System

Abstract

To provide a system according to an embodiment that is configured to enable a sales clerk to efficiently check required data in a natural language.SOLUTION: A system according to an embodiment comprises: a collection unit; a reception unit; an analysis unit; and a providing unit. The collection unit is configured to collect data. The reception unit is configured to receive a natural language inquiry on the basis of the data collected by the collection unit. The analysis unit is configured to analyze the natural language inquiry received by the reception unit. The providing unit is configured to provide a result analyzed by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it is difficult for store clerks in the service industry to efficiently refer to the data they need, and there is room for improvement in operational efficiency.

[0005] The system according to the embodiment aims to enable store clerks to efficiently check required data in natural language. [Means for solving the problem]

[0006] A system according to an embodiment includes a collection unit, a reception unit, an analysis unit, and a provision unit. The collection unit collects data. The reception unit receives a natural language query based on the data collected by the collection unit. The analysis unit analyzes the natural language query received by the reception unit. The provision unit provides a result analyzed by the analysis unit. Effect of the Invention

[0007] The system according to the embodiment can enable store clerks to efficiently check required data in natural language. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard 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." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) The business efficiency system according to the embodiment of the present invention is a system for improving the efficiency of the work of store clerks in the service industry. This business efficiency system has a generation AI learn data such as a business manual and reservation status, and enables store clerks to instantly check the necessary data in natural language. This system allows store clerks to centrally inquire about distributed data, improving business efficiency. In addition, even in customer service, which requires knowledge, new employees can play an active role as immediate assets. For example, data such as a business manual and reservation status is learned by the generation AI. At this time, the generation AI comprehensively learns all data related to the work so that the information required by the store clerk can be provided quickly. For example, the business manual includes customer service procedures and methods for dealing with problems. The reservation status includes customer reservation information and special requests. Next, the store clerk makes an inquiry in natural language. For example, the inquiry is made such as "Tell me about today's reservation status" or "Tell me about the procedure for dealing with problems." This inquiry is input to the generation AI. The generation AI analyzes the input natural language inquiry and provides appropriate data. For example, in response to an inquiry such as "Tell me about today's reservation status," the generation AI obtains the latest reservation information from the reservation system and provides it to the store clerk. In addition, when a customer asks, "What are the steps to take to resolve a problem?", the system extracts the relevant steps from the work manual and provides them to the staff. This system allows staff to quickly obtain the necessary information, improving work efficiency. It also allows new staff to play an active role in customer service, which requires knowledge. For example, if a new staff member encounters a problem while serving a customer, they can immediately check the appropriate response method by asking the generation AI. Furthermore, this system also contributes to improving the skills of staff members. By frequently checking the work manual and reservation status through the generation AI, staff members naturally acquire knowledge about their work. This improves the skills of staff members and the quality of service. As a result, the business efficiency system can improve the efficiency of staff members' work and provide fast and accurate information.

[0029] The business efficiency improvement system according to the embodiment includes a collection unit, a reception unit, an analysis unit, and a provision unit. The collection unit collects data such as a business manual, a reservation status, customer feedback, and past trouble cases. For example, the collection unit can collect the business manual in a PDF format or a web page format. The collection unit can also collect the reservation status in a calendar format or a list format. Furthermore, the collection unit can collect customer feedback as a survey result or a review comment. Past trouble cases can be collected as a report or log data. The reception unit provides an interface in a voice input or chat format. For example, the reception unit can accept voice input using voice recognition technology. Furthermore, the reception unit can provide real-time chat using a chatbot. The analysis unit uses a generation AI to analyze inquiries in natural language and provide appropriate data. For example, the analysis unit can analyze inquiries in natural language using morphological analysis or semantic analysis. The provision unit provides information in a format such as text, image, or video. For example, the provision unit can provide information in plain text or HTML format. Furthermore, the provision unit can provide images in JPEG format or PNG format. Furthermore, the providing unit can provide videos in MP4 format or AVI format. As a result, the business efficiency improvement system according to the embodiment can improve the efficiency of the business of store clerks and provide information quickly and accurately.

[0030] The collection unit collects data such as business manuals, reservation status, customer feedback, and past trouble cases. Specifically, business manuals are collected in PDF format or web page format, which allows the latest business procedures and guidelines to be constantly understood. For example, when the business manual is updated, the collection unit automatically obtains the new version and shares it within the system. Reservation status is collected in calendar or list format, which allows reservation overlaps and availability to be checked in real time. For example, when a customer makes a reservation online in cooperation with a reservation system, the information is immediately sent to the collection unit and updated within the system. Customer feedback is collected as survey results and review comments, which allows the customer satisfaction and improvements to be understood. For example, when a customer answers a survey after using a service, the results are automatically sent to the collection unit and used for analysis in the analysis unit. Past trouble cases are collected as reports and log data, which allows measures to be taken to prevent similar troubles from recurring. For example, detailed log data is collected when a trouble occurs and used for detailed analysis in the analysis unit at a later date. This allows the collection unit to efficiently collect a variety of data and strengthen the information infrastructure of the entire system. Furthermore, the collection department can centrally manage these data and link them with other systems and departments as necessary. For example, the collected data is stored on a cloud server and made accessible to the analysis department and provision department. In addition, by adjusting the frequency and accuracy of data collection, flexible responses according to specific situations and conditions are possible. This allows the collection department to collect data efficiently and effectively and improve the performance of the entire system.

[0031] The reception unit provides an interface for voice input or chat format. Specifically, the reception unit can accept voice input using voice recognition technology. For example, when a customer makes an inquiry by phone, a voice recognition system automatically converts the voice into text and inputs it into the system. Also, a chatbot can be used to provide real-time chat. For example, when a customer makes an inquiry to a chatbot on a website, the chatbot automatically responds and provides the necessary information. The reception unit can quickly and accurately accept inquiries from customers through these interfaces. Furthermore, the reception unit transmits the contents of the customer's inquiry to the analysis unit and prepares data for providing an appropriate answer. For example, the contents of the inquiry input by voice are converted into text and transmitted to the analysis unit. This allows the reception unit to facilitate communication with customers and realize a prompt response. Furthermore, the reception unit can save the customer's inquiry history and utilize it for future inquiry responses. For example, based on the past inquiry content and response history, the reception unit can grasp the customer's needs and trends and provide a more appropriate response. This allows the reception unit to play an important role in improving customer satisfaction.

[0032] The analysis unit uses the generation AI to analyze inquiries in natural language and provide appropriate data. Specifically, the natural language inquiries can be analyzed using morphological analysis and semantic analysis. For example, if a customer inquires, "When is the next reservation?", the generation AI analyzes this inquiry and extracts the relevant information from the reservation status database. The generation AI makes full use of natural language processing technology to accurately understand the intention of the inquiry and generate the optimal answer. For example, it uses morphological analysis to analyze the structure of the sentence and uses semantic analysis to understand the meaning of the sentence. Furthermore, the generation AI can provide the optimal answer to a similar inquiry based on past inquiry history and trouble cases. For example, if there has been a similar inquiry in the past, it will refer to the response history to generate a quick and accurate answer. This allows the analysis unit to respond quickly and accurately to various inquiries from customers. Furthermore, the analysis unit can analyze the content of the inquiry and grasp the needs and trends of the customer. For example, if there are many inquiries about a specific service, measures such as strengthening information about that service can be taken. This allows the analysis unit to play an important role in improving customer satisfaction.

[0033] The providing unit provides information in the form of text, image, video, etc. Specifically, the providing unit can provide information in plain text or HTML format. For example, a concise answer can be provided in plain text to the content of a customer's inquiry. In addition, by using the HTML format, rich information including links and formats can be provided. Furthermore, the providing unit can provide images in JPEG format or PNG format. For example, an image for explaining how to use a product or an illustration showing a troubleshooting procedure can be provided. Furthermore, the providing unit can provide videos in MP4 format or AVI format. For example, a product demonstration video or a video explaining an operation procedure can be provided. This allows the providing unit to provide information to customers in various formats and deepen their understanding. Furthermore, the providing unit can collect feedback to continuously improve the accuracy and quality of the information provided. For example, a customer can leave an evaluation or a comment on the provided information, and the information is improved based on the feedback. This allows the providing unit to play an important role in improving customer satisfaction.

[0034] The collection unit can collect data on the business manual, reservation status, customer feedback, and past trouble cases. The collection unit can collect, for example, the business manual in PDF format or web page format. The collection unit can also collect the reservation status in calendar format or list format. Furthermore, the collection unit can collect customer feedback as survey results or review comments. Past trouble cases can be collected as reports or log data. This makes it possible to comprehensively collect all data related to the business. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input data on the business manual and reservation status into the generation AI, which then collects the data.

[0035] The reception unit can provide a voice input or a chat-style interface. The reception unit can accept voice input using, for example, voice recognition technology. For example, the reception unit recognizes the voice of a store clerk using a microphone and accepts inquiries in natural language. The reception unit can also provide real-time chat using a chatbot. For example, the reception unit provides a chat-style interface, and the store clerk can make inquiries in text. This allows the store clerk to make inquiries in a variety of ways. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit can input a voice input or a chat-style interface to the generation AI, and the generation AI can provide the interface.

[0036] The analysis unit can analyze a natural language query and provide appropriate data. The analysis unit can, for example, use a generation AI to analyze a natural language query. For example, the analysis unit can analyze a natural language query using morphological analysis and provide appropriate data. The analysis unit can also analyze a natural language query using semantic analysis and provide appropriate data. This makes it possible to analyze a natural language query and provide appropriate data. A part or all of the above-mentioned processing in the analysis unit is performed using the generation AI. For example, the analysis unit can input a natural language query to the generation AI, which can analyze the query and provide appropriate data.

[0037] The providing unit can provide information in the format of text, image, or video. The providing unit can provide information in, for example, plain text or HTML format. The providing unit can also provide images in JPEG format or PNG format. Furthermore, the providing unit can also provide videos in MP4 format or AVI format. This makes it possible to provide information in a variety of formats. Some or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input text, image, or video data to the generation AI, which can then provide the information.

[0038] The providing unit can have a function of setting the priority of information. The providing unit can set the priority based on, for example, the importance or urgency of information. For example, the providing unit provides information of high importance with priority and postpones information of low importance. The providing unit can also provide information of high urgency with priority and postpone information of low urgency. In this way, by setting the priority of information, important information can be provided with priority. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input the priority of information to the generation AI, and the generation AI can set the priority.

[0039] The providing unit can receive feedback from the store clerk and improve the accuracy of the generation AI. The providing unit, for example, provides an interface that receives feedback from the store clerk. For example, the providing unit provides a form in which the store clerk can input feedback. The providing unit can also collect feedback from the store clerk and use it to improve the accuracy of the generation AI. For example, the providing unit analyzes the feedback from the store clerk and uses it as learning data for the generation AI. In this way, the accuracy of the generation AI can be improved by receiving feedback from the store clerk. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input feedback from the store clerk to the generation AI, and the generation AI can analyze the feedback and improve the accuracy.

[0040] The providing unit can take security measures to protect the data. The providing unit can take security measures, for example, by encrypting the data or controlling access. For example, the providing unit encrypts and stores the data to prevent unauthorized access. The providing unit can also perform access control so that only specific users can access the data. In this way, security can be ensured by protecting the data. Some or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input data encryption and access control to the generation AI, which can take security measures.

[0041] The collection unit can collect the past performance data of the clerk in addition to the work manual and the reservation status, and can use it to improve the work. For example, the collection unit collects the past customer service evaluation data of the clerk, and the generation AI provides advice for improving the work. The collection unit can also collect the past sales data of the clerk, and the generation AI can propose a strategy for improving sales. Furthermore, the collection unit can collect the past working hours data of the clerk, and the generation AI can propose an efficient shift schedule. In this way, collecting the past performance data of the clerk can be useful for improving the work. Part or all of the above-mentioned processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the past performance data of the clerk to the generation AI, and the generation AI can analyze the data and provide advice for improving the work.

[0042] The collection unit can select the optimal data collection method in consideration of the clerk's shift information when collecting data. For example, the collection unit allows the generation AI to set the optimal data collection timing based on the clerk's shift information. The collection unit can also allow the generation AI to adjust the frequency of data collection in consideration of the clerk's shift information. Furthermore, the collection unit can allow the generation AI to set a priority order for data collection based on the clerk's shift information. This allows efficient data collection by selecting the optimal data collection method in consideration of the clerk's shift information. Some or all of the above-mentioned processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the clerk's shift information to the generation AI, and the generation AI can select the optimal data collection method.

[0043] The collection unit can prioritize collecting highly relevant data in consideration of the geographical location information of the clerk when collecting data. For example, when the clerk is in a specific store, the collection unit prioritizes collecting data related to the store. In addition, when the clerk is on the move, the collection unit can also collect data related to the current location. Furthermore, when the clerk is in a specific area, the collection unit can also prioritize collecting data related to the area. This enables efficient data collection by preferentially collecting highly relevant data in consideration of the geographical location information of the clerk. Part or all of the above-mentioned processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the geographical location information of the clerk to the generation AI, and the generation AI can prioritize collecting highly relevant data.

[0044] The collection unit can analyze the social media activities of the clerk at the time of data collection and collect related data. For example, the collection unit can analyze the social media posts of the clerk and collect related business data. The collection unit can also collect related customer data based on the social media follower information of the clerk. Furthermore, the collection unit can set the optimal data collection timing based on the time of the clerk's social media activity. This allows efficient data collection by analyzing the social media activities of the clerk and collecting related data. Some or all of the above-mentioned processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the social media activity data of the clerk to the generation AI, which analyzes the data and collects related data.

[0045] The reception unit can provide an interface that accepts gesture input in addition to voice input and chat format. For example, the reception unit can make an inquiry to the generation AI by a gesture such as a store clerk waving his / her hand. The reception unit can also cause the generation AI to provide specific data when the store clerk makes a specific gesture. Furthermore, the reception unit can cause the generation AI to adjust the interface when the store clerk operates the reception unit with a gesture. This allows inquiries to be made in a variety of ways by accepting gesture input. Some or all of the above-mentioned processing in the reception unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the reception unit can input gesture input data to the generation AI, which then analyzes the gesture and provides an interface.

[0046] The reception unit can select the optimal reception method by referring to the past inquiry history of the clerk at the time of reception. For example, the reception unit preferentially provides the reception method that the clerk has frequently used in the past. The reception unit can also provide the optimal interface based on the past inquiry history of the clerk. Furthermore, the reception unit can analyze the contents of the past inquiries of the clerk and preferentially provide related data. In this way, the optimal reception method can be selected by referring to the past inquiry history of the clerk. A part or all of the above-mentioned processing in the reception unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the reception unit can input the past inquiry history of the clerk to the generation AI, and the generation AI can select the optimal reception method.

[0047] The reception unit can provide an optimal interface based on the device information of the clerk at the time of reception. For example, when the clerk is using a smartphone, the reception unit provides an interface that matches the screen size. In addition, when the clerk is using a tablet, the reception unit can also provide an interface optimized for a large screen. Furthermore, when the clerk is using a desktop, the reception unit can also provide an interface that displays detailed information. This allows efficient inquiries by providing an optimal interface in consideration of the device information of the clerk. Part or all of the above-mentioned processing in the reception unit may be performed using a generation AI or may be performed without using a generation AI. For example, the reception unit can input the device information of the clerk to the generation AI, and the generation AI can provide an optimal interface.

[0048] The reception unit can select the optimal reception method based on the working status of the clerk at the time of reception. For example, when the clerk is working, the reception unit provides an interface that can be operated quickly. In addition, when the clerk is on a break, the reception unit can also provide an interface including detailed options. Furthermore, when the clerk is near the end of a shift, the reception unit can also provide a simple interface. This enables efficient inquiries by selecting the optimal reception method in consideration of the working status of the clerk. Part or all of the above-mentioned processing in the reception unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the reception unit can input the working status of the clerk into the generation AI, which can select the optimal reception method.

[0049] When analyzing an inquiry in natural language, the analysis unit can improve the accuracy of the analysis by referring to the past inquiry history of the store clerk. For example, the analysis unit can improve the accuracy of the analysis by the generation AI based on the past inquiry history of the store clerk. The analysis unit can also analyze the contents of the past inquiries of the store clerk and analyze related data preferentially. Furthermore, the analysis unit can also select the optimal analysis method by the generation AI by referring to the past inquiry history of the store clerk. In this way, the analysis accuracy can be improved by referring to the past inquiry history of the store clerk. A part or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the past inquiry history of the store clerk to the generation AI, and the generation AI can improve the accuracy of the analysis.

[0050] The analysis unit can select the optimal analysis method in consideration of the work performance data of the clerk during the analysis. For example, the analysis unit selects the optimal analysis method by the generation AI based on the past work performance data of the clerk. The analysis unit can also analyze the work performance data of the clerk, and the generation AI can improve the accuracy of the analysis. Furthermore, the analysis unit can provide the optimal analysis method by the generation AI in consideration of the work performance data of the clerk. This enables efficient analysis by selecting the optimal analysis method in consideration of the work performance data of the clerk. Some or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the work performance data of the clerk to the generation AI, and the generation AI can select the optimal analysis method.

[0051] The analysis unit can improve the analysis accuracy by taking into account the geographical location information of the clerk during the analysis. For example, when the clerk is in a particular store, the analysis unit preferentially analyzes data related to the store. In addition, when the clerk is on the move, the analysis unit can also analyze data related to the current location. Furthermore, when the clerk is in a particular area, the analysis unit can also preferentially analyze data related to the area. This allows for efficient analysis by improving the analysis accuracy by taking into account the geographical location information of the clerk. A part or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the geographical location information of the clerk to the generation AI, and the generation AI can preferentially analyze data that is highly relevant.

[0052] During the analysis, the analysis unit can analyze the social media activities of the clerk and use related data for the analysis. For example, the analysis unit can analyze the social media posts of the clerk and analyze related business data. The analysis unit can also analyze related customer data based on the social media follower information of the clerk. Furthermore, the analysis unit can select an optimal analysis method based on the time of the clerk's social media activity. This allows for efficient analysis by analyzing the social media activities of the clerk and using related data for the analysis. Some or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the social media activity data of the clerk to the generation AI, which analyzes the data, and use the related data for the analysis.

[0053] The providing unit can select the optimal information providing method by referring to the past feedback of the clerk at the time of providing. For example, the providing unit allows the generation AI to select the optimal information providing method based on the past feedback of the clerk. The providing unit can also analyze the past feedback of the clerk and provide related information preferentially. Furthermore, the providing unit can allow the generation AI to adjust the format of information provision by referring to the past feedback of the clerk. In this way, the optimal information providing method can be selected by referring to the past feedback of the clerk. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input the past feedback of the clerk to the generation AI, and the generation AI can select the optimal information providing method.

[0054] The providing unit can select the optimal information providing method in consideration of the work performance data of the clerk at the time of providing. For example, the providing unit selects the optimal information providing method by the generation AI based on the past work performance data of the clerk. The providing unit can also analyze the work performance data of the clerk, and the generation AI can improve the accuracy of the information provision. Furthermore, the providing unit can provide the optimal information providing method by the generation AI in consideration of the work performance data of the clerk. As a result, efficient information provision is possible by selecting the optimal information providing method in consideration of the work performance data of the clerk. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input the work performance data of the clerk to the generation AI, and the generation AI can select the optimal information providing method.

[0055] The providing unit can select the optimal information providing method based on the geographical location information of the clerk at the time of providing. For example, when the clerk is in a specific store, the providing unit can provide information related to the store with priority. In addition, when the clerk is on the move, the providing unit can also provide information related to the current location. Furthermore, when the clerk is in a specific area, the providing unit can also provide information related to the area with priority. This enables efficient information provision by selecting the optimal information providing method in consideration of the geographical location information of the clerk. Part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input the geographical location information of the clerk to the generation AI, which can select the optimal information providing method.

[0056] The providing unit can analyze the social media activity of the clerk at the time of providing and provide related information. The providing unit can, for example, analyze the social media posts of the clerk and provide related business information. The providing unit can also provide related customer information based on the social media follower information of the clerk. Furthermore, the providing unit can set the optimal information providing timing based on the time of the clerk's social media activity. This makes it possible to provide information efficiently by analyzing the social media activity of the clerk and providing related information. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input the social media activity data of the clerk to the generation AI, which can analyze the data and provide related information.

[0057] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0058] The collection unit can collect the past work history of store clerks and analyze their work patterns. For example, the collection unit can collect the past work hours and break times of store clerks, and the generation AI can propose an optimal shift schedule. The collection unit can also analyze the past work performance of store clerks, and the generation AI can provide advice for improving work. Furthermore, the collection unit can predict the fatigue level of store clerks based on their past work history, and the generation AI can propose appropriate break timing. In this way, efficient shift management and work improvement are possible by collecting the past work history of store clerks.

[0059] The analysis unit can analyze inquiry trends based on the content of past inquiries made by store clerks. For example, the analysis unit can identify the content of inquiries that store clerks frequently make and provide information related to that content preferentially. The analysis unit can also analyze the content of past inquiries made by store clerks and have the generation AI prepare related information in advance. Furthermore, the analysis unit can select the optimal analysis method for the generation AI based on the inquiry trends of store clerks. This makes it possible to provide and analyze information efficiently based on the content of past inquiries made by store clerks.

[0060] The provision unit can monitor the learning progress of the clerk and provide an individual learning plan. For example, the provision unit can evaluate the extent to which the clerk understands the work manual, and the generation AI can provide learning content to make up for any deficiencies. The provision unit can also have the generation AI suggest an appropriate learning schedule based on the clerk's learning progress. Furthermore, the provision unit can monitor the clerk's learning progress, and the generation AI can evaluate the effectiveness of the learning. In this way, by monitoring the clerk's learning progress, an individual learning plan can be provided and skill improvement can be supported.

[0061] The collection unit can collect data on the working environment of store clerks and make improvement proposals to improve work efficiency. For example, the collection unit can collect data such as the temperature, humidity, and lighting brightness of the working place of the store clerk, and the generation AI can propose the optimal working environment. The collection unit can also enable the generation AI to identify areas for improvement in the working environment based on the working environment data of the store clerk and propose specific improvement measures. Furthermore, the collection unit can collect data on the working environment of the store clerks, and the generation AI can create a long-term improvement plan for the working environment. In this way, by collecting the working environment data of the store clerks, improvement proposals for improving work efficiency are possible.

[0062] The providing unit can improve the accuracy of the information provision based on the past feedback of the store clerk. For example, the providing unit can analyze what kind of feedback the store clerk gave on the information provided in the past, and the generation AI can improve the accuracy of the information provision. The providing unit can also adjust the method of the information provision by the generation AI based on the past feedback of the store clerk. Furthermore, the providing unit can also select the optimal information provision method by the generation AI with reference to the past feedback of the store clerk. This makes it possible to improve the accuracy of the information provision based on the past feedback of the store clerk.

[0063] The process flow of the first embodiment will be briefly described below.

[0064] Step 1: The collection department collects data such as operation manuals, reservation status, customer feedback, and past trouble cases. For example, the collection department can collect operation manuals in PDF format or web page format. The collection department can also collect reservation status in calendar format or list format. Furthermore, the collection department can collect customer feedback as survey results or review comments. Past trouble cases can be collected as reports or log data. Step 2: The reception unit provides a voice input or chat-style interface to accept inquiries in natural language. For example, the reception unit can accept voice input using voice recognition technology. The reception unit can also provide real-time chat using a chatbot. Step 3: The analyzer uses the generative AI to analyze the natural language query and provide appropriate data. For example, the analyzer can analyze the natural language query using morphological analysis and semantic analysis. Step 4: The providing unit provides information in a format such as text, image, video, etc. For example, the providing unit can provide information in plain text or HTML format. The providing unit can also provide images in JPEG format or PNG format. Furthermore, the providing unit can provide videos in MP4 format or AVI format.

[0065] (Example 2) The business efficiency system according to the embodiment of the present invention is a system for improving the efficiency of the work of store clerks in the service industry. This business efficiency system has a generation AI learn data such as a business manual and reservation status, and enables store clerks to instantly check the necessary data in natural language. This system allows store clerks to centrally inquire about distributed data, improving business efficiency. In addition, even in customer service, which requires knowledge, new employees can play an active role as immediate assets. For example, data such as a business manual and reservation status is learned by the generation AI. At this time, the generation AI comprehensively learns all data related to the work so that the information required by the store clerk can be provided quickly. For example, the business manual includes customer service procedures and methods for dealing with problems. The reservation status includes customer reservation information and special requests. Next, the store clerk makes an inquiry in natural language. For example, the inquiry is made such as "Tell me about today's reservation status" or "Tell me about the procedure for dealing with problems." This inquiry is input to the generation AI. The generation AI analyzes the input natural language inquiry and provides appropriate data. For example, in response to an inquiry such as "Tell me about today's reservation status," the generation AI obtains the latest reservation information from the reservation system and provides it to the store clerk. In addition, when a customer asks, "What are the steps to take to resolve a problem?", the system extracts the relevant steps from the work manual and provides them to the staff. This system allows staff to quickly obtain the necessary information, improving work efficiency. It also allows new staff to play an active role in customer service, which requires knowledge. For example, if a new staff member encounters a problem while serving a customer, they can immediately check the appropriate response method by asking the generation AI. Furthermore, this system also contributes to improving the skills of staff members. By frequently checking the work manual and reservation status through the generation AI, staff members naturally acquire knowledge about their work. This improves the skills of staff members and the quality of service. As a result, the business efficiency system can improve the efficiency of staff members' work and provide fast and accurate information.

[0066] The business efficiency improvement system according to the embodiment includes a collection unit, a reception unit, an analysis unit, and a provision unit. The collection unit collects data such as a business manual, a reservation status, customer feedback, and past trouble cases. For example, the collection unit can collect the business manual in a PDF format or a web page format. The collection unit can also collect the reservation status in a calendar format or a list format. Furthermore, the collection unit can collect customer feedback as a survey result or a review comment. Past trouble cases can be collected as a report or log data. The reception unit provides an interface in a voice input or chat format. For example, the reception unit can accept voice input using voice recognition technology. Furthermore, the reception unit can provide real-time chat using a chatbot. The analysis unit uses a generation AI to analyze inquiries in natural language and provide appropriate data. For example, the analysis unit can analyze inquiries in natural language using morphological analysis or semantic analysis. The provision unit provides information in a format such as text, image, or video. For example, the provision unit can provide information in plain text or HTML format. Furthermore, the provision unit can provide images in JPEG format or PNG format. Furthermore, the providing unit can provide videos in MP4 format or AVI format. As a result, the business efficiency improvement system according to the embodiment can improve the efficiency of the business of store clerks and provide information quickly and accurately.

[0067] The collection unit collects data such as business manuals, reservation status, customer feedback, and past trouble cases. Specifically, business manuals are collected in PDF format or web page format, which allows the latest business procedures and guidelines to be constantly understood. For example, when the business manual is updated, the collection unit automatically obtains the new version and shares it within the system. Reservation status is collected in calendar or list format, which allows reservation overlaps and availability to be checked in real time. For example, when a customer makes a reservation online in cooperation with a reservation system, the information is immediately sent to the collection unit and updated within the system. Customer feedback is collected as survey results and review comments, which allows the customer satisfaction and improvements to be understood. For example, when a customer answers a survey after using a service, the results are automatically sent to the collection unit and used for analysis in the analysis unit. Past trouble cases are collected as reports and log data, which allows measures to be taken to prevent similar troubles from recurring. For example, detailed log data is collected when a trouble occurs and used for detailed analysis in the analysis unit at a later date. This allows the collection unit to efficiently collect a variety of data and strengthen the information infrastructure of the entire system. Furthermore, the collection department can centrally manage these data and link them with other systems and departments as necessary. For example, the collected data is stored on a cloud server and made accessible to the analysis department and provision department. In addition, by adjusting the frequency and accuracy of data collection, flexible responses according to specific situations and conditions are possible. This allows the collection department to collect data efficiently and effectively and improve the performance of the entire system.

[0068] The reception unit provides an interface for voice input or chat format. Specifically, the reception unit can accept voice input using voice recognition technology. For example, when a customer makes an inquiry by phone, a voice recognition system automatically converts the voice into text and inputs it into the system. Also, a chatbot can be used to provide real-time chat. For example, when a customer makes an inquiry to a chatbot on a website, the chatbot automatically responds and provides the necessary information. The reception unit can quickly and accurately accept inquiries from customers through these interfaces. Furthermore, the reception unit transmits the contents of the customer's inquiry to the analysis unit and prepares data for providing an appropriate answer. For example, the contents of the inquiry input by voice are converted into text and transmitted to the analysis unit. This allows the reception unit to facilitate communication with customers and realize a prompt response. Furthermore, the reception unit can save the customer's inquiry history and utilize it for future inquiry responses. For example, based on the past inquiry content and response history, the reception unit can grasp the customer's needs and trends and provide a more appropriate response. This allows the reception unit to play an important role in improving customer satisfaction.

[0069] The analysis unit uses the generation AI to analyze inquiries in natural language and provide appropriate data. Specifically, the natural language inquiries can be analyzed using morphological analysis and semantic analysis. For example, if a customer inquires, "When is the next reservation?", the generation AI analyzes this inquiry and extracts the relevant information from the reservation status database. The generation AI makes full use of natural language processing technology to accurately understand the intention of the inquiry and generate the optimal answer. For example, it uses morphological analysis to analyze the structure of the sentence and uses semantic analysis to understand the meaning of the sentence. Furthermore, the generation AI can provide the optimal answer to a similar inquiry based on past inquiry history and trouble cases. For example, if there has been a similar inquiry in the past, it will refer to the response history to generate a quick and accurate answer. This allows the analysis unit to respond quickly and accurately to various inquiries from customers. Furthermore, the analysis unit can analyze the content of the inquiry and grasp the needs and trends of the customer. For example, if there are many inquiries about a specific service, measures such as strengthening information about that service can be taken. This allows the analysis unit to play an important role in improving customer satisfaction.

[0070] The providing unit provides information in the form of text, image, video, etc. Specifically, the providing unit can provide information in plain text or HTML format. For example, a concise answer can be provided in plain text to the content of a customer's inquiry. In addition, by using the HTML format, rich information including links and formats can be provided. Furthermore, the providing unit can provide images in JPEG format or PNG format. For example, an image for explaining how to use a product or an illustration showing a troubleshooting procedure can be provided. Furthermore, the providing unit can provide videos in MP4 format or AVI format. For example, a product demonstration video or a video explaining an operation procedure can be provided. This allows the providing unit to provide information to customers in various formats and deepen their understanding. Furthermore, the providing unit can collect feedback to continuously improve the accuracy and quality of the information provided. For example, a customer can leave an evaluation or a comment on the provided information, and the information is improved based on the feedback. This allows the providing unit to play an important role in improving customer satisfaction.

[0071] The collection unit can collect data on the business manual, reservation status, customer feedback, and past trouble cases. The collection unit can collect, for example, the business manual in PDF format or web page format. The collection unit can also collect the reservation status in calendar format or list format. Furthermore, the collection unit can collect customer feedback as survey results or review comments. Past trouble cases can be collected as reports or log data. This makes it possible to comprehensively collect all data related to the business. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input data on the business manual and reservation status into the generation AI, which then collects the data.

[0072] The reception unit can provide a voice input or a chat-style interface. The reception unit can accept voice input using, for example, voice recognition technology. For example, the reception unit recognizes the voice of a store clerk using a microphone and accepts inquiries in natural language. The reception unit can also provide real-time chat using a chatbot. For example, the reception unit provides a chat-style interface, and the store clerk can make inquiries in text. This allows the store clerk to make inquiries in a variety of ways. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit can input a voice input or a chat-style interface to the generation AI, and the generation AI can provide the interface.

[0073] The analysis unit can analyze a natural language query and provide appropriate data. The analysis unit can, for example, use a generation AI to analyze a natural language query. For example, the analysis unit can analyze a natural language query using morphological analysis and provide appropriate data. The analysis unit can also analyze a natural language query using semantic analysis and provide appropriate data. This makes it possible to analyze a natural language query and provide appropriate data. A part or all of the above-mentioned processing in the analysis unit is performed using the generation AI. For example, the analysis unit can input a natural language query to the generation AI, which can analyze the query and provide appropriate data.

[0074] The providing unit can provide information in the format of text, image, or video. The providing unit can provide information in, for example, plain text or HTML format. The providing unit can also provide images in JPEG format or PNG format. Furthermore, the providing unit can also provide videos in MP4 format or AVI format. This makes it possible to provide information in a variety of formats. Some or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input text, image, or video data to the generation AI, which can then provide the information.

[0075] The providing unit can have a function of setting the priority of information. The providing unit can set the priority based on, for example, the importance or urgency of information. For example, the providing unit provides information of high importance with priority and postpones information of low importance. The providing unit can also provide information of high urgency with priority and postpone information of low urgency. In this way, by setting the priority of information, important information can be provided with priority. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input the priority of information to the generation AI, and the generation AI can set the priority.

[0076] The providing unit can receive feedback from the store clerk and improve the accuracy of the generation AI. The providing unit, for example, provides an interface that receives feedback from the store clerk. For example, the providing unit provides a form in which the store clerk can input feedback. The providing unit can also collect feedback from the store clerk and use it to improve the accuracy of the generation AI. For example, the providing unit analyzes the feedback from the store clerk and uses it as learning data for the generation AI. In this way, the accuracy of the generation AI can be improved by receiving feedback from the store clerk. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input feedback from the store clerk to the generation AI, and the generation AI can analyze the feedback and improve the accuracy.

[0077] The providing unit can take security measures to protect the data. The providing unit can take security measures, for example, by encrypting the data or controlling access. For example, the providing unit encrypts and stores the data to prevent unauthorized access. The providing unit can also perform access control so that only specific users can access the data. In this way, security can be ensured by protecting the data. Some or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input data encryption and access control to the generation AI, which can take security measures.

[0078] The collection unit can estimate the user's emotion and adjust the timing of data collection based on the estimated user's emotion. For example, when a store clerk is stressed, the generation AI automatically delays data collection, and collects data when the store clerk is relaxed. In addition, when a store clerk is busy, the collection unit can also temporarily stop data collection by the generation AI and resume it when the store clerk is calm. Furthermore, when a store clerk is relaxed, the collection unit can also have the generation AI actively collect data and quickly provide the information required by the store clerk. This enables efficient data collection by adjusting the timing of data collection based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the emotion data of the store clerk to the generation AI, and the generation AI can estimate the emotion and adjust the timing of data collection.

[0079] The collection unit can collect the past performance data of the clerk in addition to the work manual and the reservation status, and can use it to improve the work. For example, the collection unit collects the past customer service evaluation data of the clerk, and the generation AI provides advice for improving the work. The collection unit can also collect the past sales data of the clerk, and the generation AI can propose a strategy for improving sales. Furthermore, the collection unit can collect the past working hours data of the clerk, and the generation AI can propose an efficient shift schedule. In this way, collecting the past performance data of the clerk can be useful for improving the work. Part or all of the above-mentioned processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the past performance data of the clerk to the generation AI, and the generation AI can analyze the data and provide advice for improving the work.

[0080] The collection unit can select the optimal data collection method in consideration of the clerk's shift information when collecting data. For example, the collection unit allows the generation AI to set the optimal data collection timing based on the clerk's shift information. The collection unit can also allow the generation AI to adjust the frequency of data collection in consideration of the clerk's shift information. Furthermore, the collection unit can allow the generation AI to set a priority order for data collection based on the clerk's shift information. This allows efficient data collection by selecting the optimal data collection method in consideration of the clerk's shift information. Some or all of the above-mentioned processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the clerk's shift information to the generation AI, and the generation AI can select the optimal data collection method.

[0081] The collection unit can estimate the user's emotion and determine the priority of data to be collected based on the estimated user's emotion. For example, when the clerk is stressed, the collection unit allows the generation AI to postpone collection of data with low importance. In addition, when the clerk is relaxed, the collection unit can also allow the generation AI to collect data with high importance preferentially. Furthermore, when the clerk is busy, the collection unit can also allow the generation AI to collect only the minimum amount of data necessary. This enables efficient data collection by determining the priority of data to be collected based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the emotion data of the clerk to the generation AI, which can estimate the emotion and determine the priority of the data.

[0082] The collection unit can prioritize collecting highly relevant data in consideration of the geographical location information of the clerk when collecting data. For example, when the clerk is in a specific store, the collection unit prioritizes collecting data related to the store. In addition, when the clerk is on the move, the collection unit can also collect data related to the current location. Furthermore, when the clerk is in a specific area, the collection unit can also prioritize collecting data related to the area. This enables efficient data collection by preferentially collecting highly relevant data in consideration of the geographical location information of the clerk. Part or all of the above-mentioned processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the geographical location information of the clerk to the generation AI, and the generation AI can prioritize collecting highly relevant data.

[0083] The collection unit can analyze the social media activities of the clerk at the time of data collection and collect related data. For example, the collection unit can analyze the social media posts of the clerk and collect related business data. The collection unit can also collect related customer data based on the social media follower information of the clerk. Furthermore, the collection unit can set the optimal data collection timing based on the time of the clerk's social media activity. This allows efficient data collection by analyzing the social media activities of the clerk and collecting related data. Some or all of the above-mentioned processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the social media activity data of the clerk to the generation AI, which analyzes the data and collects related data.

[0084] The reception unit can estimate the user's emotion and adjust the reception interface based on the estimated user's emotion. For example, when the clerk is nervous, the reception unit provides a simple and highly visible interface. Furthermore, when the clerk is relaxed, the reception unit can also provide an interface including detailed options. Furthermore, when the clerk is in a hurry, the reception unit can also provide an interface that can be operated quickly. This allows efficient inquiries by adjusting the reception interface based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the reception unit can input the emotion data of the clerk to the generation AI, which can estimate the emotion and adjust the interface.

[0085] The reception unit can provide an interface that accepts gesture input in addition to voice input and chat format. For example, the reception unit can make an inquiry to the generation AI by a gesture such as a store clerk waving his / her hand. The reception unit can also cause the generation AI to provide specific data when the store clerk makes a specific gesture. Furthermore, the reception unit can cause the generation AI to adjust the interface when the store clerk operates the reception unit with a gesture. This allows inquiries to be made in a variety of ways by accepting gesture input. Some or all of the above-mentioned processing in the reception unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the reception unit can input gesture input data to the generation AI, which then analyzes the gesture and provides an interface.

[0086] The reception unit can select the optimal reception method by referring to the past inquiry history of the clerk at the time of reception. For example, the reception unit preferentially provides the reception method that the clerk has frequently used in the past. The reception unit can also provide the optimal interface based on the past inquiry history of the clerk. Furthermore, the reception unit can analyze the contents of the past inquiries of the clerk and preferentially provide related data. In this way, the optimal reception method can be selected by referring to the past inquiry history of the clerk. A part or all of the above-mentioned processing in the reception unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the reception unit can input the past inquiry history of the clerk to the generation AI, and the generation AI can select the optimal reception method.

[0087] The reception unit can estimate the user's emotion and determine the priority of inquiries to be received based on the estimated user's emotion. For example, when the clerk is stressed, the reception unit postpones inquiries with low importance. Also, when the clerk is relaxed, the reception unit can preferentially receive inquiries with high importance. Furthermore, when the clerk is busy, the reception unit can only receive the minimum number of inquiries necessary. This enables efficient inquiries by determining the priority of inquiries based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the reception unit can input emotion data of the clerk to the generation AI, which can estimate the emotion and determine the priority of the inquiries.

[0088] The reception unit can provide an optimal interface based on the device information of the clerk at the time of reception. For example, when the clerk is using a smartphone, the reception unit provides an interface that matches the screen size. In addition, when the clerk is using a tablet, the reception unit can also provide an interface optimized for a large screen. Furthermore, when the clerk is using a desktop, the reception unit can also provide an interface that displays detailed information. This allows efficient inquiries by providing an optimal interface in consideration of the device information of the clerk. Part or all of the above-mentioned processing in the reception unit may be performed using a generation AI or may be performed without using a generation AI. For example, the reception unit can input the device information of the clerk to the generation AI, and the generation AI can provide an optimal interface.

[0089] The reception unit can select the optimal reception method based on the working status of the clerk at the time of reception. For example, when the clerk is working, the reception unit provides an interface that can be operated quickly. In addition, when the clerk is on a break, the reception unit can also provide an interface including detailed options. Furthermore, when the clerk is near the end of a shift, the reception unit can also provide a simple interface. This enables efficient inquiries by selecting the optimal reception method in consideration of the working status of the clerk. Part or all of the above-mentioned processing in the reception unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the reception unit can input the working status of the clerk into the generation AI, which can select the optimal reception method.

[0090] The analysis unit can estimate the user's emotion and adjust the accuracy of the analysis based on the estimated user's emotion. For example, when the store clerk is nervous, the generation AI increases the accuracy of the analysis and provides reliable information. In addition, when the store clerk is relaxed, the generation AI can adjust the accuracy of the analysis and provide information quickly. Furthermore, when the store clerk is in a hurry, the analysis unit can optimize the accuracy of the analysis and provide quick and accurate information. This enables efficient analysis by adjusting the accuracy of the analysis based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the emotion data of the store clerk to the generation AI, which can estimate the emotion and adjust the accuracy of the analysis.

[0091] When analyzing an inquiry in natural language, the analysis unit can improve the accuracy of the analysis by referring to the past inquiry history of the store clerk. For example, the analysis unit can improve the accuracy of the analysis by the generation AI based on the past inquiry history of the store clerk. The analysis unit can also analyze the contents of the past inquiries of the store clerk and analyze related data preferentially. Furthermore, the analysis unit can also select the optimal analysis method by the generation AI by referring to the past inquiry history of the store clerk. In this way, the analysis accuracy can be improved by referring to the past inquiry history of the store clerk. A part or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the past inquiry history of the store clerk to the generation AI, and the generation AI can improve the accuracy of the analysis.

[0092] The analysis unit can select the optimal analysis method in consideration of the work performance data of the clerk during the analysis. For example, the analysis unit selects the optimal analysis method by the generation AI based on the past work performance data of the clerk. The analysis unit can also analyze the work performance data of the clerk, and the generation AI can improve the accuracy of the analysis. Furthermore, the analysis unit can provide the optimal analysis method by the generation AI in consideration of the work performance data of the clerk. This enables efficient analysis by selecting the optimal analysis method in consideration of the work performance data of the clerk. Some or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the work performance data of the clerk to the generation AI, and the generation AI can select the optimal analysis method.

[0093] The analysis unit can estimate the user's emotion and adjust the display method of the analysis result based on the estimated user's emotion. For example, when the clerk is nervous, the analysis unit provides a simple and highly visible display method. Furthermore, when the clerk is relaxed, the analysis unit can also provide a display method including detailed information. Furthermore, when the clerk is in a hurry, the analysis unit can also provide a display method that focuses on the main points. This enables efficient information provision by adjusting the display method of the analysis result based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the emotion data of the clerk to the generation AI, which can estimate the emotion and adjust the display method.

[0094] The analysis unit can improve the analysis accuracy by taking into account the geographical location information of the clerk during the analysis. For example, when the clerk is in a particular store, the analysis unit preferentially analyzes data related to the store. In addition, when the clerk is on the move, the analysis unit can also analyze data related to the current location. Furthermore, when the clerk is in a particular area, the analysis unit can also preferentially analyze data related to the area. This allows for efficient analysis by improving the analysis accuracy by taking into account the geographical location information of the clerk. A part or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the geographical location information of the clerk to the generation AI, and the generation AI can preferentially analyze data that is highly relevant.

[0095] During the analysis, the analysis unit can analyze the social media activities of the clerk and use related data for the analysis. For example, the analysis unit can analyze the social media posts of the clerk and analyze related business data. The analysis unit can also analyze related customer data based on the social media follower information of the clerk. Furthermore, the analysis unit can select an optimal analysis method based on the time of the clerk's social media activity. This allows for efficient analysis by analyzing the social media activities of the clerk and using related data for the analysis. Some or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the social media activity data of the clerk to the generation AI, which analyzes the data, and use the related data for the analysis.

[0096] The providing unit can estimate the user's emotion and adjust the format of the information to be provided based on the estimated user's emotion. For example, when the clerk is nervous, the providing unit provides information in a simple text format. Furthermore, when the clerk is relaxed, the providing unit can also provide information including detailed images and videos. Furthermore, when the clerk is in a hurry, the providing unit can also provide concise information with the main points. This allows efficient information provision by adjusting the format of the information to be provided based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input the emotion data of the clerk to the generation AI, which can estimate the emotion and adjust the format of the information.

[0097] The providing unit can select the optimal information providing method by referring to the past feedback of the clerk at the time of providing. For example, the providing unit allows the generation AI to select the optimal information providing method based on the past feedback of the clerk. The providing unit can also analyze the past feedback of the clerk and provide related information preferentially. Furthermore, the providing unit can allow the generation AI to adjust the format of information provision by referring to the past feedback of the clerk. In this way, the optimal information providing method can be selected by referring to the past feedback of the clerk. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input the past feedback of the clerk to the generation AI, and the generation AI can select the optimal information providing method.

[0098] The providing unit can select the optimal information providing method in consideration of the work performance data of the clerk at the time of providing. For example, the providing unit selects the optimal information providing method by the generation AI based on the past work performance data of the clerk. The providing unit can also analyze the work performance data of the clerk, and the generation AI can improve the accuracy of the information provision. Furthermore, the providing unit can provide the optimal information providing method by the generation AI in consideration of the work performance data of the clerk. As a result, efficient information provision is possible by selecting the optimal information providing method in consideration of the work performance data of the clerk. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input the work performance data of the clerk to the generation AI, and the generation AI can select the optimal information providing method.

[0099] The providing unit can estimate the user's emotion and determine the priority of information to be provided based on the estimated user's emotion. For example, when the clerk is stressed, the providing unit postpones the provision of information with a low importance. In addition, when the clerk is relaxed, the providing unit can also provide information with a high importance in priority. Furthermore, when the clerk is busy, the providing unit can provide only the minimum necessary information. This enables efficient information provision by determining the priority of information to be provided based on the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input emotion data of the clerk to the generation AI, which can estimate the emotion and determine the priority of information.

[0100] The providing unit can select the optimal information providing method based on the geographical location information of the clerk at the time of providing. For example, when the clerk is in a specific store, the providing unit can provide information related to the store with priority. In addition, when the clerk is on the move, the providing unit can also provide information related to the current location. Furthermore, when the clerk is in a specific area, the providing unit can also provide information related to the area with priority. This enables efficient information provision by selecting the optimal information providing method in consideration of the geographical location information of the clerk. Part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input the geographical location information of the clerk to the generation AI, which can select the optimal information providing method.

[0101] The providing unit can analyze the social media activity of the clerk at the time of providing and provide related information. The providing unit can, for example, analyze the social media posts of the clerk and provide related business information. The providing unit can also provide related customer information based on the social media follower information of the clerk. Furthermore, the providing unit can set the optimal information providing timing based on the time of the clerk's social media activity. This makes it possible to provide information efficiently by analyzing the social media activity of the clerk and providing related information. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input the social media activity data of the clerk to the generation AI, which can analyze the data and provide related information.

[0102] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0103] The business efficiency system can further include a health management unit that monitors the health of store clerks. The health management unit can monitor the heart rate and stress level of store clerks in real time, and issue an alert if an abnormality is detected. For example, if the heart rate of a store clerk rises sharply, the health management unit can send a notification encouraging the store clerk to take a break. Also, if the stress level is high, the health management unit can suggest ways to relax. Furthermore, the health management unit can collect health data of store clerks and use it for long-term health management. In this way, by monitoring the health of store clerks, it is possible to contribute to maintaining the health of store clerks as well as improving business efficiency.

[0104] The collection unit can collect the past work history of store clerks and analyze their work patterns. For example, the collection unit can collect the past work hours and break times of store clerks, and the generation AI can propose an optimal shift schedule. The collection unit can also analyze the past work performance of store clerks, and the generation AI can provide advice for improving work. Furthermore, the collection unit can predict the fatigue level of store clerks based on their past work history, and the generation AI can propose appropriate break timing. In this way, efficient shift management and work improvement are possible by collecting the past work history of store clerks.

[0105] The reception unit can analyze the tone and speed of the clerk's voice to infer his / her emotions. For example, if the clerk's voice is high and fast, it can infer that he / she is nervous and provide a simple interface. If the clerk's voice is low and slow, it can infer that he / she is relaxed and provide an interface including detailed options. Furthermore, if the clerk's voice is unstable, it can infer that he / she is stressed and provide an interface that can be operated quickly. In this way, by analyzing the tone and speed of the clerk's voice, it is possible to provide an optimal interface based on emotions.

[0106] The analysis unit can analyze inquiry trends based on the content of past inquiries made by store clerks. For example, the analysis unit can identify the content of inquiries that store clerks frequently make and provide information related to that content preferentially. The analysis unit can also analyze the content of past inquiries made by store clerks and have the generation AI prepare related information in advance. Furthermore, the analysis unit can select the optimal analysis method for the generation AI based on the inquiry trends of store clerks. This makes it possible to provide and analyze information efficiently based on the content of past inquiries made by store clerks.

[0107] The provision unit can monitor the learning progress of the clerk and provide an individual learning plan. For example, the provision unit can evaluate the extent to which the clerk understands the work manual, and the generation AI can provide learning content to make up for any deficiencies. The provision unit can also have the generation AI suggest an appropriate learning schedule based on the clerk's learning progress. Furthermore, the provision unit can monitor the clerk's learning progress, and the generation AI can evaluate the effectiveness of the learning. In this way, by monitoring the clerk's learning progress, an individual learning plan can be provided and skill improvement can be supported.

[0108] The providing unit can estimate the emotion of the clerk and adjust the frequency of information provision based on the estimated emotion. For example, if the clerk is stressed, the frequency of information provision can be reduced, and if the clerk is relaxed, the frequency of information provision can be increased. Also, if the clerk is busy, only the minimum necessary information can be provided, and if the clerk has time, detailed information can be provided. Furthermore, if the clerk is emotionally unstable, the provision of information can be temporarily stopped and resumed when the clerk has calmed down. In this way, the frequency of information provision can be adjusted based on the emotion of the clerk, enabling efficient information provision.

[0109] The collection unit can collect data on the working environment of store clerks and make improvement proposals to improve work efficiency. For example, the collection unit can collect data such as the temperature, humidity, and lighting brightness of the working place of the store clerk, and the generation AI can propose the optimal working environment. The collection unit can also enable the generation AI to identify areas for improvement in the working environment based on the working environment data of the store clerk and propose specific improvement measures. Furthermore, the collection unit can collect data on the working environment of the store clerks, and the generation AI can create a long-term improvement plan for the working environment. In this way, by collecting the working environment data of the store clerks, improvement proposals for improving work efficiency are possible.

[0110] The reception unit can estimate the emotion of the clerk and adjust the response speed of the receptionist based on the estimated emotion. For example, if the clerk is nervous, the response speed can be increased to provide a quick response. Also, if the clerk is relaxed, the response speed can be adjusted to provide a detailed explanation. Furthermore, if the clerk is in a hurry, the response speed can be optimized to provide necessary information quickly. In this way, by adjusting the response speed of the receptionist based on the emotion of the clerk, efficient inquiry handling is possible.

[0111] The analysis unit can estimate the emotion of the store clerk and adjust the method of feedback of the analysis result based on the estimated emotion. For example, if the store clerk is nervous, simple and highly visible feedback can be provided. If the store clerk is relaxed, detailed feedback can be provided. Furthermore, if the store clerk is in a hurry, concise feedback that focuses on the main points can be provided. In this way, by adjusting the feedback method of the analysis result based on the emotion of the store clerk, it is possible to provide information efficiently.

[0112] The providing unit can improve the accuracy of the information provision based on the past feedback of the store clerk. For example, the providing unit can analyze what kind of feedback the store clerk gave on the information provided in the past, and the generation AI can improve the accuracy of the information provision. The providing unit can also adjust the method of the information provision by the generation AI based on the past feedback of the store clerk. Furthermore, the providing unit can also select the optimal information provision method by the generation AI with reference to the past feedback of the store clerk. This makes it possible to improve the accuracy of the information provision based on the past feedback of the store clerk.

[0113] The process flow of the second embodiment will be briefly described below.

[0114] Step 1: The collection department collects data such as operation manuals, reservation status, customer feedback, and past trouble cases. For example, the collection department can collect operation manuals in PDF format or web page format. The collection department can also collect reservation status in calendar format or list format. Furthermore, the collection department can collect customer feedback as survey results or review comments. Past trouble cases can be collected as reports or log data. Step 2: The reception unit provides a voice input or chat-style interface to accept inquiries in natural language. For example, the reception unit can accept voice input using voice recognition technology. The reception unit can also provide real-time chat using a chatbot. Step 3: The analyzer uses the generative AI to analyze the natural language query and provide appropriate data. For example, the analyzer can analyze the natural language query using morphological analysis and semantic analysis. Step 4: The providing unit provides information in a format such as text, image, video, etc. For example, the providing unit can provide information in plain text or HTML format. The providing unit can also provide images in JPEG format or PNG format. Furthermore, the providing unit can provide videos in MP4 format or AVI format.

[0115] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0116] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0117] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0118] Each of the multiple elements including the above-mentioned collection unit, reception unit, analysis unit, and provision unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects data such as a business manual and reservation status using the camera 42 and communication I / F 44 of the smart device 14. The reception unit provides a voice input or chat-style interface using the touch panel 38A and microphone 38B of the smart device 14. The analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes inquiries in natural language using a generation AI. The provision unit provides information in the form of text, images, videos, etc. using the display 40A and speaker 40B of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0119] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0120] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0121] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0122] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0123] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0124] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0125] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0126] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0127] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0128] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0129] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0130] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0131] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0132] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0133] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0134] Each of the multiple elements including the above-mentioned collection unit, reception unit, analysis unit, and provision unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects data such as a business manual and reservation status using the camera 42 and communication I / F 44 of the smart glasses 214. The reception unit provides a voice input or chat-style interface using the microphone 238 of the smart glasses 214. The analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes inquiries in natural language using a generation AI. The provision unit provides information in the form of text, images, videos, etc. using the speaker 240 of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0135] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0136] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0137] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0138] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

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

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0141] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0142] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0143] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0144] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0145] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0146] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0147] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0148] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0149] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0150] Each of the multiple elements including the above-mentioned collection unit, reception unit, analysis unit, and provision unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects data such as a business manual and reservation status using the camera 42 and communication I / F 44 of the headset type terminal 314. The reception unit provides a voice input or chat-style interface using the microphone 238 of the headset type terminal 314. The analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes inquiries in natural language using a generation AI. The provision unit provides information in the form of text, images, videos, etc. using the display 343 and speaker 240 of the headset type terminal 314. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0151] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0152] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0153] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0154] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

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

[0156] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0157] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0158] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0159] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0160] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0161] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0162] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0163] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0164] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0165] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0166] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0167] Each of the multiple elements including the above-mentioned collection unit, reception unit, analysis unit, and provision unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects data such as a business manual and reservation status using the camera 42 and communication I / F 44 of the robot 414. The reception unit provides a voice input or chat-style interface using the microphone 238 of the robot 414. The analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes inquiries in natural language using a generation AI. The provision unit provides information in the form of text, images, videos, etc. using the speaker 240 and control target 443 of the robot 414. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0168] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0169] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0170] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0171] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0172] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0173] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0174] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0175] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0176] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0177] In addition, 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 upon request from the data processing device 12.

[0178] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0179] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0180] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0181] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0182] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0183] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0184] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0185] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0186] (Appendix 1) A collection unit that collects data; a reception unit that receives a query in a natural language based on the data collected by the collection unit; an analysis unit that analyzes the natural language inquiry received by the reception unit; A providing unit that provides the results analyzed by the analyzing unit. A system characterized by: (Appendix 2) The collecting unit includes: Collect data on operation manuals, reservation status, customer feedback, and past trouble cases 2. The system of claim 1, (Appendix 3) The reception unit is Providing a voice-to-text or chat-style interface 2. The system of claim 1, (Appendix 4) The analysis unit is Analyze natural language queries and provide relevant data 2. The system of claim 1, (Appendix 5) The providing unit is Provide information in the form of text, images, and videos 2. The system of claim 1, (Appendix 6) The providing unit is Equipped with the ability to set information priorities 2. The system of claim 1, (Appendix 7) The providing unit is Accept feedback from store associates to improve the accuracy of generative AI 2. The system of claim 1, (Appendix 8) The providing unit is Implement security measures to protect data 2. The system of claim 1, (Appendix 9) The collecting unit includes: To estimate a user's emotion and adjust the timing of data collection based on the estimated user's emotion. 2. The system of claim 1, (Appendix 10) The collecting unit includes: In addition to work manuals and reservation status, past performance data of store staff is collected to help improve operations. 2. The system of claim 1, (Appendix 11) The collecting unit includes: When collecting data, select the optimal data collection method taking into account the store staff's shift information. 2. The system of claim 1, (Appendix 12) The collecting unit includes: Infer user sentiment and prioritize data to be collected based on the inferred user sentiment 2. The system of claim 1, (Appendix 13) The collecting unit includes: When collecting data, prioritize collection of relevant data by considering the geographic location of store associates 2. The system of claim 1, (Appendix 14) The collecting unit includes: During data collection, analyze the social media activity of store associates and collect relevant data 2. The system of claim 1, (Appendix 15) The reception unit is Estimate the user's emotions and adjust the reception interface based on the estimated user emotions. 2. The system of claim 1, (Appendix 16) The reception unit is Provide an interface that accepts gesture input in addition to voice input and chat format. 2. The system of claim 1, (Appendix 17) The reception unit is When accepting a customer, the system will refer to the staff member's past inquiry history and select the most appropriate reception method. 2. The system of claim 1, (Appendix 18) The reception unit is Estimate the user's emotions and prioritize inquiries based on the estimated user emotions. 2. The system of claim 1, (Appendix 19) The reception unit is When accepting a customer, the optimal interface is provided based on the clerk's device information. 2. The system of claim 1, (Appendix 20) The reception unit is When accepting a customer, the most appropriate reception method is selected based on the working status of the store staff. 2. The system of claim 1, (Appendix 21) The analysis unit is Estimate user emotions and adjust analysis accuracy based on the estimated user emotions 2. The system of claim 1, (Appendix 22) The analysis unit is When analyzing natural language inquiries, the accuracy of the analysis can be improved by referring to the past inquiry history of store clerks. 2. The system of claim 1, (Appendix 23) The analysis unit is When analyzing, select the optimal analysis method based on the store clerk's work performance data. 2. The system of claim 1, (Appendix 24) The analysis unit is Infer user emotions and adjust the way analysis results are displayed based on the inferred user emotions 2. The system of claim 1, (Appendix 25) The analysis unit is Improve analysis accuracy based on store associates' geographic location information during analysis 2. The system of claim 1, (Appendix 26) The analysis unit is During analysis, the social media activity of store associates is analyzed and relevant data is used for analysis. 2. The system of claim 1, (Appendix 27) The providing unit is To estimate a user's emotion and adjust a format of information to be provided based on the estimated user's emotion. 2. The system of claim 1, (Appendix 28) The providing unit is When providing information, the system refers to past feedback from store staff to select the optimal way to provide information. 2. The system of claim 1, (Appendix 29) The providing unit is When providing information, the optimal method of providing information is selected taking into account the work performance data of store staff. 2. The system of claim 1, (Appendix 30) The providing unit is Estimate the user's emotions and prioritize the information to be provided based on the estimated user's emotions. 2. The system of claim 1, (Appendix 31) The providing unit is When providing information, the optimal method of providing information is selected based on the store clerk's geographic location information. 2. The system of claim 1, (Appendix 32) The providing unit is When providing services, analyze the social media activity of store associates and provide relevant information 2. The system of claim 1, [Explanation of symbols]

[0187] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection unit that collects data; a reception unit that receives a query in a natural language based on the data collected by the collection unit; an analysis unit that analyzes the natural language inquiry received by the reception unit; A providing unit that provides the results analyzed by the analyzing unit. A system characterized by:

2. The collecting unit includes: Collect data on operation manuals, reservation status, customer feedback, and past trouble cases 2. The system of claim 1 .

3. The reception unit is Providing a voice-to-text or chat-style interface 2. The system of claim 1 .

4. The analysis unit is Analyze natural language queries and provide relevant data 2. The system of claim 1 .

5. The providing unit is Provide information in the form of text, images, and videos 2. The system of claim 1 .

6. The providing unit is Equipped with the ability to set information priorities 2. The system of claim 1 .

7. The providing unit is Accept feedback from store clerks and improve the accuracy of the generation AI 2. The system of claim 1 .

8. The providing unit is Implement security measures to protect data 2. The system of claim 1 .

Images