system

Abstract

The system according to this embodiment aims to accurately understand the needs of the other party and to articulate them in a multifaceted way. [Solution] The system according to the embodiment comprises a question generation unit, a collection unit, and an analysis unit. The question generation unit analyzes the content of what the other party says and generates appropriate questions. The collection unit collects the other party's needs based on the questions generated by the question generation unit. The analysis unit analyzes the information collected by the collection unit and verbalizes the other party's needs from multiple perspectives.

Description

Technical Field

[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, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to accurately grasp the needs of the other party and express them in a multi-faceted manner.

[0005] The system according to the embodiment aims to accurately grasp the needs of the other party and express them in a multi-faceted manner.

Means for Solving the Problems

[0006] The system according to the embodiment includes a question generation unit, a collection unit, and an analysis unit. The question generation unit analyzes the speech content of the other party and generates appropriate questions. The collection unit collects the needs of the other party based on the questions generated by the question generation unit. The analysis unit analyzes the information collected by the collection unit and expresses the needs of the other party in a multi-faceted manner. [Effects of the Invention]

[0007] The system according to this embodiment can accurately grasp the needs of the other party and articulate them from multiple perspectives. [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 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 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 counterparty needs visualization system according to the embodiment of the present invention is a powerful tool that revolutionizes communication in human relationships and business. This counterparty needs visualization system simplifies the process of understanding the other party's thoughts and needs, and utilizes advanced questioning techniques and analytical capabilities in situations where careful listening is required to articulate the other party's true feelings and genuine requests from multiple perspectives. It can be effectively used in all situations, such as business meetings, personal consultations, and customer service, and dramatically improves the quality of communication. For example, the counterparty needs visualization system uses advanced questioning techniques to understand the other party's needs. For example, in a business meeting, the counterparty needs visualization system analyzes what the other party says and generates appropriate questions. This makes it possible to elicit the other party's true feelings and genuine requests. Next, the counterparty needs visualization system analyzes the collected information and articulates the other party's needs from multiple perspectives. For example, in a customer service situation, the counterparty needs visualization system analyzes what the customer says and articulates the customer's needs specifically. This makes it possible to accurately understand the customer's requests and take appropriate action. Furthermore, the counterparty needs visualization system uses a multifaceted approach to make it easier for the other party to open up. For example, in personal consultations, the Needs Visualization System helps clients open up and fosters deeper understanding through unique and effective questioning. This builds trust and enables effective communication. This Needs Visualization System is available to a wide range of users, including companies, business professionals, counselors, life coaches, and general users. For instance, companies use it to understand customer needs and communicate effectively with business partners, while counselors and life coaches use it to understand clients' true feelings and needs. General users can also use it to deepen relationships with family and friends. By implementing this Needs Visualization System, it becomes possible to accurately understand clients' true feelings and needs even in situations where understanding needs is difficult, dramatically improving the quality of communication. It also reduces the time and cost required for thorough interviews, enabling highly accurate needs assessment through an efficient process.For example, in a business meeting, the needs visualization system can analyze what the other party says and generate appropriate questions, allowing you to understand their needs in a short amount of time. In this way, the needs visualization system is a powerful tool that revolutionizes interpersonal relationships and business communication, dramatically improving the quality of communication by verbalizing the other party's true feelings and genuine requests from multiple perspectives. As a result, the needs visualization system can accurately grasp the other party's true feelings and needs, dramatically improving the quality of communication.

[0029] The counterparty needs visualization system according to the embodiment comprises a question generation unit, a collection unit, and an analysis unit. The question generation unit analyzes the content of the counterparty's statements and generates appropriate questions. The question generation unit analyzes the content of the counterparty's statements using, for example, natural language processing technology and generates relevant questions. The question generation unit decomposes the content of the counterparty's statements using, for example, morphological analysis and performs grammatical analysis. The question generation unit can also understand the meaning of the content of the counterparty's statements using semantic analysis and generate appropriate questions. For example, the question generation unit analyzes the content of the counterparty's statements, extracts relevant keywords, and generates questions based on those keywords. The collection unit collects the counterparty's needs based on the questions generated by the question generation unit. The collection unit collects the content of the counterparty's statements in, for example, business meetings. The collection unit can collect the content of the counterparty's statements in, for example, meetings, presentations, and business negotiations. The collection unit can also collect the content of customer statements in customer service situations. For example, the collection unit collects the content of customer statements in customer support, sales, and after-sales service situations. The analysis unit analyzes the information collected by the collection unit and verbalizes the other party's needs from multiple perspectives. The analysis unit can, for example, use machine learning algorithms to analyze the collected information and extract the other party's needs. The analysis unit can analyze information using machine learning algorithms such as decision trees, neural networks, and support vector machines. Furthermore, the analysis unit can analyze the collected information from multiple perspectives and verbalize the other party's needs in concrete terms. For example, the analysis unit can analyze information using different data sources and apply multiple analysis methods to verbalize the other party's needs from multiple perspectives. As a result, the other party's needs visualization system according to this embodiment can improve the quality of communication by analyzing the content of the other party's statements, generating appropriate questions, collecting the other party's needs, and verbalizing them from multiple perspectives.

[0030] The question generation unit analyzes the content of the other party's statements and generates appropriate questions. For example, the question generation unit uses natural language processing techniques to analyze the content of the other party's statements and generate relevant questions. Specifically, it uses morphological analysis to break down the content of the other party's statements and performs grammatical analysis. Morphological analysis is a technique that breaks down a sentence into words and morphemes and identifies the part of speech and role of each. This allows the unit to understand the structure of the content of the other party's statements and generate grammatically correct questions. Furthermore, the question generation unit can also use semantic analysis to understand the meaning of the content of the content of the other party's statements and generate appropriate questions. Semantic analysis is a technique that understands the meaning of words and phrases and generates appropriate questions according to the context. For example, if the other party says, "I want to talk about a new project," the question generation unit can generate specific questions such as, "What kind of project is it?" or "What is the purpose of the project?" The question generation unit analyzes the content of the other party's statements, extracts relevant keywords, and generates questions based on those keywords. Keyword extraction is a technique that identifies important words and phrases from the content of the other party's statements and generates questions based on them. For example, if the other party says, "I'm thinking about a new marketing strategy," the question generation unit can generate questions such as, "What kind of strategy are you thinking about?" or "Where is your target market?" In this way, the question generation unit can deeply understand what the other party is saying and generate appropriate questions, thereby improving the quality of communication.

[0031] The data collection unit collects the needs of the other party based on questions generated by the question generation unit. For example, the data collection unit can collect the content of what the other party says in a business meeting. Specifically, it can collect the content of what the other party says in meetings, presentations, and business negotiations. The data collection unit uses speech recognition technology to transcribe what the other party says into text in real time and saves it to a database. Speech recognition technology is a technology that converts speech into text and can accurately record what the other party says. The data collection unit can also collect what the customer says in customer service situations. For example, it can collect what the customer says in customer support, sales, and after-sales service situations. The data collection unit collects what the customer says through communication methods such as chatbots, email, and telephone, and saves it to a database. This allows the data collection unit to collect what the other party says in a variety of situations and understand their needs. Furthermore, the data collection unit can centrally manage the collected data and link it with other systems and departments as needed. For example, the collected data can be stored on a cloud server and made accessible to the analysis unit. In addition, the data collection unit can adjust the frequency and accuracy of data collection to enable flexible responses to specific situations and conditions. This allows the data collection unit to collect data efficiently and effectively, improving the overall performance of the system.

[0032] The analysis unit analyzes the information collected by the data collection unit and verbalizes the client's needs from multiple perspectives. For example, the analysis unit can analyze the collected information using machine learning algorithms to extract the client's needs. Specifically, it can analyze information using machine learning algorithms such as decision trees, neural networks, and support vector machines. A decision tree is an algorithm that hierarchically divides data and performs classification or prediction based on the conditions at each node. A neural network is an algorithm that analyzes data using multi-layered artificial neurons and learns complex patterns. A support vector machine is an algorithm that performs classification and regression of data in high-dimensional space. By using these algorithms, the analysis unit can analyze the collected information from multiple perspectives and verbalize the client's needs concretely. For example, the analysis unit can analyze information using different data sources and apply multiple analysis methods to verbalize the client's needs from multiple perspectives. This allows the analysis unit to more accurately grasp the client's needs and formulate concrete proposals and countermeasures. Furthermore, the analysis unit can also utilize historical data and statistical information to analyze long-term fluctuations and trends in needs. For example, based on past customer data, the system can predict fluctuations in needs during specific seasons or events and formulate future countermeasures. Furthermore, the analysis unit can use anomaly detection algorithms to detect unusual patterns or abnormal data, issuing early warnings. This allows the analysis unit to not only understand the situation in real time but also to handle long-term needs management and anomaly detection, improving the overall reliability and security of the system.

[0033] The question generation unit can analyze the content of the other party's statements using natural language processing techniques and generate relevant questions. For example, the question generation unit can decompose the content of the other party's statements using morphological analysis and perform grammatical analysis. The question generation unit can also understand the meaning of the content of the other party's statements using semantic analysis and generate appropriate questions. For example, the question generation unit can analyze the content of the other party's statements, extract relevant keywords, and generate questions based on those keywords. In this way, by using natural language processing techniques, the content of the other party's statements can be analyzed more accurately and relevant questions can be generated. Natural language processing techniques include, but are not limited to, morphological analysis, grammatical analysis, and semantic analysis. Some or all of the above-described processes in the question generation unit may be performed using, for example, AI, or not using AI. For example, the question generation unit can input the content of the other party's statements into a generating AI, and the generating AI can generate relevant questions.

[0034] The data collection unit can collect the content of what the other party says during business meetings. For example, the data collection unit collects what the other party says in situations such as conferences, presentations, and business negotiations. For example, the data collection unit can automatically create meeting minutes and record the content of what was said. The data collection unit can also record the content of presentations and collect the content of what was said. For example, the data collection unit can record the content of business negotiations and collect the content of what was said. This allows for an accurate understanding of the other party's needs by collecting the content of what they say during business meetings. Business meetings include, but are not limited to, conferences, presentations, and business negotiations. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input meeting minutes into a generating AI, which can then collect the content of what was said.

[0035] The analysis unit can analyze the collected information using machine learning algorithms and extract the needs of the other party. For example, the analysis unit can analyze the information using a decision tree and extract the needs of the other party. For example, the analysis unit can also analyze the information using a neural network and extract the needs of the other party. For example, the analysis unit can analyze the information using a support vector machine and extract the needs of the other party. In this way, by using machine learning algorithms, the collected information can be analyzed more accurately and the needs of the other party can be extracted. Machine learning algorithms include, but are not limited to, decision trees, neural networks, and support vector machines. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the collected information into a generating AI, and the generating AI can extract the needs of the other party.

[0036] The data collection unit can collect customer statements in customer interaction situations. For example, the data collection unit can collect customer statements in customer support situations. For example, the data collection unit can record customer support phone calls and collect the statements. The data collection unit can also collect customer statements in sales situations. For example, the data collection unit can record conversations between salespeople and customers and collect the statements. The data collection unit can also collect customer statements in after-sales service situations. For example, the data collection unit can record after-sales service phone calls and collect the statements. By collecting customer statements in customer interaction situations, it is possible to accurately understand customer needs. Customer interaction situations include, but are not limited to, customer support, sales, and after-sales service. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input customer support phone calls into a generating AI, and the generating AI can collect the statements.

[0037] The analysis unit can analyze the collected information from multiple perspectives and articulate the client's needs in concrete terms. For example, the analysis unit can analyze information using different data sources and apply multiple analysis methods to articulate the client's needs from multiple perspectives. The analysis unit can analyze information using different data sources such as text data, audio data, and image data. Furthermore, the analysis unit can analyze information by applying multiple analysis methods and articulate the client's needs in concrete terms. For example, the analysis unit can analyze information by combining analysis methods such as text analysis, audio analysis, and image analysis. This allows for a deeper understanding by analyzing the collected information from multiple perspectives and articulating the client's needs in concrete terms. Specific methods and criteria for multifaceted analysis include, but are not limited to, the use of different data sources and the application of multiple analysis methods. Some or all of the above-described processes in the analysis unit may be performed using AI, or not. For example, the analysis unit can input the collected information into a generating AI, which can then articulate the client's needs in concrete terms.

[0038] The question generation unit can generate more specific and relevant questions by referring to the other party's past statements during question generation. For example, the question generation unit can generate specific follow-up questions based on opinions or requests previously expressed by the other party. The question generation unit can also smooth the flow of conversation by generating questions related to topics previously mentioned by the other party. For example, the question generation unit can extract themes of interest from the other party's past statements and generate questions related to those themes. This allows for the generation of more specific and relevant questions by referring to the other party's past statements. Past statements include, but are not limited to, past conversation logs and email content. Some or all of the above-described processes in the question generation unit may be performed using, for example, AI, or not. For example, the question generation unit can input the other party's past statements into a generating AI, which can then generate specific and relevant questions.

[0039] The question generation unit can adjust the difficulty of questions according to the recipient's level of expertise when generating questions. For example, if the recipient is an expert, the question generation unit will generate advanced questions that include technical terms. For example, if the recipient is a beginner, the question generation unit can also generate simple questions to confirm basic concepts. For example, the question generation unit can generate questions that gradually increase in difficulty according to the recipient's knowledge level. This allows for the generation of more appropriate questions by adjusting the difficulty of questions according to the recipient's level of expertise. The evaluation of expertise level includes, but is not limited to, qualifications, past statements, and work experience. Some or all of the above processing in the question generation unit may be performed using, for example, AI, or not using AI. For example, the question generation unit can input the recipient's level of expertise into a generating AI, which can then adjust the difficulty of the questions.

[0040] The question generation unit can generate appropriate questions by considering the cultural background of the other party when generating questions. For example, the question generation unit can generate questions using expressions and examples that are considerate of the other party's culture. For example, the question generation unit can generate carefully selected questions to avoid the other party's cultural taboos. For example, the question generation unit can generate empathetic questions based on the other party's cultural background. In this way, more appropriate questions can be generated by considering the other party's cultural background. Consideration of cultural background includes, but is not limited to, nationality, religion, and customs. Some or all of the above processing in the question generation unit may be performed using AI, for example, or without AI. For example, the question generation unit can input the other party's cultural background into a generating AI, and the generating AI can generate appropriate questions.

[0041] The question generation unit can customize questions based on the other party's current situation and environment. For example, if the other party is busy, the question generation unit will generate short, to-the-point questions. If the other party is relaxed, the question generation unit can also generate questions to elicit detailed information. For example, if the other party is in a specific location, the question generation unit will generate questions related to that location. By customizing questions based on the other party's current situation and environment, more effective communication becomes possible. Understanding the current situation and environment includes, but is not limited to, location, time, and surrounding circumstances. Some or all of the processing described above in the question generation unit may be performed using, for example, AI, or not using AI. For example, the question generation unit can input data on the other party's current situation and environment into a generating AI, which can then customize the questions.

[0042] The data collection unit can analyze the frequency and intervals of the other party's statements during collection to determine the optimal collection timing. For example, if the other party speaks frequently, the data collection unit can ask questions at appropriate intervals and collect the content of their statements. For example, if the other party speaks for a long time, the data collection unit can interject questions at appropriate times and collect the content of their statements. For example, if the other party makes repeated short statements, the data collection unit can ask questions consecutively and collect the content of their statements. By analyzing the frequency and intervals of the other party's statements, the optimal collection timing can be determined. Determining the optimal collection timing includes, but is not limited to, the frequency and intervals of statements and the other party's reactions. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input the other party's statement data into a generating AI, which can then determine the optimal collection timing.

[0043] The data collection unit can include the other party's nonverbal communication (gestures and facial expressions) as part of the data collection process. For example, the data collection unit can analyze the other party's facial expressions and collect changes in emotion. For example, the data collection unit can analyze the other party's gestures and collect their relevance to what they say. For example, the data collection unit can analyze the other party's eye movements and collect topics of interest. This allows for the collection of more multifaceted information by collecting the other party's nonverbal communication. The collection of nonverbal communication includes, but is not limited to, gestures, facial expressions, and posture. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the other party's nonverbal communication data into a generating AI, which can then collect the nonverbal communication.

[0044] The analysis unit can extract needs with greater accuracy by considering the context and background information of the other party's statements during analysis. For example, the analysis unit can analyze the context of the other party's statements and extract needs based on that context. The analysis unit can also extract relevant needs by considering the other party's background information (occupation, hobbies, etc.). For example, the analysis unit can analyze the tone and emotion of the other party's statements and extract true needs. This allows for more accurate needs extraction by considering the context and background information of the other party's statements. Consideration of context and background information includes, but is not limited to, preceding and succeeding statements and related events. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the other party's statement data into a generating AI, which can then extract needs while considering the context and background information.

[0045] The analysis unit can predict future needs by analyzing patterns and trends in the other party's statements during the analysis process. For example, the analysis unit can predict future needs by analyzing changes in the frequency and content of the other party's statements. The analysis unit can also predict future needs by analyzing trends in the other party's statements. For example, the analysis unit can predict potential needs by analyzing patterns in the other party's statements. In this way, future needs can be predicted by analyzing patterns and trends in the other party's statements. Analysis of statements and trends includes, but is not limited to, frequency analysis and time series analysis. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input the other party's statements into a generating AI, which can then analyze patterns and trends in statements to predict future needs.

[0046] The analysis unit can combine the content of the other party's statements with related external data (market data and trend information) during analysis. For example, the analysis unit can analyze the content of the other party's statements in comparison with market data to extract needs. The analysis unit can also predict future needs by combining the content of the other party's statements with trend information. For example, the analysis unit can integrate the content of the other party's statements with external data to extract more accurate needs. This allows for the extraction of more accurate needs by combining the content of the other party's statements with external data. External data includes, but is not limited to, market data, trend information, and statistical data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the other party's statement data and external data into a generating AI, which can then combine and analyze the two.

[0047] The analysis unit can extract common needs and requirements by comparing the content of one party's statements with the content of other parties' statements during analysis. For example, the analysis unit can compare the content of multiple parties' statements and extract common needs. The analysis unit can also extract common requirements by comparing the content of one party's statements with the content of other parties' statements. For example, the analysis unit can group the content of one party's statements and identify common needs. This allows the analysis unit to extract common needs and requirements by comparing the content of one party's statements with the content of other parties' statements. Extraction of common needs and requirements includes, but is not limited to, frequency analysis and clustering. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input the other party's statement data into a generating AI, which can then extract common needs and requirements by comparing it with the content of other parties' statements.

[0048] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0049] The analysis unit can evaluate the consistency of a statement by referring to the other party's past behavioral history when analyzing their statements. For example, it can check whether the current statement matches opinions the other party has expressed in the past. It can also determine whether the current statement is trustworthy based on the other party's past behavioral history. Furthermore, it can predict future behavior based on the other party's past behavioral history and evaluate the credibility of the statement. In this way, by referring to the other party's past behavioral history, the consistency of the statement can be evaluated and more accurate analysis results can be obtained.

[0050] The question generation unit can analyze the content of the other party's statements and generate questions while considering their cultural background and values. For example, if the other party belongs to a particular culture, it will generate questions that are considerate of that culture. It can also generate questions that demonstrate empathy based on the other party's values. Furthermore, it can generate questions that use appropriate examples and metaphors based on the other party's cultural background. In this way, by considering the other party's cultural background and values, it is possible to generate more appropriate questions and achieve more effective communication.

[0051] The analysis unit can evaluate the importance of a speaker's statements by analyzing the frequency and intervals between their remarks. For example, it can determine that statements frequently repeated by the speaker are likely to indicate important needs or requests. It can also evaluate that lengthy statements made by the speaker are important information requiring detailed explanation. Furthermore, if the speaker repeatedly makes short statements, it can determine that those statements are key points. By analyzing the frequency and intervals of the speaker's remarks, the importance of the statements can be evaluated, leading to more accurate analysis results.

[0052] The question generation unit can analyze the content of the other party's statements and adjust the difficulty of the questions according to the other party's level of expertise. For example, if the other party is an expert, it can generate advanced questions that include technical terms. If the other party is a beginner, it can also generate simple questions to confirm basic concepts. Furthermore, it can generate questions that gradually increase in difficulty according to the other party's level of knowledge. In this way, by adjusting the difficulty of questions according to the other party's level of expertise, it is possible to generate more appropriate questions.

[0053] The data collection unit can analyze the frequency and intervals of the other party's statements to determine the optimal timing for collection. For example, if the other party speaks frequently, it can ask questions at appropriate intervals to collect the content. If the other party speaks for extended periods, it can interject questions at appropriate times to collect the content. Furthermore, if the other party makes repeated short statements, it can ask questions consecutively to collect the content. In this way, by analyzing the frequency and intervals of the other party's statements, the optimal timing for collection can be determined.

[0054] The following briefly describes the processing flow for example form 1.

[0055] Step 1: The question generation unit analyzes the content of the other party's statement and generates appropriate questions. For example, it can use natural language processing techniques to analyze the content of the other party's statement and generate relevant questions. It can also use morphological analysis to break down the content of the other party's statement and perform grammatical analysis. Furthermore, it can use semantic analysis to understand the meaning of the content of the other party's statement and generate appropriate questions. For example, it can analyze the content of the other party's statement, extract relevant keywords, and generate questions based on those keywords. Step 2: The collection unit collects the other party's needs based on the questions generated by the question generation unit. For example, it collects the content of what the other party says in a business meeting. It can collect what the other party says in situations such as meetings, presentations, and business negotiations. It can also collect what the customer says in customer service situations. For example, it can collect what the customer says in situations such as customer support, sales, and after-sales service. Step 3: The analysis unit analyzes the information collected by the collection unit and verbalizes the client's needs from multiple perspectives. For example, it can analyze the collected information using machine learning algorithms to extract the client's needs. Machine learning algorithms such as decision trees, neural networks, and support vector machines can be used to analyze the information. It can also analyze the collected information from multiple perspectives and verbalize the client's needs in detail. For example, it can analyze the information using different data sources and apply multiple analysis methods to verbalize the client's needs from multiple perspectives.

[0056] (Example of form 2) The counterparty needs visualization system according to the embodiment of the present invention is a powerful tool that revolutionizes communication in human relationships and business. This counterparty needs visualization system simplifies the process of understanding the other party's thoughts and needs, and utilizes advanced questioning techniques and analytical capabilities in situations where careful listening is required to articulate the other party's true feelings and genuine requests from multiple perspectives. It can be effectively used in all situations, such as business meetings, personal consultations, and customer service, and dramatically improves the quality of communication. For example, the counterparty needs visualization system uses advanced questioning techniques to understand the other party's needs. For example, in a business meeting, the counterparty needs visualization system analyzes what the other party says and generates appropriate questions. This makes it possible to elicit the other party's true feelings and genuine requests. Next, the counterparty needs visualization system analyzes the collected information and articulates the other party's needs from multiple perspectives. For example, in a customer service situation, the counterparty needs visualization system analyzes what the customer says and articulates the customer's needs specifically. This makes it possible to accurately understand the customer's requests and take appropriate action. Furthermore, the counterparty needs visualization system uses a multifaceted approach to make it easier for the other party to open up. For example, in personal consultations, the Needs Visualization System helps clients open up and fosters deeper understanding through unique and effective questioning. This builds trust and enables effective communication. This Needs Visualization System is available to a wide range of users, including companies, business professionals, counselors, life coaches, and general users. For instance, companies use it to understand customer needs and communicate effectively with business partners, while counselors and life coaches use it to understand clients' true feelings and needs. General users can also use it to deepen relationships with family and friends. By implementing this Needs Visualization System, it becomes possible to accurately understand clients' true feelings and needs even in situations where understanding needs is difficult, dramatically improving the quality of communication. It also reduces the time and cost required for thorough interviews, enabling highly accurate needs assessment through an efficient process.For example, in a business meeting, the needs visualization system can analyze what the other party says and generate appropriate questions, allowing you to understand their needs in a short amount of time. In this way, the needs visualization system is a powerful tool that revolutionizes interpersonal relationships and business communication, dramatically improving the quality of communication by verbalizing the other party's true feelings and genuine requests from multiple perspectives. As a result, the needs visualization system can accurately grasp the other party's true feelings and needs, dramatically improving the quality of communication.

[0057] The counterparty needs visualization system according to the embodiment comprises a question generation unit, a collection unit, and an analysis unit. The question generation unit analyzes the content of the counterparty's statements and generates appropriate questions. The question generation unit analyzes the content of the counterparty's statements using, for example, natural language processing technology and generates relevant questions. The question generation unit decomposes the content of the counterparty's statements using, for example, morphological analysis and performs grammatical analysis. The question generation unit can also understand the meaning of the content of the counterparty's statements using semantic analysis and generate appropriate questions. For example, the question generation unit analyzes the content of the counterparty's statements, extracts relevant keywords, and generates questions based on those keywords. The collection unit collects the counterparty's needs based on the questions generated by the question generation unit. The collection unit collects the content of the counterparty's statements in, for example, business meetings. The collection unit can collect the content of the counterparty's statements in, for example, meetings, presentations, and business negotiations. The collection unit can also collect the content of customer statements in customer service situations. For example, the collection unit collects the content of customer statements in customer support, sales, and after-sales service situations. The analysis unit analyzes the information collected by the collection unit and verbalizes the other party's needs from multiple perspectives. The analysis unit can, for example, use machine learning algorithms to analyze the collected information and extract the other party's needs. The analysis unit can analyze information using machine learning algorithms such as decision trees, neural networks, and support vector machines. Furthermore, the analysis unit can analyze the collected information from multiple perspectives and verbalize the other party's needs in concrete terms. For example, the analysis unit can analyze information using different data sources and apply multiple analysis methods to verbalize the other party's needs from multiple perspectives. As a result, the other party's needs visualization system according to this embodiment can improve the quality of communication by analyzing the content of the other party's statements, generating appropriate questions, collecting the other party's needs, and verbalizing them from multiple perspectives.

[0058] The question generation unit analyzes the content of the other party's statements and generates appropriate questions. For example, the question generation unit uses natural language processing techniques to analyze the content of the other party's statements and generate relevant questions. Specifically, it uses morphological analysis to break down the content of the other party's statements and performs grammatical analysis. Morphological analysis is a technique that breaks down a sentence into words and morphemes and identifies the part of speech and role of each. This allows the unit to understand the structure of the content of the other party's statements and generate grammatically correct questions. Furthermore, the question generation unit can also use semantic analysis to understand the meaning of the content of the content of the other party's statements and generate appropriate questions. Semantic analysis is a technique that understands the meaning of words and phrases and generates appropriate questions according to the context. For example, if the other party says, "I want to talk about a new project," the question generation unit can generate specific questions such as, "What kind of project is it?" or "What is the purpose of the project?" The question generation unit analyzes the content of the other party's statements, extracts relevant keywords, and generates questions based on those keywords. Keyword extraction is a technique that identifies important words and phrases from the content of the other party's statements and generates questions based on them. For example, if the other party says, "I'm thinking about a new marketing strategy," the question generation unit can generate questions such as, "What kind of strategy are you thinking about?" or "Where is your target market?" In this way, the question generation unit can deeply understand what the other party is saying and generate appropriate questions, thereby improving the quality of communication.

[0059] The data collection unit collects the needs of the other party based on questions generated by the question generation unit. For example, the data collection unit can collect the content of what the other party says in a business meeting. Specifically, it can collect the content of what the other party says in meetings, presentations, and business negotiations. The data collection unit uses speech recognition technology to transcribe what the other party says into text in real time and saves it to a database. Speech recognition technology is a technology that converts speech into text and can accurately record what the other party says. The data collection unit can also collect what the customer says in customer service situations. For example, it can collect what the customer says in customer support, sales, and after-sales service situations. The data collection unit collects what the customer says through communication methods such as chatbots, email, and telephone, and saves it to a database. This allows the data collection unit to collect what the other party says in a variety of situations and understand their needs. Furthermore, the data collection unit can centrally manage the collected data and link it with other systems and departments as needed. For example, the collected data can be stored on a cloud server and made accessible to the analysis unit. In addition, the data collection unit can adjust the frequency and accuracy of data collection to enable flexible responses to specific situations and conditions. This allows the data collection unit to collect data efficiently and effectively, improving the overall performance of the system.

[0060] The analysis unit analyzes the information collected by the data collection unit and verbalizes the client's needs from multiple perspectives. For example, the analysis unit can analyze the collected information using machine learning algorithms to extract the client's needs. Specifically, it can analyze information using machine learning algorithms such as decision trees, neural networks, and support vector machines. A decision tree is an algorithm that hierarchically divides data and performs classification or prediction based on the conditions at each node. A neural network is an algorithm that analyzes data using multi-layered artificial neurons and learns complex patterns. A support vector machine is an algorithm that performs classification and regression of data in high-dimensional space. By using these algorithms, the analysis unit can analyze the collected information from multiple perspectives and verbalize the client's needs concretely. For example, the analysis unit can analyze information using different data sources and apply multiple analysis methods to verbalize the client's needs from multiple perspectives. This allows the analysis unit to more accurately grasp the client's needs and formulate concrete proposals and countermeasures. Furthermore, the analysis unit can also utilize historical data and statistical information to analyze long-term fluctuations and trends in needs. For example, based on past customer data, the system can predict fluctuations in needs during specific seasons or events and formulate future countermeasures. Furthermore, the analysis unit can use anomaly detection algorithms to detect unusual patterns or abnormal data, issuing early warnings. This allows the analysis unit to not only understand the situation in real time but also to handle long-term needs management and anomaly detection, improving the overall reliability and security of the system.

[0061] The question generation unit can analyze the content of the other party's statements using natural language processing techniques and generate relevant questions. For example, the question generation unit can decompose the content of the other party's statements using morphological analysis and perform grammatical analysis. The question generation unit can also understand the meaning of the content of the other party's statements using semantic analysis and generate appropriate questions. For example, the question generation unit can analyze the content of the other party's statements, extract relevant keywords, and generate questions based on those keywords. In this way, by using natural language processing techniques, the content of the other party's statements can be analyzed more accurately and relevant questions can be generated. Natural language processing techniques include, but are not limited to, morphological analysis, grammatical analysis, and semantic analysis. Some or all of the above-described processes in the question generation unit may be performed using, for example, AI, or not using AI. For example, the question generation unit can input the content of the other party's statements into a generating AI, and the generating AI can generate relevant questions.

[0062] The data collection unit can collect the content of what the other party says during business meetings. For example, the data collection unit collects what the other party says in situations such as conferences, presentations, and business negotiations. For example, the data collection unit can automatically create meeting minutes and record the content of what was said. The data collection unit can also record the content of presentations and collect the content of what was said. For example, the data collection unit can record the content of business negotiations and collect the content of what was said. This allows for an accurate understanding of the other party's needs by collecting the content of what they say during business meetings. Business meetings include, but are not limited to, conferences, presentations, and business negotiations. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input meeting minutes into a generating AI, which can then collect the content of what was said.

[0063] The analysis unit can analyze the collected information using machine learning algorithms and extract the needs of the other party. For example, the analysis unit can analyze the information using a decision tree and extract the needs of the other party. For example, the analysis unit can also analyze the information using a neural network and extract the needs of the other party. For example, the analysis unit can analyze the information using a support vector machine and extract the needs of the other party. In this way, by using machine learning algorithms, the collected information can be analyzed more accurately and the needs of the other party can be extracted. Machine learning algorithms include, but are not limited to, decision trees, neural networks, and support vector machines. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the collected information into a generating AI, and the generating AI can extract the needs of the other party.

[0064] The data collection unit can collect customer statements in customer interaction situations. For example, the data collection unit can collect customer statements in customer support situations. For example, the data collection unit can record customer support phone calls and collect the statements. The data collection unit can also collect customer statements in sales situations. For example, the data collection unit can record conversations between salespeople and customers and collect the statements. The data collection unit can also collect customer statements in after-sales service situations. For example, the data collection unit can record after-sales service phone calls and collect the statements. By collecting customer statements in customer interaction situations, it is possible to accurately understand customer needs. Customer interaction situations include, but are not limited to, customer support, sales, and after-sales service. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input customer support phone calls into a generating AI, and the generating AI can collect the statements.

[0065] The analysis unit can analyze the collected information from multiple perspectives and articulate the client's needs in concrete terms. For example, the analysis unit can analyze information using different data sources and apply multiple analysis methods to articulate the client's needs from multiple perspectives. The analysis unit can analyze information using different data sources such as text data, audio data, and image data. Furthermore, the analysis unit can analyze information by applying multiple analysis methods and articulate the client's needs in concrete terms. For example, the analysis unit can analyze information by combining analysis methods such as text analysis, audio analysis, and image analysis. This allows for a deeper understanding by analyzing the collected information from multiple perspectives and articulating the client's needs in concrete terms. Specific methods and criteria for multifaceted analysis include, but are not limited to, the use of different data sources and the application of multiple analysis methods. Some or all of the above-described processes in the analysis unit may be performed using AI, or not. For example, the analysis unit can input the collected information into a generating AI, which can then articulate the client's needs in concrete terms.

[0066] The question generation unit can estimate the other party's emotions and adjust the tone and format of the question based on the estimated emotions. For example, if the other party is nervous, the question generation unit can generate a question in a gentle tone to help them relax. For example, if the other party is excited, the question generation unit can generate a question in a calm tone to help them calm down. For example, if the other party is tired, the question generation unit can generate a question in a concise and easy-to-understand format. This allows for more effective communication by adjusting the tone and format of the question based on the other party's emotions. The estimation of the other party's emotions is achieved using an emotion estimation function, for example, using 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 generation unit may be performed using AI, for example, or not using AI. For example, the question generation unit can input the other party's emotion data into the generative AI, which can then adjust the tone and format of the question.

[0067] The question generation unit can generate more specific and relevant questions by referring to the other party's past statements during question generation. For example, the question generation unit can generate specific follow-up questions based on opinions or requests previously expressed by the other party. The question generation unit can also smooth the flow of conversation by generating questions related to topics previously mentioned by the other party. For example, the question generation unit can extract themes of interest from the other party's past statements and generate questions related to those themes. This allows for the generation of more specific and relevant questions by referring to the other party's past statements. Past statements include, but are not limited to, past conversation logs and email content. Some or all of the above-described processes in the question generation unit may be performed using, for example, AI, or not. For example, the question generation unit can input the other party's past statements into a generating AI, which can then generate specific and relevant questions.

[0068] The question generation unit can adjust the difficulty of questions according to the recipient's level of expertise when generating questions. For example, if the recipient is an expert, the question generation unit will generate advanced questions that include technical terms. For example, if the recipient is a beginner, the question generation unit can also generate simple questions to confirm basic concepts. For example, the question generation unit can generate questions that gradually increase in difficulty according to the recipient's knowledge level. This allows for the generation of more appropriate questions by adjusting the difficulty of questions according to the recipient's level of expertise. The evaluation of expertise level includes, but is not limited to, qualifications, past statements, and work experience. Some or all of the above processing in the question generation unit may be performed using, for example, AI, or not using AI. For example, the question generation unit can input the recipient's level of expertise into a generating AI, which can then adjust the difficulty of the questions.

[0069] The question generation unit can estimate the other party's emotions and adjust the order of questions based on the estimated emotions. For example, if the other party is nervous, the question generation unit may start with easy questions to help them relax. For example, if the other party is excited, the question generation unit may postpone important questions to help them calm down. For example, if the other party is tired, the question generation unit may ask the most important questions first and then ask lighter questions later. By adjusting the order of questions based on the other party's emotions, more effective communication becomes possible. The estimation of the other party's emotions 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, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the question generation unit may be performed using AI, or not using AI. For example, the question generation unit can input the other party's emotion data into the generative AI, which can then adjust the order of questions.

[0070] The question generation unit can generate appropriate questions by considering the cultural background of the other party when generating questions. For example, the question generation unit can generate questions using expressions and examples that are considerate of the other party's culture. For example, the question generation unit can generate carefully selected questions to avoid the other party's cultural taboos. For example, the question generation unit can generate empathetic questions based on the other party's cultural background. In this way, more appropriate questions can be generated by considering the other party's cultural background. Consideration of cultural background includes, but is not limited to, nationality, religion, and customs. Some or all of the above processing in the question generation unit may be performed using AI, for example, or without AI. For example, the question generation unit can input the other party's cultural background into a generating AI, and the generating AI can generate appropriate questions.

[0071] The question generation unit can customize questions based on the other party's current situation and environment. For example, if the other party is busy, the question generation unit will generate short, to-the-point questions. If the other party is relaxed, the question generation unit can also generate questions to elicit detailed information. For example, if the other party is in a specific location, the question generation unit will generate questions related to that location. By customizing questions based on the other party's current situation and environment, more effective communication becomes possible. Understanding the current situation and environment includes, but is not limited to, location, time, and surrounding circumstances. Some or all of the processing described above in the question generation unit may be performed using, for example, AI, or not using AI. For example, the question generation unit can input data on the other party's current situation and environment into a generating AI, which can then customize the questions.

[0072] The collection unit can estimate the other party's emotions and adjust the method of collecting the content of their statements based on the estimated emotions. For example, if the other party is nervous, the collection unit can ask questions in a calm tone to help them relax and collect their statements. For example, if the other party is excited, the collection unit can ask questions in a calm tone to help them calm down and collect their statements. For example, if the other party is tired, the collection unit can ask questions in a concise and easy-to-understand format and collect their statements. By adjusting the method of collecting the content of their statements based on the other party's emotions, more accurate information can be collected. The estimation of the other party's emotions is achieved using an emotion estimation function, for example, using 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 collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the other party's emotion data into the generative AI, which can then adjust the method of collecting the content of their statements.

[0073] The data collection unit can analyze the frequency and intervals of the other party's statements during collection to determine the optimal collection timing. For example, if the other party speaks frequently, the data collection unit can ask questions at appropriate intervals and collect the content of their statements. For example, if the other party speaks for a long time, the data collection unit can interject questions at appropriate times and collect the content of their statements. For example, if the other party makes repeated short statements, the data collection unit can ask questions consecutively and collect the content of their statements. By analyzing the frequency and intervals of the other party's statements, the optimal collection timing can be determined. Determining the optimal collection timing includes, but is not limited to, the frequency and intervals of statements and the other party's reactions. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input the other party's statement data into a generating AI, which can then determine the optimal collection timing.

[0074] The data collection unit can estimate the other party's emotions and determine the priority of information to collect based on the estimated emotions. For example, if the other party is tense, the data collection unit may prioritize collecting information important to help them relax. For example, if the other party is excited, the data collection unit may postpone collecting important information to help them calm down. For example, if the other party is tired, the data collection unit may collect the most important information first and then less important information later. This allows for the priority of collecting more important information by determining the priority of information to collect based on the other party's emotions. The estimation of the other party's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The 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 not using AI. For example, the data collection unit can input the other party's emotion data into the generative AI and determine the priority of information to collect by the generative AI.

[0075] The data collection unit can include the other party's nonverbal communication (gestures and facial expressions) as part of the data collection process. For example, the data collection unit can analyze the other party's facial expressions and collect changes in emotion. For example, the data collection unit can analyze the other party's gestures and collect their relevance to what they say. For example, the data collection unit can analyze the other party's eye movements and collect topics of interest. This allows for the collection of more multifaceted information by collecting the other party's nonverbal communication. The collection of nonverbal communication includes, but is not limited to, gestures, facial expressions, and posture. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the other party's nonverbal communication data into a generating AI, which can then collect the nonverbal communication.

[0076] The analysis unit can estimate the other party's emotions and adjust the perspective and method of analysis based on the estimated emotions. For example, if the other party is tense, the analysis unit can perform the analysis from a calm perspective to help them relax. For example, if the other party is excited, the analysis unit can perform the analysis from a calm perspective to help them calm down. For example, if the other party is tired, the analysis unit can perform the analysis from a concise and easy-to-understand perspective. By adjusting the perspective and method of analysis based on the other party's emotions, more accurate analysis results can be obtained. The estimation of the other party's emotions is achieved using an emotion estimation function, for example, using 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 analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the other party's emotion data into the generative AI, which can then adjust the perspective and method of analysis.

[0077] The analysis unit can extract needs with greater accuracy by considering the context and background information of the other party's statements during analysis. For example, the analysis unit can analyze the context of the other party's statements and extract needs based on that context. The analysis unit can also extract relevant needs by considering the other party's background information (occupation, hobbies, etc.). For example, the analysis unit can analyze the tone and emotion of the other party's statements and extract true needs. This allows for more accurate needs extraction by considering the context and background information of the other party's statements. Consideration of context and background information includes, but is not limited to, preceding and succeeding statements and related events. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the other party's statement data into a generating AI, which can then extract needs while considering the context and background information.

[0078] The analysis unit can predict future needs by analyzing patterns and trends in the other party's statements during the analysis process. For example, the analysis unit can predict future needs by analyzing changes in the frequency and content of the other party's statements. The analysis unit can also predict future needs by analyzing trends in the other party's statements. For example, the analysis unit can predict potential needs by analyzing patterns in the other party's statements. In this way, future needs can be predicted by analyzing patterns and trends in the other party's statements. Analysis of statements and trends includes, but is not limited to, frequency analysis and time series analysis. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input the other party's statements into a generating AI, which can then analyze patterns and trends in statements to predict future needs.

[0079] The analysis unit can estimate the other party's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the other party is tense, the analysis unit can provide a calm display method to help them relax. For example, if the other party is excited, the analysis unit can also provide a calm display method to help them calm down. For example, if the other party is tired, the analysis unit can provide a concise and easy-to-understand display method. By adjusting the display method of the analysis results based on the other party's emotions, a more appropriate display becomes possible. The estimation of the other party's emotions is achieved using an emotion estimation function, for example, using 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 analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the other party's emotion data into the generative AI, and the generative AI can adjust the display method of the analysis results.

[0080] The analysis unit can combine the content of the other party's statements with related external data (market data and trend information) during analysis. For example, the analysis unit can analyze the content of the other party's statements in comparison with market data to extract needs. The analysis unit can also predict future needs by combining the content of the other party's statements with trend information. For example, the analysis unit can integrate the content of the other party's statements with external data to extract more accurate needs. This allows for the extraction of more accurate needs by combining the content of the other party's statements with external data. External data includes, but is not limited to, market data, trend information, and statistical data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the other party's statement data and external data into a generating AI, which can then combine and analyze the two.

[0081] The analysis unit can extract common needs and requirements by comparing the content of one party's statements with the content of other parties' statements during analysis. For example, the analysis unit can compare the content of multiple parties' statements and extract common needs. The analysis unit can also extract common requirements by comparing the content of one party's statements with the content of other parties' statements. For example, the analysis unit can group the content of one party's statements and identify common needs. This allows the analysis unit to extract common needs and requirements by comparing the content of one party's statements with the content of other parties' statements. Extraction of common needs and requirements includes, but is not limited to, frequency analysis and clustering. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input the other party's statement data into a generating AI, which can then extract common needs and requirements by comparing it with the content of other parties' statements.

[0082] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0083] The question generation unit can analyze what the other person is saying and generate questions while taking into account their tone of voice and speaking speed. For example, if the other person is speaking quickly, the question generation unit will generate quick questions that match their pace. Conversely, if the other person is speaking slowly, the question generation unit can generate more detailed and in-depth questions. Also, if the other person's tone of voice is high, the question generation unit can consider the possibility that the other person is excited and generate questions to calm them down. By adjusting questions based on the other person's tone of voice and speaking speed, more effective communication becomes possible.

[0084] The data collection unit can analyze the other party's gestures and facial expressions when collecting their statements to evaluate the credibility of what they say. For example, if the other party frequently looks away while speaking, the data collection unit may determine that what they say lacks credibility. Also, if the other party is smiling while speaking, the data collection unit may evaluate that what they say is based on positive emotions. Furthermore, if the other party is making gestures that indicate tension, the data collection unit may determine that what they say has been carefully chosen. In this way, by analyzing the other party's nonverbal communication, the credibility of what they say can be evaluated and more accurate information can be collected.

[0085] The analysis unit can evaluate the consistency of a statement by referring to the other party's past behavioral history when analyzing their statements. For example, it can check whether the current statement matches opinions the other party has expressed in the past. It can also determine whether the current statement is trustworthy based on the other party's past behavioral history. Furthermore, it can predict future behavior based on the other party's past behavioral history and evaluate the credibility of the statement. In this way, by referring to the other party's past behavioral history, the consistency of the statement can be evaluated and more accurate analysis results can be obtained.

[0086] The question generation unit can analyze the content of the other party's statements and generate questions while considering their cultural background and values. For example, if the other party belongs to a particular culture, it will generate questions that are considerate of that culture. It can also generate questions that demonstrate empathy based on the other party's values. Furthermore, it can generate questions that use appropriate examples and metaphors based on the other party's cultural background. In this way, by considering the other party's cultural background and values, it is possible to generate more appropriate questions and achieve more effective communication.

[0087] The data collection unit can estimate the other party's emotions when collecting their statements and adjust the collection method based on that estimation. For example, if the other party is nervous, the data collection unit can ask questions in a calm tone to help them relax and collect their statements. If the other party is excited, it can ask questions in a calm tone to help them calm down and collect their statements. Furthermore, if the other party is tired, it can ask questions in a concise and easy-to-understand format and collect their statements. By adjusting the collection method based on the other party's emotions, more accurate information can be collected.

[0088] The analysis unit can evaluate the importance of a speaker's statements by analyzing the frequency and intervals between their remarks. For example, it can determine that statements frequently repeated by the speaker are likely to indicate important needs or requests. It can also evaluate that lengthy statements made by the speaker are important information requiring detailed explanation. Furthermore, if the speaker repeatedly makes short statements, it can determine that those statements are key points. By analyzing the frequency and intervals of the speaker's remarks, the importance of the statements can be evaluated, leading to more accurate analysis results.

[0089] The question generation unit can analyze the content of the other party's statements and adjust the difficulty of the questions according to the other party's level of expertise. For example, if the other party is an expert, it can generate advanced questions that include technical terms. If the other party is a beginner, it can also generate simple questions to confirm basic concepts. Furthermore, it can generate questions that gradually increase in difficulty according to the other party's level of knowledge. In this way, by adjusting the difficulty of questions according to the other party's level of expertise, it is possible to generate more appropriate questions.

[0090] The analysis unit can estimate the other party's emotions when analyzing what they say, and adjust the perspective and method of analysis based on those estimated emotions. For example, if the other party is nervous, the analysis can be performed from a calm perspective to help them relax. If the other party is excited, the analysis can be performed from a calm perspective to help them calm down. Furthermore, if the other party is tired, the analysis can be performed from a concise and easy-to-understand perspective. By adjusting the perspective and method of analysis based on the other party's emotions, more accurate analysis results can be obtained.

[0091] The data collection unit can analyze the frequency and intervals of the other party's statements to determine the optimal timing for collection. For example, if the other party speaks frequently, it can ask questions at appropriate intervals to collect the content. If the other party speaks for extended periods, it can interject questions at appropriate times to collect the content. Furthermore, if the other party makes repeated short statements, it can ask questions consecutively to collect the content. In this way, by analyzing the frequency and intervals of the other party's statements, the optimal timing for collection can be determined.

[0092] The analysis unit can estimate the other party's emotions when analyzing what they say, and adjust the display method of the analysis results based on the estimated emotions. For example, if the other party is nervous, it can provide a calm display method to help them relax. If the other party is excited, it can provide a calm display method to help them calm down. Furthermore, if the other party is tired, it can provide a concise and easy-to-understand display method. In this way, by adjusting the display method of the analysis results based on the other party's emotions, a more appropriate display becomes possible.

[0093] The following briefly describes the processing flow for example form 2.

[0094] Step 1: The question generation unit analyzes the content of the other party's statement and generates appropriate questions. For example, it can use natural language processing techniques to analyze the content of the other party's statement and generate relevant questions. It can also use morphological analysis to break down the content of the other party's statement and perform grammatical analysis. Furthermore, it can use semantic analysis to understand the meaning of the content of the other party's statement and generate appropriate questions. For example, it can analyze the content of the other party's statement, extract relevant keywords, and generate questions based on those keywords. Step 2: The collection unit collects the other party's needs based on the questions generated by the question generation unit. For example, it collects the content of what the other party says in a business meeting. It can collect what the other party says in situations such as meetings, presentations, and business negotiations. It can also collect what the customer says in customer service situations. For example, it can collect what the customer says in situations such as customer support, sales, and after-sales service. Step 3: The analysis unit analyzes the information collected by the collection unit and verbalizes the client's needs from multiple perspectives. For example, it can analyze the collected information using machine learning algorithms to extract the client's needs. Machine learning algorithms such as decision trees, neural networks, and support vector machines can be used to analyze the information. It can also analyze the collected information from multiple perspectives and verbalize the client's needs in detail. For example, it can analyze the information using different data sources and apply multiple analysis methods to verbalize the client's needs from multiple perspectives.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] Each of the multiple elements described above, including the question generation unit, collection unit, and analysis unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the question generation unit is implemented by the processor 46 of the smart device 14, which analyzes the content of the other party's statements and generates appropriate questions. The collection unit collects the content of the other party's statements using the camera 42 and microphone 38B of the smart device 14. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, which analyzes the collected information and verbalizes the other party's needs from multiple perspectives. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0099] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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).

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] Each of the multiple elements described above, including the question generation unit, collection unit, and analysis unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the question generation unit is implemented by the processor 46 of the smart glasses 214, which analyzes the content of the other party's statements and generates appropriate questions. The collection unit collects the content of the other party's statements using the camera 42 and microphone 238 of the smart glasses 214. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, which analyzes the collected information and verbalizes the other party's needs from multiple perspectives. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0115] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] Each of the multiple elements described above, including the question generation unit, collection unit, and analysis unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the question generation unit is implemented by the processor 46 of the headset terminal 314, which analyzes the content of the other party's statements and generates appropriate questions. The collection unit collects the content of the other party's statements using the camera 42 and microphone 238 of the headset terminal 314. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, which analyzes the collected information and verbalizes the other party's needs from multiple perspectives. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0131] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] Each of the multiple elements described above, including the question generation unit, collection unit, and analysis unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the question generation unit is implemented by the processor 46 of the robot 414, which analyzes the content of the other party's statements and generates appropriate questions. The collection unit collects the content of the other party's statements using the camera 42 and microphone 238 of the robot 414. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, which analyzes the collected information and verbalizes the other party's needs from multiple perspectives. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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."

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] (Note 1) A question generation unit analyzes the content of the other party's statements and generates appropriate questions, A collection unit collects the needs of the other party based on the questions generated by the question generation unit, The system includes an analysis unit that analyzes the information collected by the collection unit and verbalizes the other party's needs from multiple perspectives. A system characterized by the following features. (Note 2) The aforementioned question generation unit, Using natural language processing techniques, we analyze what the other person says and generate related questions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned collection unit is Collect information about what the other party says during a business meeting. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned analysis unit, We analyze the information collected using machine learning algorithms to extract the customer's needs. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is Collect the content of what the customer says during customer service interactions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, The collected information is analyzed from multiple perspectives, and the client's needs are articulated in concrete terms. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned question generation unit, Infer the other person's emotions and adjust the tone and format of the questions based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned question generation unit, When generating questions, the system references the other person's past statements to create more specific and relevant questions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned question generation unit, When generating questions, adjust the difficulty level of the questions according to the recipient's level of expertise. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned question generation unit, Infer the other person's emotions and adjust the order of questions based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned question generation unit, When generating questions, consider the cultural background of the other person to generate appropriate questions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned question generation unit, When generating a question, customize it based on the other person's current situation and environment. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is We estimate the other person's emotions and adjust the method of collecting their statements based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned collection unit is During data collection, the frequency and intervals of the other party's statements are analyzed to determine the optimal timing for collection. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned collection unit is It estimates the other person's emotions and determines the priority of information to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned collection unit is When collecting data, include the other party's nonverbal communication as part of the data collection. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, We estimate the other person's emotions and adjust the perspective and methods of analysis based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, we consider the context and background information of the other party's statements to extract needs with greater accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, During the analysis, patterns and trends in the other party's statements are analyzed to predict future needs. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit, It estimates the other person's emotions and adjusts how the analysis results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned analysis unit, During analysis, the content of the other party's statements is combined with related external data for analysis. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned analysis unit, During analysis, the content of one person's statements is compared with the content of other people's statements to extract common needs and requests. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0167] 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. A question generation unit analyzes the content of the other party's statements and generates appropriate questions, A collection unit collects the needs of the other party based on the questions generated by the question generation unit, The system includes an analysis unit that analyzes the information collected by the collection unit and verbalizes the other party's needs from multiple perspectives. A system characterized by the following features.

2. The aforementioned question generation unit, Using natural language processing techniques, we analyze what the other person says and generate related questions. The system according to feature 1.

3. The aforementioned collection unit is Collect information about what the other party says during a business meeting. The system according to feature 1.

4. The aforementioned analysis unit, We analyze the information collected using machine learning algorithms to extract the customer's needs. The system according to feature 1.

5. The aforementioned collection unit is Collect the content of what the customer says during customer service interactions. The system according to feature 1.

6. The aforementioned analysis unit, The collected information is analyzed from multiple perspectives, and the client's needs are articulated in concrete terms. The system according to feature 1.

7. The aforementioned question generation unit, Infer the other person's emotions and adjust the tone and format of the questions based on those emotions. The system according to feature 1.

8. The aforementioned question generation unit, When generating questions, the system references the other person's past statements to create more specific and relevant questions. The system according to feature 1.

9. The aforementioned question generation unit, When generating questions, adjust the difficulty level of the questions according to the recipient's level of expertise. The system according to feature 1.

10. The aforementioned question generation unit, Infer the other person's emotions and adjust the order of questions based on those emotions. The system according to feature 1.

Images