system

Abstract

An object of a system according to an embodiment is to analyze application information and a search history of a user and propose an optimal product.SOLUTION: A system according to an embodiment includes an application information collection unit, a generation AI, a retrieval history collection unit, a suggestion generation unit, and a display notifying unit. The application information collection unit collects application information installed in the smartphone main body. The generation AI analyzes the application information collected by the application information collection unit. The search history collection unit collects a history of searches performed by the user using the yahoo! engine. The generation AI analyzes the retrieval history collected by the retrieval history collection unit. The suggestion generation unit suggests an optimal SB product to the user based on the application information analyzed by the generation AI and the retrieval history. The display notification unit displays or notifies the user of the proposal content generated by the proposal generation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies have had the problem of not being able to effectively utilize users' app information and search history to suggest optimal products.

[0005] The system according to the embodiment aims to analyze the application information and search history of the user and propose the most suitable product. [Means for solving the problem]

[0006] The system according to the embodiment includes an app information collection unit, a generation AI, a search history collection unit, a proposal generation unit, and a display notification unit. The app information collection unit collects app information installed on the smartphone. The generation AI analyzes the app information collected by the app information collection unit. The search history collection unit collects user search history on the Yahoo! engine. The generation AI analyzes the search history collected by the search history collection unit. The proposal generation unit proposes optimal SB products to the user based on the app information and search history analyzed by the generation AI. The display notification unit displays or notifies the user of the proposal content generated by the proposal generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze the user's application information and search history and propose optimal products. [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 proposal system according to an embodiment of the present invention utilizes a generation AI to propose optimal SB products to users. This system uses a generation AI to analyze information about apps installed on a smartphone and search history from the Yahoo! search engine, and proposes products suitable for the user based on the results. This allows the proposal system to propose products based on the user's interests.

[0029] A proposal system according to an embodiment includes an app information collection unit, a search history collection unit, a proposal generation unit, and a display / notification unit. The app information collection unit collects app information installed on a smartphone. For example, the app information collection unit analyzes the types of apps a user frequently uses and recently installed. The app information collection unit can also collect app usage frequency and usage time. For example, the app information collection unit identifies a user's interests based on the app usage history. The search history collection unit collects a history of searches the user made on the Yahoo! Search Engine. For example, the search history collection unit analyzes recent keywords and frequently searched topics. The search history collection unit can also collect patterns of search history by time period and day of the week. For example, the search history collection unit understands the user's daily rhythm based on the time period of the search history. The proposal generation unit uses a generation AI to propose optimal SB products to a user based on the information collected by the app information collection unit and the search history collection unit. For example, if a user frequently uses health-related apps and frequently searches for health-related information, the proposal generation unit can suggest health-related SB products. The suggestion generation unit can also generate optimal suggestions by analyzing the user's behavioral patterns and interests in detail. For example, the suggestion generation unit can comprehensively analyze the user's app usage history and search history to predict the user's preferences. The display notification unit displays or notifies the user of the suggestion content generated by the suggestion generation unit. For example, the display notification unit displays the suggestion content as "Products Recommended for You" on the home screen of the app. The display notification unit can also notify the user of the suggestion content using a push notification. For example, the display notification unit notifies the user when the user is using the smartphone. This allows the suggestion system according to the embodiment to suggest products based on the user's interests and concerns. For example, by making suggestions based on the user's interests and concerns, the suggestion system can improve the accuracy of suggestions and increase user satisfaction. Furthermore, by suggesting products that the user needs in a timely manner, the system can stimulate purchasing desire and contribute to increased sales.

[0030] The app information collection unit collects not only the time and frequency of app usage but also specific operation history within the app, allowing the generation AI to analyze the user's behavioral patterns in detail. For example, the app information collection unit collects specific operation history within the app in addition to the time and frequency of use of each app. For example, the number of posts on a social networking app or the product browsing history on a shopping app may be recorded in detail, and the generation AI may analyze this. The app information collection unit may also collect the type and timing of operations performed by the user within the app. For example, the app information collection unit may collect detailed logs of the operations performed by the user within the app, and the generation AI may analyze the behavioral patterns based on this. The app information collection unit may also collect the frequency and order of operations performed by the user within the app. For example, the app information collection unit may identify behavioral patterns based on the frequency and order of operations performed by the user within the app. This allows for detailed analysis of the user's behavioral patterns.

[0031] The app information collection unit analyzes preferences for app interfaces and designs, allowing the generation AI to suggest products with UI / UX that the user prefers. For example, the app information collection unit analyzes the interface and design of each app to identify UI / UX features that the user prefers. For example, for a user who prefers simple or colorful interfaces, the generation AI suggests products with similar designs. The app information collection unit can also identify UI / UX patterns that the user prefers based on the history of operations the user performs within the app. For example, the app information collection unit analyzes the UI / UX of apps that the user frequently uses, and the generation AI suggests products based on this. The app information collection unit can also identify UI / UX patterns that the user prefers based on the history of operations the user performs within the app. For example, the app information collection unit analyzes the UI / UX of apps that the user frequently uses, and the generation AI suggests products based on this. This allows the generation AI to suggest products with UI / UX that the user prefers.

[0032] The app information collection unit collects sensor information (GPS, accelerometer, etc.) from the smartphone, and the generation AI analyzes the user's movement patterns and activity level to use in product suggestions. The app information collection unit, for example, collects GPS information from the smartphone and analyzes the user's movement patterns. For example, it identifies the user's commute route or weekend outings and suggests related products based on that. The app information collection unit can also collect accelerometer data and analyze the user's activity level. For example, it can suggest health-related products based on the user's number of steps and exercise volume. The app information collection unit can also comprehensively analyze the user's movement patterns and activity level based on the smartphone's sensor information. For example, it can combine GPS data and acceleration data to identify the user's behavioral patterns. This makes it possible to suggest products based on the user's movement patterns and activity level.

[0033] The app information collection unit also integrates app information from other devices (smartwatches, tablets, etc.), allowing the generation AI to analyze user behavior patterns more comprehensively. For example, the app information collection unit collects data from a smartwatch and integrates it with smartphone app information to analyze user behavior patterns. For example, it may suggest health-related products based on heart rate and exercise volume. The app information collection unit can also collect data from a tablet and integrate it with smartphone app information to analyze user behavior patterns. For example, it may identify user interests based on app usage history on the tablet. The app information collection unit can also comprehensively analyze data from other devices to identify user behavior patterns. For example, it may combine data from a smartwatch and a tablet to perform a detailed analysis of user behavior patterns. This allows for a more comprehensive analysis of user behavior patterns.

[0034] The search history collection unit analyzes patterns in search history by time of day and day of the week, allowing the generation AI to suggest products that fit the user's lifestyle. The search history collection unit, for example, analyzes patterns in search history by time of day and day of the week to understand the user's lifestyle. For example, for a user who searches frequently on weekday evenings, the search history collection unit can suggest products that can be used at night. The search history collection unit can also analyze keywords that users search for during specific time periods, allowing the generation AI to suggest products based on this. For example, for a user who searches health-related items in the morning, the search history collection unit can suggest health-related products that can be used in the morning. The search history collection unit can also identify the user's lifestyle based on the user's search history, allowing the generation AI to suggest products based on this. For example, if a user searches for outdoor-related items on the weekend, the search history collection unit can suggest outdoor-related products that can be used on the weekend. This allows the generation AI to suggest products that fit the user's lifestyle.

[0035] The search history collection unit also collects click histories of search results, allowing the generation AI to suggest products based on information in which the user is actually interested. The search history collection unit, for example, collects click histories of search results and analyzes information in which the user is actually interested. For example, the search history collection unit suggests products to a user who frequently clicks on pages for a particular product. The search history collection unit also allows the generation AI to suggest products based on the history of links clicked by the user. For example, if a user frequently clicks on links in a particular category, the generation AI will suggest products related to that category. The search history collection unit also allows the generation AI to analyze the user's interests in detail based on the history of links clicked by the user. For example, if a user frequently clicks on links for a particular brand, the generation AI will suggest products related to that brand. This allows the generation AI to suggest products based on information in which the user is actually interested.

[0036] The search history collection unit also integrates search histories from other search engines (such as Google and Bing), allowing the generation AI to perform a more multifaceted analysis of user interests. The search history collection unit, for example, collects search histories from other search engines and integrates them with data from the Yahoo! engine to perform a multifaceted analysis of user interests. For example, it integrates search histories from Google and Bing. The search history collection unit also allows the generation AI to perform a detailed analysis of user interests based on search histories from other search engines. For example, it compares keywords searched by a user on Google with keywords searched on the Yahoo! engine to identify common interests. The search history collection unit also allows the generation AI to perform a detailed analysis of user interests based on search histories from other search engines. For example, it compares keywords searched by a user on Google with keywords searched on the Yahoo! engine to identify common interests. This allows a more multifaceted analysis of user interests.

[0037] The search history collection unit links the search history with the content of posts on SNS, allowing the generation AI to analyze the user's entire online activity and utilize the results for product suggestions. The search history collection unit, for example, links the search history with the content of posts on SNS and analyzes the user's entire online activity. For example, it analyzes the content of posts on Twitter and Facebook and integrates it with the search history. The search history collection unit also allows the generation AI to analyze the user's interests in detail based on the content of posts on SNS. For example, it analyzes the topics that the user frequently posts on SNS and utilizes the results for product suggestions. The search history collection unit also allows the generation AI to analyze the user's interests in detail based on the content of posts on SNS. For example, it analyzes the topics that the user frequently posts on SNS and utilizes the results for product suggestions. This allows the user's entire online activity to be analyzed and utilized for product suggestions.

[0038] When generating the proposal content, the proposal generation unit also takes into account the user's past purchase history and can suggest products that are likely to be repeat purchases. The proposal generation unit, for example, collects the user's past purchase history and identifies products that are likely to be repeat purchases. For example, it suggests similar products based on products that are regularly purchased. The proposal generation unit can also use the generation AI to predict the possibility of repeat purchases based on the user's purchase history. For example, it can analyze the purchase frequency and purchase intervals of products that the user has purchased in the past and suggest products that are likely to be repeat purchases. The proposal generation unit can also use the generation AI to predict the possibility of repeat purchases based on the user's purchase history. For example, it can analyze the purchase frequency and purchase intervals of products that the user has purchased in the past and suggest products that are likely to be repeat purchases. This makes it possible to suggest products that are likely to be repeat purchases.

[0039] When generating the proposal content, the proposal generation unit also refers to the purchase histories of the user's friends and family, and can propose products that take social influence into consideration. The proposal generation unit, for example, collects the purchase histories of the user's friends and family, and proposes products that take social influence into consideration. For example, based on a product purchased by a friend, a similar product is proposed to the user. The proposal generation unit can also have the generation AI suggest products based on the purchase histories of the user's friends and family. For example, based on a product purchased by the user's friend, a similar product is proposed to the user. The proposal generation unit can also have the generation AI suggest products based on the purchase histories of the user's friends and family. For example, based on a product purchased by the user's friend, a similar product is proposed to the user. In this way, products can be proposed that take social influence into consideration.

[0040] When generating proposal content, the proposal generation unit can propose merchandise that matches a season or event (Christmas, Valentine's Day, etc.). The proposal generation unit, for example, builds a system that proposes merchandise that matches a season or event. For example, Christmas-related products are proposed during the Christmas season. The proposal generation unit can also propose merchandise that matches a season or event based on the user's past purchase history. For example, a similar product is proposed based on a product that the user previously purchased during the Christmas season. The proposal generation unit can also propose merchandise that matches a season or event based on the user's past purchase history. For example, a similar product is proposed based on a product that the user previously purchased during the Christmas season. This makes it possible to propose merchandise that matches a season or event.

[0041] When generating proposal content, the proposal generation unit can consider the user's regional characteristics (climate, culture, etc.) and propose products suitable for the region. The proposal generation unit, for example, builds a system that considers the user's regional characteristics and proposes products suitable for the region. For example, it proposes winter gear to a user living in a cold region. The proposal generation unit can also have the generation AI propose products based on the user's regional characteristics. For example, it proposes related products based on the climate and culture of the region where the user lives. The proposal generation unit can also have the generation AI propose products based on the user's regional characteristics. For example, it proposes related products based on the climate and culture of the region where the user lives. This makes it possible to propose products suitable for the region.

[0042] The display notification unit can customize the display method of the proposal content to suit the user's preferences and provide a visually attractive interface. The display notification unit, for example, builds a system that customizes the display method of the proposal content to suit the user's preferences. For example, the proposal content is displayed using the user's preferred colors and fonts. The display notification unit can also use the generation AI to suggest the optimal display method based on the user's past operation history. For example, the proposal content is customized based on display settings previously selected by the user. The display notification unit can also adjust the layout and design of the proposal content to suit the user's preferences. For example, the proposal content is displayed based on the user's preferred layout and design. This makes it possible to provide a visually attractive interface.

[0043] The display notification unit can optimize the timing of notification of suggested content to match the user's behavioral patterns and send notifications at the most effective timing. The display notification unit, for example, builds a system that optimizes the timing of notification of suggested content to match the user's behavioral patterns. For example, notifications are sent during times when the user frequently uses their smartphone. The display notification unit can also use a generation AI to suggest the optimal notification timing based on the user's past operation history. For example, the optimal notification timing is determined based on the user's reactions when receiving notifications in the past. The display notification unit can also adjust the frequency and timing of notifications based on the user's behavioral patterns. For example, if a user frequently uses their smartphone during a specific time period, notifications are sent during that time period. This allows notifications to be sent at the most effective timing.

[0044] The display notification unit can notify the content of the proposal through multiple channels, such as social media and email, allowing the user to receive the proposal in the most convenient way. The display notification unit, for example, builds a system that notifies the content of the proposal through multiple channels, such as social media and email. For example, it allows the user to select the channel that is most convenient for them. The display notification unit can also use a generation AI to suggest the optimal notification channel based on the user's past operation history. For example, it can identify the optimal notification method based on channels that the user has used in the past. The display notification unit can also customize the notification channel to suit the user's preferences. For example, it can notify the content of the proposal based on the user's preferred notification method. This allows the user to receive the proposal in the most convenient way.

[0045] The display notification unit can display the proposed content using AR (augmented reality) technology, providing the user with an experience similar to actually trying out a product. The display notification unit, for example, builds a system that displays the proposed content using AR technology. For example, the display notification unit can provide the user with an experience similar to trying out a product through a smartphone. The display notification unit can also use a generating AI to propose the optimal AR experience based on the user's past operation history. For example, the display notification unit can make the optimal proposal based on AR experiences the user has used in the past. The display notification unit can also customize the AR experience to suit the user's preferences. For example, the display notification unit can display the proposed content based on the AR experience the user prefers. This can provide the user with an experience similar to actually trying out a product.

[0046] The proposal generation unit can develop an algorithm that extracts elements from the clustered ideas that are likely to work together, automatically generates candidate combinations, and filters the most promising combinations from among them. The proposal generation unit, for example, develops an algorithm that automatically generates candidate combinations and builds a system that filters the most promising combinations from among them. For example, filtering is performed based on technical feasibility and market demand. The proposal generation unit can also use a generative AI to propose optimal combinations based on the clustered ideas. For example, ideas from different industries can be combined to discover new market needs. The proposal generation unit can also use a generative AI to propose optimal combinations based on the clustered ideas. For example, ideas from different industries can be combined to discover new market needs. This makes it possible to develop an algorithm that filters the most promising combinations.

[0047] The proposal generation unit can extract elements from the clustered ideas that are likely to be effective when combined, set evaluation criteria for the combinations from various angles, and comprehensively evaluate technical feasibility, economic effectiveness, social impact, etc. The proposal generation unit, for example, sets evaluation criteria for the combinations from various angles and builds a system that comprehensively evaluates technical feasibility, economic effectiveness, social impact, etc. For example, it calculates a score for each criterion and performs an overall evaluation. The proposal generation unit can also use a generative AI to propose optimal combinations based on the clustered ideas. For example, it can combine ideas from different industries to discover new market needs. The proposal generation unit can also use a generative AI to propose optimal combinations based on the clustered ideas. For example, it can combine ideas from different industries to discover new market needs. This allows for a comprehensive evaluation of technical feasibility, economic effectiveness, social impact, etc.

[0048] The proposal generation unit extracts elements from the clustered ideas that are likely to work well together, and combines ideas from different industries and applications to discover new market needs. The proposal generation unit, for example, builds a system that combines ideas from different industries to discover new market needs. For example, it generates ideas that combine the technology field with the consumer market. The proposal generation unit can also use a generation AI to propose optimal combinations based on the clustered ideas. For example, it can combine ideas from different industries to discover new market needs. The proposal generation unit can also use a generation AI to propose optimal combinations based on the clustered ideas. For example, it can combine ideas from different industries to discover new market needs. This makes it possible to combine ideas from different industries and applications to discover new market needs.

[0049] The proposal generation unit can introduce an agile methodology in which elements that are likely to work well together can be extracted from the clustered ideas, the combined idea can be implemented as a prototype, and the idea can be improved based on feedback. The proposal generation unit can, for example, build a system that introduces an agile methodology in which the combined idea can be implemented as a prototype and improved based on user feedback. For example, a prototype can be developed in a short period of time and user opinions can be reflected. The proposal generation unit can also use a generation AI to propose optimal combinations based on the clustered ideas. For example, ideas from different industries can be combined to discover new market needs. The proposal generation unit can also use a generation AI to propose optimal combinations based on the clustered ideas. For example, ideas from different industries can be combined to discover new market needs. This makes it possible to introduce an agile methodology in which a prototype can be implemented and improved based on feedback.

[0050] When the generation AI automatically proposes a new plan based on the extracted elements, the proposal generation unit can learn from past successes and failures and generate a proposal with the highest probability of success. For example, the proposal generation unit has the generation AI learn from past successes and failures and generate a proposal with a high probability of success when proposing a new plan. For example, the proposal generation unit automatically generates an optimal plan based on past data. The proposal generation unit can also adjust the proposal content based on past successes and failures. For example, the generation AI can refer to past successes and make a proposal under similar conditions. The proposal generation unit can also adjust the proposal content based on past successes and failures. For example, the generation AI can refer to past successes and make a proposal under similar conditions. In this way, the generation AI can learn from past successes and failures and generate a proposal with the highest probability of success.

[0051] When the generation AI automatically proposes a new plan based on the extracted elements, the proposal generation unit collects user feedback on the proposed plan in real time and can make instant improvements. The proposal generation unit, for example, builds a system that collects user feedback on proposed plans in real time and makes instant improvements based on the results. For example, it uses an online survey or comment function. The proposal generation unit can also allow the generation AI to adjust the proposal content based on user feedback. For example, it can improve the proposal content by reflecting user opinions. The proposal generation unit can also allow the generation AI to adjust the proposal content based on user feedback. For example, it can improve the proposal content by reflecting user opinions. This allows user feedback to be collected in real time and makes instant improvements.

[0052] When the generation AI automatically proposes a new plan based on the extracted elements, the proposal generation unit can automatically generate plan proposals specialized for different markets or regions. The proposal generation unit, for example, uses the generation AI to build a system that automatically generates plan proposals specialized for different markets or regions. For example, it makes proposals according to market needs and regional characteristics. The proposal generation unit can also adjust the proposal content based on the characteristics of the market or region. For example, it can propose similar products based on products that are popular in a specific region. The proposal generation unit can also adjust the proposal content based on the characteristics of the market or region. For example, it can propose similar products based on products that are popular in a specific region. This makes it possible to automatically generate plan proposals specialized for different markets or regions.

[0053] When the generation AI automatically proposes a new plan based on the extracted elements, the proposal generation unit can automatically generate a visual prototype of the proposed plan to make it easier to understand visually. The proposal generation unit, for example, uses the generation AI to develop a system that automatically generates a visual prototype of a proposed plan. For example, it visually displays a product design or a service flow. The proposal generation unit can also have the generation AI adjust the visual prototype based on user feedback. For example, it can reflect user opinions and improve the prototype. The proposal generation unit can also have the generation AI adjust the visual prototype based on user feedback. For example, it can reflect user opinions and improve the prototype. In this way, a visual prototype of the proposed plan can be automatically generated to make it easier to understand visually.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The recommendation system can further include a purchase history collection unit that collects the user's purchase history. The purchase history collection unit, for example, collects data on products purchased by the user in the past, and the generation AI suggests products based on this. For example, similar products can be suggested based on products that the user purchases regularly. The purchase history collection unit can also allow the generation AI to predict the possibility of repeat purchases based on the user's purchase history. For example, the purchase history collection unit can analyze the purchase frequency and purchase intervals of products purchased by the user in the past, and suggest products that are likely to be purchased again. This makes it possible to suggest products based on the user's purchase history.

[0056] The recommendation system can further include a social purchase history collection unit that collects the purchase histories of the user's friends and family. The social purchase history collection unit, for example, collects data on products purchased by the user's friends and family, and the generation AI suggests products based on this data. For example, based on products purchased by friends, similar products may be suggested to the user. The social purchase history collection unit can also allow the generation AI to suggest products based on the purchase histories of the user's friends and family. For example, based on products purchased by the user's friends, similar products may be suggested to the user. This makes it possible to suggest products that take social influence into consideration.

[0057] The proposal system can further include a regional characteristics collection unit that takes into account the regional characteristics of the user. The regional characteristics collection unit, for example, collects information about the climate and culture of the region where the user lives, and the generation AI proposes products based on this information. For example, it proposes cold weather gear to a user who lives in a cold region. The regional characteristics collection unit can also allow the generation AI to propose products based on the user's regional characteristics. For example, it proposes related products based on the climate and culture of the region where the user lives. This makes it possible to propose products that are suitable for the region.

[0058] The recommendation system can further include a seasonal event collection unit that suggests products that match the season or event. The seasonal event collection unit collects event information, such as Christmas or Valentine's Day, and the generation AI suggests products based on this information. For example, Christmas-related products are suggested during the Christmas season. The seasonal event collection unit can also suggest products that match the season or event based on the user's past purchase history. For example, similar products are suggested based on products that the user previously purchased during the Christmas season. This makes it possible to suggest products that match the season or event.

[0059] The proposal system can further include an online activity collection unit that analyzes the user's overall online activity. The online activity collection unit, for example, links search history and social media postings, and the generation AI analyzes the user's overall online activity. For example, it analyzes the content of posts on Twitter and Facebook and integrates it with the search history. The online activity collection unit can also allow the generation AI to perform a detailed analysis of the user's interests based on the content of social media posts. For example, it can analyze topics that the user frequently posts about on social media and suggest related products. This allows the user's overall online activity to be analyzed and used to suggest products.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The app information collection unit collects information about apps installed on the smartphone itself. For example, it analyzes the apps that the user uses most frequently, the types of apps that were recently installed, and the frequency and duration of app use, and understands the user's interests based on the app usage history. Step 2: The search history collection unit collects the user's search history on the Yahoo! search engine. For example, it analyzes the user's recent search keywords, frequently searched topics, and patterns of search history by time of day and day of the week, and understands the user's lifestyle based on the time of day of the search history. Step 3: The generation AI analyzes the app information and search history collected by the app information collection unit and search history collection unit, thereby gaining a detailed understanding of the user's behavioral patterns and interests. Step 4: The proposal generation unit proposes optimal SB products to the user based on the app information and search history analyzed by the generation AI. For example, if the user uses many health-related apps and frequently searches for health-related information, the unit will propose health-related SB products. Step 5: The display / notification unit displays or notifies the user of the proposal content generated by the proposal generation unit. For example, the display / notification unit may display the proposal content as "products recommended for you" on the home screen of the app or may notify the user of the proposal content using a push notification.

[0062] (Example 2) The proposal system according to an embodiment of the present invention utilizes a generation AI to propose optimal SB products to users. This system uses a generation AI to analyze information about apps installed on a smartphone and search history from the Yahoo! search engine, and proposes products suitable for the user based on the results. This allows the proposal system to propose products based on the user's interests.

[0063] A proposal system according to an embodiment includes an app information collection unit, a search history collection unit, a proposal generation unit, and a display / notification unit. The app information collection unit collects app information installed on a smartphone. For example, the app information collection unit analyzes the types of apps a user frequently uses and recently installed. The app information collection unit can also collect app usage frequency and usage time. For example, the app information collection unit identifies a user's interests based on the app usage history. The search history collection unit collects a history of searches the user made on the Yahoo! Search Engine. For example, the search history collection unit analyzes recent keywords and frequently searched topics. The search history collection unit can also collect patterns of search history by time period and day of the week. For example, the search history collection unit understands the user's daily rhythm based on the time period of the search history. The proposal generation unit uses a generation AI to propose optimal SB products to a user based on the information collected by the app information collection unit and the search history collection unit. For example, if a user frequently uses health-related apps and frequently searches for health-related information, the proposal generation unit can suggest health-related SB products. The suggestion generation unit can also generate optimal suggestions by analyzing the user's behavioral patterns and interests in detail. For example, the suggestion generation unit can comprehensively analyze the user's app usage history and search history to predict the user's preferences. The display notification unit displays or notifies the user of the suggestion content generated by the suggestion generation unit. For example, the display notification unit displays the suggestion content as "Products Recommended for You" on the home screen of the app. The display notification unit can also notify the user of the suggestion content using a push notification. For example, the display notification unit notifies the user when the user is using the smartphone. This allows the suggestion system according to the embodiment to suggest products based on the user's interests and concerns. For example, by making suggestions based on the user's interests and concerns, the suggestion system can improve the accuracy of suggestions and increase user satisfaction. Furthermore, by suggesting products that the user needs in a timely manner, the system can stimulate purchasing desire and contribute to increased sales.

[0064] The app information collection unit collects not only the time and frequency of app usage but also specific operation history within the app, allowing the generation AI to analyze the user's behavioral patterns in detail. For example, the app information collection unit collects specific operation history within the app in addition to the time and frequency of use of each app. For example, the number of posts on a social networking app or the product browsing history on a shopping app may be recorded in detail, and the generation AI may analyze this. The app information collection unit may also collect the type and timing of operations performed by the user within the app. For example, the app information collection unit may collect detailed logs of the operations performed by the user within the app, and the generation AI may analyze the behavioral patterns based on this. The app information collection unit may also collect the frequency and order of operations performed by the user within the app. For example, the app information collection unit may identify behavioral patterns based on the frequency and order of operations performed by the user within the app. This allows for detailed analysis of the user's behavioral patterns.

[0065] The app information collection unit analyzes preferences for app interfaces and designs, allowing the generation AI to suggest products with UI / UX that the user prefers. For example, the app information collection unit analyzes the interface and design of each app to identify UI / UX features that the user prefers. For example, for a user who prefers simple or colorful interfaces, the generation AI suggests products with similar designs. The app information collection unit can also identify UI / UX patterns that the user prefers based on the history of operations the user performs within the app. For example, the app information collection unit analyzes the UI / UX of apps that the user frequently uses, and the generation AI suggests products based on this. The app information collection unit can also identify UI / UX patterns that the user prefers based on the history of operations the user performs within the app. For example, the app information collection unit analyzes the UI / UX of apps that the user frequently uses, and the generation AI suggests products based on this. This allows the generation AI to suggest products with UI / UX that the user prefers.

[0066] The app information collection unit uses the emotion estimation function to estimate the user's emotions while using an app, and if the user frequently uses apps that elicit positive emotions, it can suggest products that match those emotions. The app information collection unit, for example, analyzes facial expressions and voice to estimate the user's emotions while using an app. For example, it uses a camera or microphone to analyze the user's emotions in real time and identifies apps that elicit positive emotions. The app information collection unit can also collect the user's biometric data (heart rate and electrodermal activity) and analyze emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on heart rate fluctuations. The app information collection unit can also analyze changes in emotions based on the user's operation history within the app. For example, it can analyze the user's emotions when performing specific operations and identify apps that elicit positive emotions. This makes it possible to suggest products that match the user's emotions.

[0067] The app information collection unit collects sensor information (GPS, accelerometer, etc.) from the smartphone, and the generation AI analyzes the user's movement patterns and activity level to use in product suggestions. The app information collection unit, for example, collects GPS information from the smartphone and analyzes the user's movement patterns. For example, it identifies the user's commute route or weekend outings and suggests related products based on that. The app information collection unit can also collect accelerometer data and analyze the user's activity level. For example, it can suggest health-related products based on the user's number of steps and exercise volume. The app information collection unit can also comprehensively analyze the user's movement patterns and activity level based on the smartphone's sensor information. For example, it can combine GPS data and acceleration data to identify the user's behavioral patterns. This makes it possible to suggest products based on the user's movement patterns and activity level.

[0068] The app information collection unit also integrates app information from other devices (smartwatches, tablets, etc.), allowing the generation AI to analyze user behavior patterns more comprehensively. For example, the app information collection unit collects data from a smartwatch and integrates it with smartphone app information to analyze user behavior patterns. For example, it may suggest health-related products based on heart rate and exercise volume. The app information collection unit can also collect data from a tablet and integrate it with smartphone app information to analyze user behavior patterns. For example, it may identify user interests based on app usage history on the tablet. The app information collection unit can also comprehensively analyze data from other devices to identify user behavior patterns. For example, it may combine data from a smartwatch and a tablet to perform a detailed analysis of user behavior patterns. This allows for a more comprehensive analysis of user behavior patterns.

[0069] The app information collection unit can use the emotion estimation function to monitor the user's emotions in real time while using the app and dynamically change product suggestions in response to changes in emotions. The app information collection unit, for example, builds a system that monitors the user's emotions in real time while using the app and dynamically changes product suggestions in response to changes in emotions. For example, if the user is feeling stressed, relaxation-related products are suggested. The app information collection unit can also analyze the user's facial expressions and voice and change the product suggestions based on the emotion score. For example, if the user is relaxed, relaxation-related products are suggested. The app information collection unit can also analyze changes in emotions based on the user's biometric data and dynamically change the product suggestions. For example, an emotion score is calculated based on fluctuations in heart rate, and the product suggestions are changed. This makes it possible to dynamically change product suggestions in response to changes in the user's emotions.

[0070] The search history collection unit analyzes patterns in search history by time of day and day of the week, allowing the generation AI to suggest products that fit the user's lifestyle. The search history collection unit, for example, analyzes patterns in search history by time of day and day of the week to understand the user's lifestyle. For example, for a user who searches frequently on weekday evenings, the search history collection unit can suggest products that can be used at night. The search history collection unit can also analyze keywords that users search for during specific time periods, allowing the generation AI to suggest products based on this. For example, for a user who searches health-related items in the morning, the search history collection unit can suggest health-related products that can be used in the morning. The search history collection unit can also identify the user's lifestyle based on the user's search history, allowing the generation AI to suggest products based on this. For example, if a user searches for outdoor-related items on the weekend, the search history collection unit can suggest outdoor-related products that can be used on the weekend. This allows the generation AI to suggest products that fit the user's lifestyle.

[0071] The search history collection unit also collects click histories of search results, allowing the generation AI to suggest products based on information in which the user is actually interested. The search history collection unit, for example, collects click histories of search results and analyzes information in which the user is actually interested. For example, the search history collection unit suggests products to a user who frequently clicks on pages for a particular product. The search history collection unit also allows the generation AI to suggest products based on the history of links clicked by the user. For example, if a user frequently clicks on links in a particular category, the generation AI will suggest products related to that category. The search history collection unit also allows the generation AI to analyze the user's interests in detail based on the history of links clicked by the user. For example, if a user frequently clicks on links for a particular brand, the generation AI will suggest products related to that brand. This allows the generation AI to suggest products based on information in which the user is actually interested.

[0072] The search history collection unit can use the emotion estimation function to analyze the user's emotions regarding the search keywords and suggest products related to the keywords that elicit positive emotions. The search history collection unit, for example, analyzes the user's emotions regarding the search keywords and identifies keywords that elicit positive emotions. For example, it can suggest products related to keywords that the user finds "fun." The search history collection unit can also analyze changes in emotions based on the user's search history, and the generation AI can suggest products based on this. For example, it can analyze the emotions when the user searches for a specific keyword and suggest products that elicit positive emotions. The search history collection unit can also analyze changes in emotions based on the user's search history, and the generation AI can suggest products based on this. For example, it can analyze the emotions when the user searches for a specific keyword and suggest products that elicit positive emotions. This makes it possible to suggest products related to keywords that elicit positive emotions.

[0073] The search history collection unit also integrates search histories from other search engines (such as Google and Bing), allowing the generation AI to perform a more multifaceted analysis of user interests. The search history collection unit, for example, collects search histories from other search engines and integrates them with data from the Yahoo! engine to perform a multifaceted analysis of user interests. For example, it integrates search histories from Google and Bing. The search history collection unit also allows the generation AI to perform a detailed analysis of user interests based on search histories from other search engines. For example, it compares keywords searched by a user on Google with keywords searched on the Yahoo! engine to identify common interests. The search history collection unit also allows the generation AI to perform a detailed analysis of user interests based on search histories from other search engines. For example, it compares keywords searched by a user on Google with keywords searched on the Yahoo! engine to identify common interests. This allows a more multifaceted analysis of user interests.

[0074] The search history collection unit links the search history with the content of posts on SNS, allowing the generation AI to analyze the user's entire online activity and utilize the results for product suggestions. The search history collection unit, for example, links the search history with the content of posts on SNS and analyzes the user's entire online activity. For example, it analyzes the content of posts on Twitter and Facebook and integrates it with the search history. The search history collection unit also allows the generation AI to analyze the user's interests in detail based on the content of posts on SNS. For example, it analyzes the topics that the user frequently posts on SNS and utilizes the results for product suggestions. The search history collection unit also allows the generation AI to analyze the user's interests in detail based on the content of posts on SNS. For example, it analyzes the topics that the user frequently posts on SNS and utilizes the results for product suggestions. This allows the user's entire online activity to be analyzed and utilized for product suggestions.

[0075] The search history collection unit can use the emotion estimation function to monitor the user's emotions based on the search history in real time and dynamically change the product suggestions in response to changes in emotion. The search history collection unit, for example, builds a system that monitors the user's emotions based on the search history in real time and dynamically changes the product suggestions in response to changes in emotion. For example, if the user is feeling stressed, relaxation-related products are suggested. The search history collection unit can also analyze the user's facial expressions and voice and change the product suggestions based on the emotion score. For example, if the user is relaxed, relaxation-related products are suggested. The search history collection unit can also analyze changes in emotion based on the user's biometric data and dynamically change the product suggestions. For example, an emotion score is calculated based on fluctuations in heart rate, and the product suggestions are changed. This makes it possible to dynamically change the product suggestions in response to changes in the user's emotions.

[0076] When generating the proposal content, the proposal generation unit also takes into account the user's past purchase history and can suggest products that are likely to be repeat purchases. The proposal generation unit, for example, collects the user's past purchase history and identifies products that are likely to be repeat purchases. For example, it suggests similar products based on products that are regularly purchased. The proposal generation unit can also use the generation AI to predict the possibility of repeat purchases based on the user's purchase history. For example, it can analyze the purchase frequency and purchase intervals of products that the user has purchased in the past and suggest products that are likely to be repeat purchases. The proposal generation unit can also use the generation AI to predict the possibility of repeat purchases based on the user's purchase history. For example, it can analyze the purchase frequency and purchase intervals of products that the user has purchased in the past and suggest products that are likely to be repeat purchases. This makes it possible to suggest products that are likely to be repeat purchases.

[0077] When generating the proposal content, the proposal generation unit also refers to the purchase histories of the user's friends and family, and can propose products that take social influence into consideration. The proposal generation unit, for example, collects the purchase histories of the user's friends and family, and proposes products that take social influence into consideration. For example, based on a product purchased by a friend, a similar product is proposed to the user. The proposal generation unit can also have the generation AI suggest products based on the purchase histories of the user's friends and family. For example, based on a product purchased by the user's friend, a similar product is proposed to the user. The proposal generation unit can also have the generation AI suggest products based on the purchase histories of the user's friends and family. For example, based on a product purchased by the user's friend, a similar product is proposed to the user. In this way, products can be proposed that take social influence into consideration.

[0078] The proposal generation unit can use the emotion estimation function to predict the emotional impact that the proposal content will have on the user and prioritize proposals that elicit positive emotions. The proposal generation unit can, for example, use the emotion estimation function to predict the emotional impact that the proposal content will have on the user. For example, it can prioritize proposals that the user finds "fun." The proposal generation unit can also have the generation AI adjust the proposal content based on the user's emotions. For example, if the user is relaxed, it can suggest relaxation-related products. The proposal generation unit can also have the generation AI adjust the proposal content based on the user's emotions. For example, if the user is relaxed, it can suggest relaxation-related products. This allows proposals that elicit positive emotions to be prioritized.

[0079] When generating proposal content, the proposal generation unit can propose merchandise that matches a season or event (Christmas, Valentine's Day, etc.). The proposal generation unit, for example, builds a system that proposes merchandise that matches a season or event. For example, Christmas-related products are proposed during the Christmas season. The proposal generation unit can also propose merchandise that matches a season or event based on the user's past purchase history. For example, a similar product is proposed based on a product that the user previously purchased during the Christmas season. The proposal generation unit can also propose merchandise that matches a season or event based on the user's past purchase history. For example, a similar product is proposed based on a product that the user previously purchased during the Christmas season. This makes it possible to propose merchandise that matches a season or event.

[0080] When generating proposal content, the proposal generation unit can consider the user's regional characteristics (climate, culture, etc.) and propose products suitable for the region. The proposal generation unit, for example, builds a system that considers the user's regional characteristics and proposes products suitable for the region. For example, it proposes winter gear to a user living in a cold region. The proposal generation unit can also have the generation AI propose products based on the user's regional characteristics. For example, it proposes related products based on the climate and culture of the region where the user lives. The proposal generation unit can also have the generation AI propose products based on the user's regional characteristics. For example, it proposes related products based on the climate and culture of the region where the user lives. This makes it possible to propose products suitable for the region.

[0081] The suggestion generation unit can use the emotion estimation function to monitor the emotional impact of the suggestion content on the user in real time and dynamically change the suggestion content in response to changes in emotion. The suggestion generation unit, for example, builds a system that monitors the emotional impact of the suggestion content on the user in real time and dynamically changes the suggestion content in response to changes in emotion. For example, if the user is feeling stressed, relaxation-related products are suggested. The suggestion generation unit can also analyze the user's facial expressions and voice and change the suggestion content based on the emotion score. For example, if the user is relaxed, relaxation-related products are suggested. The suggestion generation unit can also analyze changes in emotion based on the user's biometric data and dynamically change the suggestion content. For example, the suggestion generation unit calculates an emotion score based on fluctuations in heart rate and changes the suggestion content. This allows the suggestion content to be dynamically changed in response to changes in the user's emotion.

[0082] The display notification unit can customize the display method of the proposal content to suit the user's preferences and provide a visually attractive interface. The display notification unit, for example, builds a system that customizes the display method of the proposal content to suit the user's preferences. For example, the proposal content is displayed using the user's preferred colors and fonts. The display notification unit can also use the generation AI to suggest the optimal display method based on the user's past operation history. For example, the proposal content is customized based on display settings previously selected by the user. The display notification unit can also adjust the layout and design of the proposal content to suit the user's preferences. For example, the proposal content is displayed based on the user's preferred layout and design. This makes it possible to provide a visually attractive interface.

[0083] The display notification unit can optimize the timing of notification of suggested content to match the user's behavioral patterns and send notifications at the most effective timing. The display notification unit, for example, builds a system that optimizes the timing of notification of suggested content to match the user's behavioral patterns. For example, notifications are sent during times when the user frequently uses their smartphone. The display notification unit can also use a generation AI to suggest the optimal notification timing based on the user's past operation history. For example, the optimal notification timing is determined based on the user's reactions when receiving notifications in the past. The display notification unit can also adjust the frequency and timing of notifications based on the user's behavioral patterns. For example, if a user frequently uses their smartphone during a specific time period, notifications are sent during that time period. This allows notifications to be sent at the most effective timing.

[0084] The display notification unit can use the emotion estimation function to estimate the user's emotion at the time of notification and provide notification at a timing that elicits positive emotions. The display notification unit, for example, uses the emotion estimation function to build a system that estimates the user's emotion at the time of notification. For example, the notification is provided at a timing when the user is relaxed. The display notification unit can also analyze the user's facial expressions and voice and adjust the timing of the notification based on an emotion score. For example, if the user is relaxed, relaxation-related products are suggested. The display notification unit can also analyze changes in emotion based on the user's biometric data and adjust the timing of the notification. For example, an emotion score is calculated based on fluctuations in heart rate and the timing of the notification is adjusted. This makes it possible to provide notification at a timing that elicits positive emotions.

[0085] The display notification unit can notify the content of the proposal through multiple channels, such as social media and email, allowing the user to receive the proposal in the most convenient way. The display notification unit, for example, builds a system that notifies the content of the proposal through multiple channels, such as social media and email. For example, it allows the user to select the channel that is most convenient for them. The display notification unit can also use a generation AI to suggest the optimal notification channel based on the user's past operation history. For example, it can identify the optimal notification method based on channels that the user has used in the past. The display notification unit can also customize the notification channel to suit the user's preferences. For example, it can notify the content of the proposal based on the user's preferred notification method. This allows the user to receive the proposal in the most convenient way.

[0086] The display notification unit can display the proposed content using AR (augmented reality) technology, providing the user with an experience similar to actually trying out a product. The display notification unit, for example, builds a system that displays the proposed content using AR technology. For example, the display notification unit can provide the user with an experience similar to trying out a product through a smartphone. The display notification unit can also use a generating AI to propose the optimal AR experience based on the user's past operation history. For example, the display notification unit can make the optimal proposal based on AR experiences the user has used in the past. The display notification unit can also customize the AR experience to suit the user's preferences. For example, the display notification unit can display the proposed content based on the AR experience the user prefers. This can provide the user with an experience similar to actually trying out a product.

[0087] The display notification unit uses the emotion estimation function to monitor the user's emotion at the time of notification in real time, and can dynamically change the content and timing of the notification according to changes in emotion. The display notification unit, for example, uses the emotion estimation function to build a system that monitors the user's emotion at the time of notification in real time. For example, the notification is sent when the user is relaxed. The display notification unit can also analyze the user's facial expressions and voice and adjust the content and timing of the notification based on an emotion score. For example, if the user is relaxed, relaxation-related products are suggested. The display notification unit can also analyze changes in emotion based on the user's biometric data and adjust the content and timing of the notification. For example, an emotion score is calculated based on fluctuations in heart rate, and the content and timing of the notification are adjusted. This makes it possible to dynamically change the content and timing of the notification according to changes in emotion.

[0088] The proposal generation unit can develop an algorithm that extracts elements from the clustered ideas that are likely to work together, automatically generates candidate combinations, and filters the most promising combinations from among them. The proposal generation unit, for example, develops an algorithm that automatically generates candidate combinations and builds a system that filters the most promising combinations from among them. For example, filtering is performed based on technical feasibility and market demand. The proposal generation unit can also use a generative AI to propose optimal combinations based on the clustered ideas. For example, ideas from different industries can be combined to discover new market needs. The proposal generation unit can also use a generative AI to propose optimal combinations based on the clustered ideas. For example, ideas from different industries can be combined to discover new market needs. This makes it possible to develop an algorithm that filters the most promising combinations.

[0089] The proposal generation unit can extract elements from the clustered ideas that are likely to be effective when combined, set evaluation criteria for the combinations from various angles, and comprehensively evaluate technical feasibility, economic effectiveness, social impact, etc. The proposal generation unit, for example, sets evaluation criteria for the combinations from various angles and builds a system that comprehensively evaluates technical feasibility, economic effectiveness, social impact, etc. For example, it calculates a score for each criterion and performs an overall evaluation. The proposal generation unit can also use a generative AI to propose optimal combinations based on the clustered ideas. For example, it can combine ideas from different industries to discover new market needs. The proposal generation unit can also use a generative AI to propose optimal combinations based on the clustered ideas. For example, it can combine ideas from different industries to discover new market needs. This allows for a comprehensive evaluation of technical feasibility, economic effectiveness, social impact, etc.

[0090] The proposal generation unit extracts elements from the clustered ideas that are likely to work well together, and combines ideas from different industries and applications to discover new market needs. The proposal generation unit, for example, builds a system that combines ideas from different industries to discover new market needs. For example, it generates ideas that combine the technology field with the consumer market. The proposal generation unit can also use a generation AI to propose optimal combinations based on the clustered ideas. For example, it can combine ideas from different industries to discover new market needs. The proposal generation unit can also use a generation AI to propose optimal combinations based on the clustered ideas. For example, it can combine ideas from different industries to discover new market needs. This makes it possible to combine ideas from different industries and applications to discover new market needs.

[0091] The proposal generation unit can introduce an agile methodology in which elements that are likely to work well together can be extracted from the clustered ideas, the combined idea can be implemented as a prototype, and the idea can be improved based on feedback. The proposal generation unit can, for example, build a system that introduces an agile methodology in which the combined idea can be implemented as a prototype and improved based on user feedback. For example, a prototype can be developed in a short period of time and user opinions can be reflected. The proposal generation unit can also use a generation AI to propose optimal combinations based on the clustered ideas. For example, ideas from different industries can be combined to discover new market needs. The proposal generation unit can also use a generation AI to propose optimal combinations based on the clustered ideas. For example, ideas from different industries can be combined to discover new market needs. This makes it possible to introduce an agile methodology in which a prototype can be implemented and improved based on feedback.

[0092] The proposal generation unit extracts elements from the clustered ideas that are likely to work well together, and uses an emotion estimation function to monitor users' emotional reactions to the combined ideas in real time, continuously searching for optimal combinations. The proposal generation unit, for example, uses the emotion estimation function to develop a system that monitors users' emotional reactions to the combined ideas in real time. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. The proposal generation unit can also use a generation AI to propose optimal combinations based on the clustered ideas. For example, it can combine ideas from different industries to discover new market needs. The proposal generation unit can also use a generation AI to propose optimal combinations based on the clustered ideas. For example, it can combine ideas from different industries to discover new market needs. This makes it possible to monitor users' emotional reactions in real time and continuously search for optimal combinations.

[0093] When the generation AI automatically proposes a new plan based on the extracted elements, the proposal generation unit can learn from past successes and failures and generate a proposal with the highest probability of success. For example, the proposal generation unit has the generation AI learn from past successes and failures and generate a proposal with a high probability of success when proposing a new plan. For example, the proposal generation unit automatically generates an optimal plan based on past data. The proposal generation unit can also adjust the proposal content based on past successes and failures. For example, the generation AI can refer to past successes and make a proposal under similar conditions. The proposal generation unit can also adjust the proposal content based on past successes and failures. For example, the generation AI can refer to past successes and make a proposal under similar conditions. In this way, the generation AI can learn from past successes and failures and generate a proposal with the highest probability of success.

[0094] When the generation AI automatically proposes a new plan based on the extracted elements, the proposal generation unit collects user feedback on the proposed plan in real time and can make instant improvements. The proposal generation unit, for example, builds a system that collects user feedback on proposed plans in real time and makes instant improvements based on the results. For example, it uses an online survey or comment function. The proposal generation unit can also allow the generation AI to adjust the proposal content based on user feedback. For example, it can improve the proposal content by reflecting user opinions. The proposal generation unit can also allow the generation AI to adjust the proposal content based on user feedback. For example, it can improve the proposal content by reflecting user opinions. This allows user feedback to be collected in real time and makes instant improvements.

[0095] When the generation AI automatically proposes a new plan based on the extracted elements, the proposal generation unit can use the emotion estimation function to make personalized proposals based on the user's emotions. The proposal generation unit, for example, uses the emotion estimation function to build a system that makes personalized plan proposals based on the user's emotions. For example, the proposal generation unit proposes optimal plans based on the user's emotion score. The proposal generation unit can also adjust the proposal content based on the user's emotions. For example, if the user is relaxing, the proposal generation unit can propose relaxation-related plans. The proposal generation unit can also adjust the proposal content based on the user's emotions. For example, if the user is relaxing, the proposal generation unit can propose relaxation-related plans. This makes it possible to make personalized proposals based on the user's emotions.

[0096] When the generation AI automatically proposes a new plan based on the extracted elements, the proposal generation unit can automatically generate plan proposals specialized for different markets or regions. The proposal generation unit, for example, uses the generation AI to build a system that automatically generates plan proposals specialized for different markets or regions. For example, it makes proposals according to market needs and regional characteristics. The proposal generation unit can also adjust the proposal content based on the characteristics of the market or region. For example, it can propose similar products based on products that are popular in a specific region. The proposal generation unit can also adjust the proposal content based on the characteristics of the market or region. For example, it can propose similar products based on products that are popular in a specific region. This makes it possible to automatically generate plan proposals specialized for different markets or regions.

[0097] When the generation AI automatically proposes a new plan based on the extracted elements, the proposal generation unit can automatically generate a visual prototype of the proposed plan to make it easier to understand visually. The proposal generation unit, for example, uses the generation AI to develop a system that automatically generates a visual prototype of a proposed plan. For example, it visually displays a product design or a service flow. The proposal generation unit can also have the generation AI adjust the visual prototype based on user feedback. For example, it can reflect user opinions and improve the prototype. The proposal generation unit can also have the generation AI adjust the visual prototype based on user feedback. For example, it can reflect user opinions and improve the prototype. In this way, a visual prototype of the proposed plan can be automatically generated to make it easier to understand visually.

[0098] When the generation AI automatically proposes new projects based on the extracted elements, the proposal generation unit uses the emotion estimation function to monitor the user's emotional response to the new project proposals, thereby continuously improving the quality of the proposals. The proposal generation unit, for example, uses the emotion estimation function to develop a system that monitors the user's emotional response to new project proposals in real time. For example, the proposal generation unit analyzes the user's facial expressions and voice and calculates an emotion score. The proposal generation unit can also adjust the proposal content based on the user's emotional response. For example, if the user is relaxing, the generation AI can propose relaxation-related projects. The proposal generation unit can also adjust the proposal content based on the user's emotional response. For example, if the user is relaxing, the generation AI can propose relaxation-related projects. This makes it possible to monitor the user's emotional response and continuously improve the quality of the proposals.

[0099] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0100] The recommendation system can further include a purchase history collection unit that collects the user's purchase history. The purchase history collection unit, for example, collects data on products purchased by the user in the past, and the generation AI suggests products based on this. For example, similar products can be suggested based on products that the user purchases regularly. The purchase history collection unit can also allow the generation AI to predict the possibility of repeat purchases based on the user's purchase history. For example, the purchase history collection unit can analyze the purchase frequency and purchase intervals of products purchased by the user in the past, and suggest products that are likely to be purchased again. This makes it possible to suggest products based on the user's purchase history.

[0101] The recommendation system can further include a social purchase history collection unit that collects the purchase histories of the user's friends and family. The social purchase history collection unit, for example, collects data on products purchased by the user's friends and family, and the generation AI suggests products based on this data. For example, based on products purchased by friends, similar products may be suggested to the user. The social purchase history collection unit can also allow the generation AI to suggest products based on the purchase histories of the user's friends and family. For example, based on products purchased by the user's friends, similar products may be suggested to the user. This makes it possible to suggest products that take social influence into consideration.

[0102] The proposal system can further include a regional characteristics collection unit that takes into account the regional characteristics of the user. The regional characteristics collection unit, for example, collects information about the climate and culture of the region where the user lives, and the generation AI proposes products based on this information. For example, it proposes cold weather gear to a user who lives in a cold region. The regional characteristics collection unit can also allow the generation AI to propose products based on the user's regional characteristics. For example, it proposes related products based on the climate and culture of the region where the user lives. This makes it possible to propose products that are suitable for the region.

[0103] The recommendation system can further include a seasonal event collection unit that suggests products that match the season or event. The seasonal event collection unit collects event information, such as Christmas or Valentine's Day, and the generation AI suggests products based on this information. For example, Christmas-related products are suggested during the Christmas season. The seasonal event collection unit can also suggest products that match the season or event based on the user's past purchase history. For example, similar products are suggested based on products that the user previously purchased during the Christmas season. This makes it possible to suggest products that match the season or event.

[0104] The proposal system can further include an online activity collection unit that analyzes the user's overall online activity. The online activity collection unit, for example, links search history and social media postings, and the generation AI analyzes the user's overall online activity. For example, it analyzes the content of posts on Twitter and Facebook and integrates it with the search history. The online activity collection unit can also allow the generation AI to perform a detailed analysis of the user's interests based on the content of social media posts. For example, it can analyze topics that the user frequently posts about on social media and suggest related products. This allows the user's overall online activity to be analyzed and used to suggest products.

[0105] The proposal system can further include an emotional impact prediction unit that estimates the user's emotions and predicts the emotional impact that the proposed content will have on the user. The emotional impact prediction unit, for example, uses an emotion estimation function to predict the emotional impact that the proposed content will have on the user. For example, it prioritizes suggestions that the user finds "fun." The emotional impact prediction unit can also have the generation AI adjust the proposed content based on the user's emotions. For example, if the user is relaxed, it will suggest products related to relaxation. This makes it possible to make suggestions that elicit positive emotions.

[0106] The suggestion system may further include an emotion dynamic change unit that monitors the user's emotions in real time and dynamically changes the suggestion content in response to changes in the user's emotions. The emotion dynamic change unit, for example, monitors the emotional impact of the suggestion content on the user in real time and dynamically changes the suggestion content in response to changes in the user's emotions. For example, if the user is feeling stressed, the suggestion content may be relaxation-related. The emotion dynamic change unit may also analyze the user's facial expressions and voice and change the suggestion content based on the emotion score. This makes it possible to suggest products in response to changes in the user's emotions.

[0107] The suggestion system may further include a real-time emotion monitor that estimates the user's emotions and monitors the emotional impact of the suggested content on the user in real time. The real-time emotion monitor monitors, for example, the emotional impact of the suggested content on the user in real time and dynamically changes the suggested content according to changes in emotions. For example, if the user is feeling stressed, it may suggest relaxation-related products. The real-time emotion monitor may also analyze the user's facial expressions and voice and change the suggested content based on the emotion score. This makes it possible to suggest products according to changes in the user's emotions.

[0108] The proposal system can further include an emotional impact prediction unit that estimates the user's emotions and predicts the emotional impact that the proposed content will have on the user. The emotional impact prediction unit, for example, uses an emotion estimation function to predict the emotional impact that the proposed content will have on the user. For example, it prioritizes suggestions that the user finds "fun." The emotional impact prediction unit can also have the generation AI adjust the proposed content based on the user's emotions. For example, if the user is relaxed, it will suggest products related to relaxation. This makes it possible to make suggestions that elicit positive emotions.

[0109] The suggestion system may further include an emotion dynamic change unit that monitors the user's emotions in real time and dynamically changes the suggestion content in response to changes in the user's emotions. The emotion dynamic change unit, for example, monitors the emotional impact of the suggestion content on the user in real time and dynamically changes the suggestion content in response to changes in the user's emotions. For example, if the user is feeling stressed, the suggestion content may be relaxation-related. The emotion dynamic change unit may also analyze the user's facial expressions and voice and change the suggestion content based on the emotion score. This makes it possible to suggest products in response to changes in the user's emotions.

[0110] The processing flow of the second embodiment will be briefly explained below.

[0111] Step 1: The app information collection unit collects information about apps installed on the smartphone itself. For example, it analyzes the apps that the user uses most frequently, the types of apps that were recently installed, and the frequency and duration of app use, and understands the user's interests based on the app usage history. Step 2: The search history collection unit collects the user's search history on the Yahoo! search engine. For example, it analyzes the user's recent search keywords, frequently searched topics, and patterns of search history by time of day and day of the week, and understands the user's lifestyle based on the time of day of the search history. Step 3: The generation AI analyzes the app information and search history collected by the app information collection unit and search history collection unit, thereby gaining a detailed understanding of the user's behavioral patterns and interests. Step 4: The proposal generation unit proposes optimal SB products to the user based on the app information and search history analyzed by the generation AI. For example, if the user uses many health-related apps and frequently searches for health-related information, the unit will propose health-related SB products. Step 5: The display / notification unit displays or notifies the user of the proposal content generated by the proposal generation unit. For example, the display / notification unit may display the proposal content as "products recommended for you" on the home screen of the app or may notify the user of the proposal content using a push notification.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0146] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] 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.

[0166] 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."

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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, in order to avoid confusion and to 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.

[0178] 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]

[0179] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an application information collection unit that collects application information installed on the smartphone; A generation AI that analyzes the application information collected by the application information collection unit; a search history collection unit that collects the user's search history on the Yahoo! search engine; A generation AI that analyzes the search history collected by the search history collection unit; a proposal generation unit that proposes optimal SB products to users based on the application information and search history analyzed by the generation AI; a display / notification unit that displays or notifies the user of the proposal content generated by the proposal generation unit; A system characterized by:

2. The application information collection unit The AI ​​collects not only the time and frequency of app usage, but also specific operation history within the app, and then analyzes the user's behavioral patterns in detail.

2. The system of claim 1.

3. The application information collection unit The AI ​​collects sensor information (GPS, accelerometer, etc.) from the smartphone, analyzes the user's movement patterns and activity levels, and uses this information to propose products.

2. The system of claim 1.

4. The search history collection unit By analyzing patterns in search history by time of day and day of the week, the AI ​​generator will suggest products that fit the user's lifestyle.

2. The system of claim 1.

5. The proposal generation unit When generating recommendations, the system also takes into account the user's past purchase history and suggests products that are likely to be purchased again.

2. The system of claim 1.

6. The display notification unit Customize how suggestions are displayed to suit your preferences and provide a visually appealing interface 2. The system of claim 1.

7. The application information collection unit It estimates the user's emotions while using the app, and if the user uses many apps that evoke positive emotions, it suggests products that match those emotions.

2. The system of claim 1.

8. The search history collection unit Analyze users' feelings about search keywords and suggest products related to keywords that evoke positive emotions 2. The system of claim 1.

Images