system

Abstract

The system according to this embodiment aims to reduce lost opportunities and wasted time in business negotiations and meetings. [Solution] The system according to the embodiment comprises an introduction unit, a minutes creation unit, a confirmation unit, a learning unit, an analysis unit, a summary unit, and a prioritization unit. The introduction unit introduces services that meet customer needs. The minutes creation unit creates minutes of the business negotiation based on the services introduced by the introduction unit, using voice input. The confirmation unit confirms action items based on the minutes created by the minutes creation unit. The learning unit learns the content of the agenda based on the action items confirmed by the confirmation unit. The analysis unit analyzes the content of the brainstorming based on the content learned by the learning unit. The summary unit creates a summary considering the advantages and disadvantages of each idea based on the content of the statements analyzed by the analysis unit. The prioritization unit prioritizes based on the summary created by the summary unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a risk of opportunity loss and time waste in business negotiations and meetings.

[0005] The system according to the embodiment aims to reduce opportunity loss and time waste in business negotiations and meetings.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an introduction unit, a minutes creation unit, a confirmation unit, a learning unit, an analysis unit, a summary unit, and a prioritization unit. The introduction unit introduces services that meet customer needs. The minutes creation unit creates minutes of the business negotiation based on the services introduced by the introduction unit, using voice input. The confirmation unit confirms action items based on the minutes created by the minutes creation unit. The learning unit learns the content of the agenda based on the action items confirmed by the confirmation unit. The analysis unit analyzes the content of the brainstorming based on the content learned by the learning unit. The summary unit creates a summary considering the advantages and disadvantages of each idea based on the content of the statements analyzed by the analysis unit. The prioritization unit prioritizes based on the summary created by the summary unit. [Effects of the Invention]

[0007] The system according to this embodiment can reduce lost opportunities and wasted time in business negotiations and meetings. [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 tagged storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. 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 tagged communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 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 , 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 includes a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by contact of an indicator (e.g., a pen or a finger, etc.) by detecting the contact of the indicator. The microphone 38B receives user input by voice by detecting the voice of the user. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, a specific processing unit 290 (see FIG. 2) acquires 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 support service according to an embodiment of the present invention is a system for reducing lost opportunities and time in business negotiations, meetings, and discussions. This system provides business negotiation support functions, meeting support functions, and discussion support functions. As a business negotiation support function, the AI ​​learns the content of all services and introduces services that meet customer needs, thereby preventing lost opportunities, eliminating matters to be taken back, and promoting speedy decision-making. In addition, communication errors can be reduced by creating meeting minutes and confirming action items using voice input of business negotiations. As a meeting support function, the AI ​​learns the content of the agenda, eliminating matters to be taken back, and promoting speedy decision-making. In addition, communication errors can be reduced by creating meeting minutes and confirming action items using voice input of meetings. As a discussion support function, the AI ​​analyzes the content of brainstorming sessions, considers the merits and demerits of each idea to create a summary of ideas, prioritizes them, identifies effective ideas, and enables quick decision-making. For example, the AI ​​inputs audio from business negotiations, meetings, and discussions, and automatically creates meeting minutes and action items. Next, based on what the AI ​​has learned, it proposes the most suitable services and solutions tailored to customer needs and agendas. Finally, the AI ​​analyzes the spoken content, considers the merits and demerits of each idea, creates a summary, and prioritizes them. This system reduces the time spent on negotiations, meetings, and discussions, prevents missed opportunities, and promotes speedy decision-making. Furthermore, voice input for meeting minutes creation and action item confirmation reduces communication errors. In addition, by analyzing and summarizing brainstorming content and creating an idea summary, effective ideas can be identified, enabling quick decision-making. As a result, the support service can reduce missed opportunities and time spent on negotiations, meetings, and discussions, and promote speedy decision-making.

[0029] The support service according to this embodiment comprises an introduction unit, a minutes creation unit, a confirmation unit, a learning unit, an analysis unit, a summarization unit, and a prioritization unit. The introduction unit introduces services that meet customer needs. The introduction unit can, for example, use AI to analyze the customer's past purchase history, current projects, and areas of interest to select the most suitable service. The minutes creation unit creates minutes of business negotiations using voice input. The minutes creation unit can, for example, use speech recognition technology to transcribe the content of business negotiations into text and save it as minutes. The confirmation unit verifies action items. The confirmation unit can, for example, extract action items based on the minutes and set responsible persons and deadlines. The learning unit learns the content of the agenda. The learning unit can, for example, use machine learning algorithms to learn past agendas and business negotiation content and propose the most suitable solutions. The analysis unit analyzes the content of brainstorming sessions. The analysis unit can, for example, use text mining technology to analyze the content of the statements and extract important keywords and phrases. The summarization unit creates a summary considering the advantages and disadvantages of each idea. For example, the summarization unit can evaluate the advantages and disadvantages of an idea and create a summary based on keywords and phrases extracted by the analysis unit. The prioritization unit performs prioritization. For example, the prioritization unit can determine the priority of ideas according to their importance and urgency based on the summarization unit created. As a result, the support service according to the embodiment can introduce services that meet customer needs, create meeting minutes, confirm action items, learn about the agenda, analyze and interpret the content of statements, summarize ideas, and prioritize them.

[0030] The referral department introduces services that align with customer needs. Specifically, the referral department uses AI to analyze customers' past purchase history, current projects, and areas of interest to select the most suitable service. The AI ​​retrieves customers' past purchase history from a database and uses this to predict their preferences and needs. It also collects information on ongoing projects and areas of interest, and integrates and analyzes this data. For example, it uses natural language processing technology to analyze text data such as customer emails, memos, and project reports to identify themes and issues that customers are currently interested in. Furthermore, based on this information, the AI ​​recommends the most suitable service to the customer. The recommendation engine considers past success stories and feedback from other customers to select the most appropriate service. As a result, the referral department can quickly and accurately introduce services that best match customer needs.

[0031] The meeting minutes creation department creates meeting minutes from voice input of business negotiations. Specifically, it uses speech recognition technology to transcribe the content of the negotiations into text and saves it as meeting minutes. The speech recognition technology uses a high-precision speech recognition engine to convert what is said during the negotiation into text in real time. For example, what is said during the negotiation is collected by microphone and input into the speech recognition engine. The engine analyzes the content of the speech and outputs it as text data. This text data is automatically formatted into a meeting minutes format and saved. Furthermore, the meeting minutes creation department can categorize the content of what was said by each speaker, making it clear who said what. This makes it possible to create meeting minutes that accurately record the content of the negotiations and are useful for later reference.

[0032] The verification unit verifies action items. Specifically, it extracts action items based on meeting minutes and sets the person in charge and the deadline. The verification unit analyzes the text data of the meeting minutes to identify keywords and phrases related to the action items. For example, it automatically extracts action items based on keywords such as "by next time," "person in charge," and "deadline." The extracted action items are listed along with the person in charge and the deadline and registered in the management system. Furthermore, the verification unit also has a function to track the progress of action items and send reminders when the deadline approaches. This streamlines the management of action items and ensures that they are executed reliably.

[0033] The learning unit learns the content of the agenda. Specifically, it uses machine learning algorithms to learn about past agendas and business negotiations and proposes the optimal solution. The learning unit uses past meeting minutes and business negotiation records as datasets to train its machine learning model. For example, it learns about solutions and results for past agendas and proposes the optimal solution when similar agendas arise. The learning unit uses natural language processing technology to analyze the content of the agenda and extract relevant information. Furthermore, the learning unit evaluates the effectiveness of the proposed solutions and continuously improves the model based on the feedback. This allows the learning unit to always provide the latest information and the optimal solution.

[0034] The analysis unit analyzes and interprets the content of brainstorming sessions. Specifically, it uses text mining techniques to analyze the content of the statements and extract important keywords and phrases. The analysis unit collects the brainstorming content as text data and applies text mining algorithms. For example, it identifies frequently occurring keywords and phrases and uses these to extract the focus of the discussion and important points. Furthermore, the analysis unit can also perform sentiment analysis of the statements and classify positive and negative opinions. This allows for effective analysis of the brainstorming results, clarifying the direction of the discussion and important ideas.

[0035] The summarization team creates a summary by considering the merits and demerits of each idea. Specifically, they evaluate the merits and demerits of each idea based on the keywords and phrases extracted by the analysis team and create a summary. The summarization team evaluates the feasibility and impact of each idea and lists the merits and demerits. For example, they evaluate the resources and costs required to implement the idea, the expected effects, etc., and conduct an overall evaluation. Furthermore, based on the evaluation results, the summarization team can also propose prioritization for each idea. In this way, the summarization team can organize the results of the discussion and clarify the feasible ideas.

[0036] The prioritization unit performs the prioritization process. Specifically, based on the summaries created by the compilation unit, it determines the priority of ideas according to their importance and urgency. The prioritization unit considers the evaluation results of each idea and scores their importance and urgency. For example, it calculates scores based on factors such as business impact, difficulty of implementation, and resource availability to determine the overall priority. Furthermore, the prioritization unit can also formulate action plans and develop implementation plans based on the prioritization. In this way, the prioritization unit can provide guidance for quickly putting the most important ideas into action.

[0037] The referral department can analyze a customer's past purchase history and select the most suitable service. For example, the referral department can suggest services related to products the customer has purchased in the past. It can also prioritize recommending products in categories that the customer frequently purchases based on their purchase history. Furthermore, the referral department can suggest services tailored to the season and trends based on the customer's purchase history. This allows for the suggestion of the most suitable service based on the customer's purchase history. Some or all of the above processes in the referral department may be performed using AI, for example, or not. For example, the referral department can input customer purchase history data into a generating AI and have the generating AI select the most suitable service.

[0038] The referral department can filter services based on the customer's current projects and areas of interest when introducing services. For example, the referral department can prioritize introducing services related to the customer's current projects. It can also filter and introduce relevant services based on the customer's areas of interest. Furthermore, the referral department can select and introduce the most suitable services according to the customer's industry and job type. This allows for the introduction of services tailored to the customer's projects and areas of interest. Some or all of the above processing in the referral department may be performed using AI, for example, or not. For example, the referral department can input customer project data and areas of interest data into a generating AI and have the generating AI perform the filtering of the most suitable services.

[0039] The referral department can prioritize recommending highly relevant services by considering the customer's geographical location when introducing services. For example, it can prioritize recommending stores or services close to the customer's current location. Furthermore, the referral department can suggest region-specific services based on the customer's geographical location. In addition, the referral department can recommend services that include optimal delivery options, taking the customer's location into consideration. This allows for the recommendation of the most suitable services based on the customer's geographical location. Some or all of the above processing in the referral department may be performed using AI, for example, or without AI. For example, the referral department can input the customer's geographical location data into a generating AI and have the generating AI select highly relevant services.

[0040] The referral department can analyze a customer's social media activity and recommend relevant services when introducing services. For example, the referral department can prioritize recommending products and services that the customer has shown interest in on social media. It can also analyze the content of a customer's social media posts and suggest relevant services. Furthermore, the referral department can recommend services used by the customer's followers and friends. This allows the referral department to suggest the most suitable services based on the customer's social media activity. Some or all of the above processes in the referral department may be performed using AI, for example, or not. For example, the referral department can input the customer's social media data into a generating AI and have the generating AI select relevant services.

[0041] The minutes creation unit can adjust the level of detail in meeting minutes based on the importance of the business negotiation. For example, the minutes creation unit can create detailed minutes for important business negotiations. It can also create concise minutes for general business negotiations. Furthermore, it can create brief minutes for simple business negotiations. This allows for the creation of minutes with the optimal level of detail according to the importance of the business negotiation. Some or all of the above processes in the minutes creation unit may be performed using AI, for example, or not. For example, the minutes creation unit can input business negotiation importance data into a generating AI and have the generating AI adjust the level of detail in the minutes.

[0042] The minutes creation unit can apply different minutes creation algorithms depending on the category of the business opportunity when creating minutes. For example, in the case of a technical business opportunity, the minutes creation unit can create minutes that include technical terms. In the case of a business business opportunity, the minutes creation unit can also create minutes that include business terms. Furthermore, in the case of a general business opportunity, the minutes creation unit can create minutes that use general expressions. This allows the application of the most suitable minutes creation algorithm for each business opportunity category. Some or all of the above processes in the minutes creation unit may be performed using AI, for example, or not using AI. For example, the minutes creation unit can input business opportunity category data into a generating AI and have the generating AI execute the application of the minutes creation algorithm.

[0043] The minutes creation unit can determine the priority of meeting minutes based on the submission timing of the business deal. For example, in the case of an urgent business deal, the minutes creation unit can prioritize the creation of the minutes. In addition, in the case of a typical business deal, the minutes creation unit can create the minutes with normal priority. Furthermore, in the case of a simple business deal, the minutes creation unit can postpone the creation of the minutes. This allows for the creation of minutes with the optimal priority according to the submission timing of the business deal. Some or all of the above processes in the minutes creation unit may be performed using AI, for example, or not using AI. For example, the minutes creation unit can input data on the submission timing of business deals into a generating AI and have the generating AI determine the priority of the minutes.

[0044] The minutes creation unit can adjust the order of meeting minutes based on the relevance of the business negotiations. For example, the minutes creation unit can record important business negotiation points first. It can also record general business negotiation points in the middle. Furthermore, it can record simple business negotiation points at the end. This allows the minutes to be created in the optimal order according to the relevance of the business negotiations. Some or all of the above processing in the minutes creation unit may be performed using AI, for example, or not using AI. For example, the minutes creation unit can input business negotiation relevance data into a generating AI and have the generating AI perform the adjustment of the order of the meeting minutes.

[0045] The verification unit can adjust the level of detail of an action item based on the importance of the deal. For example, the verification unit can perform a detailed verification for important action items. It can also perform a concise verification for general action items. Furthermore, it can perform a brief verification for simple action items. This allows for verification of action items with the optimal level of detail according to the importance of the deal. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can input deal importance data into a generating AI and have the generating AI adjust the level of detail of the verification.

[0046] The verification unit can apply different verification algorithms depending on the opportunity category when verifying action items. For example, in the case of technical action items, the verification unit can perform verification including technical terms. In the case of business action items, the verification unit can also perform verification including business terms. Furthermore, in the case of general action items, the verification unit can perform verification using general expressions. This allows the application of the most appropriate verification algorithm for the opportunity category. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can input opportunity category data into a generating AI and have the generating AI execute the application of the verification algorithm.

[0047] The verification unit can determine the priority of verification for action items based on the timing of the opportunity submission. For example, the verification unit can prioritize urgent action items. It can also prioritize general action items. Furthermore, it can postpone verification of simple action items. This allows for verification of action items with the optimal priority according to the timing of the opportunity submission. Some or all of the above processing in the verification unit may be performed using AI, for example, or not. For example, the verification unit can input opportunity submission timing data into a generating AI and have the generating AI determine the verification priority.

[0048] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also analyze past learning data and improve the learning algorithm. Furthermore, the learning unit can adjust the parameters of the learning algorithm by referring to past learning data. This allows the optimal learning algorithm to be applied based on past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0049] The learning unit can weight the training data based on the timing of deal submissions during training. For example, in the case of an urgent deal, the learning unit can weight the most recent training data. Alternatively, for a typical deal, the learning unit can use the training data with a normal weighting. Furthermore, for a simple deal, the learning unit can weight past training data. This allows the learning unit to use the training data with the optimal weighting according to the timing of deal submissions. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input deal submission timing data into a generating AI and have the generating AI perform the weighting of the training data.

[0050] The analysis unit can adjust the level of detail of the analysis based on the importance of the business negotiation when analyzing the content of the statements. For example, the analysis unit can perform a detailed analysis in the case of an important business negotiation. It can also perform a concise analysis in the case of a general business negotiation. Furthermore, it can perform a simple analysis in the case of a simple business negotiation. This allows the content of the statements to be analyzed with the optimal level of detail according to the importance of the business negotiation. 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 business negotiation importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the analysis.

[0051] The analysis unit can apply different analysis algorithms depending on the category of the business negotiation when analyzing the content of the statements. For example, in the case of a technical negotiation, the analysis unit can apply an analysis algorithm that includes technical terms. In the case of a business negotiation, the analysis unit can also apply an analysis algorithm that includes business terms. Furthermore, in the case of a general negotiation, the analysis unit can apply an analysis algorithm that uses general expressions. This allows the analysis unit to apply the most appropriate analysis algorithm according to the category of the business negotiation. 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 category data of the business negotiation into a generating AI and have the generating AI execute the application of the analysis algorithm.

[0052] The analysis unit can determine the priority of analysis based on the timing of the business negotiation submission when analyzing the content of the statements. For example, the analysis unit can prioritize the analysis of urgent business negotiations. It can also perform analysis with normal priority for general business negotiations. Furthermore, it can postpone the analysis of simple business negotiations. This allows for the analysis of statements with the optimal priority according to the timing of the business negotiation submission. 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 business negotiation submission timing data into a generating AI and have the generating AI determine the analysis priority.

[0053] The summarization unit can adjust the level of detail in a summary based on the importance of the business deal. For example, it can create a detailed summary for important business deals. It can also create a concise summary for general business deals. Furthermore, it can create a brief summary for simple business deals. This allows for the creation of summaries with the optimal level of detail according to the importance of the business deal. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not. For example, the summarization unit can input business deal importance data into a generating AI and have the generating AI adjust the level of detail in the summary.

[0054] The summarization unit can apply different summarization algorithms depending on the category of the business opportunity when creating summaries. For example, in the case of a technical business opportunity, the summarization unit can apply a summarization algorithm that includes technical terms. In the case of a business business opportunity, the summarization unit can also apply a summarization algorithm that includes business terms. Furthermore, in the case of a general business opportunity, the summarization unit can apply a summarization algorithm that uses general expressions. This allows the application of the most suitable summarization algorithm for each business opportunity category. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not. For example, the summarization unit can input business opportunity category data into a generating AI and have the generating AI execute the application of the summarization algorithm.

[0055] The summarization unit can determine the priority of summaries based on the submission timing of each deal when creating them. For example, the summarization unit can create a summary with the highest priority for urgent deals. It can also create summaries with the normal priority for general deals. Furthermore, it can postpone the creation of summaries for simple deals. This allows for the creation of summaries with the optimal priority according to the submission timing of each deal. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not. For example, the summarization unit can input deal submission timing data into a generating AI and have the generating AI determine the priority of the summaries.

[0056] The prioritization unit can adjust the priority of deals based on their importance during the prioritization process. For example, it can process important deals with the highest priority. It can also process general deals with a normal priority. Furthermore, it can postpone simple deals. This allows for processing with the optimal priority according to the importance of each deal. Some or all of the above processing in the prioritization unit may be performed using AI, for example, or without AI. For example, the prioritization unit can input deal importance data into a generating AI and have the generating AI perform the priority adjustment.

[0057] The prioritization unit can apply different prioritization algorithms depending on the category of the business opportunity. For example, in the case of a technical business opportunity, the prioritization unit can apply a prioritization algorithm that includes technical terms. Similarly, in the case of a business business opportunity, the prioritization unit can apply a prioritization algorithm that includes business terms. Furthermore, in the case of a general business opportunity, the prioritization unit can apply a prioritization algorithm using general expressions. This allows for the application of the optimal prioritization algorithm according to the category of the business opportunity. Some or all of the above processing in the prioritization unit may be performed using AI, for example, or without AI. For example, the prioritization unit can input business opportunity category data into a generating AI and have the generating AI execute the application of the prioritization algorithm.

[0058] The prioritization unit can determine the priority of deals based on the submission timing. For example, the prioritization unit can process urgent deals with the highest priority. It can also process general deals with the normal priority. Furthermore, it can postpone simple deals. This allows for processing with the optimal priority according to the submission timing of the deals. Some or all of the above processing in the prioritization unit may be performed using AI, for example, or without AI. For example, the prioritization unit can input deal submission timing data into a generating AI and have the generating AI perform the priority determination.

[0059] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0060] The referral department can analyze not only the customer's purchase history but also their social media activity to recommend relevant services. For example, it can prioritize recommending products and services that the customer has shown interest in on social media. It can also analyze the content of the customer's social media posts and suggest relevant services. Furthermore, it can recommend services used by the customer's followers and friends. This allows the department to suggest the most suitable services based on the customer's social media activity. Some or all of the above processing in the referral department may be performed using AI, for example, or not. For example, the referral department can input the customer's social media data into a generating AI and have the generating AI select relevant services.

[0061] The minutes creation unit can adjust the level of detail in the minutes based on the importance of the business negotiation. For example, for important business negotiations, detailed minutes can be created. For general business negotiations, minutes that focus on the key points can be created. Furthermore, for simple business negotiations, concise minutes can be created. This allows for the creation of minutes with the optimal level of detail according to the importance of the business negotiation. Some or all of the above processes in the minutes creation unit may be performed using AI, for example, or not using AI. For example, the minutes creation unit can input business negotiation importance data into a generating AI and have the generating AI adjust the level of detail in the minutes.

[0062] The verification unit can adjust the level of detail of an action item based on the importance of the deal. For example, a detailed verification can be performed for important action items. For general action items, a concise verification can be performed. Furthermore, for simple action items, a brief verification can be performed. This allows for verification of action items with the optimal level of detail according to the importance of the deal. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can input deal importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the verification.

[0063] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, it can select the optimal learning algorithm based on past learning data. It can also analyze past learning data and improve the learning algorithm. Furthermore, it can adjust the parameters of the learning algorithm by referring to past learning data. This allows the optimal learning algorithm to be applied based on past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0064] The analysis unit can adjust the level of detail in its analysis of spoken content based on the importance of the business negotiation. For example, it can perform a detailed analysis for important business negotiations. For general business negotiations, it can perform a concise analysis focusing on the key points. Furthermore, for simple business negotiations, it can perform a simple analysis. This allows for the analysis of spoken content with the optimal level of detail according to the importance of the business negotiation. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input business negotiation importance data into a generating AI and have the generating AI adjust the level of detail in the analysis.

[0065] The following briefly describes the processing flow for example form 1.

[0066] Step 1: The referral department introduces services that meet customer needs. For example, they use AI to analyze the customer's past purchase history, current projects, and areas of interest to select the most suitable service. Step 2: The minutes creation department creates meeting minutes based on voice input of the business negotiation. For example, they use speech recognition technology to transcribe the content of the negotiation into text and save it as meeting minutes. Step 3: The verification team verifies the action items based on the meeting minutes. For example, they extract action items from the meeting minutes and set the person in charge and the deadline. Step 4: The learning unit learns the content of the agenda. For example, it uses machine learning algorithms to learn from past agendas and business negotiations and proposes the optimal solution. Step 5: The analysis unit analyzes the content of the brainstorming session. For example, it uses text mining techniques to analyze the content of the comments and extract important keywords and phrases. Step 6: The summarization team creates a summary, taking into account the merits and demerits of each idea. For example, they evaluate the merits and demerits of each idea based on the keywords and phrases extracted by the analysis team, and then create a summary. Step 7: The prioritization section prioritizes ideas based on the summary created by the summarization section. For example, the priority of ideas is determined according to their importance and urgency.

[0067] (Example of form 2) The support service according to an embodiment of the present invention is a system for reducing lost opportunities and time in business negotiations, meetings, and discussions. This system provides business negotiation support functions, meeting support functions, and discussion support functions. As a business negotiation support function, the AI ​​learns the content of all services and introduces services that meet customer needs, thereby preventing lost opportunities, eliminating matters to be taken back, and promoting speedy decision-making. In addition, communication errors can be reduced by creating meeting minutes and confirming action items using voice input of business negotiations. As a meeting support function, the AI ​​learns the content of the agenda, eliminating matters to be taken back, and promoting speedy decision-making. In addition, communication errors can be reduced by creating meeting minutes and confirming action items using voice input of meetings. As a discussion support function, the AI ​​analyzes the content of brainstorming sessions, considers the merits and demerits of each idea to create a summary of ideas, prioritizes them, identifies effective ideas, and enables quick decision-making. For example, the AI ​​inputs audio from business negotiations, meetings, and discussions, and automatically creates meeting minutes and action items. Next, based on what the AI ​​has learned, it proposes the most suitable services and solutions tailored to customer needs and agendas. Finally, the AI ​​analyzes the spoken content, considers the merits and demerits of each idea, creates a summary, and prioritizes them. This system reduces the time spent on negotiations, meetings, and discussions, prevents missed opportunities, and promotes speedy decision-making. Furthermore, voice input for meeting minutes creation and action item confirmation reduces communication errors. In addition, by analyzing and summarizing brainstorming content and creating an idea summary, effective ideas can be identified, enabling quick decision-making. As a result, the support service can reduce missed opportunities and time spent on negotiations, meetings, and discussions, and promote speedy decision-making.

[0068] The support service according to this embodiment comprises an introduction unit, a minutes creation unit, a confirmation unit, a learning unit, an analysis unit, a summarization unit, and a prioritization unit. The introduction unit introduces services that meet customer needs. The introduction unit can, for example, use AI to analyze the customer's past purchase history, current projects, and areas of interest to select the most suitable service. The minutes creation unit creates minutes of business negotiations using voice input. The minutes creation unit can, for example, use speech recognition technology to transcribe the content of business negotiations into text and save it as minutes. The confirmation unit verifies action items. The confirmation unit can, for example, extract action items based on the minutes and set responsible persons and deadlines. The learning unit learns the content of the agenda. The learning unit can, for example, use machine learning algorithms to learn past agendas and business negotiation content and propose the most suitable solutions. The analysis unit analyzes the content of brainstorming sessions. The analysis unit can, for example, use text mining technology to analyze the content of the statements and extract important keywords and phrases. The summarization unit creates a summary considering the advantages and disadvantages of each idea. For example, the summarization unit can evaluate the advantages and disadvantages of an idea and create a summary based on keywords and phrases extracted by the analysis unit. The prioritization unit performs prioritization. For example, the prioritization unit can determine the priority of ideas according to their importance and urgency based on the summarization unit created. As a result, the support service according to the embodiment can introduce services that meet customer needs, create meeting minutes, confirm action items, learn about the agenda, analyze and interpret the content of statements, summarize ideas, and prioritize them.

[0069] The referral department introduces services that align with customer needs. Specifically, the referral department uses AI to analyze customers' past purchase history, current projects, and areas of interest to select the most suitable service. The AI ​​retrieves customers' past purchase history from a database and uses this to predict their preferences and needs. It also collects information on ongoing projects and areas of interest, and integrates and analyzes this data. For example, it uses natural language processing technology to analyze text data such as customer emails, memos, and project reports to identify themes and issues that customers are currently interested in. Furthermore, based on this information, the AI ​​recommends the most suitable service to the customer. The recommendation engine considers past success stories and feedback from other customers to select the most appropriate service. As a result, the referral department can quickly and accurately introduce services that best match customer needs.

[0070] The meeting minutes creation department creates meeting minutes from voice input of business negotiations. Specifically, it uses speech recognition technology to transcribe the content of the negotiations into text and saves it as meeting minutes. The speech recognition technology uses a high-precision speech recognition engine to convert what is said during the negotiation into text in real time. For example, what is said during the negotiation is collected by microphone and input into the speech recognition engine. The engine analyzes the content of the speech and outputs it as text data. This text data is automatically formatted into a meeting minutes format and saved. Furthermore, the meeting minutes creation department can categorize the content of what was said by each speaker, making it clear who said what. This makes it possible to create meeting minutes that accurately record the content of the negotiations and are useful for later reference.

[0071] The verification unit verifies action items. Specifically, it extracts action items based on meeting minutes and sets the person in charge and the deadline. The verification unit analyzes the text data of the meeting minutes to identify keywords and phrases related to the action items. For example, it automatically extracts action items based on keywords such as "by next time," "person in charge," and "deadline." The extracted action items are listed along with the person in charge and the deadline and registered in the management system. Furthermore, the verification unit also has a function to track the progress of action items and send reminders when the deadline approaches. This streamlines the management of action items and ensures that they are executed reliably.

[0072] The learning unit learns the content of the agenda. Specifically, it uses machine learning algorithms to learn about past agendas and business negotiations and proposes the optimal solution. The learning unit uses past meeting minutes and business negotiation records as datasets to train its machine learning model. For example, it learns about solutions and results for past agendas and proposes the optimal solution when similar agendas arise. The learning unit uses natural language processing technology to analyze the content of the agenda and extract relevant information. Furthermore, the learning unit evaluates the effectiveness of the proposed solutions and continuously improves the model based on the feedback. This allows the learning unit to always provide the latest information and the optimal solution.

[0073] The analysis unit analyzes and interprets the content of brainstorming sessions. Specifically, it uses text mining techniques to analyze the content of the statements and extract important keywords and phrases. The analysis unit collects the brainstorming content as text data and applies text mining algorithms. For example, it identifies frequently occurring keywords and phrases and uses these to extract the focus of the discussion and important points. Furthermore, the analysis unit can also perform sentiment analysis of the statements and classify positive and negative opinions. This allows for effective analysis of the brainstorming results, clarifying the direction of the discussion and important ideas.

[0074] The summarization team creates a summary by considering the merits and demerits of each idea. Specifically, they evaluate the merits and demerits of each idea based on the keywords and phrases extracted by the analysis team and create a summary. The summarization team evaluates the feasibility and impact of each idea and lists the merits and demerits. For example, they evaluate the resources and costs required to implement the idea, the expected effects, etc., and conduct an overall evaluation. Furthermore, based on the evaluation results, the summarization team can also propose prioritization for each idea. In this way, the summarization team can organize the results of the discussion and clarify the feasible ideas.

[0075] The prioritization unit performs the prioritization process. Specifically, based on the summaries created by the compilation unit, it determines the priority of ideas according to their importance and urgency. The prioritization unit considers the evaluation results of each idea and scores their importance and urgency. For example, it calculates scores based on factors such as business impact, difficulty of implementation, and resource availability to determine the overall priority. Furthermore, the prioritization unit can also formulate action plans and develop implementation plans based on the prioritization. In this way, the prioritization unit can provide guidance for quickly putting the most important ideas into action.

[0076] The introduction unit can estimate the customer's emotions and adjust the timing of service introductions based on those emotions. For example, if the customer is excited, the introduction unit can immediately introduce the service to pique their interest. If the customer is relaxed, the introduction unit can provide a slower, more detailed explanation. Furthermore, if the customer is in a hurry, the introduction unit can convey the key points concisely. This allows for service introductions at the optimal time according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the introduction unit may be performed using AI or not. For example, the introduction unit can input customer facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0077] The referral department can analyze a customer's past purchase history and select the most suitable service. For example, the referral department can suggest services related to products the customer has purchased in the past. It can also prioritize recommending products in categories that the customer frequently purchases based on their purchase history. Furthermore, the referral department can suggest services tailored to the season and trends based on the customer's purchase history. This allows for the suggestion of the most suitable service based on the customer's purchase history. Some or all of the above processes in the referral department may be performed using AI, for example, or not. For example, the referral department can input customer purchase history data into a generating AI and have the generating AI select the most suitable service.

[0078] The referral department can filter services based on the customer's current projects and areas of interest when introducing services. For example, the referral department can prioritize introducing services related to the customer's current projects. It can also filter and introduce relevant services based on the customer's areas of interest. Furthermore, the referral department can select and introduce the most suitable services according to the customer's industry and job type. This allows for the introduction of services tailored to the customer's projects and areas of interest. Some or all of the above processing in the referral department may be performed using AI, for example, or not. For example, the referral department can input customer project data and areas of interest data into a generating AI and have the generating AI perform the filtering of the most suitable services.

[0079] The referral department can estimate the customer's emotions and prioritize the services to recommend based on those emotions. For example, if the customer is excited, the referral department can prioritize recommending the most appealing services. If the customer is relaxed, the referral department can prioritize recommending services that require detailed explanations. Furthermore, if the customer is in a hurry, the referral department can prioritize recommending services that can be explained concisely. This allows for the recommendation of the most suitable services based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the referral department may be performed using AI or not. For example, the referral department can input customer facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0080] The referral department can prioritize recommending highly relevant services by considering the customer's geographical location when introducing services. For example, it can prioritize recommending stores or services close to the customer's current location. Furthermore, the referral department can suggest region-specific services based on the customer's geographical location. In addition, the referral department can recommend services that include optimal delivery options, taking the customer's location into consideration. This allows for the recommendation of the most suitable services based on the customer's geographical location. Some or all of the above processing in the referral department may be performed using AI, for example, or without AI. For example, the referral department can input the customer's geographical location data into a generating AI and have the generating AI select highly relevant services.

[0081] The referral department can analyze a customer's social media activity and recommend relevant services when introducing services. For example, the referral department can prioritize recommending products and services that the customer has shown interest in on social media. It can also analyze the content of a customer's social media posts and suggest relevant services. Furthermore, the referral department can recommend services used by the customer's followers and friends. This allows the referral department to suggest the most suitable services based on the customer's social media activity. Some or all of the above processes in the referral department may be performed using AI, for example, or not. For example, the referral department can input the customer's social media data into a generating AI and have the generating AI select relevant services.

[0082] The minutes creation unit can estimate the emotions of the business negotiation participants and adjust the expression of the minutes based on the estimated emotions. For example, if a business negotiation participant is nervous, the minutes creation unit can use concise and clear language. If a business negotiation participant is relaxed, the minutes creation unit can also use language that includes detailed explanations. Furthermore, if a business negotiation participant is excited, the minutes creation unit can also use positive language. This allows the minutes to be created using the most appropriate expression according to the emotions of the business negotiation participants. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the minutes creation unit may be performed using AI, for example, or not using AI. For example, the minutes creation unit can input facial expression data of the business negotiation participants into the generative AI and have the generative AI perform the estimation of the business negotiation participants' emotions.

[0083] The minutes creation unit can adjust the level of detail in meeting minutes based on the importance of the business negotiation. For example, the minutes creation unit can create detailed minutes for important business negotiations. It can also create concise minutes for general business negotiations. Furthermore, it can create brief minutes for simple business negotiations. This allows for the creation of minutes with the optimal level of detail according to the importance of the business negotiation. Some or all of the above processes in the minutes creation unit may be performed using AI, for example, or not. For example, the minutes creation unit can input business negotiation importance data into a generating AI and have the generating AI adjust the level of detail in the minutes.

[0084] The minutes creation unit can apply different minutes creation algorithms depending on the category of the business opportunity when creating minutes. For example, in the case of a technical business opportunity, the minutes creation unit can create minutes that include technical terms. In the case of a business business opportunity, the minutes creation unit can also create minutes that include business terms. Furthermore, in the case of a general business opportunity, the minutes creation unit can create minutes that use general expressions. This allows the application of the most suitable minutes creation algorithm for each business opportunity category. Some or all of the above processes in the minutes creation unit may be performed using AI, for example, or not using AI. For example, the minutes creation unit can input business opportunity category data into a generating AI and have the generating AI execute the application of the minutes creation algorithm.

[0085] The minutes creation unit can estimate the emotions of the business negotiation participants and adjust the length of the minutes based on the estimated emotions. For example, if a business negotiation participant is nervous, the minutes creation unit can create short, concise minutes. Conversely, if a business negotiation participant is relaxed, the minutes creation unit can create longer minutes that include detailed explanations. Furthermore, if a business negotiation participant is excited, the minutes creation unit can create minutes that include positive expressions. This allows for the creation of minutes of the optimal length according to the emotions of the business negotiation participants. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the minutes creation unit may be performed using AI or not. For example, the minutes creation unit can input facial expression data of the business negotiation participants into the generative AI and have the generative AI perform the estimation of the business negotiation participants' emotions.

[0086] The minutes creation unit can determine the priority of meeting minutes based on the submission timing of the business deal. For example, in the case of an urgent business deal, the minutes creation unit can prioritize the creation of the minutes. In addition, in the case of a typical business deal, the minutes creation unit can create the minutes with normal priority. Furthermore, in the case of a simple business deal, the minutes creation unit can postpone the creation of the minutes. This allows for the creation of minutes with the optimal priority according to the submission timing of the business deal. Some or all of the above processes in the minutes creation unit may be performed using AI, for example, or not using AI. For example, the minutes creation unit can input data on the submission timing of business deals into a generating AI and have the generating AI determine the priority of the minutes.

[0087] The minutes creation unit can adjust the order of meeting minutes based on the relevance of the business negotiations. For example, the minutes creation unit can record important business negotiation points first. It can also record general business negotiation points in the middle. Furthermore, it can record simple business negotiation points at the end. This allows the minutes to be created in the optimal order according to the relevance of the business negotiations. Some or all of the above processing in the minutes creation unit may be performed using AI, for example, or not using AI. For example, the minutes creation unit can input business negotiation relevance data into a generating AI and have the generating AI perform the adjustment of the order of the meeting minutes.

[0088] The confirmation unit can estimate the emotions of the sales participant and adjust the confirmation method for action items based on the estimated emotions. For example, if the sales participant is nervous, the confirmation unit can use a concise and clear confirmation method. If the sales participant is relaxed, the confirmation unit can also use a confirmation method that includes detailed explanations. Furthermore, if the sales participant is excited, the confirmation unit can use a confirmation method that uses positive language. This allows for confirmation of action items using the most appropriate method according to the sales participant's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the confirmation unit may be performed using AI or not using AI. For example, the confirmation unit can input the sales participant's facial expression data into the generative AI and have the generative AI perform the estimation of the sales participant's emotions.

[0089] The verification unit can adjust the level of detail of an action item based on the importance of the deal. For example, the verification unit can perform a detailed verification for important action items. It can also perform a concise verification for general action items. Furthermore, it can perform a brief verification for simple action items. This allows for verification of action items with the optimal level of detail according to the importance of the deal. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can input deal importance data into a generating AI and have the generating AI adjust the level of detail of the verification.

[0090] The verification unit can apply different verification algorithms depending on the opportunity category when verifying action items. For example, in the case of technical action items, the verification unit can perform verification including technical terms. In the case of business action items, the verification unit can also perform verification including business terms. Furthermore, in the case of general action items, the verification unit can perform verification using general expressions. This allows the application of the most appropriate verification algorithm for the opportunity category. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can input opportunity category data into a generating AI and have the generating AI execute the application of the verification algorithm.

[0091] The verification unit can estimate the emotions of the sales participant and determine the priority of action items based on the estimated emotions. For example, if the sales participant is nervous, the verification unit can prioritize important action items. If the sales participant is relaxed, the verification unit can also prioritize action items that require detailed explanations. Furthermore, if the sales participant is excited, the verification unit can also prioritize action items that use positive language. This allows for the verification of action items with the optimal priority according to the sales participant's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the verification unit may be performed using AI or not using AI. For example, the verification unit can input the sales participant's facial expression data into the generative AI and have the generative AI perform the estimation of the sales participant's emotions.

[0092] The verification unit can determine the priority of verification for action items based on the timing of the opportunity submission. For example, the verification unit can prioritize urgent action items. It can also prioritize general action items. Furthermore, it can postpone verification of simple action items. This allows for verification of action items with the optimal priority according to the timing of the opportunity submission. Some or all of the above processing in the verification unit may be performed using AI, for example, or not. For example, the verification unit can input opportunity submission timing data into a generating AI and have the generating AI determine the verification priority.

[0093] The learning unit can estimate the emotions of the sales participants and select training data based on the estimated emotions. For example, if the sales participant is nervous, the learning unit can select concise and clear training data. If the sales participant is relaxed, the learning unit can also select training data that includes detailed explanations. Furthermore, if the sales participant is excited, the learning unit can also select training data that includes positive expressions. This allows for the selection of optimal training data according to the emotions of the sales participants. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI or not using AI. For example, the learning unit can input the sales participant's facial expression data into the generative AI and have the generative AI perform the estimation of the sales participant's emotions.

[0094] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also analyze past learning data and improve the learning algorithm. Furthermore, the learning unit can adjust the parameters of the learning algorithm by referring to past learning data. This allows the optimal learning algorithm to be applied based on past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0095] The learning unit can estimate the emotions of the sales participant and adjust the learning frequency based on the estimated emotions. For example, if the sales participant is nervous, the learning unit can reduce the learning frequency to alleviate the burden. Conversely, if the sales participant is relaxed, the learning unit can increase the learning frequency to provide more detailed information. Furthermore, if the sales participant is excited, the learning unit can adjust the learning frequency to provide appropriate information. This allows learning to be performed at an optimal frequency according to the sales participant's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the sales participant's facial expression data into the generative AI and have the generative AI perform the estimation of the sales participant's emotions.

[0096] The learning unit can weight the training data based on the timing of deal submissions during training. For example, in the case of an urgent deal, the learning unit can weight the most recent training data. Alternatively, for a typical deal, the learning unit can use the training data with a normal weighting. Furthermore, for a simple deal, the learning unit can weight past training data. This allows the learning unit to use the training data with the optimal weighting according to the timing of deal submissions. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input deal submission timing data into a generating AI and have the generating AI perform the weighting of the training data.

[0097] The analysis unit can estimate the emotions of the negotiation participants and adjust the analysis method of their statements based on the estimated emotions. For example, if a negotiation participant is nervous, the analysis unit can use a concise and clear analysis method. If a negotiation participant is relaxed, the analysis unit can also use a detailed analysis method. Furthermore, if a negotiation participant is excited, the analysis unit can use an analysis method that includes positive expressions. This allows the analysis of statements to be performed using the most appropriate method according to the negotiation participant's emotions. Emotion estimation 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 analysis unit may be performed using AI, or not using AI. For example, the analysis unit can input the negotiation participant's facial expression data into the generative AI and have the generative AI perform the estimation of the negotiation participant's emotions.

[0098] The analysis unit can adjust the level of detail of the analysis based on the importance of the business negotiation when analyzing the content of the statements. For example, the analysis unit can perform a detailed analysis in the case of an important business negotiation. It can also perform a concise analysis in the case of a general business negotiation. Furthermore, it can perform a simple analysis in the case of a simple business negotiation. This allows the content of the statements to be analyzed with the optimal level of detail according to the importance of the business negotiation. 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 business negotiation importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the analysis.

[0099] The analysis unit can apply different analysis algorithms depending on the category of the business negotiation when analyzing the content of the statements. For example, in the case of a technical negotiation, the analysis unit can apply an analysis algorithm that includes technical terms. In the case of a business negotiation, the analysis unit can also apply an analysis algorithm that includes business terms. Furthermore, in the case of a general negotiation, the analysis unit can apply an analysis algorithm that uses general expressions. This allows the analysis unit to apply the most appropriate analysis algorithm according to the category of the business negotiation. 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 category data of the business negotiation into a generating AI and have the generating AI execute the application of the analysis algorithm.

[0100] The analysis unit can estimate the emotions of the sales participants and adjust the display method of the analysis results based on the estimated emotions. For example, if a sales participant is nervous, the analysis unit can provide a simple and highly visible display method. If a sales participant is relaxed, the analysis unit can also provide a display method that includes detailed information. Furthermore, if a sales participant is excited, the analysis unit can also provide a display method that includes positive expressions. This allows the analysis results to be provided in the most appropriate display method according to the emotions of the sales participants. Emotion estimation 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 not using AI. For example, the analysis unit can input the sales participant's facial expression data into the generative AI and have the generative AI perform the estimation of the sales participant's emotions.

[0101] The analysis unit can determine the priority of analysis based on the timing of the business negotiation submission when analyzing the content of the statements. For example, the analysis unit can prioritize the analysis of urgent business negotiations. It can also perform analysis with normal priority for general business negotiations. Furthermore, it can postpone the analysis of simple business negotiations. This allows for the analysis of statements with the optimal priority according to the timing of the business negotiation submission. 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 business negotiation submission timing data into a generating AI and have the generating AI determine the analysis priority.

[0102] The summarizing unit can estimate the emotions of the negotiation participants and adjust the way the summary is presented based on the estimated emotions. For example, if the negotiation participant is nervous, the summarizing unit can use concise and clear language. If the negotiation participant is relaxed, the summarizing unit can also use language that includes detailed explanations. Furthermore, if the negotiation participant is excited, the summarizing unit can also use positive language. This allows the summarizing unit to create a summary using the most appropriate language according to the negotiation participant's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the summarizing unit may be performed using AI or not using AI. For example, the summarizing unit can input the negotiation participant's facial expression data into the generative AI and have the generative AI perform the estimation of the negotiation participant's emotions.

[0103] The summarization unit can adjust the level of detail in a summary based on the importance of the business deal. For example, it can create a detailed summary for important business deals. It can also create a concise summary for general business deals. Furthermore, it can create a brief summary for simple business deals. This allows for the creation of summaries with the optimal level of detail according to the importance of the business deal. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not. For example, the summarization unit can input business deal importance data into a generating AI and have the generating AI adjust the level of detail in the summary.

[0104] The summarization unit can apply different summarization algorithms depending on the category of the business opportunity when creating summaries. For example, in the case of a technical business opportunity, the summarization unit can apply a summarization algorithm that includes technical terms. In the case of a business business opportunity, the summarization unit can also apply a summarization algorithm that includes business terms. Furthermore, in the case of a general business opportunity, the summarization unit can apply a summarization algorithm that uses general expressions. This allows the application of the most suitable summarization algorithm for each business opportunity category. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not. For example, the summarization unit can input business opportunity category data into a generating AI and have the generating AI execute the application of the summarization algorithm.

[0105] The summarization unit can estimate the emotions of the negotiation participants and adjust the length of the summary based on the estimated emotions. For example, if the negotiation participant is nervous, the summarization unit can create a short, concise summary. If the negotiation participant is relaxed, the summarization unit can create a longer summary that includes detailed explanations. Furthermore, if the negotiation participant is excited, the summarization unit can create a summary that includes positive expressions. This allows for the creation of a summary of the optimal length according to the negotiation participant's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the summarization unit may be performed using AI or not. For example, the summarization unit can input the negotiation participant's facial expression data into the generative AI and have the generative AI perform the estimation of the negotiation participant's emotions.

[0106] The summarization unit can determine the priority of summaries based on the submission timing of each deal when creating them. For example, the summarization unit can create a summary with the highest priority for urgent deals. It can also create summaries with the normal priority for general deals. Furthermore, it can postpone the creation of summaries for simple deals. This allows for the creation of summaries with the optimal priority according to the submission timing of each deal. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not. For example, the summarization unit can input deal submission timing data into a generating AI and have the generating AI determine the priority of the summaries.

[0107] The prioritization unit can estimate the emotions of the sales participants and adjust the prioritization criteria based on the estimated emotions. For example, if a sales participant is nervous, the prioritization unit can prioritize processing important items. If a sales participant is relaxed, the prioritization unit can prioritize processing items that require detailed explanations. Furthermore, if a sales participant is excited, the prioritization unit can prioritize processing items that use positive expressions. This allows prioritization to be performed using the optimal criteria according to the emotions of the sales participants. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the prioritization unit may be performed using AI or not using AI. For example, the prioritization unit can input the sales participant's facial expression data into the generative AI and have the generative AI perform the estimation of the sales participant's emotions.

[0108] The prioritization unit can adjust the priority of deals based on their importance during the prioritization process. For example, it can process important deals with the highest priority. It can also process general deals with a normal priority. Furthermore, it can postpone simple deals. This allows for processing with the optimal priority according to the importance of each deal. Some or all of the above processing in the prioritization unit may be performed using AI, for example, or without AI. For example, the prioritization unit can input deal importance data into a generating AI and have the generating AI perform the priority adjustment.

[0109] The prioritization unit can apply different prioritization algorithms depending on the category of the business opportunity. For example, in the case of a technical business opportunity, the prioritization unit can apply a prioritization algorithm that includes technical terms. Similarly, in the case of a business business opportunity, the prioritization unit can apply a prioritization algorithm that includes business terms. Furthermore, in the case of a general business opportunity, the prioritization unit can apply a prioritization algorithm using general expressions. This allows for the application of the optimal prioritization algorithm according to the category of the business opportunity. Some or all of the above processing in the prioritization unit may be performed using AI, for example, or without AI. For example, the prioritization unit can input business opportunity category data into a generating AI and have the generating AI execute the application of the prioritization algorithm.

[0110] The prioritization unit can estimate the emotions of the sales participants and adjust the order in which the prioritization results are displayed based on the estimated emotions. For example, if a sales participant is nervous, the prioritization unit can display important items first. If a sales participant is relaxed, the prioritization unit can also display items that require detailed explanation first. Furthermore, if a sales participant is excited, the prioritization unit can also display items using positive language first. This allows the prioritization results to be displayed in the optimal order according to the emotions of the sales participants. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the prioritization unit may be performed using AI or not using AI. For example, the prioritization unit can input the sales participant's facial expression data into the generative AI and have the generative AI perform the estimation of the sales participant's emotions.

[0111] The prioritization unit can determine the priority of deals based on the submission timing. For example, the prioritization unit can process urgent deals with the highest priority. It can also process general deals with the normal priority. Furthermore, it can postpone simple deals. This allows for processing with the optimal priority according to the submission timing of the deals. Some or all of the above processing in the prioritization unit may be performed using AI, for example, or without AI. For example, the prioritization unit can input deal submission timing data into a generating AI and have the generating AI perform the priority determination.

[0112] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0113] The referral department can analyze not only the customer's purchase history but also their social media activity to recommend relevant services. For example, it can prioritize recommending products and services that the customer has shown interest in on social media. It can also analyze the content of the customer's social media posts and suggest relevant services. Furthermore, it can recommend services used by the customer's followers and friends. This allows the department to suggest the most suitable services based on the customer's social media activity. Some or all of the above processing in the referral department may be performed using AI, for example, or not. For example, the referral department can input the customer's social media data into a generating AI and have the generating AI select relevant services.

[0114] The introduction unit can estimate the customer's emotions and adjust the timing of service introductions based on those emotions. For example, if the customer is excited, the service can be introduced immediately to pique their interest. If the customer is relaxed, a slow, detailed explanation can be given. Furthermore, if the customer is in a hurry, the information can be presented concisely. This allows for service introductions at the optimal time according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the introduction unit may be performed using AI or not. For example, the introduction unit can input customer facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0115] The minutes creation unit can adjust the level of detail in the minutes based on the importance of the business negotiation. For example, for important business negotiations, detailed minutes can be created. For general business negotiations, minutes that focus on the key points can be created. Furthermore, for simple business negotiations, concise minutes can be created. This allows for the creation of minutes with the optimal level of detail according to the importance of the business negotiation. Some or all of the above processes in the minutes creation unit may be performed using AI, for example, or not using AI. For example, the minutes creation unit can input business negotiation importance data into a generating AI and have the generating AI adjust the level of detail in the minutes.

[0116] The minutes creation unit can estimate the emotions of the business negotiation participants and adjust the expression of the minutes based on the estimated emotions. For example, if a business negotiation participant is nervous, concise and clear language can be used. If a business negotiation participant is relaxed, language including detailed explanations can be used. Furthermore, if a business negotiation participant is excited, positive language can be used. This allows for the creation of minutes using the most appropriate expression according to the emotions of the business negotiation participants. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the minutes creation unit may be performed using AI, or not using AI. For example, the minutes creation unit can input facial expression data of the business negotiation participants into the generative AI and have the generative AI perform the estimation of the business negotiation participants' emotions.

[0117] The verification unit can adjust the level of detail of an action item based on the importance of the deal. For example, a detailed verification can be performed for important action items. For general action items, a concise verification can be performed. Furthermore, for simple action items, a brief verification can be performed. This allows for verification of action items with the optimal level of detail according to the importance of the deal. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can input deal importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the verification.

[0118] The confirmation unit can estimate the emotions of the sales participant and adjust the confirmation method for action items based on the estimated emotions. For example, if the sales participant is nervous, a concise and clear confirmation method can be used. If the sales participant is relaxed, a confirmation method including detailed explanations can be used. Furthermore, if the sales participant is excited, a confirmation method using positive language can be used. This allows for confirmation of action items using the most appropriate method according to the sales participant's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the confirmation unit may be performed using AI or not using AI. For example, the confirmation unit can input the sales participant's facial expression data into the generative AI and have the generative AI perform the estimation of the sales participant's emotions.

[0119] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, it can select the optimal learning algorithm based on past learning data. It can also analyze past learning data and improve the learning algorithm. Furthermore, it can adjust the parameters of the learning algorithm by referring to past learning data. This allows the optimal learning algorithm to be applied based on past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0120] The learning unit can estimate the emotions of the sales participants and select training data based on the estimated emotions. For example, if the sales participant is nervous, it can select concise and clear training data. If the sales participant is relaxed, it can select training data that includes detailed explanations. Furthermore, if the sales participant is excited, it can select training data that includes positive expressions. This allows for the selection of optimal training data according to the emotions of the sales participants. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI or not using AI. For example, the learning unit can input the sales participant's facial expression data into the generative AI and have the generative AI perform the estimation of the sales participant's emotions.

[0121] The analysis unit can adjust the level of detail in its analysis of spoken content based on the importance of the business negotiation. For example, it can perform a detailed analysis for important business negotiations. For general business negotiations, it can perform a concise analysis focusing on the key points. Furthermore, for simple business negotiations, it can perform a simple analysis. This allows for the analysis of spoken content with the optimal level of detail according to the importance of the business negotiation. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input business negotiation importance data into a generating AI and have the generating AI adjust the level of detail in the analysis.

[0122] The analysis unit can estimate the emotions of the negotiation participants and adjust the analysis method of their statements based on the estimated emotions. For example, if a negotiation participant is nervous, a concise and clear analysis method can be used. If a negotiation participant is relaxed, a detailed analysis method can be used. Furthermore, if a negotiation participant is excited, an analysis method including positive expressions can be used. This allows for the analysis of statements using the most appropriate method according to the negotiation participant's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, or not using AI. For example, the analysis unit can input the negotiation participant's facial expression data into the generative AI and have the generative AI perform the estimation of the negotiation participant's emotions.

[0123] The following briefly describes the processing flow for example form 2.

[0124] Step 1: The referral department introduces services that meet customer needs. For example, they use AI to analyze the customer's past purchase history, current projects, and areas of interest to select the most suitable service. Step 2: The minutes creation department creates meeting minutes based on voice input of the business negotiation. For example, they use speech recognition technology to transcribe the content of the negotiation into text and save it as meeting minutes. Step 3: The verification team verifies the action items based on the meeting minutes. For example, they extract action items from the meeting minutes and set the person in charge and the deadline. Step 4: The learning unit learns the content of the agenda. For example, it uses machine learning algorithms to learn from past agendas and business negotiations and proposes the optimal solution. Step 5: The analysis unit analyzes the content of the brainstorming session. For example, it uses text mining techniques to analyze the content of the comments and extract important keywords and phrases. Step 6: The summarization team creates a summary, taking into account the merits and demerits of each idea. For example, they evaluate the merits and demerits of each idea based on the keywords and phrases extracted by the analysis team, and then create a summary. Step 7: The prioritization section prioritizes ideas based on the summary created by the summarization section. For example, the priority of ideas is determined according to their importance and urgency.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] Each of the multiple elements described above, including the introduction unit, meeting minutes creation unit, confirmation unit, learning unit, analysis unit, summarization unit, and prioritization unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the introduction unit is implemented by the control unit 46A of the smart device 14, which analyzes the customer's past purchase history, current projects, and areas of interest to select the most suitable service. The meeting minutes creation unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12, which uses speech recognition technology to transcribe the content of the business negotiation into text and saves it as meeting minutes. The confirmation unit is implemented by, for example, the control unit 46A of the smart device 14, which extracts action items based on the meeting minutes and sets the person in charge and deadline. The learning unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12, which uses machine learning algorithms to learn past agendas and business negotiation content and proposes the most suitable solution. The analysis unit is implemented by, for example, the control unit 46A of the smart device 14, which uses text mining technology to analyze the content of the statements and extract important keywords and phrases. The summarization unit is implemented, for example, by the specific processing unit 290 of the data processing device 12. Based on the keywords and phrases extracted by the analysis unit, it evaluates the merits and demerits of the ideas and creates a summary. The prioritization unit is implemented, for example, by the control unit 46A of the smart device 14. Based on the summary created by the summarization unit, it determines the priority of the ideas according to their importance and urgency. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0129] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] Each of the multiple elements described above, including the introduction unit, meeting minutes creation unit, confirmation unit, learning unit, analysis unit, summarization unit, and prioritization unit, is implemented by at least one of the smart glasses 214 and the data processing unit 12. For example, the introduction unit is implemented by the control unit 46A of the smart glasses 214, which analyzes the customer's past purchase history, current projects, and areas of interest to select the most suitable service. The meeting minutes creation unit is implemented by the identification processing unit 290 of the data processing unit 12, which uses speech recognition technology to transcribe the content of the business negotiation into text and saves it as meeting minutes. The confirmation unit is implemented by the control unit 46A of the smart glasses 214, which extracts action items based on the meeting minutes and sets the person in charge and deadline. The learning unit is implemented by the identification processing unit 290 of the data processing unit 12, which uses machine learning algorithms to learn past agendas and business negotiation content and proposes the most suitable solution. The analysis unit is implemented by the control unit 46A of the smart glasses 214, which uses text mining technology to analyze the content of the statements and extract important keywords and phrases. The summarization unit is implemented, for example, by the specific processing unit 290 of the data processing device 12. Based on the keywords and phrases extracted by the analysis unit, it evaluates the merits and demerits of the ideas and creates a summary. The prioritization unit is implemented, for example, by the control unit 46A of the smart glasses 214. Based on the summary created by the summarization unit, it determines the priority of the ideas according to their importance and urgency. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

[0145] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0154] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0155] In 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.

[0156] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0157] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0158] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0159] The data processing system 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.

[0160] Each of the multiple elements described above, including the introduction unit, meeting minutes creation unit, confirmation unit, learning unit, analysis unit, summarization unit, and prioritization unit, is implemented by at least one of the headset terminal 314 and the data processing unit 12. For example, the introduction unit is implemented by the control unit 46A of the headset terminal 314, which analyzes the customer's past purchase history, current projects, and areas of interest to select the most suitable service. The meeting minutes creation unit is implemented by the identification processing unit 290 of the data processing unit 12, which uses speech recognition technology to transcribe the content of the business negotiation into text and saves it as meeting minutes. The confirmation unit is implemented by the control unit 46A of the headset terminal 314, which extracts action items based on the meeting minutes and sets the person in charge and deadline. The learning unit is implemented by the identification processing unit 290 of the data processing unit 12, which uses a machine learning algorithm to learn past agendas and business negotiation content and propose the most suitable solution. The analysis unit is implemented, for example, by the control unit 46A of the headset terminal 314, and analyzes the content of speech using text mining technology to extract important keywords and phrases. The summarization unit is implemented, for example, by the identification processing unit 290 of the data processing device 12, and evaluates the merits and demerits of ideas based on the keywords and phrases extracted by the analysis unit, and creates a summary. The prioritization unit is implemented, for example, by the control unit 46A of the headset terminal 314, and determines the priority of ideas according to their importance and urgency based on the summary created by the summarization unit. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0161] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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).

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.).

[0174] 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.

[0175] 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.

[0176] 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.

[0177] Each of the multiple elements described above, including the introduction unit, meeting minutes creation unit, confirmation unit, learning unit, analysis unit, summarization unit, and prioritization unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the introduction unit is implemented by the control unit 46A of the robot 414, which analyzes the customer's past purchase history, current projects, and areas of interest to select the most suitable service. The meeting minutes creation unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12, which uses speech recognition technology to transcribe the content of the business negotiation into text and saves it as meeting minutes. The confirmation unit is implemented by, for example, the control unit 46A of the robot 414, which extracts action items based on the meeting minutes and sets the person in charge and the deadline. The learning unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12, which uses machine learning algorithms to learn past agendas and business negotiation content and proposes the most suitable solution. The analysis unit is implemented by, for example, the control unit 46A of the robot 414, which uses text mining technology to analyze the content of speech and extract important keywords and phrases. The summarization unit is implemented, for example, by the specific processing unit 290 of the data processing device 12. Based on the keywords and phrases extracted by the analysis unit, it evaluates the merits and demerits of the ideas and creates a summary. The prioritization unit is implemented, for example, by the control unit 46A of the robot 414. Based on the summary created by the summarization unit, it determines the priority of the ideas according to their importance and urgency. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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."

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] (Note 1) The introduction department introduces services that meet customer needs, A meeting minutes creation unit creates meeting minutes by voice input of business negotiations based on the services introduced by the aforementioned introduction unit, A verification unit that verifies action items based on the minutes created by the minutes creation unit, A learning unit learns the content of the agenda based on the action items confirmed by the aforementioned verification unit, An analysis unit analyzes and interprets the content of brainstorming based on the content learned by the aforementioned learning unit, Based on the content of the statements analyzed by the aforementioned analysis unit, the summarization unit creates a summary considering the advantages and disadvantages of each idea. The system includes a prioritization unit that performs prioritization based on the summaries created by the summarization unit. A system characterized by the following features. (Note 2) The aforementioned introduction section is, We estimate customer emotions and adjust the timing of service introductions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned introductory section is, We analyze the customer's past purchase history and select the most suitable service. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned introductory section is, When introducing services, filtering is performed based on the customer's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned introductory section is, We estimate customer emotions and prioritize the services we recommend based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned introductory section is, When introducing services, we prioritize recommending highly relevant services by taking into account the customer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned introductory section is, When introducing a service, we analyze the customer's social media activity and recommend relevant services. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned minutes preparation department, The system estimates the emotions of the business negotiation participants and adjusts the wording of the meeting minutes based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned minutes preparation department, When creating meeting minutes, adjust the level of detail based on the importance of the business negotiation. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned minutes preparation department, When creating meeting minutes, different minute-taking algorithms are applied depending on the category of the business opportunity. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned minutes preparation department, The system estimates the emotions of the business negotiation participants and adjusts the length of the meeting minutes based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned minutes preparation department, When creating meeting minutes, prioritize the minutes based on when the business negotiations were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned minutes preparation department, When creating meeting minutes, adjust the order of the minutes based on the relevance of the business discussions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned verification unit is The system estimates the emotions of the sales participants and adjusts how action items are reviewed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned verification unit is When reviewing action items, adjust the level of detail based on the importance of the deal. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned verification unit is When reviewing action items, different review algorithms are applied depending on the opportunity category. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned verification unit is The system estimates the emotions of the business negotiation participants and prioritizes action items based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned verification unit is When reviewing action items, prioritize the review based on when the opportunity was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned learning unit, The system estimates the emotions of the business negotiation participants and selects training data based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned learning unit, The system estimates the emotions of the business negotiation participants and adjusts the frequency of learning based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned learning unit, During training, the training data is weighted based on when the business opportunity was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned analysis unit, We estimate the emotions of the business negotiation participants and adjust the analysis method of their statements based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned analysis unit, When analyzing the content of the conversation, the level of detail of the analysis is adjusted based on the importance of the business negotiation. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned analysis unit, When analyzing the content of the conversation, different analysis algorithms are applied depending on the category of the business negotiation. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned analysis unit, The system estimates the emotions of the business negotiation participants and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned analysis unit, When analyzing the content of the statements, the priority of the analysis is determined based on the timing of the business proposal submission. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned summary section is, We estimate the emotions of the business negotiation participants and adjust the way the summary is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned summary section is, When creating a summary, adjust the level of detail based on the importance of the business negotiation. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned summary section is, When creating summaries, different summarization algorithms are applied depending on the category of the business opportunity. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned summary section is, The system estimates the emotions of the business negotiation participants and adjusts the length of the summary based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned summary section is, When creating summaries, prioritize them based on when the business negotiations should be submitted. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned prioritization unit, The system estimates the emotions of the business negotiation participants and adjusts the prioritization criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned prioritization unit, When prioritizing, adjust priorities based on the importance of each deal. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned prioritization unit, When prioritizing, different prioritization algorithms are applied depending on the category of the opportunity. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned prioritization unit, It estimates the emotions of the sales participants and adjusts the order in which the results of the prioritization are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned prioritization unit, When prioritizing, determine priority based on when the business opportunity was submitted. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0197] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The introduction department introduces services that meet customer needs, A meeting minutes creation unit creates meeting minutes by voice input of business negotiations based on the services introduced by the aforementioned introduction unit, A verification unit that verifies action items based on the minutes created by the minutes creation unit, A learning unit learns the content of the agenda based on the action items confirmed by the aforementioned verification unit, An analysis unit analyzes and interprets the content of brainstorming based on the content learned by the aforementioned learning unit, Based on the content of the statements analyzed by the aforementioned analysis unit, the summarization unit creates a summary considering the advantages and disadvantages of each idea. The system includes a prioritization unit that performs prioritization based on the summaries created by the summarization unit. A system characterized by the following features.

2. The aforementioned introduction section is, We estimate customer emotions and adjust the timing of service introductions based on those estimated emotions. The system according to feature 1.

3. The aforementioned introduction section is, We analyze the customer's past purchase history and select the most suitable service. The system according to feature 1.

4. The aforementioned introduction section is, When introducing services, filtering is performed based on the customer's current projects and areas of interest. The system according to feature 1.

5. The aforementioned introductory section is, We estimate customer emotions and prioritize the services we recommend based on those estimated emotions. The system according to feature 1.

6. The aforementioned introduction section is, When introducing services, we prioritize recommending highly relevant services by taking into account the customer's geographical location. The system according to feature 1.

7. The aforementioned introductory section is, When introducing a service, we analyze the customer's social media activity and recommend relevant services. The system according to feature 1.

8. The aforementioned minutes preparation department, The system estimates the emotions of the business negotiation participants and adjusts the wording of the meeting minutes based on those estimated emotions. The system according to feature 1.

9. The aforementioned minutes preparation department, When creating meeting minutes, adjust the level of detail based on the importance of the business negotiation. The system according to feature 1.

10. The aforementioned minutes preparation department, When creating meeting minutes, different minute-taking algorithms are applied depending on the category of the business opportunity. The system according to feature 1.

Images