System

Abstract

An object of a system according to an embodiment is to analyze an emotion of a customer in real time and propose a service or a campaign based on the analysis.SOLUTION: A system includes a collection unit, an analysis unit, a provision unit, and a proposal unit. The collection unit collects a facial expression or a voice of a customer. The analysis unit analyzes the data collected by the collection unit and analyzes the emotion of the customer in real time. The providing unit provides the analysis result obtained by the analysis unit. The proposing section proposes a service or a campaign based on the data provided by the providing section.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 an instruction sentence related to a description of 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has the problem of making it difficult to accurately grasp customer sentiment in real time and propose services and campaigns based on that sentiment.

[0005] The system according to the embodiment aims to analyze customer sentiment in real time and propose services and campaigns based on the analysis. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a provision unit, and a proposal unit. The collection unit collects facial expressions or voices of customers. The analysis unit analyzes the data collected by the collection unit and analyzes customer emotions in real time. The provision unit provides the analysis results obtained by the analysis unit. The proposal unit proposes services or campaigns based on the data provided by the provision unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze customer sentiment in real time and suggest services and campaigns based on the analysis. [Brief explanation 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. [Figure 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. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 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. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 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 INVENTION

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

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

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single 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 coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, 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 symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and 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. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "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, RAM 30, and 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 (for example, 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., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with 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 CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

[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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 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 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. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) An emotion analysis system according to an embodiment of the present invention collects customer facial expressions and voices, analyzes their emotions in real time using a generation AI, and provides the results. The emotion analysis system collects customer facial expressions and voices, analyzes them using a generation AI, and analyzes their emotions in real time, thereby enabling restaurants to identify areas for improvement and improve the quality of their services and products. For example, the emotion analysis system collects customer facial expressions and voices using cameras and microphones installed in restaurants. The emotion analysis system then analyzes the collected data using a generation AI to identify the customer's emotions. For example, if a customer is smiling while speaking, the generation AI can analyze the data and identify the emotion of "happiness." The emotion analysis system then provides the restaurant with the emotion identified by the generation AI. For example, if a customer looks dissatisfied, the restaurant can identify the cause and improve its service. Furthermore, the emotion analysis system proposes personalized services and campaigns based on the customer's emotions. For example, if a customer is happy, offering them special services or campaigns can improve customer satisfaction. This allows the emotion analysis system to understand customer emotions and needs and develop more effective marketing strategies. This allows the sentiment analysis system to analyze customer sentiment in real time and provide the results to restaurants, maximizing the effectiveness of service improvements and campaigns and improving customer satisfaction. For example, by implementing campaigns tailored to specific times of day or days of the week based on customer sentiment data, it is possible to increase the frequency of customer visits. Analyzing customer sentiment data also allows restaurants to understand which menu items are popular, which can be used to improve menus and develop new products.

[0029] An emotion analysis system according to an embodiment includes a collection unit, an analysis unit, a provision unit, and a suggestion unit. The collection unit collects facial expressions or voices of customers. The collection unit can collect the facial expressions or voices of customers using, for example, a camera or a microphone installed in a restaurant. The analysis unit analyzes the data collected by the collection unit and analyzes the customer's emotions in real time. The analysis unit, for example, analyzes the collected facial expressions and voice data using a generation AI to identify the customer's emotions. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and identifies emotions based on the collected data. The provision unit provides the analysis results obtained by the analysis unit to the restaurant. The provision unit can provide the analysis results, for example, as a digital report or a real-time notification. The suggestion unit proposes services and campaigns based on the data provided by the provision unit. The suggestion unit can propose personalized services and campaigns based on the provided emotion data, for example. This allows the emotion analysis system according to an embodiment to analyze customer emotions in real time and propose services and campaigns.

[0030] The collection unit can collect facial expressions or voices of customers using cameras or microphones installed in the restaurant. Examples of cameras or microphones installed in the restaurant include, but are not limited to, cameras installed on the ceiling and microphones installed on tables. For example, the collection unit collects facial expressions of customers using cameras installed on the ceiling. The collection unit can also collect voices of customers using microphones installed on tables. Furthermore, the collection unit can collect overall movements of customers using cameras installed on the wall. In this way, the facial expressions and voices of customers can be accurately collected by using cameras and microphones installed in the restaurant.

[0031] The analysis unit can analyze the collected facial expression or voice data to identify the customer's emotions. For example, the analysis unit can analyze the collected facial expression data using a facial expression recognition algorithm to identify the customer's emotions. For example, the analysis unit can analyze a smiling expression to identify the emotion of "happiness." The analysis unit can also analyze the collected voice data using voice analysis technology to identify the customer's emotions. For example, the analysis unit can analyze the tone and volume of a voice to identify the emotion of "anger" or "sadness." The analysis unit can also combine a facial expression recognition algorithm with voice analysis technology to more accurately identify the customer's emotions. For example, the analysis unit can combine a smiling expression and a bright tone of voice to identify the emotion of "happiness." In this way, the analysis of the collected data can accurately identify the customer's emotions.

[0032] The providing unit can provide the analysis results to the restaurant. For example, the providing unit provides the analysis results to the restaurant as a digital report. For example, the providing unit provides the analysis results as a report in PDF format. The providing unit can also provide the analysis results to the restaurant as a real-time notification. For example, the providing unit notifies the restaurant of the analysis results in real time via a smartphone app. The providing unit can also provide the analysis results in a visualized form. For example, the providing unit displays the analysis results as graphs or charts and provides them in a format that is visually easy to understand. In this way, providing the analysis results to the restaurant makes it easier for the restaurant to understand customer sentiment.

[0033] The suggestion unit can suggest personalized services or campaigns based on the provided emotion data. The suggestion unit, for example, suggests special services based on the provided emotion data. For example, if a customer is happy, the suggestion unit suggests a special discount service to the customer. The suggestion unit can also suggest a special campaign based on the provided emotion data. For example, if a customer is satisfied, the suggestion unit suggests a campaign with a special benefit to the customer. The suggestion unit can also suggest personalized menus based on the provided emotion data. For example, if a customer expresses favorable emotions toward a particular menu, the suggestion unit suggests a special set menu that includes that menu. In this way, customer satisfaction can be improved by making personalized suggestions based on the customer's emotion data.

[0034] The proposal unit can propose campaigns tailored to specific time periods or days of the week based on the customer's emotional data. For example, the proposal unit proposes campaigns tailored to weekday lunchtime based on the customer's emotional data. For example, the proposal unit proposes a special lunch set to customers who visit the restaurant during weekday lunchtime. The proposal unit can also propose campaigns tailored to weekend dinnertime based on the customer's emotional data. For example, the proposal unit proposes a special dinner course to customers who visit the restaurant during weekend dinnertime. The proposal unit can also propose campaigns tailored to specific days of the week based on the customer's emotional data. For example, the proposal unit proposes a special drink service to customers who visit the restaurant on Friday nights. In this way, by proposing campaigns tailored to specific time periods or days of the week, it is possible to increase the frequency of customers visiting the restaurant.

[0035] The collection unit can analyze the customer's past store visit history and select the optimal collection method. For example, if the customer has visited the store frequently in the past, the collection unit can quickly collect data using facial recognition technology. For example, if the customer is visiting the store for the first time, the collection unit can also collect detailed data using voice recognition technology. For example, if the customer tends to visit the store during a specific time period, the collection unit can select a collection method that suits that time period. In this way, the optimal collection method can be selected by analyzing the customer's past store visit history. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the customer's store visit history data into the generation AI and have the generation AI select the optimal collection method.

[0036] During collection, the collection unit can optimize the placement of cameras or microphones based on the customer's seating position or movement line. For example, the collection unit may position a camera that captures the customer's facial expression at an optimal angle when the customer takes a seat. For example, the collection unit may also position a microphone that can clearly collect audio as the customer moves along their movement line. For example, if a customer stays in a specific area, the collection unit may preferentially position cameras and microphones in that area. This allows for more accurate data collection by optimizing the placement of cameras and microphones based on the customer's seating position and movement line. Some or all of the above-described processing in the collection unit may be performed using, or without, AI. For example, the collection unit may input customer seating position data into a generation AI and have the generation AI execute optimal placement of cameras and microphones.

[0037] The collection unit can filter the data to be collected according to the customer's age or gender during collection. For example, if the customer is young, the collection unit can collect subtle changes in facial expression and tone of voice. For example, if the customer is elderly, the collection unit can also collect significant changes in facial expression and clear changes in tone of voice. For example, the collection unit can preferentially collect specific facial expressions and tones of voice according to the customer's gender. This allows for more appropriate data to be collected by filtering data according to the customer's age and gender. Some or all of the above-described processing in the collection unit may be performed using, or without, AI. For example, the collection unit can input customer age and gender data into the generation AI and have the generation AI filter the data to be collected.

[0038] During collection, the collection unit can adjust the collection method taking into account the time of day or day of the week when the customer visits the store. For example, if the customer visits the store during the daytime on a weekday, the collection unit may prioritize collecting voice data in a quiet environment. For example, if the customer visits the store on a weekend evening, the collection unit may prioritize collecting facial expressions in a crowded environment. For example, if customers tend to visit the store on a specific day of the week, the collection unit can select a collection method that matches that day of the week. This allows the optimal collection method to be selected by taking into account the time of day and day of the week when the customer visits the store. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input data on the time of day and day of the week when the customer visits the store into the generation AI and cause the generation AI to adjust the collection method.

[0039] During collection, the collection unit can analyze the customer's social media activities and collect related data. For example, the collection unit collects information on locations where the customer has checked in on social media. For example, the collection unit can analyze the content of the customer's social media posts and collect related sentiment data. For example, the collection unit can also collect related data by referring to the activities of the customer's friends on social media. In this way, related data can be collected by analyzing the customer's social media activities. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the customer's social media data into a generation AI and have the generation AI collect related data.

[0040] The collection unit can customize the collection method by reflecting the customer's past feedback when collecting data. For example, the collection unit adjusts the type of data to be collected based on feedback provided by the customer in the past. For example, the collection unit can also focus on collecting specific facial expressions or tones of voice from the customer's past feedback. For example, the collection unit can also optimize the collection method by referring to the customer's past feedback. In this way, the collection method can be optimized by reflecting the customer's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input the customer's past feedback data into the generation AI and cause the generation AI to customize the collection method.

[0041] The analysis unit can evaluate the reliability of the collected data during analysis and improve the accuracy of the analysis results. For example, the analysis unit can evaluate the reliability of the collected data and use only highly reliable data for the analysis. For example, the analysis unit can cross-check multiple data sources to evaluate the reliability of the data. For example, the analysis unit can evaluate the reliability of the data and filter out unreliable data. In this way, the accuracy of the analysis results can be improved by evaluating the reliability of the collected data. Some or all of the above-mentioned processing in the analysis unit can be performed using, or without, the generation AI. For example, the analysis unit can input the collected data into the generation AI and have the generation AI perform a reliability evaluation of the data.

[0042] During analysis, the analysis unit can track changes in the customer's facial expression or voice in real time to identify emotional fluctuations. For example, the analysis unit can track changes in the customer's facial expression in real time to identify emotional fluctuations. For example, the analysis unit can also track changes in the customer's voice tone in real time to identify emotional fluctuations. For example, the analysis unit can track both the customer's facial expression and voice in real time to identify emotional fluctuations. In this way, by tracking changes in the customer's facial expression and voice in real time, emotional fluctuations can be accurately identified. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input the customer's facial expression and voice data into the generation AI and have the generation AI identify emotional fluctuations.

[0043] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the customer's past emotional data. For example, the analysis unit can refer to the customer's past emotional data to more accurately analyze the customer's current emotional state. For example, the analysis unit can also identify patterns of emotional fluctuations based on the customer's past emotional data. For example, the analysis unit can also refer to the customer's past emotional data and adjust the analysis algorithm. In this way, by referring to the customer's past emotional data, the accuracy of the analysis can be improved. Some or all of the above-described processing in the analysis unit can be performed using, or without, the generation AI. For example, the analysis unit can input the customer's past emotional data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0044] The analysis unit can perform the analysis while taking into account temporal fluctuations in the collected data. For example, the analysis unit analyzes patterns of emotional fluctuations by taking into account temporal fluctuations in the collected data. For example, the analysis unit can also identify emotional fluctuations based on temporal fluctuations in the data. For example, the analysis unit can also adjust the analysis algorithm by taking into account temporal fluctuations. This allows for accurate analysis of patterns of emotional fluctuations by taking into account temporal fluctuations in the collected data. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the collected data into a generation AI and have the generation AI perform an analysis that takes into account temporal fluctuations.

[0045] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the customer's related purchase history. The analysis unit, for example, refers to the customer's purchase history and identifies patterns of emotional fluctuations. The analysis unit can also analyze emotional fluctuations based on the customer's purchase history. The analysis unit can also adjust the analysis algorithm by referring to the customer's purchase history, for example. This makes it possible to accurately analyze patterns of emotional fluctuations by referring to the customer's purchase history. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI, for example. For example, the analysis unit can input customer purchase history data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0046] The analysis unit can perform the analysis while taking into account customer attribute information (age, gender, etc.). The analysis unit, for example, analyzes emotional fluctuations while taking into account the customer's age. The analysis unit can also analyze emotional fluctuations while taking into account the customer's gender, for example. The analysis unit can also adjust the analysis algorithm based on the customer's attribute information, for example. This allows for more accurate analysis of emotional fluctuations by taking into account the customer's attribute information. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI, for example. For example, the analysis unit can input customer attribute information into the generation AI and have the generation AI improve the accuracy of the analysis.

[0047] The providing unit can adjust the level of detail of the data according to the skill level of the restaurant staff when providing the data. For example, if the staff is a novice, the providing unit provides concise, easy-to-understand data. For example, if the staff is experienced, the providing unit can also provide detailed data. For example, the providing unit can also adjust the way the data is displayed according to the skill level of the staff. This makes it possible to provide easy-to-understand data by adjusting the level of detail of the data according to the skill level of the staff. Some or all of the above-mentioned processing in the providing unit may be performed using, or without, a generation AI. For example, the providing unit can input staff skill level data into the generation AI and have the generation AI adjust the level of detail of the data.

[0048] The providing unit can adjust the timing of providing data taking into account the current business status of the restaurant when providing the data. For example, the providing unit delays the provision of data when the restaurant is crowded. For example, the providing unit can also provide data quickly when the restaurant is empty. The providing unit can also adjust the timing of providing data according to the business status, for example. In this way, by adjusting the timing of providing data according to the business status, data can be provided at an appropriate time. Some or all of the above-mentioned processing by the providing unit may be performed using, or without, the generation AI, for example. For example, the providing unit can input business status data of the restaurant into the generation AI and cause the generation AI to adjust the timing of providing data.

[0049] The providing unit can optimize the data provision method by referring to past provision results when providing data. The providing unit, for example, selects the optimal data provision method based on past provision results. The providing unit can also identify the effective timing for providing data from past provision results, for example. The providing unit can also customize the data provision method by referring to past provision results, for example. In this way, the optimal data provision method can be selected by referring to past provision results. Some or all of the above-described processing in the providing unit may be performed using, or without, the generation AI, for example. For example, the providing unit can input past provision result data into the generation AI and cause the generation AI to optimize the data provision method.

[0050] The providing unit can adjust the data providing method at the time of providing data, taking into account the geographical location information of the restaurant. For example, in the case of a restaurant in an urban area, the providing unit can prioritize quick data provision. For example, in the case of a restaurant in a suburban area, the providing unit can also prioritize detailed data provision. The providing unit can also adjust the data providing method according to the geographical location information. This makes it possible to provide appropriate data by adjusting the data providing method according to the geographical location information. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the providing unit can input the geographical location information of the restaurant into the generation AI and cause the generation AI to adjust the data providing method.

[0051] At the time of providing, the providing unit can analyze the social media activity of the restaurant and provide the related data. For example, the providing unit can analyze the content of posts made by the restaurant on social media and provide the related data. For example, the providing unit can also provide the related data by referring to the activity of the restaurant's followers on social media. For example, the providing unit can also provide the related data based on campaign information on the restaurant's social media. In this way, the related data can be provided by analyzing social media activity. Some or all of the above-described processing by the providing unit may be performed using, or without, the generation AI. For example, the providing unit can input the restaurant's social media data into the generation AI and cause the generation AI to provide the related data.

[0052] The providing unit can customize the data providing method by reflecting the restaurant's past feedback when providing data. The providing unit, for example, selects the optimal data providing method based on the past feedback. The providing unit can also identify, for example, an effective timing for providing data from the past feedback. The providing unit can also customize the data providing method by referring to the past feedback. In this way, the optimal data providing method can be selected by reflecting the past feedback. Some or all of the above-described processing in the providing unit may be performed using, or without, the generation AI. For example, the providing unit can input past feedback data into the generation AI and have the generation AI customize the data providing method.

[0053] When making a proposal, the proposal unit can adjust the level of detail of the proposal based on the importance of the customer's emotional data. The proposal unit, for example, makes a detailed proposal based on emotional data with a high importance. The proposal unit can also make a concise proposal based on emotional data with a low importance. The proposal unit can also adjust the level of detail of the proposal according to the importance of the emotional data. This enables an appropriate proposal by adjusting the level of detail of the proposal based on the importance of the emotional data. Some or all of the above-mentioned processing in the proposal unit may be performed using, or without, a generation AI. For example, the proposal unit can input the customer's emotional data into the generation AI and cause the generation AI to adjust the level of detail of the proposal.

[0054] When making a suggestion, the suggestion unit can apply different suggestion algorithms depending on the category of the customer's emotional data. For example, the suggestion unit can apply a positive suggestion algorithm based on positive emotional data. For example, the suggestion unit can also apply a suggestion algorithm that highlights areas for improvement based on negative emotional data. For example, the suggestion unit can also apply a natural suggestion algorithm based on natural emotional data. This enables more appropriate suggestions by applying a suggestion algorithm depending on the category of emotional data. Some or all of the above-mentioned processing in the suggestion unit can be performed using, or without, a generation AI. For example, the suggestion unit can input the customer's emotional data into the generation AI and cause the generation AI to apply the suggestion algorithm.

[0055] When making a proposal, the proposal unit can improve the accuracy of the proposal by referring to past proposal results for the customer. The proposal unit, for example, makes an optimal proposal based on past proposal results. The proposal unit can also identify an effective proposal method from past proposal results, for example. The proposal unit can also adjust the proposal algorithm by referring to past proposal results, for example. In this way, the accuracy of the proposal can be improved by referring to past proposal results. Some or all of the above-mentioned processing in the proposal unit may be performed using, or without, the generation AI, for example. For example, the proposal unit can input past proposal result data for the customer into the generation AI and cause the generation AI to improve the accuracy of the proposal.

[0056] When making a proposal, the proposal unit can determine the priority of the proposal based on the time of submission of the customer's emotion data. For example, the proposal unit can prioritize proposals based on emotion data that was submitted most recently. For example, the proposal unit can also postpone proposals based on emotion data that was submitted earlier. For example, the proposal unit can also adjust the priority of the proposal based on the time of submission. This enables proposals to be made at an appropriate time by determining the priority of the proposal based on the time of submission of the emotion data. Some or all of the above-mentioned processing in the proposal unit may be performed using, or without, the generation AI. For example, the proposal unit can input the time of submission of the customer's emotion data into the generation AI and have the generation AI determine the priority of the proposals.

[0057] When making a proposal, the proposal unit can adjust the order of proposals based on the relevance of the customer's emotional data. For example, the proposal unit prioritizes proposals based on highly relevant emotional data. For example, the proposal unit can also postpone proposals based on less relevant emotional data. For example, the proposal unit can also adjust the order of proposals according to the relevance of the emotional data. This enables more appropriate proposals by adjusting the order of proposals based on the relevance of the emotional data. Some or all of the above-described processing in the proposal unit may be performed using, or without, a generation AI. For example, the proposal unit can input the customer's emotional data into the generation AI and cause the generation AI to adjust the order of proposals.

[0058] When making a proposal, the suggestion unit can adjust the use of technical terminology in the proposal according to the customer's level of expertise. For example, the suggestion unit makes a proposal that uses a lot of technical terminology for a customer with a high level of expertise. For example, the suggestion unit can also make a concise and easy-to-understand proposal for a customer with a low level of expertise. The suggestion unit can also adjust the use of technical terminology in the proposal according to the level of expertise. This makes it possible to make a proposal that is easier to understand by adjusting the use of technical terminology according to the customer's level of expertise. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input customer expertise level data into the generation AI and cause the generation AI to adjust the use of technical terminology.

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

[0060] The collection unit can analyze the customer's past visit history and select the optimal collection method. For example, if the customer has visited the store frequently in the past, facial recognition technology can be used to quickly collect data. If the customer is visiting the store for the first time, detailed data can be collected using voice recognition technology. If the customer tends to visit the store at a specific time of day, a collection method suited to that time of day can be selected. In this way, the optimal collection method can be selected by analyzing the customer's past visit history.

[0061] When collecting data, the collection unit can optimize the placement of cameras or microphones based on the seating position or movement line of customers. For example, a camera can be placed at the optimal angle to capture facial expressions when a customer takes a seat. A microphone can also be placed to clearly collect audio as the customer moves along their movement line. If customers stay in a specific area, cameras and microphones can be placed preferentially in that area. This allows for more accurate data collection by optimizing the placement of cameras and microphones based on the seating position and movement line of customers.

[0062] During analysis, the analysis unit can evaluate the reliability of the collected data and improve the accuracy of the analysis results. For example, the reliability of the collected data is evaluated and only highly reliable data is used for analysis. To evaluate the reliability of the data, multiple data sources can be cross-checked. The reliability of the data can also be evaluated and low-reliability data can be filtered. In this way, the accuracy of the analysis results can be improved by evaluating the reliability of the collected data.

[0063] The providing unit can adjust the level of detail of the data according to the skill level of the restaurant staff when providing the data. For example, if the staff is a novice, concise and easy-to-understand data can be provided. If the staff is experienced, detailed data can also be provided. The way in which the data is displayed can also be adjusted according to the skill level of the staff. In this way, by adjusting the level of detail of the data according to the skill level of the staff, it is possible to provide data that is easy to understand.

[0064] When making a suggestion, the suggestion unit can apply different suggestion algorithms depending on the category of the customer's emotional data. For example, a positive suggestion algorithm can be applied based on positive emotional data. A suggestion algorithm that highlights areas for improvement can also be applied based on negative emotional data. A natural suggestion algorithm can also be applied based on natural emotional data. This makes it possible to make more appropriate suggestions by applying a suggestion algorithm depending on the category of emotional data.

[0065] The processing flow of the first embodiment will be briefly explained below.

[0066] Step 1: The collection unit collects facial expressions or voices of customers. For example, the collection unit can collect facial expressions or voices of customers using a camera or microphone installed in the restaurant. Step 2: The analysis unit analyzes the data collected by the collection unit and analyzes the customer's emotions in real time. For example, it uses a generation AI to analyze the collected facial expressions and voice data to identify the customer's emotions. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and identifies emotions based on the collected data. Step 3: The providing unit provides the restaurant with the analysis results obtained by the analysis unit. For example, the analysis results can be provided as a digital report or a real-time notification. Step 4: The suggestion unit suggests services and campaigns based on the data provided by the provision unit. For example, personalized services and campaigns can be suggested based on the provided emotion data.

[0067] (Example 2) An emotion analysis system according to an embodiment of the present invention collects customer facial expressions and voices, analyzes their emotions in real time using a generation AI, and provides the results. The emotion analysis system collects customer facial expressions and voices, analyzes them using a generation AI, and analyzes their emotions in real time, thereby enabling restaurants to identify areas for improvement and improve the quality of their services and products. For example, the emotion analysis system collects customer facial expressions and voices using cameras and microphones installed in restaurants. The emotion analysis system then analyzes the collected data using a generation AI to identify the customer's emotions. For example, if a customer is smiling while speaking, the generation AI can analyze the data and identify the emotion of "happiness." The emotion analysis system then provides the restaurant with the emotion identified by the generation AI. For example, if a customer looks dissatisfied, the restaurant can identify the cause and improve its service. Furthermore, the emotion analysis system proposes personalized services and campaigns based on the customer's emotions. For example, if a customer is happy, offering them special services or campaigns can improve customer satisfaction. This allows the emotion analysis system to understand customer emotions and needs and develop more effective marketing strategies. This allows the sentiment analysis system to analyze customer sentiment in real time and provide the results to restaurants, maximizing the effectiveness of service improvements and campaigns and improving customer satisfaction. For example, by implementing campaigns tailored to specific times of day or days of the week based on customer sentiment data, it is possible to increase the frequency of customer visits. Analyzing customer sentiment data also allows restaurants to understand which menu items are popular, which can be used to improve menus and develop new products.

[0068] An emotion analysis system according to an embodiment includes a collection unit, an analysis unit, a provision unit, and a suggestion unit. The collection unit collects facial expressions or voices of customers. The collection unit can collect the facial expressions or voices of customers using, for example, a camera or a microphone installed in a restaurant. The analysis unit analyzes the data collected by the collection unit and analyzes the customer's emotions in real time. The analysis unit, for example, analyzes the collected facial expressions and voice data using a generation AI to identify the customer's emotions. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and identifies emotions based on the collected data. The provision unit provides the analysis results obtained by the analysis unit to the restaurant. The provision unit can provide the analysis results, for example, as a digital report or a real-time notification. The suggestion unit proposes services and campaigns based on the data provided by the provision unit. The suggestion unit can propose personalized services and campaigns based on the provided emotion data, for example. This allows the emotion analysis system according to an embodiment to analyze customer emotions in real time and propose services and campaigns.

[0069] The collection unit can collect facial expressions or voices of customers using cameras or microphones installed in the restaurant. Examples of cameras or microphones installed in the restaurant include, but are not limited to, cameras installed on the ceiling and microphones installed on tables. For example, the collection unit collects facial expressions of customers using cameras installed on the ceiling. The collection unit can also collect voices of customers using microphones installed on tables. Furthermore, the collection unit can collect overall movements of customers using cameras installed on the wall. In this way, the facial expressions and voices of customers can be accurately collected by using cameras and microphones installed in the restaurant.

[0070] The analysis unit can analyze the collected facial expression or voice data to identify the customer's emotions. For example, the analysis unit can analyze the collected facial expression data using a facial expression recognition algorithm to identify the customer's emotions. For example, the analysis unit can analyze a smiling expression to identify the emotion of "happiness." The analysis unit can also analyze the collected voice data using voice analysis technology to identify the customer's emotions. For example, the analysis unit can analyze the tone and volume of a voice to identify the emotion of "anger" or "sadness." The analysis unit can also combine a facial expression recognition algorithm with voice analysis technology to more accurately identify the customer's emotions. For example, the analysis unit can combine a smiling expression and a bright tone of voice to identify the emotion of "happiness." In this way, the analysis of the collected data can accurately identify the customer's emotions.

[0071] The providing unit can provide the analysis results to the restaurant. For example, the providing unit provides the analysis results to the restaurant as a digital report. For example, the providing unit provides the analysis results as a report in PDF format. The providing unit can also provide the analysis results to the restaurant as a real-time notification. For example, the providing unit notifies the restaurant of the analysis results in real time via a smartphone app. The providing unit can also provide the analysis results in a visualized form. For example, the providing unit displays the analysis results as graphs or charts and provides them in a format that is visually easy to understand. In this way, providing the analysis results to the restaurant makes it easier for the restaurant to understand customer sentiment.

[0072] The suggestion unit can suggest personalized services or campaigns based on the provided emotion data. The suggestion unit, for example, suggests special services based on the provided emotion data. For example, if a customer is happy, the suggestion unit suggests a special discount service to the customer. The suggestion unit can also suggest a special campaign based on the provided emotion data. For example, if a customer is satisfied, the suggestion unit suggests a campaign with a special benefit to the customer. The suggestion unit can also suggest personalized menus based on the provided emotion data. For example, if a customer expresses favorable emotions toward a particular menu, the suggestion unit suggests a special set menu that includes that menu. In this way, customer satisfaction can be improved by making personalized suggestions based on the customer's emotion data.

[0073] The proposal unit can propose campaigns tailored to specific time periods or days of the week based on the customer's emotional data. For example, the proposal unit proposes campaigns tailored to weekday lunchtime based on the customer's emotional data. For example, the proposal unit proposes a special lunch set to customers who visit the restaurant during weekday lunchtime. The proposal unit can also propose campaigns tailored to weekend dinnertime based on the customer's emotional data. For example, the proposal unit proposes a special dinner course to customers who visit the restaurant during weekend dinnertime. The proposal unit can also propose campaigns tailored to specific days of the week based on the customer's emotional data. For example, the proposal unit proposes a special drink service to customers who visit the restaurant on Friday nights. In this way, by proposing campaigns tailored to specific time periods or days of the week, it is possible to increase the frequency of customers visiting the restaurant.

[0074] The collection unit can estimate the customer's emotions and adjust the type of data to be collected based on the estimated customer's emotions. For example, if the customer is happy, the collection unit can prioritize collecting smiling facial expressions and a bright tone of voice. For example, if the customer is dissatisfied, the collection unit can also focus on collecting wrinkles between the eyebrows and a low tone of voice. For example, if the customer is relaxed, the collection unit can also collect natural facial expressions and a calm tone of voice. This allows for more accurate data to be collected by adjusting the type of data to be collected based on the customer's emotions. Some or all of the above-mentioned processing in the collection unit may be performed using, or without, AI. For example, the collection unit can input customer facial expression data into the generation AI and cause the generation AI to adjust the type of data to be collected.

[0075] The collection unit can analyze the customer's past store visit history and select the optimal collection method. For example, if the customer has visited the store frequently in the past, the collection unit can quickly collect data using facial recognition technology. For example, if the customer is visiting the store for the first time, the collection unit can also collect detailed data using voice recognition technology. For example, if the customer tends to visit the store during a specific time period, the collection unit can select a collection method that suits that time period. In this way, the optimal collection method can be selected by analyzing the customer's past store visit history. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the customer's store visit history data into the generation AI and have the generation AI select the optimal collection method.

[0076] During collection, the collection unit can optimize the placement of cameras or microphones based on the customer's seating position or movement line. For example, the collection unit may position a camera that captures the customer's facial expression at an optimal angle when the customer takes a seat. For example, the collection unit may also position a microphone that can clearly collect audio as the customer moves along their movement line. For example, if a customer stays in a specific area, the collection unit may preferentially position cameras and microphones in that area. This allows for more accurate data collection by optimizing the placement of cameras and microphones based on the customer's seating position and movement line. Some or all of the above-described processing in the collection unit may be performed using, or without, AI. For example, the collection unit may input customer seating position data into a generation AI and have the generation AI execute optimal placement of cameras and microphones.

[0077] The collection unit can filter the data to be collected according to the customer's age or gender during collection. For example, if the customer is young, the collection unit can collect subtle changes in facial expression and tone of voice. For example, if the customer is elderly, the collection unit can also collect significant changes in facial expression and clear changes in tone of voice. For example, the collection unit can preferentially collect specific facial expressions and tones of voice according to the customer's gender. This allows for more appropriate data to be collected by filtering data according to the customer's age and gender. Some or all of the above-described processing in the collection unit may be performed using, or without, AI. For example, the collection unit can input customer age and gender data into the generation AI and have the generation AI filter the data to be collected.

[0078] The collection unit can estimate the customer's emotions and determine the priority of data to be collected based on the estimated customer emotions. For example, if the customer is happy, the collection unit can prioritize collecting smiling facial expressions and a bright tone of voice. For example, if the customer is dissatisfied, the collection unit can also focus on collecting wrinkles between the eyebrows and a low tone of voice. For example, if the customer is relaxed, the collection unit can also collect natural facial expressions and a calm tone of voice. This allows important data to be collected preferentially by determining the priority of data based on the customer's emotions. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input customer emotion data into the generation AI and have the generation AI determine the priority of data to be collected.

[0079] During collection, the collection unit can adjust the collection method taking into account the time of day or day of the week when the customer visits the store. For example, if the customer visits the store during the daytime on a weekday, the collection unit may prioritize collecting voice data in a quiet environment. For example, if the customer visits the store on a weekend evening, the collection unit may prioritize collecting facial expressions in a crowded environment. For example, if customers tend to visit the store on a specific day of the week, the collection unit can select a collection method that matches that day of the week. This allows the optimal collection method to be selected by taking into account the time of day and day of the week when the customer visits the store. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input data on the time of day and day of the week when the customer visits the store into the generation AI and cause the generation AI to adjust the collection method.

[0080] During collection, the collection unit can analyze the customer's social media activities and collect related data. For example, the collection unit collects information on locations where the customer has checked in on social media. For example, the collection unit can analyze the content of the customer's social media posts and collect related sentiment data. For example, the collection unit can also collect related data by referring to the activities of the customer's friends on social media. In this way, related data can be collected by analyzing the customer's social media activities. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the customer's social media data into a generation AI and have the generation AI collect related data.

[0081] The collection unit can customize the collection method by reflecting the customer's past feedback when collecting data. For example, the collection unit adjusts the type of data to be collected based on feedback provided by the customer in the past. For example, the collection unit can also focus on collecting specific facial expressions or tones of voice from the customer's past feedback. For example, the collection unit can also optimize the collection method by referring to the customer's past feedback. In this way, the collection method can be optimized by reflecting the customer's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input the customer's past feedback data into the generation AI and cause the generation AI to customize the collection method.

[0082] The analysis unit can estimate the customer's emotions and adjust the analysis algorithm based on the estimated customer emotions. For example, if the customer is happy, the analysis unit applies an analysis algorithm that emphasizes positive emotions. For example, if the customer is dissatisfied, the analysis unit can also apply an algorithm that analyzes negative emotions in detail. For example, if the customer is relaxed, the analysis unit can also apply an algorithm that analyzes natural emotions. By adjusting the analysis algorithm based on the customer's emotions, the accuracy of the analysis can be improved. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input customer emotion data into the generation AI and have the generation AI adjust the analysis algorithm.

[0083] The analysis unit can evaluate the reliability of the collected data during analysis and improve the accuracy of the analysis results. For example, the analysis unit can evaluate the reliability of the collected data and use only highly reliable data for the analysis. For example, the analysis unit can cross-check multiple data sources to evaluate the reliability of the data. For example, the analysis unit can evaluate the reliability of the data and filter out unreliable data. In this way, the accuracy of the analysis results can be improved by evaluating the reliability of the collected data. Some or all of the above-mentioned processing in the analysis unit can be performed using, or without, the generation AI. For example, the analysis unit can input the collected data into the generation AI and have the generation AI perform a reliability evaluation of the data.

[0084] During analysis, the analysis unit can track changes in the customer's facial expression or voice in real time to identify emotional fluctuations. For example, the analysis unit can track changes in the customer's facial expression in real time to identify emotional fluctuations. For example, the analysis unit can also track changes in the customer's voice tone in real time to identify emotional fluctuations. For example, the analysis unit can track both the customer's facial expression and voice in real time to identify emotional fluctuations. In this way, by tracking changes in the customer's facial expression and voice in real time, emotional fluctuations can be accurately identified. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input the customer's facial expression and voice data into the generation AI and have the generation AI identify emotional fluctuations.

[0085] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the customer's past emotional data. For example, the analysis unit can refer to the customer's past emotional data to more accurately analyze the customer's current emotional state. For example, the analysis unit can also identify patterns of emotional fluctuations based on the customer's past emotional data. For example, the analysis unit can also refer to the customer's past emotional data and adjust the analysis algorithm. In this way, by referring to the customer's past emotional data, the accuracy of the analysis can be improved. Some or all of the above-described processing in the analysis unit can be performed using, or without, the generation AI. For example, the analysis unit can input the customer's past emotional data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0086] The analysis unit can estimate the customer's emotions and adjust the display method of the analysis results based on the estimated customer emotions. For example, if the customer is happy, the analysis unit provides a display method that emphasizes positive emotions. For example, if the customer is dissatisfied, the analysis unit can also provide a method that displays negative emotions in detail. For example, if the customer is relaxed, the analysis unit can also provide a method that displays natural emotions. This enables more appropriate display by adjusting the display method of the analysis results based on the customer's emotions. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input customer emotion data into the generation AI and have the generation AI adjust the display method of the analysis results.

[0087] The analysis unit can perform the analysis while taking into account temporal fluctuations in the collected data. For example, the analysis unit analyzes patterns of emotional fluctuations by taking into account temporal fluctuations in the collected data. For example, the analysis unit can also identify emotional fluctuations based on temporal fluctuations in the data. For example, the analysis unit can also adjust the analysis algorithm by taking into account temporal fluctuations. This allows for accurate analysis of patterns of emotional fluctuations by taking into account temporal fluctuations in the collected data. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the collected data into a generation AI and have the generation AI perform an analysis that takes into account temporal fluctuations.

[0088] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the customer's related purchase history. The analysis unit, for example, refers to the customer's purchase history and identifies patterns of emotional fluctuations. The analysis unit can also analyze emotional fluctuations based on the customer's purchase history. The analysis unit can also adjust the analysis algorithm by referring to the customer's purchase history, for example. This makes it possible to accurately analyze patterns of emotional fluctuations by referring to the customer's purchase history. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI, for example. For example, the analysis unit can input customer purchase history data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0089] The analysis unit can perform the analysis while taking into account customer attribute information (age, gender, etc.). The analysis unit, for example, analyzes emotional fluctuations while taking into account the customer's age. The analysis unit can also analyze emotional fluctuations while taking into account the customer's gender, for example. The analysis unit can also adjust the analysis algorithm based on the customer's attribute information, for example. This allows for more accurate analysis of emotional fluctuations by taking into account the customer's attribute information. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI, for example. For example, the analysis unit can input customer attribute information into the generation AI and have the generation AI improve the accuracy of the analysis.

[0090] The providing unit can estimate the customer's emotions and adjust the format of the data to be provided based on the estimated customer emotions. For example, if the customer is happy, the providing unit can provide a data format that emphasizes positive emotions. For example, if the customer is dissatisfied, the providing unit can also provide a data format that displays negative emotions in detail. For example, if the customer is relaxed, the providing unit can also provide a data format that displays natural emotions. This makes it possible to provide more appropriate data by adjusting the data format based on the customer's emotions. Some or all of the above-mentioned processing in the providing unit can be performed using, or without, a generation AI. For example, the providing unit can input customer emotion data into the generation AI and have the generation AI adjust the data format.

[0091] The providing unit can adjust the level of detail of the data according to the skill level of the restaurant staff when providing the data. For example, if the staff is a novice, the providing unit provides concise, easy-to-understand data. For example, if the staff is experienced, the providing unit can also provide detailed data. For example, the providing unit can also adjust the way the data is displayed according to the skill level of the staff. This makes it possible to provide easy-to-understand data by adjusting the level of detail of the data according to the skill level of the staff. Some or all of the above-mentioned processing in the providing unit may be performed using, or without, a generation AI. For example, the providing unit can input staff skill level data into the generation AI and have the generation AI adjust the level of detail of the data.

[0092] The providing unit can adjust the timing of providing data taking into account the current business status of the restaurant when providing the data. For example, the providing unit delays the provision of data when the restaurant is crowded. For example, the providing unit can also provide data quickly when the restaurant is empty. The providing unit can also adjust the timing of providing data according to the business status, for example. In this way, by adjusting the timing of providing data according to the business status, data can be provided at an appropriate time. Some or all of the above-mentioned processing by the providing unit may be performed using, or without, the generation AI, for example. For example, the providing unit can input business status data of the restaurant into the generation AI and cause the generation AI to adjust the timing of providing data.

[0093] The providing unit can optimize the data provision method by referring to past provision results when providing data. The providing unit, for example, selects the optimal data provision method based on past provision results. The providing unit can also identify the effective timing for providing data from past provision results, for example. The providing unit can also customize the data provision method by referring to past provision results, for example. In this way, the optimal data provision method can be selected by referring to past provision results. Some or all of the above-described processing in the providing unit may be performed using, or without, the generation AI, for example. For example, the providing unit can input past provision result data into the generation AI and cause the generation AI to optimize the data provision method.

[0094] The providing unit can estimate the customer's emotions and determine the priority of data to be provided based on the estimated customer emotions. For example, if the customer is happy, the providing unit can prioritize data that emphasizes positive emotions. For example, if the customer is dissatisfied, the providing unit can also prioritize data that displays negative emotions in detail. For example, if the customer is relaxed, the providing unit can also prioritize data that displays natural emotions. In this way, by determining the priority of data based on the customer's emotions, important data can be provided preferentially. Some or all of the above-mentioned processing in the providing unit may be performed using, or without, a generation AI. For example, the providing unit can input customer emotion data into the generation AI and have the generation AI determine the priority of the data.

[0095] The providing unit can adjust the data providing method at the time of providing data, taking into account the geographical location information of the restaurant. For example, in the case of a restaurant in an urban area, the providing unit can prioritize quick data provision. For example, in the case of a restaurant in a suburban area, the providing unit can also prioritize detailed data provision. The providing unit can also adjust the data providing method according to the geographical location information. This makes it possible to provide appropriate data by adjusting the data providing method according to the geographical location information. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the providing unit can input the geographical location information of the restaurant into the generation AI and cause the generation AI to adjust the data providing method.

[0096] At the time of providing, the providing unit can analyze the social media activity of the restaurant and provide the related data. For example, the providing unit can analyze the content of posts made by the restaurant on social media and provide the related data. For example, the providing unit can also provide the related data by referring to the activity of the restaurant's followers on social media. For example, the providing unit can also provide the related data based on campaign information on the restaurant's social media. In this way, the related data can be provided by analyzing social media activity. Some or all of the above-described processing by the providing unit may be performed using, or without, the generation AI. For example, the providing unit can input the restaurant's social media data into the generation AI and cause the generation AI to provide the related data.

[0097] The providing unit can customize the data providing method by reflecting the restaurant's past feedback when providing data. The providing unit, for example, selects the optimal data providing method based on the past feedback. The providing unit can also identify, for example, an effective timing for providing data from the past feedback. The providing unit can also customize the data providing method by referring to the past feedback. In this way, the optimal data providing method can be selected by reflecting the past feedback. Some or all of the above-described processing in the providing unit may be performed using, or without, the generation AI. For example, the providing unit can input past feedback data into the generation AI and have the generation AI customize the data providing method.

[0098] The suggestion unit can estimate the customer's emotions and adjust the way the suggestion is expressed based on the estimated customer's emotions. For example, if the customer is happy, the suggestion unit can make the suggestion in a positive manner. For example, if the customer is dissatisfied, the suggestion unit can make the suggestion in a manner that emphasizes areas for improvement. For example, if the customer is relaxed, the suggestion unit can make the suggestion in a natural manner. This enables more appropriate suggestions to be made by adjusting the way the suggestion is expressed based on the customer's emotions. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input customer emotion data into the generation AI and cause the generation AI to adjust the way the suggestion is expressed.

[0099] When making a proposal, the proposal unit can adjust the level of detail of the proposal based on the importance of the customer's emotional data. The proposal unit, for example, makes a detailed proposal based on emotional data with a high importance. The proposal unit can also make a concise proposal based on emotional data with a low importance. The proposal unit can also adjust the level of detail of the proposal according to the importance of the emotional data. This enables an appropriate proposal by adjusting the level of detail of the proposal based on the importance of the emotional data. Some or all of the above-mentioned processing in the proposal unit may be performed using, or without, a generation AI. For example, the proposal unit can input the customer's emotional data into the generation AI and cause the generation AI to adjust the level of detail of the proposal.

[0100] When making a suggestion, the suggestion unit can apply different suggestion algorithms depending on the category of the customer's emotional data. For example, the suggestion unit can apply a positive suggestion algorithm based on positive emotional data. For example, the suggestion unit can also apply a suggestion algorithm that highlights areas for improvement based on negative emotional data. For example, the suggestion unit can also apply a natural suggestion algorithm based on natural emotional data. This enables more appropriate suggestions by applying a suggestion algorithm depending on the category of emotional data. Some or all of the above-mentioned processing in the suggestion unit can be performed using, or without, a generation AI. For example, the suggestion unit can input the customer's emotional data into the generation AI and cause the generation AI to apply the suggestion algorithm.

[0101] When making a proposal, the proposal unit can improve the accuracy of the proposal by referring to past proposal results for the customer. The proposal unit, for example, makes an optimal proposal based on past proposal results. The proposal unit can also identify an effective proposal method from past proposal results, for example. The proposal unit can also adjust the proposal algorithm by referring to past proposal results, for example. In this way, the accuracy of the proposal can be improved by referring to past proposal results. Some or all of the above-mentioned processing in the proposal unit may be performed using, or without, the generation AI, for example. For example, the proposal unit can input past proposal result data for the customer into the generation AI and cause the generation AI to improve the accuracy of the proposal.

[0102] The suggestion unit can estimate the customer's emotions and adjust the length of the suggestion based on the estimated customer's emotions. For example, if the customer is happy, the suggestion unit can make a detailed suggestion. For example, if the customer is dissatisfied, the suggestion unit can also make a concise suggestion. For example, if the customer is relaxed, the suggestion unit can also make a suggestion of a natural length. This enables more appropriate suggestions to be made by adjusting the length of the suggestion based on the customer's emotions. Some or all of the above-described processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input customer emotion data into the generation AI and cause the generation AI to adjust the length of the suggestion.

[0103] When making a proposal, the proposal unit can determine the priority of the proposal based on the time of submission of the customer's emotion data. For example, the proposal unit can prioritize proposals based on emotion data that was submitted most recently. For example, the proposal unit can also postpone proposals based on emotion data that was submitted earlier. For example, the proposal unit can also adjust the priority of the proposal based on the time of submission. This enables proposals to be made at an appropriate time by determining the priority of the proposal based on the time of submission of the emotion data. Some or all of the above-mentioned processing in the proposal unit may be performed using, or without, the generation AI. For example, the proposal unit can input the time of submission of the customer's emotion data into the generation AI and have the generation AI determine the priority of the proposals.

[0104] When making a proposal, the proposal unit can adjust the order of proposals based on the relevance of the customer's emotional data. For example, the proposal unit prioritizes proposals based on highly relevant emotional data. For example, the proposal unit can also postpone proposals based on less relevant emotional data. For example, the proposal unit can also adjust the order of proposals according to the relevance of the emotional data. This enables more appropriate proposals by adjusting the order of proposals based on the relevance of the emotional data. Some or all of the above-described processing in the proposal unit may be performed using, or without, a generation AI. For example, the proposal unit can input the customer's emotional data into the generation AI and cause the generation AI to adjust the order of proposals.

[0105] When making a proposal, the suggestion unit can adjust the use of technical terminology in the proposal according to the customer's level of expertise. For example, the suggestion unit makes a proposal that uses a lot of technical terminology for a customer with a high level of expertise. For example, the suggestion unit can also make a concise and easy-to-understand proposal for a customer with a low level of expertise. The suggestion unit can also adjust the use of technical terminology in the proposal according to the level of expertise. This makes it possible to make a proposal that is easier to understand by adjusting the use of technical terminology according to the customer's level of expertise. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input customer expertise level data into the generation AI and cause the generation AI to adjust the use of technical terminology. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, provision unit, and suggestion unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit can collect facial expressions and voices of customers using the camera 42 and microphone 38B of the smart device 14. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected data and analyzes the customer's emotions in real time. The provision unit, realized, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, provides the analysis results to the restaurant. The suggestion unit, realized, for example, by the specific processing unit 290 of the data processing device 12, proposes services and campaigns based on the provided emotion data. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, provision unit, and suggestion unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit can collect facial expressions and voices of customers using the camera 42 and microphone 238 of the smart glasses 214. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected data and analyzes the customer's emotions in real time. The provision unit, realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, provides the analysis results to the restaurant. The suggestion unit, realized, for example, by the specific processing unit 290 of the data processing device 12, proposes services and campaigns based on the provided emotion data. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, analysis unit, provision unit, and suggestion unit described above is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the collection unit can collect facial expressions and voices of customers using the camera 42 and microphone 238 of the headset terminal 314. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data and analyzes the customer's emotions in real time. The provision unit is realized, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12, and provides the analysis results to the restaurant. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests services and campaigns based on the provided emotion data. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, analysis unit, provision unit, and suggestion unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit can collect facial expressions and voices of customers using the camera 42 and microphone 238 of the robot 414. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected data and analyzes the customer's emotions in real time. The provision unit is realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and provides the analysis results to the restaurant. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests services and campaigns based on the provided emotion data.

[0106] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0107] The analysis unit can estimate the customer's emotions and adjust the analysis algorithm based on the estimated customer emotions. For example, if the customer is happy, an analysis algorithm that emphasizes positive emotions can be applied. If the customer is dissatisfied, an algorithm that analyzes negative emotions in detail can be applied. If the customer is relaxed, an algorithm that analyzes natural emotions can be applied. In this way, by adjusting the analysis algorithm based on the customer's emotions, the accuracy of the analysis can be improved.

[0108] The collection unit can analyze the customer's past visit history and select the optimal collection method. For example, if the customer has visited the store frequently in the past, facial recognition technology can be used to quickly collect data. If the customer is visiting the store for the first time, detailed data can be collected using voice recognition technology. If the customer tends to visit the store at a specific time of day, a collection method suited to that time of day can be selected. In this way, the optimal collection method can be selected by analyzing the customer's past visit history.

[0109] The providing unit can estimate the customer's emotions and adjust the format of the data to be provided based on the estimated customer emotions. For example, if the customer is happy, a data format that emphasizes positive emotions can be provided. If the customer is dissatisfied, a data format that displays negative emotions in detail can be provided. If the customer is relaxed, a data format that displays natural emotions can be provided. In this way, by adjusting the data format based on the customer's emotions, more appropriate data can be provided.

[0110] When collecting data, the collection unit can optimize the placement of cameras or microphones based on the seating position or movement line of customers. For example, a camera can be placed at the optimal angle to capture facial expressions when a customer takes a seat. A microphone can also be placed to clearly collect audio as the customer moves along their movement line. If customers stay in a specific area, cameras and microphones can be placed preferentially in that area. This allows for more accurate data collection by optimizing the placement of cameras and microphones based on the seating position and movement line of customers.

[0111] The suggestion unit can estimate the customer's emotions and adjust the way the suggestion is expressed based on the estimated customer's emotions. For example, if the customer is happy, the suggestion can be made in a positive way. If the customer is dissatisfied, the suggestion can be made in a way that emphasizes areas for improvement. If the customer is relaxed, the suggestion can be made in a natural way. In this way, by adjusting the way the suggestion is expressed based on the customer's emotions, more appropriate suggestions can be made.

[0112] During analysis, the analysis unit can evaluate the reliability of the collected data and improve the accuracy of the analysis results. For example, the reliability of the collected data is evaluated and only highly reliable data is used for analysis. To evaluate the reliability of the data, multiple data sources can be cross-checked. The reliability of the data can also be evaluated and low-reliability data can be filtered. In this way, the accuracy of the analysis results can be improved by evaluating the reliability of the collected data.

[0113] The collection unit can estimate the customer's emotions and adjust the type of data to be collected based on the estimated customer emotions. For example, if the customer is happy, it can prioritize collecting smiling facial expressions and a bright tone of voice. If the customer is dissatisfied, it can also focus on collecting wrinkles between the eyebrows and a low tone of voice. If the customer is relaxed, it can also collect natural facial expressions and a calm tone of voice. In this way, by adjusting the type of data to be collected based on the customer's emotions, it is possible to collect more accurate data.

[0114] The providing unit can adjust the level of detail of the data according to the skill level of the restaurant staff when providing the data. For example, if the staff is a novice, concise and easy-to-understand data can be provided. If the staff is experienced, detailed data can also be provided. The way in which the data is displayed can also be adjusted according to the skill level of the staff. In this way, by adjusting the level of detail of the data according to the skill level of the staff, it is possible to provide data that is easy to understand.

[0115] When making a suggestion, the suggestion unit can apply different suggestion algorithms depending on the category of the customer's emotional data. For example, a positive suggestion algorithm can be applied based on positive emotional data. A suggestion algorithm that highlights areas for improvement can also be applied based on negative emotional data. A natural suggestion algorithm can also be applied based on natural emotional data. This makes it possible to make more appropriate suggestions by applying a suggestion algorithm depending on the category of emotional data.

[0116] The providing unit can estimate the customer's emotions and determine the priority of data to be provided based on the estimated customer emotions. For example, if the customer is happy, data that emphasizes positive emotions can be provided preferentially. If the customer is dissatisfied, data that displays negative emotions in detail can be provided preferentially. If the customer is relaxed, data that displays natural emotions can be provided preferentially. Thus, by determining the priority of data based on the customer's emotions, important data can be provided preferentially.

[0117] The processing flow of the second embodiment will be briefly explained below.

[0118] Step 1: The collection unit collects facial expressions or voices of customers. For example, the collection unit can collect facial expressions or voices of customers using a camera or microphone installed in the restaurant. Step 2: The analysis unit analyzes the data collected by the collection unit and analyzes the customer's emotions in real time. For example, it uses a generation AI to analyze the collected facial expressions and voice data to identify the customer's emotions. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and identifies emotions based on the collected data. Step 3: The providing unit provides the restaurant with the analysis results obtained by the analysis unit. For example, the analysis results can be provided as a digital report or a real-time notification. Step 4: The suggestion unit suggests services and campaigns based on the data provided by the provision unit. For example, personalized services and campaigns can be suggested based on the provided emotion data.

[0119] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0120] 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 engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). 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 speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0121] Furthermore, the processing by the data processing system 10 described above 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 necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0122] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0123] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0124] 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.

[0125] 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, RAM 30, and 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.

[0126] 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.

[0127] 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 audio according to instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and 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 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0129] 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 carried out in a secure state.

[0130] Fig. 4 shows an example of the 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.

[0131] 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.

[0132] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0133] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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. The smart glasses 214 also 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 perform processing similar to that of the specific processing unit 290 using these models.

[0134] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0135] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0136] 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. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0137] 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 also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, 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, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0138] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0139] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0140] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0141] 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, RAM 30, and 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.

[0142] 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.

[0143] 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 audio according to instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and 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 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0145] 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 carried out in a secure state.

[0146] 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.

[0147] 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.

[0148] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0149] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification 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.

[0150] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0151] 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 audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0152] 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. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0153] 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 also 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. Furthermore, 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, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0156] 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.

[0157] 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, RAM 30, and 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.

[0158] 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.

[0159] 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 audio according to instructions from the processor 46.

[0160] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0161] 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 carried out in a secure state.

[0162] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the 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.

[0163] 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.

[0164] 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.

[0165] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0166] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also 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 perform the same process as the identification processing unit 290 using these models.

[0167] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0168] 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 voice indicating a user input regarding 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.

[0169] 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. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0170] 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 also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, 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.

[0171] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0172] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0173] FIG. 9 illustrates 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. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0174] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically 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.

[0175] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0176] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0177] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0178] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of 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, "relieved," "calm," and "reassuring," have similar emotion values.

[0179] 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.

[0180] 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 USB (Universal Serial Bus) 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.

[0181] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0182] 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.

[0183] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0184] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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.

[0185] As an example of a system configured with a single 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 system that uses a processor that realizes the functions of an 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.

[0186] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0187] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0188] The above-described description and illustrations are a detailed explanation 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, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects 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 replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0189] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0190] [Explanation of symbols]

[0191] 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 facial expressions or voices of customers; an analysis unit that analyzes the data collected by the collection unit and analyzes customer emotions in real time; a providing unit that provides the analysis results obtained by the analysis unit; a proposal unit that proposes a service or a campaign based on the data provided by the provision unit; Equipped with A system characterized by:

2. The collecting unit Collecting facial expressions or voices of customers using cameras or microphones installed in restaurants 2. The system of claim 1.

3. The analysis unit Analyzing collected facial expression or voice data to identify customer emotions 2. The system of claim 1.

4. The providing unit Provide analysis results to restaurants 2. The system of claim 1.

5. The proposal unit Suggesting personalized services or campaigns based on the emotional data provided 2. The system of claim 1.

6. The proposal unit Use customer sentiment data to suggest promotions for specific times of day or days of the week 2. The system of claim 1.

7. The collecting unit Infer customer sentiment and adjust the type of data you collect based on that sentiment 2. The system of claim 1.

8. The collecting unit Analyze customer visit history and select the appropriate collection method 2. The system of claim 1.

9. The collecting unit Optimize camera or microphone placement based on customer seating location or movement during collection 2. The system of claim 1.

Images