System

Abstract

An object of a system according to an embodiment is to efficiently perform restaurant selection, reservation, ordering, and word-of-mouth extraction on the basis of a user's desire.SOLUTION: A system includes an analysis part, an update part, a reservation part, an order part, and an extraction part. The analysis unit analyzes a desire of a user. The updating unit updates the proposal content based on the information analyzed by the analyzing unit. The reservation unit makes a reservation based on the proposal content updated by the update unit. The ordering unit supports ordering at the restaurant reserved by the reservation unit. The extraction unit extracts a word-of-mouth based on the content ordered by the ordering unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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 technologies have had the problem of making it difficult to consistently and efficiently select restaurants, make reservations, place orders, and extract reviews based on users' preferences.

[0005] The system according to the embodiment aims to efficiently carry out everything from restaurant selection to reservations, ordering, and review extraction based on the user's preferences. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, an update unit, a reservation unit, an ordering unit, and an extraction unit. The analysis unit analyzes the user's preferences. The update unit updates the proposal content based on the information analyzed by the analysis unit. The reservation unit makes a reservation based on the proposal content updated by the update unit. The order unit supports ordering at the restaurant reserved by the reservation unit. The extraction unit extracts reviews based on the content ordered by the order unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently perform everything from restaurant selection to reservations, ordering, and review extraction based on the user's preferences. [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) A restaurant selection system according to an embodiment of the present invention analyzes a user's preferences, updates recommendations, makes reservations, supports ordering, and extracts reviews. The restaurant selection system analyzes a user's preferences, updates recommendations, makes reservations, supports ordering, and extracts reviews, thereby efficiently and efficiently supporting the user's restaurant selection. For example, a user inputs preferences and requirements for a restaurant into the restaurant selection system. For example, the user inputs information such as "I want Japanese food," "My budget is under 3,000 yen," and "A place close to the station." This information is then input into an AI. The restaurant selection system then analyzes the user's input information using AI to suggest optimal restaurants. For example, the system may suggest Japanese restaurants with a budget of under 3,000 yen and close to the station. Furthermore, the restaurant selection system personalizes the recommendations through dialogue with the user. For example, if the user adds a preference such as "I prefer a quiet atmosphere," the AI ​​updates the recommendations to reflect that preference. This allows the system to suggest restaurants that better meet the user's needs. The user can then make a reservation at the suggested restaurants. The restaurant selection system works in conjunction with a reservation system to make reservations for the user's desired date and time. For example, if a user inputs, "I'd like to make a reservation for tomorrow at 7 p.m.," the AI ​​will make the reservation for that time. Furthermore, the restaurant selection system also supports users when ordering at restaurants. When a user selects a menu, the AI ​​suggests recommended dishes. For example, it provides information such as, "This restaurant recommends sushi." Finally, the restaurant selection system also supports users when posting reviews about their restaurant experiences. The AI ​​analyzes users' reviews and extracts information useful to other users. For example, it extracts reviews such as, "The sushi at this restaurant was fresh and delicious" and provides this information to other users. In this way, the restaurant selection system efficiently supports users' restaurant selection, providing consistent support from reservations to orders to review extraction. This allows users to efficiently support their restaurant selection, providing consistent support from reservations to orders to review extraction. For example, it can reduce the time it takes to select a restaurant and allow them to make a more appropriate choice.Furthermore, by making suggestions based on the user's wishes, the level of satisfaction can be improved.

[0029] A restaurant selection system according to an embodiment includes an analysis unit, an update unit, a reservation unit, an order unit, and an extraction unit. The analysis unit analyzes a user's preferences. The user's preferences include, but are not limited to, the type of restaurant, budget, location, and time of day. The analysis unit analyzes the user's preferences using, for example, natural language processing technology. The analysis unit can also analyze the user's preferences using a machine learning algorithm. The analysis unit can also suggest optimal restaurants based on the user's preferences. For example, the analysis unit selects appropriate candidates from a restaurant database based on the user's preferences. The update unit updates the suggestions based on the information analyzed by the analysis unit. For example, the update unit updates the suggestions through a dialogue with the user. For example, the update unit uses a chatbot to communicate with the user and update the suggestions. The update unit can also use voice recognition technology to communicate with the user and update the suggestions. The update unit can also personalize the suggestions based on the user's preferences. For example, if the user expresses an additional preference such as "preferably a quiet atmosphere," the update unit updates the suggestions to reflect that preference. The reservation unit makes a reservation based on the proposal content updated by the update unit. The reservation unit, for example, cooperates with an online reservation system to make a reservation. The reservation unit can also cooperate with a telephone reservation system to make a reservation. The reservation unit can also make a reservation based on a user's desired date and time. For example, if a user inputs, "I would like to make a reservation for tomorrow at 7 p.m.", the reservation unit makes a reservation for that time. The order unit supports ordering at the restaurant reserved by the reservation unit. For example, the order unit suggests recommended menu items when the user selects a menu. For example, the order unit provides information such as, "This restaurant's recommendation is sushi." The order unit can also suggest recommended menu items based on the user's past ordering history. The order unit can also suggest recommended menu items based on the user's health condition and dietary restrictions. For example, if the user is on a diet, the order unit suggests a low-calorie menu item. The extraction unit extracts reviews based on the contents ordered by the order unit. For example, the extraction unit analyzes user reviews and extracts information useful to other users.For example, the extraction unit extracts reviews such as "The sushi at this restaurant was fresh and delicious" and provides them to other users. The extraction unit can also extract reviews using text analysis technology. The extraction unit can also estimate a user's emotions and extract reviews based on the emotions. For example, if a user is feeling stressed, the extraction unit extracts simple and intuitive reviews. This allows the restaurant selection system according to the embodiment to consistently support analysis, suggestions, reservations, orders, and review extraction based on the user's preferences.

[0030] The analysis unit can analyze the user's preferences and suggest appropriate restaurants. The analysis unit analyzes the user's preferences using, for example, natural language processing technology. For example, when the user inputs preferences such as "I want to eat Japanese food," "My budget is under 3,000 yen," and "A place close to the station," the analysis unit analyzes the information. The analysis unit can also analyze the user's preferences using a machine learning algorithm. For example, the analysis unit can learn the user's past selection history and perform analysis based on the user's preferences. The analysis unit can also suggest optimal restaurants based on the user's preferences. For example, the analysis unit selects appropriate candidates from a restaurant database based on the user's preferences. This makes it possible to suggest optimal restaurants based on the user's preferences. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's preferences into a generation AI, which then performs analysis.

[0031] The update unit can change the proposal content through a dialogue with the user. The update unit, for example, uses a chatbot to dialogue with the user and update the proposal content. For example, if the user expresses an additional preference such as "a quiet atmosphere is preferable," the update unit updates the proposal content to reflect that preference. The update unit can also use voice recognition technology to dialogue with the user and update the proposal content. For example, if the user expresses "I would like to make a reservation for tomorrow at 7 p.m.", the update unit updates the proposal content to reflect that preference. The update unit can also personalize the proposal content based on the user's preference. For example, if the user expresses "I would like to eat Japanese food," the update unit updates the proposal content to reflect that preference. In this way, the proposal content can be personalized through a dialogue with the user. Some or all of the above-described processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input the content of the dialogue with the user into a generation AI, which then updates the proposal content.

[0032] The reservation unit can make a reservation based on the user's desired date and time. The reservation unit, for example, works in conjunction with an online reservation system to make a reservation. For example, when a user inputs, "I want to make a reservation for tomorrow at 7 p.m.," the reservation unit makes a reservation for that time. The reservation unit can also make a reservation in conjunction with a telephone reservation system. For example, when a user inputs, "I want to make a reservation now," the reservation unit makes a reservation through the telephone reservation system. The reservation unit can also make a reservation based on the user's desired date and time. For example, when a user inputs, "I want to make a reservation for a weekend night," the reservation unit makes a reservation for that time. In this way, a reservation can be made based on the user's desired date and time. Some or all of the above-described processing in the reservation unit may be performed, for example, using AI, or may be performed without using AI. For example, the reservation unit can input the user's desired date and time into a generation AI, and the generation AI can make a reservation.

[0033] The ordering unit can suggest recommended menu items when the user selects a menu. For example, the ordering unit may provide information such as, "This restaurant's recommendation is sushi." The ordering unit can also suggest recommended menu items based on the user's past order history. For example, the ordering unit may analyze the user's preference trends based on data on menu items previously ordered by the user and suggest similar menu items. The ordering unit can also suggest recommended menu items based on the user's health status and dietary restrictions. For example, if the user is on a diet, the ordering unit may suggest low-calorie menu items. This allows the ordering unit to suggest recommended menu items when the user selects a menu. Some or all of the above-described processing in the ordering unit may be performed using, for example, AI, or may be performed without using AI. For example, the ordering unit may input the user's order information into a generation AI, which may then suggest recommended menu items.

[0034] The extraction unit can analyze user reviews and extract information that is useful to other users. For example, the extraction unit analyzes user reviews and extracts information that is useful to other users. For example, the extraction unit extracts reviews such as "The sushi at this restaurant was fresh and delicious" and provides the reviews to other users. The extraction unit can also extract reviews using text analysis technology. For example, the extraction unit analyzes user reviews using text analysis technology and extracts useful information. The extraction unit can also estimate user emotions and extract reviews based on the emotions. For example, if a user is feeling stressed, the extraction unit extracts simple and intuitive reviews. This makes it possible to analyze user reviews and extract useful information. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input user review data into a generation AI, which then extracts reviews.

[0035] The analysis unit can analyze the user's past restaurant selection history and select an appropriate analysis algorithm. For example, the analysis unit analyzes the user's past restaurant selection history and selects the optimal analysis algorithm. For example, the analysis unit analyzes preference trends based on data on restaurants the user has visited in the past. The analysis unit can also extract characteristics of restaurants that the user has previously rated highly and suggest restaurants with similar characteristics. The analysis unit can also analyze characteristics to be avoided based on data on restaurants the user has previously avoided and exclude them from suggestions. This allows the optimal analysis algorithm to be selected based on the past history. The analysis algorithm can be realized using techniques such as machine learning algorithms and statistical analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's past restaurant selection history into a generation AI, which then selects the analysis algorithm.

[0036] The analysis unit can adjust the analysis results based on the user's current living situation and health condition. The analysis unit customizes the analysis results based on the user's current living situation and health condition, for example. For example, if the user is on a diet, the analysis unit can prioritize restaurants offering low-calorie menus. Furthermore, if the user inputs the results of a health check, the analysis unit can suggest restaurants offering healthy menus based on the results. Furthermore, if the user has a specific allergy, the analysis unit can suggest restaurants offering menus that cater to the allergy. This allows the analysis results to be customized based on the user's living situation and health condition. Information about the user's living situation and health condition is obtained, for example, from the user's occupation, family environment, medical data, self-reporting, etc. Some or all of the above-described processing by the analysis unit may be performed using, or without, AI. For example, the analysis unit can input data about the user's living situation and health condition into a generation AI, which can then adjust the analysis results.

[0037] The analysis unit can evaluate the reliability of the information input by the user and prioritize processing of highly reliable information. The analysis unit, for example, evaluates the reliability of the information input by the user and prioritizes analysis of highly reliable information. For example, the analysis unit can evaluate the accuracy of information previously provided by the user and perform analysis based on the highly reliable information. The analysis unit can also check the consistency of the information provided by the user and perform analysis based on the consistent information. The analysis unit can also evaluate the source of the information provided by the user and perform analysis based on information from highly reliable sources. This allows highly reliable information to be analyzed preferentially. The reliability evaluation criteria and method are based on, for example, the source of the data, past performance, etc. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's input information to a generation AI, and the generation AI can evaluate reliability.

[0038] The analysis unit can prioritize processing region-specific restaurant information by taking into account the user's geographical location information. The analysis unit, for example, prioritizes analyzing region-specific restaurant information by taking into account the user's geographical location information. For example, the analysis unit prioritizes suggesting restaurants close to the user's current location. Furthermore, if the user is in a specific region, the analysis unit can prioritize suggesting restaurants that serve local specialties. Furthermore, if the user is traveling, the analysis unit can prioritize suggesting restaurants near tourist spots. This allows analysis to take geographical location information into consideration. The geographical location information is acquired and used based on, for example, GPS data, address information, etc. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's geographical location information into a generation AI, which then analyzes region-specific restaurant information.

[0039] The analysis unit can analyze the user's social media activity and process related restaurant information. The analysis unit, for example, analyzes the user's social media activity and analyzes the related restaurant information. For example, the analysis unit can suggest related restaurants based on the locations where the user has checked in on social media. The analysis unit can also analyze the content of the user's social media posts and suggest restaurants that the user may be interested in. The analysis unit can also suggest related restaurants based on information about restaurants visited by the user's friends. This enables analysis based on social media activity. The analysis method and criteria for social media activity are based on, for example, the content of posts, the number of likes, etc. Some or all of the above-mentioned processing by the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the user's social media activity data into a generation AI, which then analyzes the related restaurant information.

[0040] The analysis unit can adjust the analysis algorithm by reflecting the user's past feedback. The analysis unit, for example, customizes the analysis algorithm by reflecting the user's past feedback. For example, the analysis unit can analyze the characteristics of restaurants that the user has previously rated highly and suggest restaurants with similar characteristics. The analysis unit can also analyze the characteristics of restaurants that the user has previously rated poorly and exclude restaurants with similar characteristics from suggestions. The analysis unit can also adjust the analysis algorithm based on feedback provided by the user in the past to make more appropriate suggestions. This allows the analysis algorithm to be customized by reflecting past feedback. The content and acquisition method of the feedback are based on, for example, survey results, user comments, etc. Some or all of the above-mentioned processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past feedback data into a generation AI, which can adjust the analysis algorithm.

[0041] The update unit can analyze the user's dialogue history and select an appropriate update algorithm. The update unit, for example, analyzes the user's dialogue history and selects an optimal update algorithm. For example, the update unit selects an optimal update algorithm based on the content of dialogues the user has had in the past. The update unit can also adjust the update algorithm based on feedback the user has provided in the past. The update unit can also analyze the user's preferences and tendencies from the dialogue history and select an optimal update algorithm. This makes it possible to select an optimal update algorithm based on the dialogue history. The content and analysis method of the dialogue history are based on, for example, chat logs, voice data, etc. Some or all of the above-mentioned processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input the user's dialogue history data to a generation AI, which then selects an update algorithm.

[0042] The update unit can adjust the suggestion content based on the user's current interests and trends. The update unit, for example, customizes the suggestion content based on the user's current interests and trends. For example, the update unit customizes the suggestion content based on topics in which the user is currently interested. The update unit can also customize the suggestion content based on keywords recently searched by the user. The update unit can also customize the suggestion content based on information about accounts the user follows on social media. This allows the suggestion content to be customized based on interests and trends. The content and acquisition method of the interests and trends are based on, for example, the user's hobbies, recent search history, social media trends, news articles, etc. Some or all of the above-mentioned processing in the update unit may be performed using, or without, AI. For example, the update unit can input the user's interests and trend data into a generation AI, which can then adjust the suggestion content.

[0043] The update unit can analyze changes in the user's input information in real time and instantly change the content of the suggestions. For example, the update unit can analyze changes in the user's input information in real time and instantly update the content of the suggestions. For example, the update unit updates the content of the suggestions in real time when the user inputs new information. The update unit can also instantly update the content of the suggestions based on information provided by the user during dialogue. The update unit can also analyze changes in the information input by the user in real time and provide appropriate content of the suggestions. This allows the content of the suggestions to be instantly updated based on changes in the input information. The content of the changes in the input information and the method of acquiring the changes are determined based on, for example, real-time data updates, changes in user behavior, etc. Some or all of the above-mentioned processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input the user's input information to a generation AI, which can instantly update the content of the suggestions.

[0044] The update unit can prioritize changing the region-specific proposal content in consideration of the user's geographical location information. The update unit, for example, prioritizes updating the region-specific proposal content in consideration of the user's geographical location information. For example, the update unit prioritizes updating information about restaurants close to the user's current location. Furthermore, if the user is in a specific region, the update unit can prioritize updating information about restaurants that serve local specialties. Furthermore, if the user is traveling, the update unit can prioritize updating information about restaurants near tourist spots. This allows the proposal content to be updated in consideration of the geographical location information. The geographical location information is acquired and used based on, for example, GPS data, address information, etc. Some or all of the above-described processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input the user's geographical location information to a generation AI, which can then update the region-specific proposal content.

[0045] The update unit can analyze the user's social media activity and change the related suggestions. The update unit, for example, analyzes the user's social media activity and updates the related suggestions. For example, the update unit prioritizes updating information about places the user has checked in to on social media. The update unit can also analyze the user's social media posts and update the related suggestions. The update unit can also update the related suggestions based on information about restaurants visited by the user's friends. This makes it possible to update the suggestions based on social media activity. The analysis method and criteria for social media activity are based on, for example, the post content, the number of likes, etc. Some or all of the above-mentioned processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input the user's social media activity data into a generation AI, which then updates the related suggestions.

[0046] The update unit can adjust the content of suggestions by reflecting the user's past feedback. The update unit, for example, customizes the content of suggestions by reflecting the user's past feedback. For example, the update unit can analyze the characteristics of restaurants that the user has previously rated highly and suggest restaurants with similar characteristics. The update unit can also analyze the characteristics of restaurants that the user has previously rated poorly and exclude restaurants with similar characteristics from the suggestions. The update unit can also customize the content of suggestions based on feedback provided by the user in the past. This allows the content of suggestions to be customized by reflecting past feedback. The content of the feedback and the method of obtaining it are based on, for example, survey results, user comments, etc. Some or all of the above-mentioned processing in the update unit may be performed using, or without, AI. For example, the update unit can input the user's past feedback data into a generation AI, which can then adjust the content of suggestions.

[0047] The reservation unit can analyze the user's past reservation history and select an appropriate reservation method. The reservation unit, for example, analyzes the user's past reservation history and selects the optimal reservation method. For example, the reservation unit can suggest the optimal reservation method based on the reservation methods the user has used in the past. The reservation unit can also suggest a reservation method that avoids congestion based on the user's past reservation history. The reservation unit can also analyze the user's past reservation history and suggest the most efficient reservation method. This makes it possible to select the optimal reservation method based on the past reservation history. The content and analysis method of the reservation history are based on, for example, past reservation data, cancellation history, etc. Some or all of the above-mentioned processing in the reservation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reservation unit can input the user's past reservation history data into a generation AI, which can select a reservation method.

[0048] The reservation unit can adjust the reservation contents based on the user's current schedule and plans. The reservation unit customizes the reservation contents based on the user's current schedule and plans, for example. For example, the reservation unit refers to the user's calendar information and suggests the optimal reservation date and time. The reservation unit can also customize the reservation contents to match the user's schedule. The reservation unit can also suggest the optimal reservation method based on the user's plans. This allows the reservation contents to be customized based on the schedule and plans. The contents and acquisition method of the schedule and plans are based on, for example, a calendar app, the contents of a planner, etc. Some or all of the above-mentioned processing in the reservation unit may be performed using, or without, AI. For example, the reservation unit can input the user's schedule and plan data into a generation AI, which can then adjust the reservation contents.

[0049] The reservation unit can evaluate the reliability of information input by the user and prioritize reliable information. The reservation unit, for example, evaluates the reliability of information input by the user and makes a reservation based on the reliable information. For example, the reservation unit can evaluate the accuracy of information previously provided by the user and make a reservation based on the reliable information. The reservation unit can also check the consistency of information provided by the user and make a reservation based on the consistent information. The reservation unit can also evaluate the source of information provided by the user and make a reservation based on information from a reliable source. This allows a reservation to be made based on reliable information. The reliability evaluation criteria and method are based on, for example, the source of the data, past performance, etc. Some or all of the above-mentioned processing in the reservation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reservation unit can input the user's input information to a generation AI, and the generation AI can evaluate the reliability.

[0050] The reservation unit can prioritize processing region-specific reservation information by taking into account the user's geographical location information. The reservation unit, for example, prioritizes acquiring region-specific reservation information by taking into account the user's geographical location information. For example, the reservation unit prioritizes acquiring reservation information for restaurants close to the user's current location. Furthermore, if the user is in a specific region, the reservation unit can prioritize acquiring reservation information for restaurants that serve local specialties. Furthermore, if the user is traveling, the reservation unit can prioritize acquiring reservation information for restaurants near tourist spots. This makes it possible to acquire reservation information by taking into account the geographical location information. The acquisition and use of geographical location information is based on, for example, GPS data, address information, etc. Some or all of the above-described processing in the reservation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reservation unit can input the user's geographical location information into a generation AI, which can then acquire region-specific reservation information.

[0051] The reservation unit can analyze the user's social media activity and process related reservation information. The reservation unit, for example, analyzes the user's social media activity and acquires related reservation information. For example, the reservation unit prioritizes acquiring reservation information related to places where the user has checked in on social media. The reservation unit can also analyze the content of the user's social media posts and acquire related reservation information. The reservation unit can also acquire related reservation information based on reservation information for restaurants visited by the user's friends. This makes it possible to acquire reservation information based on social media activity. The analysis method and criteria for social media activity are based on, for example, the content of posts, the number of likes, etc. Some or all of the above-described processing in the reservation unit may be performed using, or without, AI. For example, the reservation unit can input the user's social media activity data into a generation AI, which then acquires related reservation information.

[0052] The reservation unit can adjust the reservation method by reflecting the user's past feedback. The reservation unit, for example, customizes the reservation method by reflecting the user's past feedback. For example, the reservation unit suggests a similar reservation method based on a reservation method that the user has previously rated highly. The reservation unit can also exclude a similar reservation method from suggestions based on a reservation method that the user has previously rated poorly. The reservation unit can also customize the reservation method based on feedback provided by the user in the past. This makes it possible to customize the reservation method by reflecting past feedback. The content and acquisition method of the feedback are based on, for example, survey results, user comments, etc. Some or all of the above-mentioned processing in the reservation unit may be performed using AI, for example, or may be performed without using AI. For example, the reservation unit can input the user's past feedback data into a generation AI, and the generation AI can adjust the reservation method.

[0053] The ordering unit can analyze the user's past order history and select an appropriate menu suggestion algorithm. For example, the ordering unit analyzes the user's past order history and selects the optimal menu suggestion algorithm. For example, the ordering unit analyzes preference trends based on data on menus the user has previously ordered. The ordering unit can also extract characteristics of menus that the user has previously rated highly and suggest menus with similar characteristics. The ordering unit can also analyze characteristics to be avoided based on data on menus the user has previously avoided and exclude them from suggestions. This makes it possible to select the optimal menu suggestion algorithm based on the past order history. The content and analysis method of the order history are based on, for example, past order data, frequency, etc. Some or all of the above-mentioned processing in the ordering unit may be performed using, for example, AI, or may be performed without AI. For example, the ordering unit can input the user's past order history data into a generation AI, which then selects a menu suggestion algorithm.

[0054] The ordering unit can adjust the menu suggestions based on the user's current health condition and dietary restrictions. The ordering unit customizes the menu suggestions based on the user's current health condition and dietary restrictions, for example. For example, if the user is on a diet, the ordering unit can prioritize low-calorie menu suggestions. Furthermore, if the user inputs the results of a health check, the ordering unit can also suggest healthy menus based on those results. Furthermore, if the user has specific allergies, the ordering unit can also suggest menus that accommodate those allergies. This allows the menu suggestions to be customized based on the user's health condition and dietary restrictions. Information on the user's health condition and dietary restrictions is obtained, for example, from medical data, self-reporting, allergy information, doctor's instructions, etc. Some or all of the above-described processing in the ordering unit may be performed using, for example, AI, or may be performed without AI. For example, the ordering unit can input data on the user's health condition and dietary restrictions into a generation AI, which can then adjust the menu suggestions.

[0055] The order unit can evaluate the reliability of information input by the user and prioritize reliable information. The order unit, for example, evaluates the reliability of information input by the user and suggests a menu based on the reliable information. For example, the order unit can evaluate the accuracy of information previously provided by the user and suggest a menu based on the reliable information. The order unit can also check the consistency of information provided by the user and suggest a menu based on the consistent information. The order unit can also evaluate the source of information provided by the user and suggest a menu based on information from a reliable source. This makes it possible to suggest a menu based on reliable information. The reliability evaluation criteria and method are based on, for example, the source of the data, past performance, etc. Some or all of the above-mentioned processing in the order unit may be performed using, for example, AI, or may be performed without using AI. For example, the order unit can input the user's input information into a generation AI, which can evaluate the reliability.

[0056] The ordering unit can prioritize processing region-specific menu information by taking into account the user's geographical location information. The ordering unit, for example, prioritizes suggesting region-specific menu information by taking into account the user's geographical location information. For example, the ordering unit prioritizes suggesting menus from restaurants close to the user's current location. Furthermore, if the user is in a specific region, the ordering unit can prioritize suggesting menus offering local specialties. Furthermore, if the user is traveling, the ordering unit can prioritize suggesting menus from restaurants near tourist spots. This makes it possible to suggest menu information by taking into account the geographical location information. The method of acquiring and using the geographical location information is based on, for example, GPS data, address information, etc. Some or all of the above-described processing in the ordering unit may be performed using, for example, AI, or may be performed without using AI. For example, the ordering unit can input the user's geographical location information into a generation AI, which then suggests region-specific menu information.

[0057] The ordering unit can analyze the user's social media activity and process related menu information. For example, the ordering unit can analyze the user's social media activity and suggest related menu information. For example, the ordering unit can prioritize suggesting menus from places where the user has checked in on social media. The ordering unit can also analyze the user's social media posts and suggest related menus. The ordering unit can also suggest related menus based on menus from restaurants visited by the user's friends. This makes it possible to suggest menu information based on social media activity. The analysis method and criteria for social media activity are based on, for example, the content of posts, the number of likes, etc. Some or all of the above-mentioned processing in the ordering unit may be performed using, or without, AI. For example, the ordering unit can input the user's social media activity data into a generation AI, which then suggests related menu information.

[0058] The ordering unit can adjust the menu suggestion method by reflecting the user's past feedback. The ordering unit, for example, customizes the menu suggestion method by reflecting the user's past feedback. For example, the ordering unit can analyze the characteristics of menus that the user has previously rated highly and suggest menus with similar characteristics. The ordering unit can also analyze the characteristics of menus that the user has previously rated poorly and exclude menus with similar characteristics from suggestions. The ordering unit can also customize the menu suggestion method based on feedback provided by the user in the past. This allows the menu suggestion method to be customized by reflecting past feedback. The content and acquisition method of the feedback are based on, for example, survey results, user comments, etc. Some or all of the above-mentioned processing in the ordering unit may be performed using, or without, AI. For example, the ordering unit can input the user's past feedback data into a generation AI, which can then adjust the menu suggestion method.

[0059] The extraction unit can analyze a user's past review history and select an appropriate extraction algorithm. For example, the extraction unit analyzes a user's past review history and selects an optimal extraction algorithm. For example, the extraction unit analyzes preference trends based on data of reviews posted by the user in the past. The extraction unit can also extract characteristics of reviews that the user has previously given high ratings and preferentially extract reviews with similar characteristics. The extraction unit can also analyze characteristics to be avoided based on data of reviews that the user has previously avoided and exclude them from extraction. This allows the optimal extraction algorithm to be selected based on the past review history. The content and analysis method of the review history are based on, for example, past review data, ratings, etc. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without AI. For example, the extraction unit can input the user's past review history data into a generation AI, which then selects an extraction algorithm.

[0060] The extraction unit can adjust the review extraction based on the user's current interests and trends. The extraction unit, for example, customizes the review extraction based on the user's current interests and trends. For example, the extraction unit customizes the review extraction based on topics that the user is currently interested in. The extraction unit can also customize the review extraction based on keywords recently searched by the user. The extraction unit can also customize the review extraction based on information about accounts the user follows on social media. This allows the review extraction to be customized based on interests and trends. The content and acquisition method of the interests and trends are based on, for example, the user's hobbies, recent search history, social media trends, news articles, etc. Some or all of the above-described processing in the extraction unit may be performed using, or without, AI. For example, the extraction unit can input user interests and trend data into a generation AI, which can then adjust the review extraction.

[0061] The extraction unit can evaluate the reliability of information input by a user and prioritize reliable information. The extraction unit, for example, evaluates the reliability of information input by a user and extracts reviews based on reliable information. For example, the extraction unit can evaluate the accuracy of information previously provided by a user and extract reviews based on reliable information. The extraction unit can also check the consistency of information provided by a user and extract reviews based on consistent information. The extraction unit can also evaluate the source of information provided by a user and extract reviews based on information from reliable sources. This makes it possible to extract reviews based on reliable information. The reliability evaluation criteria and method are based on, for example, the source of data, past performance, etc. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input user input information to a generation AI, which then evaluates reliability.

[0062] The extraction unit can prioritize processing region-specific word-of-mouth information by taking into account the user's geographical location information. The extraction unit, for example, prioritizes extracting region-specific word-of-mouth information by taking into account the user's geographical location information. For example, the extraction unit prioritizes extracting reviews of restaurants close to the user's current location. Furthermore, if the user is in a specific region, the extraction unit can prioritize extracting reviews of restaurants that offer local specialties. Furthermore, if the user is traveling, the extraction unit can prioritize extracting reviews of restaurants near tourist spots. This allows word-of-mouth information to be extracted by taking into account the geographical location information. The geographical location information can be acquired and used based on, for example, GPS data, address information, etc. Some or all of the above-described processing by the extraction unit may be performed using, for example, AI, or may be performed without AI. For example, the extraction unit can input the user's geographical location information into a generation AI, which then extracts region-specific word-of-mouth information.

[0063] The extraction unit can analyze the user's social media activity and process related word-of-mouth information. The extraction unit, for example, analyzes the user's social media activity and extracts related word-of-mouth information. For example, the extraction unit prioritizes extracting reviews of places where the user has checked in on social media. The extraction unit can also analyze the content of the user's social media posts and extract related reviews. The extraction unit can also extract related reviews based on reviews of restaurants visited by the user's friends. This makes it possible to extract word-of-mouth information based on social media activity. The analysis method and criteria for social media activity are based on, for example, the content of posts, the number of likes, etc. Some or all of the above-mentioned processing by the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the user's social media activity data into a generation AI, which then extracts related word-of-mouth information.

[0064] The extraction unit can adjust the review extraction method by reflecting the user's past feedback. The extraction unit, for example, customizes the review extraction method by reflecting the user's past feedback. For example, the extraction unit analyzes the characteristics of reviews that the user has previously given a high rating and prioritizes extracting reviews with similar characteristics. The extraction unit can also analyze the characteristics of reviews that the user has previously given a low rating and exclude reviews with similar characteristics from extraction. The extraction unit can also customize the review extraction method based on feedback provided by the user in the past. This allows the review extraction method to be customized by reflecting past feedback. The content of the feedback and the method of obtaining it are based on, for example, survey results, user comments, etc. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without AI. For example, the extraction unit can input the user's past feedback data into a generation AI, and the generation AI can adjust the review extraction method.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] The analysis unit can also take into account the user's past search history and browsing history when analyzing the user's preferences. For example, the analysis unit analyzes the user's preferences and tendencies based on keywords the user has searched for in the past and the content of pages the user has viewed. The analysis unit can also suggest restaurants with similar characteristics based on information about restaurants the user has viewed in the past. Furthermore, the analysis unit can analyze the frequency and timing of keywords the user has searched for in the past to estimate the user's current interests. This allows for more accurate suggestions to be made based on the user's past behavioral history.

[0067] The analysis unit may also take into account the user's social media activity when analyzing the user's preferences. For example, the analysis unit may analyze the content of posts that the user has "liked" or commented on on social media to estimate the user's preferences and interests. The analysis unit may also suggest restaurants that the user may be interested in based on information about accounts the user follows. Furthermore, the analysis unit may analyze the user's check-in history on social media and suggest restaurants with similar characteristics based on information about places and restaurants the user has visited in the past. This allows for more personalized suggestions to be made based on the user's social media activity.

[0068] The reservation unit can also take into account the user's past reservation history when making a reservation based on the user's desired date and time. For example, the reservation unit can analyze the date and frequency of the user's past reservations to estimate the user's reservation patterns. The reservation unit can also suggest restaurants with similar characteristics based on information about restaurants the user has previously reserved. Furthermore, the reservation unit can analyze the history of reservations the user has canceled in the past and make suggestions to reduce the risk of cancellation. This allows more appropriate reservation suggestions to be made based on the user's past reservation history.

[0069] The ordering unit can also take into consideration the user's current health condition and dietary restrictions when suggesting recommended menus when the user is selecting a menu. For example, if the user is on a diet, the ordering unit can preferentially suggest low-calorie menus. Also, if the user has a specific allergy, the ordering unit can suggest menus that accommodate that allergy. Furthermore, if the user inputs the results of a health check, the ordering unit can suggest healthy menus based on the results. This allows for more appropriate menu suggestions to be made based on the user's health condition and dietary restrictions.

[0070] The analysis unit can also take into account the user's current living situation and health condition when analyzing the user's preferences. For example, if the user is on a diet, the analysis unit can preferentially suggest restaurants that offer low-calorie menus. Also, if the user inputs the results of a health check, the analysis unit can suggest restaurants that offer healthy menus based on those results. Furthermore, if the user has a specific allergy, the analysis unit can suggest restaurants that offer menus that cater to that allergy. This allows for more appropriate restaurant suggestions to be made based on the user's living situation and health condition.

[0071] The update unit may also take into account the user's current interests and trends when changing the suggestions through interaction with the user. For example, the update unit may customize the suggestions based on topics that the user is currently interested in. The update unit may also customize the suggestions based on keywords that the user has recently searched for. Furthermore, the update unit may customize the suggestions based on information about accounts that the user follows on social media. This allows for more appropriate suggestions based on the user's current interests and trends.

[0072] The processing flow of the first embodiment will be briefly explained below.

[0073] Step 1: The analysis unit analyzes the user's preferences, which include the type of restaurant, budget, location, time of day, etc. The analysis unit uses natural language processing technology and machine learning algorithms to analyze the user's preferences and selects appropriate candidates from a restaurant database to suggest the most suitable restaurant. Step 2: The update unit updates the suggestions based on the information analyzed by the analysis unit. The update unit updates the suggestions through dialogue with the user, using chatbots and voice recognition technology to communicate with the user, and personalizes the suggestions based on the user's preferences. Step 3: The reservation unit makes a reservation based on the proposal updated by the update unit. The reservation unit makes a reservation in cooperation with the online reservation system and the telephone reservation system, and makes a reservation based on the user's desired date and time. Step 4: The ordering unit supports ordering at the restaurant reserved by the reservation unit. The ordering unit suggests menu recommendations when the user selects a menu, and suggests menu recommendations based on the user's past ordering history, health condition, and dietary restrictions. Step 5: The extraction unit extracts reviews based on the order details. The extraction unit analyzes the user reviews and uses text analysis and sentiment estimation techniques to extract information that is useful to other users.

[0074] (Example 2) A restaurant selection system according to an embodiment of the present invention analyzes a user's preferences, updates recommendations, makes reservations, supports ordering, and extracts reviews. The restaurant selection system analyzes a user's preferences, updates recommendations, makes reservations, supports ordering, and extracts reviews, thereby efficiently and efficiently supporting the user's restaurant selection. For example, a user inputs preferences and requirements for a restaurant into the restaurant selection system. For example, the user inputs information such as "I want Japanese food," "My budget is under 3,000 yen," and "A place close to the station." This information is then input into an AI. The restaurant selection system then analyzes the user's input information using AI to suggest optimal restaurants. For example, the system may suggest Japanese restaurants with a budget of under 3,000 yen and close to the station. Furthermore, the restaurant selection system personalizes the recommendations through dialogue with the user. For example, if the user adds a preference such as "I prefer a quiet atmosphere," the AI ​​updates the recommendations to reflect that preference. This allows the system to suggest restaurants that better meet the user's needs. The user can then make a reservation at the suggested restaurants. The restaurant selection system works in conjunction with a reservation system to make reservations for the user's desired date and time. For example, if a user inputs, "I'd like to make a reservation for tomorrow at 7 p.m.," the AI ​​will make the reservation for that time. Furthermore, the restaurant selection system also supports users when ordering at restaurants. When a user selects a menu, the AI ​​suggests recommended dishes. For example, it provides information such as, "This restaurant recommends sushi." Finally, the restaurant selection system also supports users when posting reviews about their restaurant experiences. The AI ​​analyzes users' reviews and extracts information useful to other users. For example, it extracts reviews such as, "The sushi at this restaurant was fresh and delicious" and provides this information to other users. In this way, the restaurant selection system efficiently supports users' restaurant selection, providing consistent support from reservations to orders to review extraction. This allows users to efficiently support their restaurant selection, providing consistent support from reservations to orders to review extraction. For example, it can reduce the time it takes to select a restaurant and allow them to make a more appropriate choice.Furthermore, by making suggestions based on the user's wishes, the level of satisfaction can be improved.

[0075] A restaurant selection system according to an embodiment includes an analysis unit, an update unit, a reservation unit, an order unit, and an extraction unit. The analysis unit analyzes a user's preferences. The user's preferences include, but are not limited to, the type of restaurant, budget, location, and time of day. The analysis unit analyzes the user's preferences using, for example, natural language processing technology. The analysis unit can also analyze the user's preferences using a machine learning algorithm. The analysis unit can also suggest optimal restaurants based on the user's preferences. For example, the analysis unit selects appropriate candidates from a restaurant database based on the user's preferences. The update unit updates the suggestions based on the information analyzed by the analysis unit. For example, the update unit updates the suggestions through a dialogue with the user. For example, the update unit uses a chatbot to communicate with the user and update the suggestions. The update unit can also use voice recognition technology to communicate with the user and update the suggestions. The update unit can also personalize the suggestions based on the user's preferences. For example, if the user expresses an additional preference such as "preferably a quiet atmosphere," the update unit updates the suggestions to reflect that preference. The reservation unit makes a reservation based on the proposal content updated by the update unit. The reservation unit, for example, cooperates with an online reservation system to make a reservation. The reservation unit can also cooperate with a telephone reservation system to make a reservation. The reservation unit can also make a reservation based on a user's desired date and time. For example, if a user inputs, "I would like to make a reservation for tomorrow at 7 p.m.", the reservation unit makes a reservation for that time. The order unit supports ordering at the restaurant reserved by the reservation unit. For example, the order unit suggests recommended menu items when the user selects a menu. For example, the order unit provides information such as, "This restaurant's recommendation is sushi." The order unit can also suggest recommended menu items based on the user's past ordering history. The order unit can also suggest recommended menu items based on the user's health condition and dietary restrictions. For example, if the user is on a diet, the order unit suggests a low-calorie menu item. The extraction unit extracts reviews based on the contents ordered by the order unit. For example, the extraction unit analyzes user reviews and extracts information useful to other users.For example, the extraction unit extracts reviews such as "The sushi at this restaurant was fresh and delicious" and provides them to other users. The extraction unit can also extract reviews using text analysis technology. The extraction unit can also estimate a user's emotions and extract reviews based on the emotions. For example, if a user is feeling stressed, the extraction unit extracts simple and intuitive reviews. This allows the restaurant selection system according to the embodiment to consistently support analysis, suggestions, reservations, orders, and review extraction based on the user's preferences.

[0076] The analysis unit can analyze the user's preferences and suggest appropriate restaurants. The analysis unit analyzes the user's preferences using, for example, natural language processing technology. For example, when the user inputs preferences such as "I want to eat Japanese food," "My budget is under 3,000 yen," and "A place close to the station," the analysis unit analyzes the information. The analysis unit can also analyze the user's preferences using a machine learning algorithm. For example, the analysis unit can learn the user's past selection history and perform analysis based on the user's preferences. The analysis unit can also suggest optimal restaurants based on the user's preferences. For example, the analysis unit selects appropriate candidates from a restaurant database based on the user's preferences. This makes it possible to suggest optimal restaurants based on the user's preferences. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's preferences into a generation AI, which then performs analysis.

[0077] The update unit can change the proposal content through a dialogue with the user. The update unit, for example, uses a chatbot to dialogue with the user and update the proposal content. For example, if the user expresses an additional preference such as "a quiet atmosphere is preferable," the update unit updates the proposal content to reflect that preference. The update unit can also use voice recognition technology to dialogue with the user and update the proposal content. For example, if the user expresses "I would like to make a reservation for tomorrow at 7 p.m.", the update unit updates the proposal content to reflect that preference. The update unit can also personalize the proposal content based on the user's preference. For example, if the user expresses "I would like to eat Japanese food," the update unit updates the proposal content to reflect that preference. In this way, the proposal content can be personalized through a dialogue with the user. Some or all of the above-described processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input the content of the dialogue with the user into a generation AI, which then updates the proposal content.

[0078] The reservation unit can make a reservation based on the user's desired date and time. The reservation unit, for example, works in conjunction with an online reservation system to make a reservation. For example, when a user inputs, "I want to make a reservation for tomorrow at 7 p.m.," the reservation unit makes a reservation for that time. The reservation unit can also make a reservation in conjunction with a telephone reservation system. For example, when a user inputs, "I want to make a reservation now," the reservation unit makes a reservation through the telephone reservation system. The reservation unit can also make a reservation based on the user's desired date and time. For example, when a user inputs, "I want to make a reservation for a weekend night," the reservation unit makes a reservation for that time. In this way, a reservation can be made based on the user's desired date and time. Some or all of the above-described processing in the reservation unit may be performed, for example, using AI, or may be performed without using AI. For example, the reservation unit can input the user's desired date and time into a generation AI, and the generation AI can make a reservation.

[0079] The ordering unit can suggest recommended menu items when the user selects a menu. For example, the ordering unit may provide information such as, "This restaurant's recommendation is sushi." The ordering unit can also suggest recommended menu items based on the user's past order history. For example, the ordering unit may analyze the user's preference trends based on data on menu items previously ordered by the user and suggest similar menu items. The ordering unit can also suggest recommended menu items based on the user's health status and dietary restrictions. For example, if the user is on a diet, the ordering unit may suggest low-calorie menu items. This allows the ordering unit to suggest recommended menu items when the user selects a menu. Some or all of the above-described processing in the ordering unit may be performed using, for example, AI, or may be performed without using AI. For example, the ordering unit may input the user's order information into a generation AI, which may then suggest recommended menu items.

[0080] The extraction unit can analyze user reviews and extract information that is useful to other users. For example, the extraction unit analyzes user reviews and extracts information that is useful to other users. For example, the extraction unit extracts reviews such as "The sushi at this restaurant was fresh and delicious" and provides the reviews to other users. The extraction unit can also extract reviews using text analysis technology. For example, the extraction unit analyzes user reviews using text analysis technology and extracts useful information. The extraction unit can also estimate user emotions and extract reviews based on the emotions. For example, if a user is feeling stressed, the extraction unit extracts simple and intuitive reviews. This makes it possible to analyze user reviews and extract useful information. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input user review data into a generation AI, which then extracts reviews.

[0081] The analysis unit can estimate the user's emotions and adjust the analysis method based on the estimated user emotions. For example, the analysis unit can estimate the user's emotions and adjust the analysis method based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit can provide a simple and intuitive analysis method to reduce the user's burden. Furthermore, if the user is relaxed, the analysis unit can provide a detailed analysis method to allow the user to obtain more information. Furthermore, if the user is in a hurry, the analysis unit can simplify the analysis method to provide results quickly. This allows the analysis method to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotion data into the generation AI, and the generation AI can adjust the analysis method.

[0082] The analysis unit can analyze the user's past restaurant selection history and select an appropriate analysis algorithm. For example, the analysis unit analyzes the user's past restaurant selection history and selects the optimal analysis algorithm. For example, the analysis unit analyzes preference trends based on data on restaurants the user has visited in the past. The analysis unit can also extract characteristics of restaurants that the user has previously rated highly and suggest restaurants with similar characteristics. The analysis unit can also analyze characteristics to be avoided based on data on restaurants the user has previously avoided and exclude them from suggestions. This allows the optimal analysis algorithm to be selected based on the past history. The analysis algorithm can be realized using techniques such as machine learning algorithms and statistical analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's past restaurant selection history into a generation AI, which then selects the analysis algorithm.

[0083] The analysis unit can adjust the analysis results based on the user's current living situation and health condition. The analysis unit customizes the analysis results based on the user's current living situation and health condition, for example. For example, if the user is on a diet, the analysis unit can prioritize restaurants offering low-calorie menus. Furthermore, if the user inputs the results of a health check, the analysis unit can suggest restaurants offering healthy menus based on the results. Furthermore, if the user has a specific allergy, the analysis unit can suggest restaurants offering menus that cater to the allergy. This allows the analysis results to be customized based on the user's living situation and health condition. Information about the user's living situation and health condition is obtained, for example, from the user's occupation, family environment, medical data, self-reporting, etc. Some or all of the above-described processing by the analysis unit may be performed using, or without, AI. For example, the analysis unit can input data about the user's living situation and health condition into a generation AI, which can then adjust the analysis results.

[0084] The analysis unit can evaluate the reliability of the information input by the user and prioritize processing of highly reliable information. The analysis unit, for example, evaluates the reliability of the information input by the user and prioritizes analysis of highly reliable information. For example, the analysis unit can evaluate the accuracy of information previously provided by the user and perform analysis based on the highly reliable information. The analysis unit can also check the consistency of the information provided by the user and perform analysis based on the consistent information. The analysis unit can also evaluate the source of the information provided by the user and perform analysis based on information from highly reliable sources. This allows highly reliable information to be analyzed preferentially. The reliability evaluation criteria and method are based on, for example, the source of the data, past performance, etc. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's input information to a generation AI, and the generation AI can evaluate reliability.

[0085] The analysis unit can estimate the user's emotions and determine the order of analysis results based on the estimated user emotions. The analysis unit, for example, estimates the user's emotions and determines the priority of the analysis results based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit can prioritize restaurants that offer relaxation. Furthermore, if the user is relaxed, the analysis unit can prioritize restaurants that offer adventurous dining. Furthermore, if the user is in a hurry, the analysis unit can prioritize restaurants that can provide quick service. This allows the priority of analysis results to be determined based on emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotion data into a generation AI, which can then determine the priority of the analysis results.

[0086] The analysis unit can prioritize processing region-specific restaurant information by taking into account the user's geographical location information. The analysis unit, for example, prioritizes analyzing region-specific restaurant information by taking into account the user's geographical location information. For example, the analysis unit prioritizes suggesting restaurants close to the user's current location. Furthermore, if the user is in a specific region, the analysis unit can prioritize suggesting restaurants that serve local specialties. Furthermore, if the user is traveling, the analysis unit can prioritize suggesting restaurants near tourist spots. This allows analysis to take geographical location information into consideration. The geographical location information is acquired and used based on, for example, GPS data, address information, etc. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's geographical location information into a generation AI, which then analyzes region-specific restaurant information.

[0087] The analysis unit can analyze the user's social media activity and process related restaurant information. The analysis unit, for example, analyzes the user's social media activity and analyzes the related restaurant information. For example, the analysis unit can suggest related restaurants based on the locations where the user has checked in on social media. The analysis unit can also analyze the content of the user's social media posts and suggest restaurants that the user may be interested in. The analysis unit can also suggest related restaurants based on information about restaurants visited by the user's friends. This enables analysis based on social media activity. The analysis method and criteria for social media activity are based on, for example, the content of posts, the number of likes, etc. Some or all of the above-mentioned processing by the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the user's social media activity data into a generation AI, which then analyzes the related restaurant information.

[0088] The analysis unit can adjust the analysis algorithm by reflecting the user's past feedback. The analysis unit, for example, customizes the analysis algorithm by reflecting the user's past feedback. For example, the analysis unit can analyze the characteristics of restaurants that the user has previously rated highly and suggest restaurants with similar characteristics. The analysis unit can also analyze the characteristics of restaurants that the user has previously rated poorly and exclude restaurants with similar characteristics from suggestions. The analysis unit can also adjust the analysis algorithm based on feedback provided by the user in the past to make more appropriate suggestions. This allows the analysis algorithm to be customized by reflecting past feedback. The content and acquisition method of the feedback are based on, for example, survey results, user comments, etc. Some or all of the above-mentioned processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past feedback data into a generation AI, which can adjust the analysis algorithm.

[0089] The update unit can estimate the user's emotions and change the update frequency of the suggested content based on the estimated user emotions. The update unit, for example, estimates the user's emotions and adjusts the update frequency of the suggested content based on the estimated user emotions. For example, if the user is feeling stressed, the update unit can reduce the update frequency of the suggested content to reduce the user's burden. Furthermore, if the user is relaxed, the update unit can increase the update frequency of the suggested content to provide more options. Furthermore, if the user is in a hurry, the update unit can quickly update the suggested content to provide appropriate options. This makes it possible to adjust the update frequency of the suggested content based on emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the update unit may be performed using an AI, for example, or without an AI. For example, the update unit can input user emotion data into the generation AI, and the generation AI can adjust the update frequency of the suggested content.

[0090] The update unit can analyze the user's dialogue history and select an appropriate update algorithm. The update unit, for example, analyzes the user's dialogue history and selects an optimal update algorithm. For example, the update unit selects an optimal update algorithm based on the content of dialogues the user has had in the past. The update unit can also adjust the update algorithm based on feedback the user has provided in the past. The update unit can also analyze the user's preferences and tendencies from the dialogue history and select an optimal update algorithm. This makes it possible to select an optimal update algorithm based on the dialogue history. The content and analysis method of the dialogue history are based on, for example, chat logs, voice data, etc. Some or all of the above-mentioned processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input the user's dialogue history data to a generation AI, which then selects an update algorithm.

[0091] The update unit can adjust the suggestion content based on the user's current interests and trends. The update unit, for example, customizes the suggestion content based on the user's current interests and trends. For example, the update unit customizes the suggestion content based on topics in which the user is currently interested. The update unit can also customize the suggestion content based on keywords recently searched by the user. The update unit can also customize the suggestion content based on information about accounts the user follows on social media. This allows the suggestion content to be customized based on interests and trends. The content and acquisition method of the interests and trends are based on, for example, the user's hobbies, recent search history, social media trends, news articles, etc. Some or all of the above-mentioned processing in the update unit may be performed using, or without, AI. For example, the update unit can input the user's interests and trend data into a generation AI, which can then adjust the suggestion content.

[0092] The update unit can analyze changes in the user's input information in real time and instantly change the content of the suggestions. For example, the update unit can analyze changes in the user's input information in real time and instantly update the content of the suggestions. For example, the update unit updates the content of the suggestions in real time when the user inputs new information. The update unit can also instantly update the content of the suggestions based on information provided by the user during dialogue. The update unit can also analyze changes in the information input by the user in real time and provide appropriate content of the suggestions. This allows the content of the suggestions to be instantly updated based on changes in the input information. The content of the changes in the input information and the method of acquiring the changes are determined based on, for example, real-time data updates, changes in user behavior, etc. Some or all of the above-mentioned processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input the user's input information to a generation AI, which can instantly update the content of the suggestions.

[0093] The update unit can estimate the user's emotions and change the display method of the suggested content based on the estimated user emotions. The update unit, for example, estimates the user's emotions and adjusts the display method of the suggested content based on the estimated user emotions. For example, if the user is feeling stressed, the update unit provides a simple, highly visible display method. If the user is relaxed, the update unit can provide a display method including detailed information. If the user is in a hurry, the update unit can provide a display method that focuses on the main points. This makes it possible to adjust the display method of the suggested content based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the update unit may be performed using an AI, or may be performed without using an AI. For example, the update unit can input the user's emotion data into the generation AI, and the generation AI can adjust the display method of the suggested content.

[0094] The update unit can prioritize changing the region-specific proposal content in consideration of the user's geographical location information. The update unit, for example, prioritizes updating the region-specific proposal content in consideration of the user's geographical location information. For example, the update unit prioritizes updating information about restaurants close to the user's current location. Furthermore, if the user is in a specific region, the update unit can prioritize updating information about restaurants that serve local specialties. Furthermore, if the user is traveling, the update unit can prioritize updating information about restaurants near tourist spots. This allows the proposal content to be updated in consideration of the geographical location information. The geographical location information is acquired and used based on, for example, GPS data, address information, etc. Some or all of the above-described processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input the user's geographical location information to a generation AI, which can then update the region-specific proposal content.

[0095] The update unit can analyze the user's social media activity and change the related suggestions. The update unit, for example, analyzes the user's social media activity and updates the related suggestions. For example, the update unit prioritizes updating information about places the user has checked in to on social media. The update unit can also analyze the user's social media posts and update the related suggestions. The update unit can also update the related suggestions based on information about restaurants visited by the user's friends. This makes it possible to update the suggestions based on social media activity. The analysis method and criteria for social media activity are based on, for example, the post content, the number of likes, etc. Some or all of the above-mentioned processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input the user's social media activity data into a generation AI, which then updates the related suggestions.

[0096] The update unit can adjust the content of suggestions by reflecting the user's past feedback. The update unit, for example, customizes the content of suggestions by reflecting the user's past feedback. For example, the update unit can analyze the characteristics of restaurants that the user has previously rated highly and suggest restaurants with similar characteristics. The update unit can also analyze the characteristics of restaurants that the user has previously rated poorly and exclude restaurants with similar characteristics from the suggestions. The update unit can also customize the content of suggestions based on feedback provided by the user in the past. This allows the content of suggestions to be customized by reflecting past feedback. The content of the feedback and the method of obtaining it are based on, for example, survey results, user comments, etc. Some or all of the above-mentioned processing in the update unit may be performed using, or without, AI. For example, the update unit can input the user's past feedback data into a generation AI, which can then adjust the content of suggestions.

[0097] The reservation unit can estimate a user's emotions and change the timing of a reservation based on the estimated user emotions. The reservation unit, for example, estimates a user's emotions and adjusts the timing of a reservation based on the estimated user emotions. For example, if a user is feeling stressed, the reservation unit can quickly make a reservation to reduce the user's burden. Furthermore, if a user is relaxed, the reservation unit can adjust the timing of a reservation to suit the user's wishes. Furthermore, if a user is in a hurry, the reservation unit can immediately make a reservation and respond quickly. This makes it possible to adjust the timing of a reservation based on emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the reservation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reservation unit can input user emotion data into the generation AI, and the generation AI can adjust the timing of the reservation.

[0098] The reservation unit can analyze the user's past reservation history and select an appropriate reservation method. The reservation unit, for example, analyzes the user's past reservation history and selects the optimal reservation method. For example, the reservation unit can suggest the optimal reservation method based on the reservation methods the user has used in the past. The reservation unit can also suggest a reservation method that avoids congestion based on the user's past reservation history. The reservation unit can also analyze the user's past reservation history and suggest the most efficient reservation method. This makes it possible to select the optimal reservation method based on the past reservation history. The content and analysis method of the reservation history are based on, for example, past reservation data, cancellation history, etc. Some or all of the above-mentioned processing in the reservation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reservation unit can input the user's past reservation history data into a generation AI, which can select a reservation method.

[0099] The reservation unit can adjust the reservation contents based on the user's current schedule and plans. The reservation unit customizes the reservation contents based on the user's current schedule and plans, for example. For example, the reservation unit refers to the user's calendar information and suggests the optimal reservation date and time. The reservation unit can also customize the reservation contents to match the user's schedule. The reservation unit can also suggest the optimal reservation method based on the user's plans. This allows the reservation contents to be customized based on the schedule and plans. The contents and acquisition method of the schedule and plans are based on, for example, a calendar app, the contents of a planner, etc. Some or all of the above-mentioned processing in the reservation unit may be performed using, or without, AI. For example, the reservation unit can input the user's schedule and plan data into a generation AI, which can then adjust the reservation contents.

[0100] The reservation unit can evaluate the reliability of information input by the user and prioritize reliable information. The reservation unit, for example, evaluates the reliability of information input by the user and makes a reservation based on the reliable information. For example, the reservation unit can evaluate the accuracy of information previously provided by the user and make a reservation based on the reliable information. The reservation unit can also check the consistency of information provided by the user and make a reservation based on the consistent information. The reservation unit can also evaluate the source of information provided by the user and make a reservation based on information from a reliable source. This allows a reservation to be made based on reliable information. The reliability evaluation criteria and method are based on, for example, the source of the data, past performance, etc. Some or all of the above-mentioned processing in the reservation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reservation unit can input the user's input information to a generation AI, and the generation AI can evaluate the reliability.

[0101] The reservation unit can estimate a user's emotions and determine the order of reservations based on the estimated user emotions. The reservation unit, for example, estimates a user's emotions and determines the priority of reservations based on the estimated user emotions. For example, if a user is feeling stressed, the reservation unit can quickly make reservations to reduce the user's burden. The reservation unit can also adjust the priority of reservations to suit the user's wishes if the user is relaxed. The reservation unit can also make reservations immediately and respond quickly if the user is in a hurry. This makes it possible to determine the priority of reservations based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the reservation unit may be performed using an AI, for example, or without an AI. For example, the reservation unit can input user emotion data into a generation AI, which can then determine the priority of reservations.

[0102] The reservation unit can prioritize processing region-specific reservation information by taking into account the user's geographical location information. The reservation unit, for example, prioritizes acquiring region-specific reservation information by taking into account the user's geographical location information. For example, the reservation unit prioritizes acquiring reservation information for restaurants close to the user's current location. Furthermore, if the user is in a specific region, the reservation unit can prioritize acquiring reservation information for restaurants that serve local specialties. Furthermore, if the user is traveling, the reservation unit can prioritize acquiring reservation information for restaurants near tourist spots. This makes it possible to acquire reservation information by taking into account the geographical location information. The acquisition and use of geographical location information is based on, for example, GPS data, address information, etc. Some or all of the above-described processing in the reservation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reservation unit can input the user's geographical location information into a generation AI, which can then acquire region-specific reservation information.

[0103] The reservation unit can analyze the user's social media activity and process related reservation information. The reservation unit, for example, analyzes the user's social media activity and acquires related reservation information. For example, the reservation unit prioritizes acquiring reservation information related to places where the user has checked in on social media. The reservation unit can also analyze the content of the user's social media posts and acquire related reservation information. The reservation unit can also acquire related reservation information based on reservation information for restaurants visited by the user's friends. This makes it possible to acquire reservation information based on social media activity. The analysis method and criteria for social media activity are based on, for example, the content of posts, the number of likes, etc. Some or all of the above-described processing in the reservation unit may be performed using, or without, AI. For example, the reservation unit can input the user's social media activity data into a generation AI, which then acquires related reservation information.

[0104] The reservation unit can adjust the reservation method by reflecting the user's past feedback. The reservation unit, for example, customizes the reservation method by reflecting the user's past feedback. For example, the reservation unit suggests a similar reservation method based on a reservation method that the user has previously rated highly. The reservation unit can also exclude a similar reservation method from suggestions based on a reservation method that the user has previously rated poorly. The reservation unit can also customize the reservation method based on feedback provided by the user in the past. This makes it possible to customize the reservation method by reflecting past feedback. The content and acquisition method of the feedback are based on, for example, survey results, user comments, etc. Some or all of the above-mentioned processing in the reservation unit may be performed using AI, for example, or may be performed without using AI. For example, the reservation unit can input the user's past feedback data into a generation AI, and the generation AI can adjust the reservation method.

[0105] The ordering unit can estimate the user's emotions and change the method of suggesting recommended menu items based on the estimated user emotions. The ordering unit, for example, estimates the user's emotions and adjusts the method of suggesting recommended menu items based on the estimated user emotions. For example, the ordering unit can suggest simple and intuitive menu items when the user is stressed. The ordering unit can also suggest detailed menu items when the user is relaxed. The ordering unit can also quickly suggest recommended menu items when the user is in a hurry. This makes it possible to adjust the method of suggesting recommended menu items based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the ordering unit may be performed using AI, or may be performed without AI. For example, the ordering unit can input the user's emotion data into the generation AI, and the generation AI can adjust the method of suggesting recommended menu items.

[0106] The ordering unit can analyze the user's past order history and select an appropriate menu suggestion algorithm. For example, the ordering unit analyzes the user's past order history and selects the optimal menu suggestion algorithm. For example, the ordering unit analyzes preference trends based on data on menus the user has previously ordered. The ordering unit can also extract characteristics of menus that the user has previously rated highly and suggest menus with similar characteristics. The ordering unit can also analyze characteristics to be avoided based on data on menus the user has previously avoided and exclude them from suggestions. This makes it possible to select the optimal menu suggestion algorithm based on the past order history. The content and analysis method of the order history are based on, for example, past order data, frequency, etc. Some or all of the above-mentioned processing in the ordering unit may be performed using, for example, AI, or may be performed without AI. For example, the ordering unit can input the user's past order history data into a generation AI, which then selects a menu suggestion algorithm.

[0107] The ordering unit can adjust the menu suggestions based on the user's current health condition and dietary restrictions. The ordering unit customizes the menu suggestions based on the user's current health condition and dietary restrictions, for example. For example, if the user is on a diet, the ordering unit can prioritize low-calorie menu suggestions. Furthermore, if the user inputs the results of a health check, the ordering unit can also suggest healthy menus based on those results. Furthermore, if the user has specific allergies, the ordering unit can also suggest menus that accommodate those allergies. This allows the menu suggestions to be customized based on the user's health condition and dietary restrictions. Information on the user's health condition and dietary restrictions is obtained, for example, from medical data, self-reporting, allergy information, doctor's instructions, etc. Some or all of the above-described processing in the ordering unit may be performed using, for example, AI, or may be performed without AI. For example, the ordering unit can input data on the user's health condition and dietary restrictions into a generation AI, which can then adjust the menu suggestions.

[0108] The order unit can evaluate the reliability of information input by the user and prioritize reliable information. The order unit, for example, evaluates the reliability of information input by the user and suggests a menu based on the reliable information. For example, the order unit can evaluate the accuracy of information previously provided by the user and suggest a menu based on the reliable information. The order unit can also check the consistency of information provided by the user and suggest a menu based on the consistent information. The order unit can also evaluate the source of information provided by the user and suggest a menu based on information from a reliable source. This makes it possible to suggest a menu based on reliable information. The reliability evaluation criteria and method are based on, for example, the source of the data, past performance, etc. Some or all of the above-mentioned processing in the order unit may be performed using, for example, AI, or may be performed without using AI. For example, the order unit can input the user's input information into a generation AI, which can evaluate the reliability.

[0109] The ordering unit can estimate the user's emotions and determine the order of menu suggestions based on the estimated user emotions. The ordering unit, for example, estimates the user's emotions and determines the priority of menu suggestions based on the estimated user emotions. For example, if the user is feeling stressed, the ordering unit can prioritize suggesting relaxing menu items. Also, if the user is relaxed, the ordering unit can prioritize suggesting adventurous menu items. Also, if the user is in a hurry, the ordering unit can prioritize suggesting menu items that can be served quickly. This allows the priority of menu suggestions to be determined based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the ordering unit may be performed using AI, for example, or without AI. For example, the ordering unit can input the user's emotion data into the generation AI, and the generation AI can determine the priority of menu suggestions.

[0110] The ordering unit can prioritize processing region-specific menu information by taking into account the user's geographical location information. The ordering unit, for example, prioritizes suggesting region-specific menu information by taking into account the user's geographical location information. For example, the ordering unit prioritizes suggesting menus from restaurants close to the user's current location. Furthermore, if the user is in a specific region, the ordering unit can prioritize suggesting menus offering local specialties. Furthermore, if the user is traveling, the ordering unit can prioritize suggesting menus from restaurants near tourist spots. This makes it possible to suggest menu information by taking into account the geographical location information. The method of acquiring and using the geographical location information is based on, for example, GPS data, address information, etc. Some or all of the above-described processing in the ordering unit may be performed using, for example, AI, or may be performed without using AI. For example, the ordering unit can input the user's geographical location information into a generation AI, which then suggests region-specific menu information.

[0111] The ordering unit can analyze the user's social media activity and process related menu information. For example, the ordering unit can analyze the user's social media activity and suggest related menu information. For example, the ordering unit can prioritize suggesting menus from places where the user has checked in on social media. The ordering unit can also analyze the user's social media posts and suggest related menus. The ordering unit can also suggest related menus based on menus from restaurants visited by the user's friends. This makes it possible to suggest menu information based on social media activity. The analysis method and criteria for social media activity are based on, for example, the content of posts, the number of likes, etc. Some or all of the above-mentioned processing in the ordering unit may be performed using, or without, AI. For example, the ordering unit can input the user's social media activity data into a generation AI, which then suggests related menu information.

[0112] The ordering unit can adjust the menu suggestion method by reflecting the user's past feedback. The ordering unit, for example, customizes the menu suggestion method by reflecting the user's past feedback. For example, the ordering unit can analyze the characteristics of menus that the user has previously rated highly and suggest menus with similar characteristics. The ordering unit can also analyze the characteristics of menus that the user has previously rated poorly and exclude menus with similar characteristics from suggestions. The ordering unit can also customize the menu suggestion method based on feedback provided by the user in the past. This allows the menu suggestion method to be customized by reflecting past feedback. The content and acquisition method of the feedback are based on, for example, survey results, user comments, etc. Some or all of the above-mentioned processing in the ordering unit may be performed using, or without, AI. For example, the ordering unit can input the user's past feedback data into a generation AI, which can then adjust the menu suggestion method.

[0113] The extraction unit can estimate a user's emotions and change the review extraction method based on the estimated user emotions. For example, the extraction unit can estimate a user's emotions and adjust the review extraction method based on the estimated user emotions. For example, the extraction unit can provide a simple and intuitive review extraction method when the user is stressed. The extraction unit can also provide a detailed review extraction method when the user is relaxed. The extraction unit can also simplify the extraction method to quickly extract reviews when the user is in a hurry. This allows the review extraction method to be adjusted based on emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the extraction unit can be performed using AI, or without AI. For example, the extraction unit can input user emotion data into the generation AI, which can then adjust the review extraction method.

[0114] The extraction unit can analyze a user's past review history and select an appropriate extraction algorithm. For example, the extraction unit analyzes a user's past review history and selects an optimal extraction algorithm. For example, the extraction unit analyzes preference trends based on data of reviews posted by the user in the past. The extraction unit can also extract characteristics of reviews that the user has previously given high ratings and preferentially extract reviews with similar characteristics. The extraction unit can also analyze characteristics to be avoided based on data of reviews that the user has previously avoided and exclude them from extraction. This allows the optimal extraction algorithm to be selected based on the past review history. The content and analysis method of the review history are based on, for example, past review data, ratings, etc. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without AI. For example, the extraction unit can input the user's past review history data into a generation AI, which then selects an extraction algorithm.

[0115] The extraction unit can adjust the review extraction based on the user's current interests and trends. The extraction unit, for example, customizes the review extraction based on the user's current interests and trends. For example, the extraction unit customizes the review extraction based on topics that the user is currently interested in. The extraction unit can also customize the review extraction based on keywords recently searched by the user. The extraction unit can also customize the review extraction based on information about accounts the user follows on social media. This allows the review extraction to be customized based on interests and trends. The content and acquisition method of the interests and trends are based on, for example, the user's hobbies, recent search history, social media trends, news articles, etc. Some or all of the above-described processing in the extraction unit may be performed using, or without, AI. For example, the extraction unit can input user interests and trend data into a generation AI, which can then adjust the review extraction.

[0116] The extraction unit can evaluate the reliability of information input by a user and prioritize reliable information. The extraction unit, for example, evaluates the reliability of information input by a user and extracts reviews based on reliable information. For example, the extraction unit can evaluate the accuracy of information previously provided by a user and extract reviews based on reliable information. The extraction unit can also check the consistency of information provided by a user and extract reviews based on consistent information. The extraction unit can also evaluate the source of information provided by a user and extract reviews based on information from reliable sources. This makes it possible to extract reviews based on reliable information. The reliability evaluation criteria and method are based on, for example, the source of data, past performance, etc. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input user input information to a generation AI, which then evaluates reliability.

[0117] The extraction unit can estimate a user's emotions and change the display method of reviews based on the estimated user emotions. The extraction unit, for example, estimates a user's emotions and adjusts the display method of reviews based on the estimated user emotions. For example, if the user is feeling stressed, the extraction unit provides a simple, highly visible display method. If the user is relaxed, the extraction unit can provide a display method including detailed information. If the user is in a hurry, the extraction unit can provide a display method that focuses on the main points. This allows the display method of reviews to be adjusted based on emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the extraction unit may be performed using AI, or may be performed without AI. For example, the extraction unit can input user emotion data into the generation AI, which can then adjust the display method of reviews.

[0118] The extraction unit can prioritize processing region-specific word-of-mouth information by taking into account the user's geographical location information. The extraction unit, for example, prioritizes extracting region-specific word-of-mouth information by taking into account the user's geographical location information. For example, the extraction unit prioritizes extracting reviews of restaurants close to the user's current location. Furthermore, if the user is in a specific region, the extraction unit can prioritize extracting reviews of restaurants that offer local specialties. Furthermore, if the user is traveling, the extraction unit can prioritize extracting reviews of restaurants near tourist spots. This allows word-of-mouth information to be extracted by taking into account the geographical location information. The geographical location information can be acquired and used based on, for example, GPS data, address information, etc. Some or all of the above-described processing by the extraction unit may be performed using, for example, AI, or may be performed without AI. For example, the extraction unit can input the user's geographical location information into a generation AI, which then extracts region-specific word-of-mouth information.

[0119] The extraction unit can analyze the user's social media activity and process related word-of-mouth information. The extraction unit, for example, analyzes the user's social media activity and extracts related word-of-mouth information. For example, the extraction unit prioritizes extracting reviews of places where the user has checked in on social media. The extraction unit can also analyze the content of the user's social media posts and extract related reviews. The extraction unit can also extract related reviews based on reviews of restaurants visited by the user's friends. This makes it possible to extract word-of-mouth information based on social media activity. The analysis method and criteria for social media activity are based on, for example, the content of posts, the number of likes, etc. Some or all of the above-mentioned processing by the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the user's social media activity data into a generation AI, which then extracts related word-of-mouth information.

[0120] The extraction unit can adjust the review extraction method by reflecting the user's past feedback. The extraction unit, for example, customizes the review extraction method by reflecting the user's past feedback. For example, the extraction unit analyzes the characteristics of reviews that the user has previously given a high rating and prioritizes extracting reviews with similar characteristics. The extraction unit can also analyze the characteristics of reviews that the user has previously given a low rating and exclude reviews with similar characteristics from extraction. The extraction unit can also customize the review extraction method based on feedback provided by the user in the past. This allows the review extraction method to be customized by reflecting past feedback. The content of the feedback and the method of obtaining it are based on, for example, survey results, user comments, etc. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without AI. For example, the extraction unit can input the user's past feedback data into a generation AI, and the generation AI can adjust the review extraction method. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned analysis unit, update unit, reservation unit, order unit, and extraction unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the smart device 14 and analyzes the user's preferences. The update unit is realized by the specific processing unit 290 of the data processing device 12 and updates the recommendations. The reservation unit is realized by the control unit 46A of the smart device 14 and makes reservations. The order unit is realized by the specific processing unit 290 of the data processing device 12 and supports orders. The extraction unit is realized by the control unit 46A of the smart device 14 and extracts word-of-mouth reviews. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned analysis unit, update unit, reservation unit, order unit, and extraction unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the smart glasses 214 and analyzes the user's preferences. The update unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and updates the proposal content. The reservation unit is realized, for example, by the control unit 46A of the smart glasses 214 and makes reservations. The order unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and supports orders. The extraction unit is realized, for example, by the control unit 46A of the smart glasses 214 and extracts word-of-mouth reviews. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, update unit, reservation unit, ordering unit, and extraction unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the headset type terminal 314 and analyzes the user's preferences. The update unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and updates the proposal content. The reservation unit is realized, for example, by the control unit 46A of the headset type terminal 314 and makes reservations. The ordering unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and supports orders. The extraction unit is realized, for example, by the control unit 46A of the headset type terminal 314 and extracts word-of-mouth reviews. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, update unit, reservation unit, order unit, and extraction unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the robot 414 and analyzes the user's preferences. The update unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and updates the content of the recommendations. The reservation unit is realized, for example, by the control unit 46A of the robot 414 and makes reservations. The order unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and supports orders. The extraction unit is realized, for example, by the control unit 46A of the robot 414 and extracts word-of-mouth reviews.

[0121] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0122] The analysis unit can also take into account the user's past search history and browsing history when analyzing the user's preferences. For example, the analysis unit analyzes the user's preferences and tendencies based on keywords the user has searched for in the past and the content of pages the user has viewed. The analysis unit can also suggest restaurants with similar characteristics based on information about restaurants the user has viewed in the past. Furthermore, the analysis unit can analyze the frequency and timing of keywords the user has searched for in the past to estimate the user's current interests. This allows for more accurate suggestions to be made based on the user's past behavioral history.

[0123] The analysis unit may also take into account the user's social media activity when analyzing the user's preferences. For example, the analysis unit may analyze the content of posts that the user has "liked" or commented on on social media to estimate the user's preferences and interests. The analysis unit may also suggest restaurants that the user may be interested in based on information about accounts the user follows. Furthermore, the analysis unit may analyze the user's check-in history on social media and suggest restaurants with similar characteristics based on information about places and restaurants the user has visited in the past. This allows for more personalized suggestions to be made based on the user's social media activity.

[0124] When changing the content of the suggestions through dialogue with the user, the update unit may estimate the user's emotions and adjust the tone and content of the dialogue based on the estimated emotions. For example, if the user is feeling stressed, the update unit may provide a dialogue that helps the user relax, thereby reducing the user's burden. If the user is relaxed, the update unit may provide detailed information to allow the user to consider more options. Furthermore, if the user is in a hurry, the update unit may quickly update the content of the suggestions to allow the user to make a quick selection. This allows the tone and content of the dialogue to be adjusted based on the user's emotions, making it possible to provide more appropriate suggestions.

[0125] The reservation unit can also take into account the user's past reservation history when making a reservation based on the user's desired date and time. For example, the reservation unit can analyze the date and frequency of the user's past reservations to estimate the user's reservation patterns. The reservation unit can also suggest restaurants with similar characteristics based on information about restaurants the user has previously reserved. Furthermore, the reservation unit can analyze the history of reservations the user has canceled in the past and make suggestions to reduce the risk of cancellation. This allows more appropriate reservation suggestions to be made based on the user's past reservation history.

[0126] The ordering unit can also take into consideration the user's current health condition and dietary restrictions when suggesting recommended menus when the user is selecting a menu. For example, if the user is on a diet, the ordering unit can preferentially suggest low-calorie menus. Also, if the user has a specific allergy, the ordering unit can suggest menus that accommodate that allergy. Furthermore, if the user inputs the results of a health check, the ordering unit can suggest healthy menus based on the results. This allows for more appropriate menu suggestions to be made based on the user's health condition and dietary restrictions.

[0127] When analyzing a user's reviews, the extraction unit can estimate the user's emotions and adjust the display method of the reviews based on the estimated emotions. For example, if the user is feeling stressed, the extraction unit can provide a simple, highly visible display method. If the user is relaxed, the extraction unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the extraction unit can also provide a display method that focuses on the main points. This allows the display method of the reviews to be adjusted based on the user's emotions, making it possible to provide more appropriate information.

[0128] The analysis unit can also take into account the user's current living situation and health condition when analyzing the user's preferences. For example, if the user is on a diet, the analysis unit can preferentially suggest restaurants that offer low-calorie menus. Also, if the user inputs the results of a health check, the analysis unit can suggest restaurants that offer healthy menus based on those results. Furthermore, if the user has a specific allergy, the analysis unit can suggest restaurants that offer menus that cater to that allergy. This allows for more appropriate restaurant suggestions to be made based on the user's living situation and health condition.

[0129] The update unit may also take into account the user's current interests and trends when changing the suggestions through interaction with the user. For example, the update unit may customize the suggestions based on topics that the user is currently interested in. The update unit may also customize the suggestions based on keywords that the user has recently searched for. Furthermore, the update unit may customize the suggestions based on information about accounts that the user follows on social media. This allows for more appropriate suggestions based on the user's current interests and trends.

[0130] When making a reservation based on the user's desired date and time, the reservation unit can also estimate the user's emotions and adjust the timing of the reservation based on the estimated emotions. For example, if the user is feeling stressed, the reservation unit can make a reservation quickly to reduce the user's burden. Also, if the user is relaxed, the reservation unit can adjust the timing of the reservation to suit the user's wishes. Furthermore, if the user is in a hurry, the reservation unit can make a reservation immediately and respond quickly. This allows the timing of the reservation to be adjusted based on the user's emotions, making more appropriate reservation suggestions.

[0131] When the ordering unit suggests a recommended menu when the user selects a menu, the ordering unit can estimate the user's emotions and adjust the suggestion method based on the estimated emotions. For example, if the user is feeling stressed, the ordering unit can suggest a simple and intuitive menu. If the user is relaxed, the ordering unit can also suggest a detailed menu. Furthermore, if the user is in a hurry, the ordering unit can quickly suggest a recommended menu. This allows the menu suggestion method to be adjusted based on the user's emotions, making more appropriate suggestions.

[0132] The processing flow of the second embodiment will be briefly explained below.

[0133] Step 1: The analysis unit analyzes the user's preferences, which include the type of restaurant, budget, location, time of day, etc. The analysis unit uses natural language processing technology and machine learning algorithms to analyze the user's preferences and selects appropriate candidates from a restaurant database to suggest the most suitable restaurant. Step 2: The update unit updates the suggestions based on the information analyzed by the analysis unit. The update unit updates the suggestions through dialogue with the user, using chatbots and voice recognition technology to communicate with the user, and personalizes the suggestions based on the user's preferences. Step 3: The reservation unit makes a reservation based on the proposal updated by the update unit. The reservation unit makes a reservation in cooperation with the online reservation system and the telephone reservation system, and makes a reservation based on the user's desired date and time. Step 4: The ordering unit supports ordering at the restaurant reserved by the reservation unit. The ordering unit suggests menu recommendations when the user selects a menu, and suggests menu recommendations based on the user's past ordering history, health condition, and dietary restrictions. Step 5: The extraction unit extracts reviews based on the order details. The extraction unit analyzes the user reviews and uses text analysis and sentiment estimation techniques to extract information that is useful to other users.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0138] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0139] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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 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.

[0152] 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.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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 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.

[0168] 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.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0171] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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).

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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 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.

[0185] 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.

[0186] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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).

[0191] 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 area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0192] 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."

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] [Explanation of symbols]

[0206] 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. an analysis unit that analyzes a user's wishes; an update unit that updates the proposal content based on the information analyzed by the analysis unit; a reservation unit that makes a reservation based on the proposal content updated by the update unit; an ordering unit that supports ordering at the restaurant reserved by the reservation unit; An extraction unit that extracts word-of-mouth reviews based on the contents of the order made by the ordering unit.

2. The analysis unit Analyzes user preferences and suggests appropriate restaurants 2. The system of claim 1.

3. The update unit Modifying suggestions through user interaction 2. The system of claim 1.

4. The reservation unit Make a reservation based on the user's desired date and time 2. The system of claim 1.

5. The ordering unit Suggest menu items when users choose a menu 2. The system of claim 1.

6. The extraction unit Analyze user reviews and extract information that will be useful to other users 2. The system of claim 1.

7. The analysis unit Estimate the user's emotions and adjust the analysis method based on the estimated user emotions.

2. The system of claim 1.

8. The analysis unit Analyze the user's past restaurant selection history and select the appropriate analysis algorithm 2. The system of claim 1.

Images