System

Abstract

An object of a system according to an embodiment is to provide review information suitable for individual preference of a user.SOLUTION: A system according to an embodiment includes an evaluation accumulation unit, an interaction inquiry unit, a reviewer narrowing-down unit, and a scoring unit. The evaluation accumulation unit accumulates past evaluations and review contents of the user. The interactive question unit grasps the preference of the user in detail based on the information accumulated by the evaluation accumulation unit. A reviewer narrowing-down part narrows down reviewer candidates similar to the tendency of the preference of the user grasped by the interaction inquiry part. The scoring unit scores and displays the evaluation data narrowed down by the reviewer narrowing-down unit on the basis of whether the evaluation data is suitable for the user's preference.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 techniques have not adequately provided review information suited to individual user preferences, and there is room for improvement.

[0005] The system according to the embodiment aims to provide review information that is suited to the individual preferences of the user. [Means for solving the problem]

[0006] The system according to the embodiment includes a rating accumulation unit, a dialogue question unit, a reviewer narrowing down unit, and a scoring unit. The rating accumulation unit accumulates users' past ratings and review contents. The dialogue question unit grasps the user's preferences in detail based on the information accumulated by the rating accumulation unit. The reviewer narrowing down unit narrows down reviewer candidates who have similar preferences to the user grasped by the dialogue question unit. The scoring unit scores and displays the rating data narrowed down by the reviewer narrowing down unit based on whether it is suitable for the user's preferences. [Effects of the Invention]

[0007] The system according to the embodiment can provide review information that is suited to the individual preferences of the user. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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) The AI ​​system according to the embodiment of the present invention is a system for finding "restaurants that I find really good," which is what the user really wants to know. This system scores and displays restaurants that match the user's individual preferences. This allows the AI ​​system to find restaurants that match the user's individual preferences.

[0029] The AI ​​system according to the embodiment includes a rating accumulation unit, a dialogue question unit, a reviewer selection unit, and a scoring unit. The rating accumulation unit accumulates users' past ratings and review content. For example, if a user rates a ramen shop as "the soup was rich and delicious," that information is accumulated. The rating accumulation unit also stores information about the shops and products rated by the user, the rating content, and the review text in a database. The dialogue question unit understands the user's preferences in detail based on the information accumulated by the rating accumulation unit. For example, the generation AI asks the user questions such as "What kind of food do you like?" or "What kind of atmosphere do you like in a restaurant?" and analyzes the user's preferences based on the answers. The generation AI analyzes the user's preferences using a text generation AI (e.g., LLM). The generation AI can also understand the user's preferences in detail using a multimodal generation AI. The reviewer selection unit narrows down reviewer candidates who share similar preferences to the user identified by the dialogue question unit. For example, if a user answers "I like spicy food," the system narrows down the results to reviewers who rate spicy food highly. The reviewer narrowing down unit also considers the similarity of the restaurants and products recommended by the reviewers, the content of their reviews, and, conversely, information about reviews that the reviewers have judged to be unacceptable. The scoring unit scores and displays the evaluation data narrowed down by the reviewer narrowing down unit based on whether the data matches the user's preferences. For example, if a user answers "I like Japanese food," the system prioritizes displaying reviews by reviewers who rate Japanese food highly. The scoring unit also displays restaurant information that matches the user's preferences, as well as phrases and photos of reviews that the user can "truly empathize with." This allows the AI ​​system according to the embodiment to find restaurants that match the user's individual preferences. For example, if a user answers "I like Italian food," the system can find recommended Italian restaurants based on reviews by reviewers who rate Italian food highly. If a user answers "I like restaurants with a quiet atmosphere," the system can find recommended restaurants based on reviews by reviewers who rate restaurants with that kind of atmosphere highly.

[0030] The rating accumulation unit can automatically extract a user's dietary preferences and allergy information based on the user's ratings and review content, and accommodate individual dietary restrictions. The rating accumulation unit, for example, analyzes the content of reviews previously rated by the user and automatically extracts preferences and allergy information for specific ingredients or dishes. For example, it detects reviews in which the user states, "I have a nut allergy," and stores this in a database. The rating accumulation unit also analyzes the user's ratings to identify dietary preferences and allergy information. For example, if a user rates a product as "I like spicy food," the rating accumulation unit extracts dietary preferences based on that information. This makes it possible to provide information that accommodates the user's dietary restrictions.

[0031] The rating accumulation unit can analyze the user's rating history over time and identify seasonal changes and trends in preferences. The rating accumulation unit, for example, analyzes the user's rating history over time and identifies seasonal changes in preferences. For example, it analyzes whether there is a tendency to prefer cold dishes in the summer. The rating accumulation unit also identifies trends based on the user's rating history. For example, it identifies dishes and ingredients that are popular in a particular season. This makes it possible to identify seasonal changes and trends in preferences.

[0032] The dialogue question unit allows the generation AI to learn the user's preferences in real time based on the user's answers and reflect them in the next dialogue question. The dialogue question unit, for example, builds a system in which the generation AI learns the user's preferences in real time based on the user's answers and reflects them in the next dialogue question. For example, if the user answers "I like spicy food," a question about spicy food will be added to the next question. In addition, the dialogue question unit allows the generation AI to analyze the content of the user's answers and learn preference trends. For example, if the user answers "I like Japanese food," a question about Japanese food will be added to the next question. This allows the user's preferences to be learned in real time and reflected in the next dialogue question.

[0033] The dialogue question unit can analyze the content of the user's answers and classify and save the details of preferences by category. The dialogue question unit, for example, builds a system that analyzes the content of the user's answers and classifies and saves the details of preferences by category. For example, the categories are classified into types of cuisine, atmosphere, price range, etc. The dialogue question unit also identifies the details of preferences based on the content of the user's answers and saves them by category. For example, if the user answers "I like Italian food," information about Italian food is saved by category. This allows the details of the user's preferences to be saved by category.

[0034] The dialogue question unit can introduce dialogue questions using images and audio to understand the user's preferences in detail. The dialogue question unit, for example, builds a system that introduces dialogue questions using images and audio to understand the user's preferences in detail. For example, it shows an image of a dish and asks, "Do you like this dish?" The dialogue question unit also uses audio to understand the user's preferences in detail. For example, it asks the user by audio, "What kind of food do you like?" and analyzes the preferences based on the answer. In this way, by introducing dialogue questions using images and audio, the user's preferences can be understood in detail.

[0035] The dialogue question unit can generate questions that refer to the response data of other users in order to understand the user's preferences. The dialogue question unit, for example, builds a system that generates questions that refer to the response data of other users in order to understand the user's preferences. For example, questions are generated based on responses from users who have the same preferences. The dialogue question unit also analyzes the response data of other users to generate questions that match the user's preferences. For example, if a user answers "I like spicy food," a question about spicy food is generated based on the response data of other users. In this way, the user's preferences can be understood by generating questions that refer to the response data of other users.

[0036] The reviewer narrowing down unit can analyze the reviewer's rating history and identify the reviewer's rating pattern that matches the user's preferences. The reviewer narrowing down unit, for example, builds a system that analyzes the reviewer's rating history and identifies the reviewer's rating pattern that matches the user's preferences. For example, it analyzes whether the reviewer also highly rates a dish that the user highly rates. The reviewer narrowing down unit also identifies the rating pattern based on the reviewer's rating history. For example, it analyzes the criteria used by the reviewer when rating and determines whether the criteria match the user's preferences. This makes it possible to identify the reviewer's rating pattern that matches the user's preferences.

[0037] The reviewer narrowing down unit can analyze the details of the reviewer's evaluation and extract the reviewer's evaluation criteria that match the user's preferences. The reviewer narrowing down unit, for example, builds a system that analyzes the details of the reviewer's evaluation and extracts the reviewer's evaluation criteria that match the user's preferences. For example, it analyzes the criteria used by the reviewer when rating and determines whether they match the user's preferences. The reviewer narrowing down unit also identifies the evaluation criteria based on the reviewer's evaluation. For example, it analyzes the characteristics of the dishes and restaurants that the reviewer highly rates and determines whether they match the user's preferences. This makes it possible to extract the reviewer's evaluation criteria that match the user's preferences.

[0038] The reviewer narrowing unit can integrate the reviewer's evaluation data with other data sets (e.g., social media posts) to create a more detailed reviewer profile. The reviewer narrowing unit, for example, builds a system that integrates the reviewer's evaluation data with social media posts to create a more detailed reviewer profile. For example, it analyzes the content of the reviewer's posts to understand the reviewer's preferences and evaluation criteria in detail. The reviewer narrowing unit also creates a reviewer profile based on other data sets. For example, it analyzes the content of the reviewer's social media posts to identify the reviewer's preferences and evaluation criteria. This allows a more detailed reviewer profile to be created.

[0039] The reviewer narrowing down unit can recommend new reviewers who match the user's preferences based on the reviewer's evaluation content. The reviewer narrowing down unit, for example, builds a system that recommends new reviewers who match the user's preferences based on the reviewer's evaluation content. For example, the unit recommends new reviewers based on whether reviewers also highly rate dishes that the user has highly rated. The reviewer narrowing down unit also analyzes the reviewer's evaluation content to identify new reviewers. For example, it analyzes the reviewer's evaluation criteria and determines whether they match the user's preferences. This makes it possible to recommend new reviewers who match the user's preferences.

[0040] The scoring unit can score the evaluation data in real time based on the user's preferences and provide the latest information. The scoring unit, for example, builds a system that scores the evaluation data in real time based on the user's preferences and provides the latest information. For example, if the user answers "I like Japanese food," the scoring unit prioritizes scoring the evaluation data for Japanese food. The scoring unit also scores the evaluation data that matches the user's preferences in real time. For example, if the user answers "I like Italian food," the scoring unit prioritizes scoring the evaluation data for Italian food. This allows the evaluation data to be scored in real time based on the user's preferences and provide the latest information.

[0041] The scoring unit can weight and reflect the user's past evaluation history when scoring the evaluation data. The scoring unit, for example, builds a system that weights and reflects the user's past evaluation history when scoring the evaluation data. For example, the scoring unit weights and scores evaluation data of restaurants that the user has rated highly in the past. The scoring unit also performs scoring based on the user's evaluation history. For example, if the user answers "I like Japanese food," the scoring unit weights and scores the evaluation data of Japanese food. In this way, by weighting and reflecting the user's past evaluation history, more accurate scoring is possible.

[0042] The scoring unit can visualize the evaluation data and display it in a graph or chart so that the user can intuitively understand it. The scoring unit, for example, builds a system that visualizes the evaluation data and displays it in a graph or chart so that the user can intuitively understand it. For example, the evaluation score is displayed in a bar graph or pie chart. The scoring unit also visually displays the evaluation data. For example, if the user answers "I like Japanese food," the evaluation data for Japanese food is displayed in a graph or chart. This makes it possible to visualize the evaluation data and display it so that the user can intuitively understand it.

[0043] The scoring unit can share the evaluation data with other users and display the evaluations with the highest degree of empathy in a ranking format. The scoring unit, for example, builds a system that shares the evaluation data with other users and displays the evaluations with the highest degree of empathy in a ranking format. For example, evaluations with a higher number of positive emotional responses are displayed at the top. The scoring unit also displays the evaluation data in a ranking format. For example, if a user answers "I like Japanese food," the evaluation data for Japanese food is displayed in a ranking format. In this way, the evaluations with the highest degree of empathy can be displayed in a ranking format and shared with other users.

[0044] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0045] The AI ​​system can also recommend restaurants that take into account the user's health condition. For example, if the user inputs the results of a health check, the system can use that information to recommend restaurants that offer healthy menus. Also, if the user wants to consume a specific nutrient, the system can prioritize restaurants that offer dishes that contain a lot of that nutrient. Furthermore, if the user is on a diet, it can recommend restaurants that offer low-calorie menus.

[0046] The AI ​​system can recommend restaurants at a travel destination based on the user's past travel history. For example, by inputting information about cities or countries the user has visited in the past, the system can display highly rated restaurants in that area. Also, if the user plans to visit a specific tourist spot, the system can recommend restaurants in the surrounding area. Furthermore, it can recommend restaurants with a similar atmosphere or cuisine based on the reviews of restaurants the user has visited in the past.

[0047] The AI ​​system can recommend restaurants that take into account the preferences of the user's friends and family. For example, if the user inputs the preferences of their friends and family, the system can recommend restaurants that will satisfy everyone based on that information. Also, if the user is planning a specific event (such as a birthday or anniversary), the system can recommend restaurants that are suitable for that event. Furthermore, it can display recommended restaurants based on the food and atmosphere that the user wants to share with their friends and family.

[0048] AI systems can recommend new products and services that a user might be interested in based on their past purchase history. For example, they can recommend similar products and services based on information about products and services a user has purchased in the past. Also, if a user frequently purchases products in a particular category, they can prioritize the display of new products in that category. Furthermore, they can provide new recommendations based on products and services that a user has rated highly in the past.

[0049] AI systems can recommend services to support daily life based on a user's lifestyle. For example, if a user has a busy lifestyle, they can recommend time-saving services. If a user is health-conscious, they can also provide health-conscious services. Furthermore, if a user has specific hobbies or interests, they can recommend services related to those hobbies or interests.

[0050] The processing flow of the first embodiment will be briefly explained below.

[0051] Step 1: The rating accumulation unit accumulates the user's past ratings and review content. For example, if a user rates a ramen shop as "the soup was rich and delicious," that information is accumulated. The rating accumulation unit also saves information about the shops and products rated by the user, the rating content, and the review text in a database. Step 2: The dialogue questioning unit obtains a detailed understanding of the user's preferences based on the information accumulated by the evaluation accumulation unit. For example, the generation AI asks the user questions such as "What kind of food do you like?" or "What kind of restaurant atmosphere do you like?" and analyzes the user's preferences based on the answers. The generation AI analyzes the user's preferences using a text generation AI (e.g., LLM). The generation AI can also obtain a detailed understanding of the user's preferences using a multimodal generation AI. Step 3: The reviewer selection unit narrows down the reviewer candidates to those with similar tastes to the user identified by the dialogue question unit. For example, if the user answers "I like spicy food," the unit narrows down the candidates to reviewers who rate spicy food highly. The reviewer selection unit also considers the similarity of the stores and products recommended by the reviewers, the content of their reviews, and, conversely, information that the reviewers have judged to be unacceptable. Step 4: The scoring unit scores the evaluation data narrowed down by the reviewer narrowing unit based on whether it matches the user's preferences and displays it. For example, if the user answers "I like Japanese food," reviews by reviewers who rate Japanese food highly will be displayed preferentially. The scoring unit also displays restaurant information that matches the user's preferences, as well as text and photos of "reviews that the user can truly relate to."

[0052] (Example 2) The AI ​​system according to the embodiment of the present invention is a system for finding "restaurants that I find really good," which is what the user really wants to know. This system scores and displays restaurants that match the user's individual preferences. This allows the AI ​​system to find restaurants that match the user's individual preferences.

[0053] The AI ​​system according to the embodiment includes a rating accumulation unit, a dialogue question unit, a reviewer selection unit, and a scoring unit. The rating accumulation unit accumulates users' past ratings and review content. For example, if a user rates a ramen shop as "the soup was rich and delicious," that information is accumulated. The rating accumulation unit also stores information about the shops and products rated by the user, the rating content, and the review text in a database. The dialogue question unit understands the user's preferences in detail based on the information accumulated by the rating accumulation unit. For example, the generation AI asks the user questions such as "What kind of food do you like?" or "What kind of atmosphere do you like in a restaurant?" and analyzes the user's preferences based on the answers. The generation AI analyzes the user's preferences using a text generation AI (e.g., LLM). The generation AI can also understand the user's preferences in detail using a multimodal generation AI. The reviewer selection unit narrows down reviewer candidates who share similar preferences to the user identified by the dialogue question unit. For example, if a user answers "I like spicy food," the system narrows down the results to reviewers who rate spicy food highly. The reviewer narrowing down unit also considers the similarity of the restaurants and products recommended by the reviewers, the content of their reviews, and, conversely, information about reviews that the reviewers have judged to be unacceptable. The scoring unit scores and displays the evaluation data narrowed down by the reviewer narrowing down unit based on whether the data matches the user's preferences. For example, if a user answers "I like Japanese food," the system prioritizes displaying reviews by reviewers who rate Japanese food highly. The scoring unit also displays restaurant information that matches the user's preferences, as well as phrases and photos of reviews that the user can "truly empathize with." This allows the AI ​​system according to the embodiment to find restaurants that match the user's individual preferences. For example, if a user answers "I like Italian food," the system can find recommended Italian restaurants based on reviews by reviewers who rate Italian food highly. If a user answers "I like restaurants with a quiet atmosphere," the system can find recommended restaurants based on reviews by reviewers who rate restaurants with that kind of atmosphere highly.

[0054] The rating accumulation unit can automatically extract a user's dietary preferences and allergy information based on the user's ratings and review content, and accommodate individual dietary restrictions. The rating accumulation unit, for example, analyzes the content of reviews previously rated by the user and automatically extracts preferences and allergy information for specific ingredients or dishes. For example, it detects reviews in which the user states, "I have a nut allergy," and stores this in a database. The rating accumulation unit also analyzes the user's ratings to identify dietary preferences and allergy information. For example, if a user rates a product as "I like spicy food," the rating accumulation unit extracts dietary preferences based on that information. This makes it possible to provide information that accommodates the user's dietary restrictions.

[0055] The rating accumulation unit can analyze the user's rating history over time and identify seasonal changes and trends in preferences. The rating accumulation unit, for example, analyzes the user's rating history over time and identifies seasonal changes in preferences. For example, it analyzes whether there is a tendency to prefer cold dishes in the summer. The rating accumulation unit also identifies trends based on the user's rating history. For example, it identifies dishes and ingredients that are popular in a particular season. This makes it possible to identify seasonal changes and trends in preferences.

[0056] The rating accumulation unit can use the emotion estimation function to analyze the intensity of emotion from the content of a user's review, and prioritize accumulation of ratings with particularly strong emotions. The rating accumulation unit, for example, uses the emotion estimation function to analyze the intensity of emotion from the content of a user's review, and prioritize accumulation of ratings with particularly strong emotions. For example, a review such as "This food was amazing!" is saved as a high emotion score. The rating accumulation unit also classifies the review content based on the intensity of emotion, and prioritizes saving ratings with particularly strong emotions. For example, reviews with strong positive emotions are saved preferentially. This allows ratings with particularly strong emotions to be saved preferentially.

[0057] The dialogue question unit allows the generation AI to learn the user's preferences in real time based on the user's answers and reflect them in the next dialogue question. The dialogue question unit, for example, builds a system in which the generation AI learns the user's preferences in real time based on the user's answers and reflects them in the next dialogue question. For example, if the user answers "I like spicy food," a question about spicy food will be added to the next question. In addition, the dialogue question unit allows the generation AI to analyze the content of the user's answers and learn preference trends. For example, if the user answers "I like Japanese food," a question about Japanese food will be added to the next question. This allows the user's preferences to be learned in real time and reflected in the next dialogue question.

[0058] The dialogue question unit can analyze the content of the user's answers and classify and save the details of preferences by category. The dialogue question unit, for example, builds a system that analyzes the content of the user's answers and classifies and saves the details of preferences by category. For example, the categories are classified into types of cuisine, atmosphere, price range, etc. The dialogue question unit also identifies the details of preferences based on the content of the user's answers and saves them by category. For example, if the user answers "I like Italian food," information about Italian food is saved by category. This allows the details of the user's preferences to be saved by category.

[0059] The dialogue question unit can use the emotion estimation function to analyze the emotion of the user when answering a question and generate questions that elicit positive emotions. The dialogue question unit, for example, uses the emotion estimation function to analyze the emotion of the user when answering a question and builds a system that generates questions that elicit positive emotions. For example, if the user answers "I like this dish," a positive question about that dish will be added to the next question. The dialogue question unit also analyzes the intensity of the emotion based on the content of the user's answer and generates questions that elicit positive emotions. For example, if the user answers "I like Japanese food," a positive question about Japanese food will be added to the next question. In this way, questions that elicit positive emotions can be generated.

[0060] The dialogue question unit can introduce dialogue questions using images and audio to understand the user's preferences in detail. The dialogue question unit, for example, builds a system that introduces dialogue questions using images and audio to understand the user's preferences in detail. For example, it shows an image of a dish and asks, "Do you like this dish?" The dialogue question unit also uses audio to understand the user's preferences in detail. For example, it asks the user by audio, "What kind of food do you like?" and analyzes the preferences based on the answer. In this way, by introducing dialogue questions using images and audio, the user's preferences can be understood in detail.

[0061] The dialogue question unit can generate questions that refer to the response data of other users in order to understand the user's preferences. The dialogue question unit, for example, builds a system that generates questions that refer to the response data of other users in order to understand the user's preferences. For example, questions are generated based on responses from users who have the same preferences. The dialogue question unit also analyzes the response data of other users to generate questions that match the user's preferences. For example, if a user answers "I like spicy food," a question about spicy food is generated based on the response data of other users. In this way, the user's preferences can be understood by generating questions that refer to the response data of other users.

[0062] The dialogue question unit can use the emotion estimation function to collect the emotional reactions of other users to the user's answers and generate questions that are highly relatable. The dialogue question unit, for example, uses the emotion estimation function to collect the emotional reactions of other users to the user's answers and builds a system that generates questions that are highly relatable. For example, questions that have a high number of positive emotional reactions are preferentially generated. The dialogue question unit also generates questions that are highly relatable based on the emotional reactions of other users. For example, if a user answers "I like Japanese food," a question about Japanese food that is highly relatable is generated based on the emotional reactions of other users. In this way, by generating questions that are highly relatable, the user's preferences can be understood in detail.

[0063] The reviewer narrowing down unit can analyze the reviewer's rating history and identify the reviewer's rating pattern that matches the user's preferences. The reviewer narrowing down unit, for example, builds a system that analyzes the reviewer's rating history and identifies the reviewer's rating pattern that matches the user's preferences. For example, it analyzes whether the reviewer also highly rates a dish that the user highly rates. The reviewer narrowing down unit also identifies the rating pattern based on the reviewer's rating history. For example, it analyzes the criteria used by the reviewer when rating and determines whether the criteria match the user's preferences. This makes it possible to identify the reviewer's rating pattern that matches the user's preferences.

[0064] The reviewer narrowing down unit can analyze the details of the reviewer's evaluation and extract the reviewer's evaluation criteria that match the user's preferences. The reviewer narrowing down unit, for example, builds a system that analyzes the details of the reviewer's evaluation and extracts the reviewer's evaluation criteria that match the user's preferences. For example, it analyzes the criteria used by the reviewer when rating and determines whether they match the user's preferences. The reviewer narrowing down unit also identifies the evaluation criteria based on the reviewer's evaluation. For example, it analyzes the characteristics of the dishes and restaurants that the reviewer highly rates and determines whether they match the user's preferences. This makes it possible to extract the reviewer's evaluation criteria that match the user's preferences.

[0065] The reviewer narrowing down unit can use the emotion estimation function to analyze the intensity of emotions from the content of reviewers' evaluations, and prioritize narrow down reviewers who can empathize emotionally. The reviewer narrowing down unit, for example, uses the emotion estimation function to analyze the intensity of emotions from the content of reviewers' evaluations, and builds a system that prioritizes narrowing down reviewers who can empathize emotionally. For example, it prioritizes narrowing down reviewers who have strong positive emotions. The reviewer narrowing down unit also classifies reviewers based on the intensity of emotions, and prioritizes narrowing down reviewers who can empathize emotionally. For example, if a reviewer rated "This dish was amazing!", it prioritizes narrowing down reviewers who can empathize emotionally. This makes it possible to prioritize narrow down reviewers who can empathize emotionally.

[0066] The reviewer narrowing unit can integrate the reviewer's evaluation data with other data sets (e.g., social media posts) to create a more detailed reviewer profile. The reviewer narrowing unit, for example, builds a system that integrates the reviewer's evaluation data with social media posts to create a more detailed reviewer profile. For example, it analyzes the content of the reviewer's posts to understand the reviewer's preferences and evaluation criteria in detail. The reviewer narrowing unit also creates a reviewer profile based on other data sets. For example, it analyzes the content of the reviewer's social media posts to identify the reviewer's preferences and evaluation criteria. This allows a more detailed reviewer profile to be created.

[0067] The reviewer narrowing down unit can recommend new reviewers who match the user's preferences based on the reviewer's evaluation content. The reviewer narrowing down unit, for example, builds a system that recommends new reviewers who match the user's preferences based on the reviewer's evaluation content. For example, the unit recommends new reviewers based on whether reviewers also highly rate dishes that the user has highly rated. The reviewer narrowing down unit also analyzes the reviewer's evaluation content to identify new reviewers. For example, it analyzes the reviewer's evaluation criteria and determines whether they match the user's preferences. This makes it possible to recommend new reviewers who match the user's preferences.

[0068] The reviewer narrowing down unit can use the emotion estimation function to collect the emotional reactions of other users to the reviewer's evaluation content and narrow down the reviewers who have a high degree of empathy. The reviewer narrowing down unit, for example, uses the emotion estimation function to collect the emotional reactions of other users to the reviewer's evaluation content and builds a system that narrows down the reviewers who have a high degree of empathy. For example, it prioritizes narrowing down reviewers who have a large number of positive emotional reactions. The reviewer narrowing down unit also classifies reviewers based on the emotional reactions of other users and narrows down the reviewers who have a high degree of empathy. For example, if a reviewer rated "This dish was the best!", it prioritizes narrowing down the reviewers who have a high degree of empathy. This makes it possible to narrow down the reviewers who have a high degree of empathy.

[0069] The scoring unit can score the evaluation data in real time based on the user's preferences and provide the latest information. The scoring unit, for example, builds a system that scores the evaluation data in real time based on the user's preferences and provides the latest information. For example, if the user answers "I like Japanese food," the scoring unit prioritizes scoring the evaluation data for Japanese food. The scoring unit also scores the evaluation data that matches the user's preferences in real time. For example, if the user answers "I like Italian food," the scoring unit prioritizes scoring the evaluation data for Italian food. This allows the evaluation data to be scored in real time based on the user's preferences and provide the latest information.

[0070] The scoring unit can weight and reflect the user's past evaluation history when scoring the evaluation data. The scoring unit, for example, builds a system that weights and reflects the user's past evaluation history when scoring the evaluation data. For example, the scoring unit weights and scores evaluation data of restaurants that the user has rated highly in the past. The scoring unit also performs scoring based on the user's evaluation history. For example, if the user answers "I like Japanese food," the scoring unit weights and scores the evaluation data of Japanese food. In this way, by weighting and reflecting the user's past evaluation history, more accurate scoring is possible.

[0071] The scoring unit can use the emotion estimation function to display evaluation data that matches the user's preferences in an emotionally relatable manner. The scoring unit, for example, uses the emotion estimation function to build a system that displays evaluation data that matches the user's preferences in an emotionally relatable manner. For example, evaluation data with a strong positive emotion is preferentially displayed. The scoring unit also displays evaluation data that matches the user's preferences in an emotionally relatable manner. For example, if the user answers "I like Japanese food," the evaluation data for Japanese food is displayed in an emotionally relatable manner. This makes it possible to display evaluation data that matches the user's preferences in an emotionally relatable manner.

[0072] The scoring unit can visualize the evaluation data and display it in a graph or chart so that the user can intuitively understand it. The scoring unit, for example, builds a system that visualizes the evaluation data and displays it in a graph or chart so that the user can intuitively understand it. For example, the evaluation score is displayed in a bar graph or pie chart. The scoring unit also visually displays the evaluation data. For example, if the user answers "I like Japanese food," the evaluation data for Japanese food is displayed in a graph or chart. This makes it possible to visualize the evaluation data and display it so that the user can intuitively understand it.

[0073] The scoring unit can share the evaluation data with other users and display the evaluations with the highest degree of empathy in a ranking format. The scoring unit, for example, builds a system that shares the evaluation data with other users and displays the evaluations with the highest degree of empathy in a ranking format. For example, evaluations with a higher number of positive emotional responses are displayed at the top. The scoring unit also displays the evaluation data in a ranking format. For example, if a user answers "I like Japanese food," the evaluation data for Japanese food is displayed in a ranking format. In this way, the evaluations with the highest degree of empathy can be displayed in a ranking format and shared with other users.

[0074] The scoring unit can use the emotion estimation function to collect other users' emotional reactions to the evaluation data and prioritize displaying evaluations with a high degree of empathy. The scoring unit, for example, uses the emotion estimation function to collect other users' emotional reactions to the evaluation data and builds a system that prioritizes displaying evaluations with a high degree of empathy. For example, evaluations with a large number of positive emotional reactions are displayed preferentially. The scoring unit also displays evaluation data based on the emotional reactions of other users. For example, if a user answers "I like Japanese food," the evaluation data for Japanese food is displayed in a manner that allows for emotional empathy. In this way, by preferentially displaying evaluations with a high degree of empathy, the emotional reactions of other users can be reflected.

[0075] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0076] The AI ​​system can also recommend restaurants that take into account the user's health condition. For example, if the user inputs the results of a health check, the system can use that information to recommend restaurants that offer healthy menus. Also, if the user wants to consume a specific nutrient, the system can prioritize restaurants that offer dishes that contain a lot of that nutrient. Furthermore, if the user is on a diet, it can recommend restaurants that offer low-calorie menus.

[0077] The AI ​​system can recommend restaurants at a travel destination based on the user's past travel history. For example, by inputting information about cities or countries the user has visited in the past, the system can display highly rated restaurants in that area. Also, if the user plans to visit a specific tourist spot, the system can recommend restaurants in the surrounding area. Furthermore, it can recommend restaurants with a similar atmosphere or cuisine based on the reviews of restaurants the user has visited in the past.

[0078] The AI ​​system can recommend restaurants that take into account the preferences of the user's friends and family. For example, if the user inputs the preferences of their friends and family, the system can recommend restaurants that will satisfy everyone based on that information. Also, if the user is planning a specific event (such as a birthday or anniversary), the system can recommend restaurants that are suitable for that event. Furthermore, it can display recommended restaurants based on the food and atmosphere that the user wants to share with their friends and family.

[0079] The AI ​​system can estimate the user's emotions and recommend restaurants where they can relieve stress and relax. For example, if the user is feeling stressed, it can recommend restaurants with a relaxing atmosphere or that offer relaxation menus. Also, if the user is feeling positive, it can recommend restaurants with a fun atmosphere that will further enhance those emotions. Furthermore, if the user is feeling a specific emotion, it can also recommend restaurants that match that emotion.

[0080] AI systems can estimate a user's emotions and provide special offers and coupons based on those emotions. For example, if a user has positive emotions, they can provide special offers to enhance those emotions. Also, if a user has negative emotions, they can provide coupons to alleviate those emotions. Furthermore, if a user has a specific emotion, they can provide special offers and coupons that match that emotion.

[0081] AI systems can estimate a user's emotions and provide music and entertainment based on those emotions. For example, if a user wants to relax, they can provide relaxing music. If a user is in a happy mood, they can provide entertainment that enhances that mood. Furthermore, if a user is feeling a certain emotion, they can provide music and entertainment that matches that emotion.

[0082] AI systems can estimate a user's emotions and provide emotionally-based mental health support. For example, if a user is feeling stressed, they can provide advice and resources for stress relief. If a user is feeling anxious, they can provide mental health support to alleviate that anxiety. Furthermore, if a user is experiencing a specific emotion, they can provide mental health support tailored to that emotion.

[0083] The AI ​​system can estimate the user's emotions and provide feedback based on the emotions. For example, if the user has positive emotions, it can provide feedback that further enhances those emotions. Also, if the user has negative emotions, it can provide feedback to alleviate those emotions. Furthermore, if the user has a specific emotion, it can provide feedback that matches that emotion.

[0084] AI systems can recommend new products and services that a user might be interested in based on their past purchase history. For example, they can recommend similar products and services based on information about products and services a user has purchased in the past. Also, if a user frequently purchases products in a particular category, they can prioritize the display of new products in that category. Furthermore, they can provide new recommendations based on products and services that a user has rated highly in the past.

[0085] AI systems can recommend services to support daily life based on a user's lifestyle. For example, if a user has a busy lifestyle, they can recommend time-saving services. If a user is health-conscious, they can also provide health-conscious services. Furthermore, if a user has specific hobbies or interests, they can recommend services related to those hobbies or interests.

[0086] The processing flow of the second embodiment will be briefly explained below.

[0087] Step 1: The rating accumulation unit accumulates the user's past ratings and review content. For example, if a user rates a ramen shop as "the soup was rich and delicious," that information is accumulated. The rating accumulation unit also saves information about the shops and products rated by the user, the rating content, and the review text in a database. Step 2: The dialogue questioning unit obtains a detailed understanding of the user's preferences based on the information accumulated by the evaluation accumulation unit. For example, the generation AI asks the user questions such as "What kind of food do you like?" or "What kind of restaurant atmosphere do you like?" and analyzes the user's preferences based on the answers. The generation AI analyzes the user's preferences using a text generation AI (e.g., LLM). The generation AI can also obtain a detailed understanding of the user's preferences using a multimodal generation AI. Step 3: The reviewer selection unit narrows down the reviewer candidates to those with similar tastes to the user identified by the dialogue question unit. For example, if the user answers "I like spicy food," the unit narrows down the candidates to reviewers who rate spicy food highly. The reviewer selection unit also considers the similarity of the stores and products recommended by the reviewers, the content of their reviews, and, conversely, information that the reviewers have judged to be unacceptable. Step 4: The scoring unit scores the evaluation data narrowed down by the reviewer narrowing unit based on whether it matches the user's preferences and displays it. For example, if the user answers "I like Japanese food," reviews by reviewers who rate Japanese food highly will be displayed preferentially. The scoring unit also displays restaurant information that matches the user's preferences, as well as text and photos of "reviews that the user can truly relate to."

[0088] 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.

[0089] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<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.

[0090] 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.

[0091] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0092] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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).

[0097] 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.

[0098] 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.

[0099] 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.

[0100] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0101] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0107] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0116] 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 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0122] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0132] In the robot 414, the processor 46 performs the identification process. 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. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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).

[0141] 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.

[0142] 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."

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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. [Explanation of symbols]

[0155] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a rating accumulation unit that accumulates past ratings and review contents of users; a dialogue questioning unit that grasps the user's preferences in detail based on the information accumulated by the evaluation accumulation unit; a reviewer narrowing-down unit that narrows down reviewer candidates having similar taste tendencies to the user grasped by the dialogue questioning unit; a scoring unit that scores and displays the evaluation data narrowed down by the reviewer narrowing down unit based on whether the evaluation data is suited to the user's preferences. A system characterized by:

2. The evaluation accumulation unit The intensity of emotions is analyzed from the review contents of the user, and the evaluations with particularly strong emotions are preferentially accumulated.

2. The system of claim 1.

3. The dialogue question unit Based on the user's answers, the generation AI learns the user's preferences in real time and reflects them in the next dialogue question.

2. The system of claim 1.

4. The reviewer narrowing down unit Analyzing a reviewer's rating history to identify a rating pattern of the reviewer that matches the preferences of the user.

2. The system of claim 1.

5. The scoring unit The evaluation data is scored in real time based on the user's preferences to provide up-to-date information.

2. The system of claim 1.

6. The dialogue question unit Analyzing the emotions of the user when answering questions and generating questions that elicit positive emotions 2. The system of claim 1.

7. The reviewer narrowing down unit Analyze the emotional intensity of the reviewers' evaluations and prioritize reviewers who empathize with you emotionally.

2. The system of claim 1.

8. The scoring unit Displaying the rating data that matches the preferences of the user in an emotionally relatable manner 2. The system of claim 1.

Images