on high-importance questions, or simplified processing on low-importance questions. The question processing unit can also determine processing priorities based on the importance of the questions. This allows for efficient question processing by adjusting the level of detail based on the importance of the questions. Some or all of the processing described above in the question processing unit may be performed using AI, or not. For example, the question processing unit can input question importance data into a generating AI and have the generating AI adjust the level of detail in processing.

[0042] The question processing unit can apply different processing algorithms depending on the category of the question when processing it. For example, the question processing unit can apply a specialized processing algorithm to technical questions. For example, the question processing unit can also apply a simplified processing algorithm to general questions. For example, the question processing unit can select the optimal processing algorithm depending on the category of the question. This allows for efficient question processing by applying the optimal processing algorithm according to the category of the question. Some or all of the processing described above in the question processing unit may be performed using AI, for example, or without AI. For example, the question processing unit can input question category data into a generating AI and have the generating AI execute the application of a processing algorithm.

[0043] The question processing unit can determine the processing priority based on when the question was submitted. For example, the question processing unit can determine the processing priority based on when the question was submitted. For example, the question processing unit can prioritize processing if the question was submitted earlier. For example, the question processing unit can process if the question was submitted more recently. This allows for efficient question processing by determining the processing priority based on when the question was submitted. Some or all of the above processing in the question processing unit may be performed using AI, for example, or without AI. For example, the question processing unit can input question submission time data into a generating AI and have the generating AI determine the processing priority.

[0044] The question processing unit can adjust the order of processing based on the relevance of the questions. For example, if a question is highly relevant, it will be processed preferentially. If a question is less relevant, it may be postponed. The question processing unit can also determine the optimal processing order based on the relevance of the questions. This allows for efficient question processing by adjusting the order of processing based on the relevance of the questions. Some or all of the above processing in the question processing unit may be performed using AI, for example, or without AI. For example, the question processing unit can input question relevance data into a generating AI and have the generating AI adjust the order of processing.

[0045] The generation unit can adjust the level of detail in the answers based on the importance of the questions when generating the answers. For example, the generation unit can generate detailed answers for high-importance questions. For example, the generation unit can also generate simplified answers for low-importance questions. The generation unit can also determine the priority of answers according to the importance of the questions. This allows for efficient answer generation by adjusting the level of detail in the answers based on the importance of the questions. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input question importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the answers.

[0046] The generation unit can apply different generation algorithms depending on the question category when generating answers. For example, the generation unit can apply a specialized generation algorithm to technical questions. For example, the generation unit can also apply a simplified generation algorithm to general questions. The generation unit can also select the optimal generation algorithm depending on the question category. This allows for efficient answer generation by applying the optimal generation algorithm according to the question category. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input question category data into a generation AI and have the generation AI execute the application of a generation algorithm.

[0047] The generation unit can determine the priority of answers based on when the questions were submitted when generating answers. For example, the generation unit can determine the priority of answers based on when the questions were submitted. For example, the generation unit can also prioritize generating answers if the questions were submitted earlier. For example, the generation unit can also quickly generate answers if the questions were submitted more recently. This allows for efficient answer generation by determining the priority of answers based on when the questions were submitted. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input question submission date data into a generation AI and have the generation AI perform the determination of answer priority.

[0048] The generation unit can adjust the order of answers based on the relevance of the questions when generating answers. For example, the generation unit will prioritize generating answers when the questions are highly relevant. For example, the generation unit may postpone generating answers when the questions are less relevant. The generation unit can also determine the optimal order of answers based on the relevance of the questions. This allows for efficient answer generation by adjusting the order of answers based on the relevance of the questions. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input question relevance data into a generation AI and have the generation AI perform the adjustment of the order of answers.

[0049] The service provider can select the optimal service method when providing answers by referring to the user's past question history. For example, the service provider may prioritize service methods that the user has frequently used in the past. The service provider may also suggest the optimal service method based on the user's past question history. The service provider may also analyze the user's past question history and select the most efficient service method. This allows the service provider to select the optimal service method by referring to the user's past question history. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider may input the user's past question history data into a generating AI and have the generating AI select the optimal service method.

[0050] The service provider can customize the means of providing answers based on the user's current areas of interest. For example, the service provider may prioritize providing answers related to topics the user is currently interested in. The service provider may also select the optimal means of providing answers based on the user's current areas of interest. For example, the service provider may analyze the user's areas of interest in real time and suggest the optimal means of providing answers. This allows for efficient answer provision by customizing the means of providing answers based on the user's current areas of interest. Some or all of the above-described processes in the service provider may be performed using AI, for example, or without AI. For example, the service provider may input user area of ​​interest data into a generating AI and have the generating AI perform the customization of the means of providing answers.

[0051] The service provider can select the optimal delivery method when providing answers, taking into account the user's geographical location information. For example, if the user is in a specific region, the service provider will prioritize providing answers relevant to that region. The service provider can also filter region-specific answers based on the user's geographical location information. The service provider can also select the optimal delivery method based on the user's current location. This allows the service provider to select the optimal delivery method by considering the user's geographical location information. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's geographical location data into a generating AI and have the generating AI select the optimal delivery method.

[0052] The service provider can analyze the user's social media activity and suggest a means of providing a response when providing a response. For example, the service provider can provide a response related to a topic the user has shown interest in on social media. The service provider can also analyze the user's social media activity and provide the most relevant response. The service provider can also suggest the optimal means of providing a response based on the user's social media posts. This allows the service provider to suggest the optimal means of providing a response by analyzing the user's social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's social media activity data into a generating AI and have the generating AI suggest a means of providing a response.

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

[0054] The business support system can also include a history analysis unit that analyzes the user's past question history. For example, the history analysis unit can identify topics that the user has frequently asked about in the past and prioritize the collection of questions related to those topics. The history analysis unit can also select a method for collecting data at specific time periods based on the user's past question history. Furthermore, the history analysis unit can analyze the user's past question history and propose the most efficient collection method. This allows for the selection of the optimal collection method by analyzing the user's past question history.

[0055] The question processing unit can adjust the level of detail in question processing based on the importance of the question. For example, it will perform detailed processing on high-importance questions. For example, it can perform simplified processing on low-importance questions. The question processing unit can also determine the processing priority based on the importance of the question. This allows for efficient question processing by adjusting the level of detail based on the importance of the question.

[0056] The collection unit can filter questions based on the user's current areas of interest during the collection process. For example, the collection unit can prioritize collecting questions related to topics the user is currently interested in. The collection unit can also filter out unnecessary questions based on the user's current areas of interest. For example, the collection unit can analyze the user's areas of interest in real time and collect the most relevant questions. This allows for the collection of highly relevant questions by filtering questions based on the user's current areas of interest.

[0057] The generation unit can adjust the level of detail in the answers based on the importance of the questions when generating responses. For example, it can generate detailed answers for high-importance questions. It can also generate simplified answers for low-importance questions. The generation unit can also determine the priority of answers based on the importance of the questions. This allows for efficient response generation by adjusting the level of detail based on the importance of the questions.

[0058] 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 prioritize delivery methods that the user has frequently used in the past. For example, the service provider can also suggest the optimal delivery method based on 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. In this way, the optimal delivery method can be selected by referring to the user's past question history.

[0059] The service provider can select the optimal delivery method when providing responses, taking into account the user's geographical location. For example, if the user is in a specific region, the service provider will prioritize providing responses relevant to that region. The service provider can also filter region-specific responses based on the user's geographical location. For example, the service provider can select the optimal delivery method based on the user's current location. This allows the service provider to select the optimal delivery method by considering the user's geographical location.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The collection unit collects questions. The collection unit scrapes questions from websites and databases by, for example, setting predetermined keywords. The collection unit can set keywords to collect questions related to a specific topic. The collection unit can, for example, analyze the HTML structure of a website and extract questions. The collection unit can, for example, retrieve questions that match specific conditions from a database using queries. Step 2: The question processing unit processes the questions collected by the collection unit. For example, the question processing unit corrects inconsistencies in the wording of questions. For example, the question processing unit can unify synonyms and correct spelling mistakes. For example, the question processing unit can analyze and standardize the grammatical structure of questions. For example, the question processing unit generates variations of questions. For example, the question processing unit can perform synonym substitutions and grammatical structure modifications to ensure diversity in the training data. For example, the question processing unit can automatically generate variations of questions using generative AI. Step 3: The generation unit generates an answer based on the processing results from the question processing unit. The generation unit generates an appropriate answer to the question, for example, using a generation AI. The generation unit can, for example, search for relevant information based on the content of the question and generate an answer. The generation unit can, for example, understand the context of the question and generate an appropriate answer. Step 4: The provider unit provides the responses generated by the generator unit. The provider unit can provide responses, for example, through a web application or a mobile application. The provider unit can provide responses, for example, using email or a messaging app. The provider unit can store the responses in a database for later reference.

[0062] (Example of form 2) The business support system according to an embodiment of the present invention is a system for streamlining business support for questions and answers (QA) using a chatbot. This business support system includes a collection unit for collecting questions, a question processing unit for processing questions, a generation unit for generating answers, and a provision unit for providing the generated answers. First, the collection unit sets predetermined keywords and scrapes questions from websites and databases. Next, the collected questions are processed by the question processing unit. The question processing unit corrects inconsistencies in the wording of the questions and automatically creates variations of question data for training using a generation AI. Furthermore, based on the processing results by the question processing unit, the generation unit generates answers. The generated answers are provided by the provision unit. This system makes it possible to make the chatbot usable with minimal human intervention. For example, the collection unit sets predetermined keywords and scrapes questions from websites and databases. Next, the collected questions are processed by the question processing unit. The question processing unit corrects inconsistencies in the wording of the questions and automatically creates variations of question data for training using a generation AI. Furthermore, based on the processing results by the question processing unit, the generation unit generates answers. The generated answers are provided by the provision unit. This system makes it possible to make chatbots available with minimal human intervention. As a result, business support systems can efficiently handle everything from collecting questions to providing answers.

[0063] The business support system according to this embodiment comprises a collection unit, a question processing unit, a generation unit, and a provision unit. The collection unit collects questions. The collection unit scrapes questions from websites and databases by setting predetermined keywords, for example. The collection unit can set keywords to collect questions related to a specific topic, for example. The collection unit can analyze the HTML structure of a website and extract questions, for example. The collection unit can obtain questions that match specific conditions from a database using queries, for example. The question processing unit processes the questions collected by the collection unit. The question processing unit can correct inconsistencies in the wording of questions, for example. The question processing unit can unify synonyms and correct spelling mistakes, for example. The question processing unit can analyze and standardize the grammatical structure of questions, for example. The question processing unit can generate variations of questions, for example. The question processing unit can ensure diversity in training data by performing synonym substitutions and grammatical structure changes, for example. The question processing unit can automatically generate variations of questions using a generation AI, for example. The generation unit generates answers based on the processing results of the question processing unit. The generation unit generates appropriate answers to questions, for example, using generation AI. The generation unit can, for example, search for relevant information based on the content of the question and generate answers. The generation unit can, for example, understand the context of the question and generate appropriate answers. The provision unit provides the answers generated by the generation unit. The provision unit can, for example, provide answers through web applications or mobile applications. The provision unit can, for example, provide answers using email or messaging apps. The provision unit can, for example, save answers in a database for later reference. As a result, the business support system according to the embodiment can efficiently perform tasks from question collection to answer provision.

[0064] The data collection unit collects questions. For example, the data collection unit scrapes questions from websites and databases by setting predetermined keywords. Specifically, the data collection unit analyzes the HTML structure of websites and extracts questions based on specific tags and class names. For example, if an element containing a question has a specific class name, the question can be extracted based on that class name. The data collection unit can also obtain questions using website APIs. By using APIs, data can be collected more efficiently and necessary information can be obtained quickly. Furthermore, the data collection unit can retrieve questions that match specific conditions from databases using queries. For example, it can use SQL queries to search for and retrieve questions containing specific keywords. By combining these methods, the data collection unit can collect questions from diverse sources and increase data comprehensiveness. The data collection unit centrally manages the collected questions and stores them in a database. This allows subsequent processing units to efficiently access and process the data. In addition, the data collection unit cleans and filters the collected data to ensure its quality. For example, it can improve data quality by deleting duplicate questions and excluding inappropriate questions. This enables the data collection unit to achieve efficient and high-quality data collection, thereby improving the overall system performance.

[0065] The question processing unit processes the questions collected by the collection unit. For example, the question processing unit corrects inconsistencies in question notation. Specifically, it uses natural language processing techniques to unify synonyms and correct spelling errors. For instance, it can maintain question consistency by referring to a dictionary database and unifying synonyms and related words. It can also automatically correct spelling errors using a spell checker. The question processing unit also analyzes and standardizes the grammatical structure of questions. For example, it uses dependency structure analysis to analyze the grammatical structure of questions and converts it into a standard format. This allows for an accurate understanding of the meaning of the questions and facilitates subsequent processing. Furthermore, the question processing unit generates variations of questions. For example, it can perform synonym substitutions and grammatical structure modifications to ensure diversity in training data. This enables the generative AI to handle a variety of questions. The question processing unit can also automatically generate variations of questions using the generative AI. For example, the generative AI uses a transformer model to generate diverse variations based on the input questions. This allows the question processing unit to process questions efficiently and with high accuracy, improving the overall system performance.

[0066] The generation unit generates answers based on the processing results from the question processing unit. The generation unit generates appropriate answers to questions, for example, using a generation AI. Specifically, the generation AI uses a transformer model or a large-scale language model (LLM) to understand the content of the question and generate an appropriate answer. For example, if the question is "What are the latest technology trends?", the generation AI searches for information on the latest technology trends and generates an appropriate answer. The generation unit uses information retrieval techniques to understand the context of the question and search for relevant information. For example, it searches relevant literature and databases based on the keywords of the question and obtains appropriate information. The generation unit generates an appropriate answer to the question based on the obtained information. The generation unit evaluates the quality of the generated answer and makes corrections as necessary. For example, if the generated answer is inappropriate, it runs the generation AI again to generate a more appropriate answer. In this way, the generation unit can provide high-quality answers to questions. Furthermore, the generation unit saves the generated answers to a database so that they can be referenced later. This allows for quick answers to the same question. Through these processes, the generation unit can achieve efficient and high-quality answer generation and improve the overall system performance.

[0067] The provider unit provides answers generated by the generator unit. The provider unit can provide answers through, for example, web applications or mobile applications. Specifically, when a user enters a question, the provider unit displays the answer retrieved from the generator unit in real time. In web applications, the answer is displayed visually through the user interface, making it easy for the user to understand. In mobile applications, answers can be provided quickly to the user using push notifications or in-app notifications. The provider unit can also provide answers via email or messaging apps. For example, when a user submits a question, the provider unit sends the answer retrieved from the generator unit to the user via email or messaging app. This allows the user to receive answers anytime, anywhere. The provider unit can also store answers in a database for later reference. For example, past questions and answers can be stored in a database for later reference. This allows for quicker responses to the same questions. Through these processes, the provider unit can provide users with quick and appropriate answers, improving the overall system performance. Furthermore, the provider unit can collect user feedback and continuously improve the quality and delivery method of the answers. For example, users can evaluate the responses provided, and the quality of the responses can be improved based on those evaluations. Furthermore, the service provider can reliably transmit information using multiple communication methods. This allows the service provider to provide responses to users quickly and reliably, improving the overall reliability of the system and user satisfaction.

[0068] The question processing unit can correct inconsistencies in the spelling of questions collected by the collection unit. For example, the question processing unit can unify synonyms and correct spelling errors. The question processing unit can also analyze and standardize the grammatical structure of questions. The question processing unit can also automatically correct inconsistencies in the spelling of questions using natural language processing techniques. This ensures consistency in the question data by correcting inconsistencies in the spelling of questions. Some or all of the above-described processes in the question processing unit may be performed using AI, for example, or without AI. For example, the question processing unit can input the collected question data into a generating AI and have the generating AI perform the correction of inconsistencies in spelling.

[0069] The question processing unit can generate variations of questions collected by the collection unit. The question processing unit can ensure diversity in the training data by, for example, substituting synonyms or changing grammatical structures. The question processing unit can also automatically generate variations of questions using, for example, a generative AI. The question processing unit can also generate variations of different expressions based on the content of the question. In this way, diversity in the training data can be ensured by generating variations of questions. Some or all of the above processing in the question processing unit may be performed using, for example, an AI, or without an AI. For example, the question processing unit can input the collected question data into a generative AI and have the generative AI perform the generation of variations.

[0070] The collection unit can set predetermined keywords and scrape questions from at least one website. The collection unit can set keywords, for example, to collect questions related to a specific topic. The collection unit can also, for example, analyze the HTML structure of a website and extract questions. The collection unit can also, for example, retrieve questions that match specific conditions from a database using queries. This allows for efficient question collection by setting predetermined keywords. Some or all of the above processing in the collection unit may be performed using AI, for example, or not using AI. For example, the collection unit can input predetermined keywords into a generating AI and have the generating AI perform question scraping.

[0071] The data collection unit can estimate the user's emotions and adjust the timing of question collection based on the estimated emotions. For example, if the user is stressed, the data collection unit can delay the collection timing and wait until the user is relaxed. If the user is relaxed, the data collection unit can collect questions immediately and process them efficiently. If the user is in a hurry, the data collection unit can speed up the collection timing to quickly collect questions. By adjusting the timing of question collection according to the user's emotions, user stress can be reduced. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's emotion data into a generative AI and have the generative AI perform emotion estimation.

[0072] The collection unit can analyze the user's past question history when collecting questions and select an appropriate collection method. For example, the collection unit may prioritize collecting topics that the user has frequently asked about in the past. The collection unit can also select a method for collecting questions at a specific time period based on the user's past question history. The collection unit can also analyze the user's past question history and suggest the most efficient collection method. This allows the optimal collection method to be selected by analyzing the user's past question history. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's past question history data into a generating AI and have the generating AI select the optimal collection method.

[0073] The collection unit can filter questions based on the user's current areas of interest when collecting them. For example, the collection unit can prioritize collecting questions related to topics the user is currently interested in. The collection unit can also filter out unnecessary questions based on the user's current areas of interest. The collection unit can also analyze the user's areas of interest in real time and collect the most relevant questions. This allows for the collection of highly relevant questions by filtering questions based on the user's current areas of interest. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input user area of ​​interest data into a generating AI and have the generating AI perform the filtering.

[0074] The data collection unit can estimate the user's emotions and determine the priority of questions to collect based on the estimated emotions. For example, if the user is stressed, the data collection unit may postpone less important questions. For example, if the user is relaxed, the data collection unit may prioritize collecting more important questions. For example, if the user is in a hurry, the data collection unit may prioritize collecting questions that require a quick answer. This allows for efficient question collection by prioritizing questions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0075] The collection unit can prioritize collecting questions that are highly relevant based on the user's geographical location information when collecting questions. For example, if the user is in a specific region, the collection unit will prioritize collecting questions related to that region. The collection unit can also filter region-specific questions based on the user's geographical location information. The collection unit can also collect the most relevant questions based on the user's current location. This allows for the priority collection of highly relevant questions by considering the user's geographical location information. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's geographical location data into a generating AI and have the generating AI collect highly relevant questions.

[0076] The collection unit can analyze the user's social media activity and collect relevant questions when collecting questions. For example, the collection unit can collect questions related to topics the user has shown interest in on social media. The collection unit can also analyze the user's social media activity and collect the most relevant questions. For example, the collection unit can collect the most relevant questions based on the user's social media posts. This allows for the collection of highly relevant questions by analyzing the user's social media activity. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's social media activity data into a generating AI and have the generating AI collect relevant questions.

[0077] The question processing unit can estimate the user's emotions and adjust the method of correcting inconsistencies in the question's wording based on the estimated emotions. For example, if the user is stressed, the question processing unit can perform simple corrections to correct inconsistencies. If the user is relaxed, for example, the question processing unit can also perform more detailed corrections to correct inconsistencies. If the user is in a hurry, for example, the question processing unit can also perform rapid corrections to correct inconsistencies. This allows for efficient question processing by adjusting the method of correcting inconsistencies according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the question processing unit may be performed using AI or not using AI. For example, the question processing unit can input user emotion data into a generative AI and have the generative AI adjust the method of correcting inconsistencies.

[0078] The question processing unit can adjust the level of detail in processing questions based on their importance. For example, it may perform detailed processing on high-importance questions, or simplified processing on low-importance questions. The question processing unit can also determine processing priorities based on the importance of the questions. This allows for efficient question processing by adjusting the level of detail based on the importance of the questions. Some or all of the processing described above in the question processing unit may be performed using AI, or not. For example, the question processing unit can input question importance data into a generating AI and have the generating AI adjust the level of detail in processing.

[0079] The question processing unit can apply different processing algorithms depending on the category of the question when processing it. For example, the question processing unit can apply a specialized processing algorithm to technical questions. For example, the question processing unit can also apply a simplified processing algorithm to general questions. For example, the question processing unit can select the optimal processing algorithm depending on the category of the question. This allows for efficient question processing by applying the optimal processing algorithm according to the category of the question. Some or all of the processing described above in the question processing unit may be performed using AI, for example, or without AI. For example, the question processing unit can input question category data into a generating AI and have the generating AI execute the application of a processing algorithm.

[0080] The question processing unit can estimate the user's emotions and adjust the method of generating variations of the question based on the estimated user emotions. For example, if the user is stressed, the question processing unit can generate simple variations. For example, if the user is relaxed, the question processing unit can also generate detailed variations. For example, if the user is in a hurry, the question processing unit can also generate variations quickly. This allows for efficient question processing by adjusting the method of generating variations according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the question processing unit may be performed using AI or not. For example, the question processing unit can input user emotion data into the generative AI and have the generative AI adjust the method of generating variations.

[0081] The question processing unit can determine the processing priority based on when the question was submitted. For example, the question processing unit can determine the processing priority based on when the question was submitted. For example, the question processing unit can prioritize processing if the question was submitted earlier. For example, the question processing unit can process if the question was submitted more recently. This allows for efficient question processing by determining the processing priority based on when the question was submitted. Some or all of the above processing in the question processing unit may be performed using AI, for example, or without AI. For example, the question processing unit can input question submission time data into a generating AI and have the generating AI determine the processing priority.

[0082] The question processing unit can adjust the order of processing based on the relevance of the questions. For example, if a question is highly relevant, it will be processed preferentially. If a question is less relevant, it may be postponed. The question processing unit can also determine the optimal processing order based on the relevance of the questions. This allows for efficient question processing by adjusting the order of processing based on the relevance of the questions. Some or all of the above processing in the question processing unit may be performed using AI, for example, or without AI. For example, the question processing unit can input question relevance data into a generating AI and have the generating AI adjust the order of processing.

[0083] The generation unit can estimate the user's emotions and adjust the response generation method based on the estimated user emotions. For example, if the user is stressed, the generation unit can generate a simple response. For example, if the user is relaxed, the generation unit can also generate a detailed response. For example, if the user is in a hurry, the generation unit can generate a response quickly. This allows for efficient response generation by adjusting the response generation method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, or not using AI. For example, the generation unit can input user emotion data into the generation AI and have the generation AI adjust the response generation method.

[0084] The generation unit can adjust the level of detail in the answers based on the importance of the questions when generating the answers. For example, the generation unit can generate detailed answers for high-importance questions. For example, the generation unit can also generate simplified answers for low-importance questions. The generation unit can also determine the priority of answers according to the importance of the questions. This allows for efficient answer generation by adjusting the level of detail in the answers based on the importance of the questions. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input question importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the answers.

[0085] The generation unit can apply different generation algorithms depending on the question category when generating answers. For example, the generation unit can apply a specialized generation algorithm to technical questions. For example, the generation unit can also apply a simplified generation algorithm to general questions. The generation unit can also select the optimal generation algorithm depending on the question category. This allows for efficient answer generation by applying the optimal generation algorithm according to the question category. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input question category data into a generation AI and have the generation AI execute the application of a generation algorithm.

[0086] The generation unit can estimate the user's emotions and adjust the length of the response based on the estimated emotions. For example, if the user is stressed, the generation unit can generate a short response. For example, if the user is relaxed, the generation unit can also generate a detailed response. For example, if the user is in a hurry, the generation unit can generate a quick response. This allows for efficient response generation by adjusting the length of the response according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using AI, or not using AI. For example, the generation unit can input user emotion data into the generation AI and have the generation AI adjust the length of the response.

[0087] The generation unit can determine the priority of answers based on when the questions were submitted when generating answers. For example, the generation unit can determine the priority of answers based on when the questions were submitted. For example, the generation unit can also prioritize generating answers if the questions were submitted earlier. For example, the generation unit can also quickly generate answers if the questions were submitted more recently. This allows for efficient answer generation by determining the priority of answers based on when the questions were submitted. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input question submission date data into a generation AI and have the generation AI perform the determination of answer priority.

[0088] The generation unit can adjust the order of answers based on the relevance of the questions when generating answers. For example, the generation unit will prioritize generating answers when the questions are highly relevant. For example, the generation unit may postpone generating answers when the questions are less relevant. The generation unit can also determine the optimal order of answers based on the relevance of the questions. This allows for efficient answer generation by adjusting the order of answers based on the relevance of the questions. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input question relevance data into a generation AI and have the generation AI perform the adjustment of the order of answers.

[0089] The service provider can estimate the user's emotions and adjust the method of providing responses based on the estimated emotions. For example, if the user is stressed, the service provider may select a simpler method of providing responses. If the user is relaxed, the service provider may select a more detailed method of providing responses. If the user is in a hurry, the service provider may provide responses quickly. This allows for efficient response provision by adjusting the method of providing responses according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the service provider may be performed using AI or not using AI. For example, the service provider can input user emotion data into a generative AI and have the generative AI adjust the method of providing responses.

[0090] The service provider can select the optimal service method when providing answers by referring to the user's past question history. For example, the service provider may prioritize service methods that the user has frequently used in the past. The service provider may also suggest the optimal service method based on the user's past question history. The service provider may also analyze the user's past question history and select the most efficient service method. This allows the service provider to select the optimal service method by referring to the user's past question history. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider may input the user's past question history data into a generating AI and have the generating AI select the optimal service method.

[0091] The service provider can customize the means of providing answers based on the user's current areas of interest. For example, the service provider may prioritize providing answers related to topics the user is currently interested in. The service provider may also select the optimal means of providing answers based on the user's current areas of interest. For example, the service provider may analyze the user's areas of interest in real time and suggest the optimal means of providing answers. This allows for efficient answer provision by customizing the means of providing answers based on the user's current areas of interest. Some or all of the above-described processes in the service provider may be performed using AI, for example, or without AI. For example, the service provider may input user area of ​​interest data into a generating AI and have the generating AI perform the customization of the means of providing answers.

[0092] The service provider can estimate the user's emotions and determine the priority of providing answers based on the estimated emotions. For example, if the user is stressed, the service provider may postpone less important answers. For example, if the user is relaxed, the service provider may prioritize providing more important answers. For example, if the user is in a hurry, the service provider may prioritize providing questions that require a quick answer. This allows for efficient answer provision by determining the priority of answers according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input user emotion data into a generative AI and have the generative AI determine the priority of answers.

[0093] The service provider can select the optimal delivery method when providing answers, taking into account the user's geographical location information. For example, if the user is in a specific region, the service provider will prioritize providing answers relevant to that region. The service provider can also filter region-specific answers based on the user's geographical location information. The service provider can also select the optimal delivery method based on the user's current location. This allows the service provider to select the optimal delivery method by considering the user's geographical location information. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's geographical location data into a generating AI and have the generating AI select the optimal delivery method.

[0094] The service provider can analyze the user's social media activity and suggest a means of providing a response when providing a response. For example, the service provider can provide a response related to a topic the user has shown interest in on social media. The service provider can also analyze the user's social media activity and provide the most relevant response. The service provider can also suggest the optimal means of providing a response based on the user's social media posts. This allows the service provider to suggest the optimal means of providing a response by analyzing the user's social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's social media activity data into a generating AI and have the generating AI suggest a means of providing a response.

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

[0096] The business support system can also include a history analysis unit that analyzes the user's past question history. For example, the history analysis unit can identify topics that the user has frequently asked about in the past and prioritize the collection of questions related to those topics. The history analysis unit can also select a method for collecting data at specific time periods based on the user's past question history. Furthermore, the history analysis unit can analyze the user's past question history and propose the most efficient collection method. This allows for the selection of the optimal collection method by analyzing the user's past question history.

[0097] The question processing unit can estimate the user's emotions and adjust the method of correcting inconsistencies in the question's wording based on the estimated emotions. For example, if the user is stressed, the question processing unit can perform simple corrections to correct inconsistencies. If the user is relaxed, for example, the question processing unit can perform more detailed corrections to correct inconsistencies. If the user is in a hurry, for example, the question processing unit can perform rapid corrections to correct inconsistencies. In this way, questions can be processed efficiently by adjusting the method of correcting inconsistencies according to the user's emotions.

[0098] The question processing unit can adjust the level of detail in question processing based on the importance of the question. For example, it will perform detailed processing on high-importance questions. For example, it can perform simplified processing on low-importance questions. The question processing unit can also determine the processing priority based on the importance of the question. This allows for efficient question processing by adjusting the level of detail based on the importance of the question.

[0099] The data collection unit can estimate the user's emotions and adjust the timing of question collection based on the estimated emotions. For example, if the user is stressed, the data collection unit can delay the collection timing and wait until the user is relaxed. If the user is relaxed, for example, the data collection unit can collect questions immediately and process them efficiently. If the user is in a hurry, for example, the data collection unit can speed up the collection timing to quickly collect questions. In this way, by adjusting the timing of question collection according to the user's emotions, user stress can be reduced.

[0100] The collection unit can filter questions based on the user's current areas of interest during the collection process. For example, the collection unit can prioritize collecting questions related to topics the user is currently interested in. The collection unit can also filter out unnecessary questions based on the user's current areas of interest. For example, the collection unit can analyze the user's areas of interest in real time and collect the most relevant questions. This allows for the collection of highly relevant questions by filtering questions based on the user's current areas of interest.

[0101] The generation unit can estimate the user's emotions and adjust the response generation method based on the estimated emotions. For example, if the user is stressed, the generation unit will generate a simple response. If the user is relaxed, for example, the generation unit can also generate a detailed response. If the user is in a hurry, for example, the generation unit can generate a quick response. This allows for efficient response generation by adjusting the response generation method according to the user's emotions.

[0102] The generation unit can adjust the level of detail in the answers based on the importance of the questions when generating responses. For example, it can generate detailed answers for high-importance questions. It can also generate simplified answers for low-importance questions. The generation unit can also determine the priority of answers based on the importance of the questions. This allows for efficient response generation by adjusting the level of detail based on the importance of the questions.

[0103] The system can estimate the user's emotions and adjust the method of providing answers based on those emotions. For example, if the user is stressed, the system might select a simpler method of providing answers. If the user is relaxed, for example, the system might select a more detailed method of providing answers. If the user is in a hurry, for example, the system might provide answers quickly. This allows for efficient answer delivery by adjusting the method of providing answers according to the user's emotions.

[0104] 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 prioritize delivery methods that the user has frequently used in the past. For example, the service provider can also suggest the optimal delivery method based on 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. In this way, the optimal delivery method can be selected by referring to the user's past question history.

[0105] The service provider can select the optimal delivery method when providing responses, taking into account the user's geographical location. For example, if the user is in a specific region, the service provider will prioritize providing responses relevant to that region. The service provider can also filter region-specific responses based on the user's geographical location. For example, the service provider can select the optimal delivery method based on the user's current location. This allows the service provider to select the optimal delivery method by considering the user's geographical location.

[0106] The following briefly describes the processing flow for example form 2.

[0107] Step 1: The collection unit collects questions. The collection unit scrapes questions from websites and databases by, for example, setting predetermined keywords. The collection unit can set keywords to collect questions related to a specific topic. The collection unit can, for example, analyze the HTML structure of a website and extract questions. The collection unit can, for example, retrieve questions that match specific conditions from a database using queries. Step 2: The question processing unit processes the questions collected by the collection unit. For example, the question processing unit corrects inconsistencies in the wording of questions. For example, the question processing unit can unify synonyms and correct spelling mistakes. For example, the question processing unit can analyze and standardize the grammatical structure of questions. For example, the question processing unit generates variations of questions. For example, the question processing unit can perform synonym substitutions and grammatical structure modifications to ensure diversity in the training data. For example, the question processing unit can automatically generate variations of questions using generative AI. Step 3: The generation unit generates an answer based on the processing results from the question processing unit. The generation unit generates an appropriate answer to the question, for example, using a generation AI. The generation unit can, for example, search for relevant information based on the content of the question and generate an answer. The generation unit can, for example, understand the context of the question and generate an appropriate answer. Step 4: The provider unit provides the responses generated by the generator unit. The provider unit can provide responses, for example, through a web application or a mobile application. The provider unit can provide responses, for example, using email or a messaging app. The provider unit can store the responses in a database for later reference.

[0108] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating 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.

[0109] 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.

[0110] 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.

[0111] For example, the data collection unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the question processing unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the data generation unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the data provision unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

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

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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).

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.).

[0124] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating 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.

[0125] 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.

[0126] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is 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.

[0127] For example, the data collection unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the question processing unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the data generation unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the data provision unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

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

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.).

[0140] 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.

[0141] 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.

[0142] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is 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.

[0143] For example, the data collection unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the question processing unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the data generation unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the data provision unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

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

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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).

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.).

[0157] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the 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.

[0158] 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.

[0159] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is 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.

[0160] For example, the data collection unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the question processing unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the data generation unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the data provision unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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."

[0167] 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.

[0168] 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.

[0169] 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.

[0170] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] (Note 1) The question collection department, A question processing unit that processes questions collected by the collection unit, A generation unit that generates an answer based on the processing result by the aforementioned question processing 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 question processing unit, Correct inconsistencies in the wording of questions collected by the aforementioned collection unit. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned question processing unit, The collection unit generates variations of the questions collected. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned collection unit is Set a set of keywords and scrape questions from at least one of the websites. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is We estimate the user's emotions and adjust the timing of question collection based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is When collecting questions, analyze the user's past question history to select the appropriate collection method. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is When collecting questions, filter them based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is The system estimates the user's emotions and prioritizes the questions to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting questions, the system prioritizes collecting questions that are highly relevant based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is When collecting questions, we analyze users' social media activity and gather relevant questions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned question processing unit, We estimate the user's sentiment and adjust the method for correcting inconsistencies in question wording based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned question processing unit, When processing questions, adjust the level of detail based on the importance of the question. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned question processing unit, When processing questions, different processing algorithms are applied depending on the question category. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned question processing unit, We estimate the user's emotions and adjust the method of generating question variations based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned question processing unit, When processing questions, the priority of processing is determined based on when the question was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned question processing unit, When processing questions, the order of processing is adjusted based on the relevance of the questions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is It estimates the user's emotions and adjusts the response generation method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) 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 19) 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 20) The generating unit is It estimates the user's emotions and adjusts the length of the response based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) 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 22) 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 23) The aforementioned supply unit is, We estimate the user's emotions and adjust how we provide responses based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) 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 25) The aforementioned supply unit is, When providing responses, customize the method of delivery based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, The system estimates the user's emotions and prioritizes the provision of responses based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When providing responses, the optimal method of delivery will be selected, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, When providing responses, we analyze the user's social media activity and suggest methods for providing them. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0180] 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 question collection department, A question processing unit that processes questions collected by the collection unit, A generation unit that generates an answer based on the processing result by the aforementioned question processing 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 question processing unit, Correct inconsistencies in the wording of questions collected by the aforementioned collection unit. The system according to feature 1.

3. The aforementioned question processing unit, The collection unit generates variations of the questions collected. The system according to feature 1.

4. The aforementioned collection unit is Set a set of keywords and scrape questions from at least one of the websites. The system according to feature 1.

5. The aforementioned collection unit is We estimate the user's emotions and adjust the timing of question collection based on the estimated user emotions. The system according to feature 1.

6. The aforementioned collection unit is When collecting questions, analyze the user's past question history to select the appropriate collection method. The system according to feature 1.

7. The aforementioned collection unit is When collecting questions, filter them based on the user's current areas of interest. The system according to feature 1.

8. The aforementioned collection unit is The system estimates the user's emotions and prioritizes the questions to collect based on those estimated emotions. The system according to feature 1.

Images