System

Abstract

The system according to the embodiment aims to provide a user with a new discovery or encounter value.SOLUTION: A system according to an embodiment includes a reception unit, an analysis unit, a proposal unit, and a learning unit. The reception unit receives a search query or an image or a sound from a user. The analysis unit analyzes the data received by the reception unit and searches for a related place. The suggestion unit suggests the search result obtained by the analysis unit to the user. The learning unit collects feedback of the user with respect to the place proposed by the proposing unit and uses the feedback as learning data of the analyzing 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 technology only provides map searches based on limited information such as addresses and names, and there is room for improvement in terms of providing the value of new discoveries and encounters.

[0005] The system according to the embodiment aims to provide users with the value of new discoveries and encounters. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a proposal unit, and a learning unit. The reception unit accepts search queries, images, or audio from a user. The analysis unit analyzes the data accepted by the reception unit and searches for related places. The proposal unit proposes search results obtained by the analysis unit to the user. The learning unit collects user feedback on places proposed by the proposal unit and uses the feedback as learning data for the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can provide users with the value of new discoveries and encounters. [Brief explanation of the drawings]

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

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

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

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

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

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention incorporates multimodal AI functionality into a map, providing a new search method beyond address-based or name-based map searches. When users search maps using a smartphone or car navigation system, this system offers a new search method utilizing multimodal AI functionality in addition to traditional address-based or name-based search methods. For example, when a user enters an ambiguous search query such as "good restaurants nearby" or "children's parks," the multimodal AI analyzes the query and suggests appropriate locations. The multimodal AI then considers contextual information, such as the user's past search history, current location, and time of day, to provide more personalized search results. Furthermore, multimodal AI can also perform searches using multimodal data such as images and audio. For example, when a user uploads a photo taken with their smartphone, the system can search for related places based on the photo. Voice input also allows users to search simply by speaking. This system enables users to discover new places and experiences that could not be found using traditional search methods. The system also collects user feedback and continuously learns to improve the accuracy of search results. For example, when a user rates a suggested place, the rating data is fed back to the multimodal AI and reflected in the next search results. This allows the system to continue to evolve to suit the user's preferences and needs. This allows the system to provide users with the value of new discoveries and encounters. For example, users can discover new places and experiences that they would not have been able to find using traditional search methods, improving user convenience. The system also continues to evolve to suit the user's preferences and needs by collecting user feedback and continuously learning to improve the accuracy of search results.

[0029] A search system according to an embodiment includes a receiving unit, an analysis unit, a suggestion unit, and a learning unit. The receiving unit receives a search query, an image, or a voice from a user. For example, the receiving unit receives a search query in text format entered by a user. The receiving unit can also receive images uploaded by a user. The receiving unit can also receive voice spoken by a user. The analysis unit analyzes the data received by the receiving unit and searches for related places. For example, the analysis unit analyzes images using deep learning technology. The analysis unit can also analyze voice using natural language processing technology. The analysis unit can also provide personalized search results by taking into account context information such as a user's past search history, current location information, and time of day. The suggestion unit suggests search results obtained by the analysis unit to a user. For example, the suggestion unit provides personalized search results by taking into account context information such as a user's past search history, current location information, and time of day. The suggestion unit can also reflect data on places rated by the user in subsequent search results. The learning unit collects user feedback on places suggested by the suggestion unit and uses the feedback as learning data for the analysis unit. For example, the learning unit collects data on users' evaluations of suggested places and uses the evaluation data as learning data for the analysis unit. As a result, the search system according to the embodiment can provide users with new search methods by accepting, analyzing, suggesting, and collecting feedback on users' search queries, images, and voices.

[0030] The reception unit can analyze the user's past search history and select a reception method. For example, the reception unit can automatically display search queries that the user has frequently input in the past as candidates. The reception unit can also prioritize and suggest input methods (voice, text, etc.) that the user has used in the past. The reception unit can also predict and suggest search queries to be used in a specific time period based on the user's past search history. This makes it possible to provide an optimal reception method by analyzing the user's past search history. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input the user's past search history data into a generation AI and have the generation AI select an optimal reception method.

[0031] The reception unit can perform filtering based on the user's current location information and time period when receiving a search query. For example, the reception unit can prioritize displaying search results that are close to the user's current location. The reception unit can also predict places the user will visit during a specific time period and filter the search results. The reception unit can also provide optimal search results based on the user's current location information. This makes it possible to provide more relevant search results by filtering the search results based on the user's current location information and time period. Some or all of the above-described processing in the reception unit can be performed using, or without, AI, for example. For example, the reception unit can input the user's location information data to a generation AI and have the generation AI perform filtering.

[0032] When receiving a search query, the reception unit can select a reception means according to the user's input method. For example, when the user inputs a search query by voice, the reception unit analyzes the query using voice recognition technology. Furthermore, when the user uploads an image, the reception unit can search for related places using image recognition technology. Furthermore, when the user inputs a search query by text, the reception unit can analyze the query using natural language processing technology. This allows for selecting the optimal reception means according to the user's input method, thereby providing a smoother search experience. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's voice data to a generation AI and have the generation AI perform voice recognition.

[0033] The analysis unit can analyze images using deep learning technology and audio using natural language processing technology. The analysis unit can analyze images using, for example, deep learning technology. For example, the analysis unit can extract image features using a convolutional neural network (CNN) and identify related locations. The analysis unit can also analyze image time series data using a recurrent neural network (RNN). The analysis unit can also analyze audio using natural language processing technology. For example, the analysis unit can convert audio data into text using morphological analysis and perform grammatical analysis. The analysis unit can also understand the meaning of audio data and identify related locations using semantic analysis. This improves the accuracy of image and audio analysis by using deep learning technology and natural language processing technology. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input a user's image data into a generation AI and have the generation AI perform image analysis.

[0034] The suggestion unit can provide personalized search results by taking into account the user's past search history or context information such as current location information and time of day. The suggestion unit can provide personalized search results by taking into account, for example, the user's past search history. For example, the suggestion unit can suggest related places based on data on places the user has previously searched for or rated. The suggestion unit can also provide personalized search results by taking into account the user's current location information. For example, the suggestion unit can prioritize suggesting places close to the user's current location. The suggestion unit can also provide personalized search results by taking into account the user's time of day. For example, the suggestion unit can predict places the user will visit during a specific time of day and suggest related places. This makes it possible to provide more personalized search results by taking into account the user's context information. Some or all of the above-described processing in the suggestion unit can be performed using AI, for example, or without AI. For example, the suggestion unit can input the user's context information into a generation AI and cause the generation AI to generate personalized search results.

[0035] The learning unit can collect user feedback and use it as learning data for the analysis unit. For example, the learning unit can collect data on users' ratings of suggested places and use the rating data as learning data for the analysis unit. The learning unit can also collect user comments and behavioral data and use it as learning data for the analysis unit. For example, the learning unit can collect ratings and comments made by users on suggested places and use the data as learning data for the analysis unit. The learning unit can also collect user behavioral data (e.g., visit history and stay time) and use it as learning data for the analysis unit. In this way, by collecting user feedback, the analysis unit can use it as learning data to improve the accuracy of the system. Some or all of the above-mentioned processing in the learning unit can be performed, for example, using AI or without AI. For example, the learning unit can input user feedback data to the generation AI and cause the generation AI to update the learning data.

[0036] The suggestion unit can reflect the data of places rated by the user in the next search results. The suggestion unit, for example, reflects the data of places rated by the user in the next search results. For example, the suggestion unit prioritizes suggesting places that the user has given a high rating. The suggestion unit can also exclude places that the user has given a low rating from the search results. The suggestion unit can also personalize the next search results based on the user's rating data. For example, the suggestion unit analyzes data of places rated by the user and provides search results tailored to the user's preferences and needs. This enables more accurate suggestions by reflecting the data of places rated by the user in the next search results. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input the user's rating data into a generation AI and cause the generation AI to generate the next search results.

[0037] When receiving a search query, the reception unit can prioritize receiving highly relevant queries by taking into account the user's geographical location information. For example, the reception unit can prioritize displaying search results that are close to the user's current location. Furthermore, if the user is in a specific area, the reception unit can prioritize receiving queries related to that area. Furthermore, the reception unit can provide optimal search results based on the user's geographical location information. In this way, by taking the user's geographical location information into account, highly relevant queries can be prioritized. Some or all of the above-described processing by the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit can input the user's location information data to a generation AI and cause the generation AI to prioritize highly relevant queries.

[0038] The reception unit can analyze the user's social media activity when receiving a search query and receive related queries. For example, the reception unit can preferentially receive queries related to places where the user has checked in on social media. The reception unit can also analyze the content of the user's social media posts and receive related queries. The reception unit can also receive related queries by referring to the activities of the user's friends on social media. In this way, related queries can be received by analyzing the user's social media activity. Some or all of the above-described processing by the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input the user's social media data into a generation AI and cause the generation AI to receive related queries.

[0039] The reception unit can customize the reception method by reflecting the user's past feedback when receiving a search query. The reception unit can, for example, suggest an optimal reception method based on search results previously evaluated by the user. The reception unit can also analyze the user's past feedback and customize the reception method. The reception unit can also suggest an optimal search query based on the user's past feedback. In this way, the reception method can be customized by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input the user's feedback data into a generation AI and cause the generation AI to customize the reception method.

[0040] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the search query. For example, the analysis unit provides detailed analysis results for queries with high importance. The analysis unit can also provide concise analysis results for queries with low importance. The analysis unit can also dynamically adjust the level of detail of the analysis according to the importance. This makes it possible to provide more appropriate analysis results by adjusting the level of detail of the analysis based on the importance of the search query. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input importance data of the search query to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0041] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the search query. For example, in the case of a restaurant search, the analysis unit can apply an analysis algorithm that emphasizes user reviews and ratings. In addition, in the case of a park search, the analysis unit can apply an analysis algorithm that emphasizes facility information and access information. In addition, in the case of a shopping search, the analysis unit can apply an analysis algorithm that emphasizes product inventory status and price information. In this way, by applying different analysis algorithms depending on the category of the search query, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input search query category data to the generation AI and cause the generation AI to apply the analysis algorithm.

[0042] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, optimizes the analysis algorithm based on analysis results previously evaluated by the user. The analysis unit can also analyze the user's past analysis results to improve the accuracy of the analysis. The analysis unit can also suggest an optimal analysis method by referring to the user's past analysis results. In this way, the accuracy of the analysis can be improved by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past analysis result data into the generation AI and cause the generation AI to optimize the analysis algorithm.

[0043] During analysis, the analysis unit can determine the analysis priority based on the submission time of the search query. For example, the analysis unit prioritizes analysis of queries with high urgency. The analysis unit can also prioritize analysis of queries submitted earlier. The analysis unit can also dynamically adjust the analysis priority based on the submission time. This makes it possible to provide more appropriate analysis results by determining the analysis priority based on the submission time of the search query. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input search query submission time data into the generation AI and have the generation AI determine the analysis priority.

[0044] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the search queries. For example, the analysis unit prioritizes analysis of highly relevant queries. The analysis unit can also postpone analysis of less relevant queries. The analysis unit can also dynamically adjust the order of analysis based on the relevance. This makes it possible to provide more appropriate analysis results by adjusting the order of analysis based on the relevance of the search queries. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input relevance data of the search queries to the generation AI and cause the generation AI to adjust the order of analysis.

[0045] During analysis, the analysis unit can adjust the use of technical terminology in the analysis according to the user's level of expertise. For example, the analysis unit can provide analysis results that use a lot of technical terminology to a user with high levels of expertise. The analysis unit can also provide concise and easy-to-understand analysis results to a user with low levels of expertise. The analysis unit can also dynamically adjust the use of technical terminology in the analysis according to the user's level of expertise. This makes it possible to provide more appropriate analysis results by adjusting the use of technical terminology in the analysis according to the user's level of expertise. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's level of expertise data into a generation AI and have the generation AI execute the use of technical terminology.

[0046] The suggestion unit can adjust the level of detail of the suggestion based on the importance of the search result when making a suggestion. For example, the suggestion unit provides a detailed suggestion for a search result with high importance. The suggestion unit can also provide a concise suggestion for a search result with low importance. The suggestion unit can also dynamically adjust the level of detail of the suggestion according to the importance. As a result, by adjusting the level of detail of the suggestion based on the importance of the search result, more appropriate suggestions can be provided. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input importance data of the search result to the generation AI and cause the generation AI to adjust the level of detail of the suggestion.

[0047] When making a suggestion, the suggestion unit can apply different suggestion algorithms depending on the category of the search result. For example, in the case of a restaurant search, the suggestion unit can apply a suggestion algorithm that emphasizes user reviews and ratings. In addition, in the case of a park search, the suggestion unit can apply a suggestion algorithm that emphasizes facility information and access information. In addition, in the case of a shopping search, the suggestion unit can apply a suggestion algorithm that emphasizes product inventory status and price information. In this way, by applying different suggestion algorithms depending on the category of the search result, more appropriate suggestions can be provided. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input category data of the search result to the generation AI and cause the generation AI to apply the suggestion algorithm.

[0048] When making a proposal, the suggestion unit can improve the accuracy of the proposal by referring to the user's past proposal results. The suggestion unit, for example, optimizes the proposal algorithm based on proposal results previously evaluated by the user. The suggestion unit can also analyze the user's past proposal results to improve the accuracy of the proposal. The suggestion unit can also suggest an optimal proposal method by referring to the user's past proposal results. In this way, the accuracy of the proposal can be improved by referring to the user's past proposal results. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input the user's past proposal result data into the generation AI and cause the generation AI to optimize the proposal algorithm.

[0049] When making a proposal, the suggestion unit can determine the priority of the proposal based on the submission time of the search results. For example, the suggestion unit can prioritize suggesting search results with a high urgency. The suggestion unit can also prioritize suggesting search results that were submitted earlier. The suggestion unit can also dynamically adjust the priority of the proposal based on the submission time. This makes it possible to provide more appropriate proposals by determining the priority of the proposal based on the submission time of the search results. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input data on the submission time of the search results into the generation AI and cause the generation AI to determine the priority of the proposals.

[0050] The suggestion unit can adjust the order of suggestions based on the relevance of search results when making suggestions. For example, the suggestion unit prioritizes suggesting highly relevant search results. The suggestion unit can also postpone less relevant search results. The suggestion unit can also dynamically adjust the order of suggestions based on the relevance. This makes it possible to provide more appropriate suggestions by adjusting the order of suggestions based on the relevance of search results. Some or all of the above-described processing in the suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the suggestion unit can input relevance data of search results to a generation AI and cause the generation AI to adjust the order of suggestions.

[0051] When making a proposal, the suggestion unit can adjust the use of technical terminology in the proposal according to the user's level of expertise. For example, the suggestion unit can provide a proposal that uses a lot of technical terminology to a user with high technical expertise. The suggestion unit can also provide a concise and easy-to-understand proposal to a user with low technical expertise. The suggestion unit can also dynamically adjust the use of technical terminology in the proposal according to the user's level of expertise. This makes it possible to provide more appropriate proposals by adjusting the use of technical terminology in the proposal according to the user's level of expertise. Some or all of the above-described processing in the suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the suggestion unit can input the user's level of expertise data to a generation AI and cause the generation AI to execute the use of technical terminology.

[0052] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on past learning data. The learning unit can also analyze past learning data to improve the accuracy of the learning algorithm. The learning unit can also dynamically adjust the learning algorithm by referring to past learning data. In this way, the learning algorithm can be optimized by referring to past learning data. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input past learning data into a generation AI and cause the generation AI to optimize the learning algorithm.

[0053] The learning unit can update the learning data by reflecting user feedback during learning. The learning unit updates the learning data based on, for example, feedback evaluated by the user. The learning unit can also analyze the user feedback and improve the accuracy of the learning data. The learning unit can also dynamically update the learning data by referring to the user feedback. In this way, the learning data can be updated by reflecting the user feedback. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input user feedback data into the generation AI and cause the generation AI to update the learning data.

[0054] During learning, the learning unit can weight the learning data based on the time of submission of the search query. For example, the learning unit weights the learning data by prioritizing recently submitted search queries. The learning unit can also weight the learning data by disregarding older submitted search queries. The learning unit can also dynamically adjust the weighting of the learning data based on the submission time. This allows for more appropriate learning by weighting the learning data based on the submission time of the search query. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input search query submission time data into the generation AI and cause the generation AI to weight the learning data.

[0055] During learning, the learning unit can integrate information from different data sources to enrich the training data. For example, the learning unit can integrate data from social media to enrich the training data. The learning unit can also integrate information from public databases to enrich the training data. The learning unit can also integrate user feedback to enrich the training data. This allows the training data to be enriched by integrating information from different data sources. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input data from different data sources into the generation AI and cause the generation AI to integrate the data.

[0056] During learning, the learning unit can select learning data based on the user's interests. For example, the learning unit selects data related to topics in which the user is interested as learning data. The learning unit can also select data that is likely to be of interest to the user based on the user's past search history as learning data. The learning unit can also analyze the user's social media activities and select data that is likely to be of interest to the user as learning data. This allows for more appropriate learning by selecting learning data based on the user's interests. Some or all of the above-described processing in the learning unit may be performed using, or without, AI. For example, the learning unit can input the user's interest data into the generation AI and have the generation AI select the learning data.

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

[0058] When accepting a user's search query, the acceptance unit can adjust the display method of search results taking into account the remaining battery level of the user's device. For example, when the remaining battery level is low, the acceptance unit can display simple search results consisting of only text. When the remaining battery level is sufficient, the acceptance unit can also display rich search results including images and videos. Furthermore, when the remaining battery level is moderate, the acceptance unit can also display search results that combine text and some images. This makes it possible to provide an optimal display method of search results depending on the remaining battery level of the user's device.

[0059] When analyzing a user's search query, the analysis unit can adjust the level of analysis detail taking into account the user's Internet connection speed. For example, if the Internet connection speed is slow, the analysis unit can provide a concise analysis result. If the Internet connection speed is fast, the analysis unit can provide a detailed analysis result. Furthermore, if the Internet connection speed is medium, the analysis unit can provide an analysis result with a moderate level of detail. This allows the analysis unit to provide optimal analysis results according to the user's Internet connection speed.

[0060] When making suggestions for a user's search query, the suggestion unit can adjust how the suggestions are displayed, taking into account the screen size of the user's device. For example, when the screen size is small, the suggestion unit can display simple text-only suggestions. When the screen size is large, the suggestion unit can display rich suggestions that include images and videos. Furthermore, when the screen size is medium, the suggestion unit can display suggestions that combine text and some images. This makes it possible to provide an optimal way to display suggestions depending on the screen size of the user's device.

[0061] When collecting user feedback, the learning unit can adjust the update frequency of the learning data taking into account the frequency of the user feedback. For example, if the frequency of feedback is high, the learning unit can update the learning data frequently. Also, if the frequency of feedback is low, the learning unit can reduce the update frequency of the learning data. Furthermore, if the frequency of feedback is medium, the learning unit can update the learning data at an appropriate frequency. This makes it possible to provide an optimal update frequency of the learning data according to the frequency of user feedback.

[0062] When accepting a user's search query, the accepting unit can adjust the method of accepting the search query by taking into account the user's device usage history. For example, the accepting unit can identify applications frequently used by the user from the device usage history and preferentially accept search queries related to those applications. The accepting unit can also predict applications that the user will use during a specific time period from the device usage history and preferentially accept search queries related to that time period. Furthermore, the accepting unit can analyze the user's preferences from the device usage history and suggest search queries that match the user's preferences. This makes it possible to provide an optimal method of accepting search queries according to the user's device usage history.

[0063] The processing flow of the first embodiment will be briefly explained below.

[0064] Step 1: The reception unit receives a search query, an image, or a voice from a user. For example, the reception unit can receive a text search query entered by a user, an uploaded image, or a spoken voice. Step 2: The analysis unit analyzes the data received by the reception unit and searches for related places. For example, it uses deep learning technology to analyze images and natural language processing technology to analyze voice. It can also provide personalized search results by taking into account context information such as the user's past search history, current location, and time of day. Step 3: The suggestion unit suggests the search results obtained by the analysis unit to the user. For example, it provides personalized search results by taking into account the user's past search history, current location, time of day, and other contextual information. It can also reflect the location data rated by the user in the next search results. Step 4: The learning unit collects user feedback on the places suggested by the suggestion unit and uses it as learning data for the analysis unit. For example, data on users' ratings of the suggested places is collected and the rating data is used as learning data for the analysis unit.

[0065] (Example 2) A system according to an embodiment of the present invention incorporates multimodal AI functionality into a map, providing a new search method beyond address-based or name-based map searches. When users search maps using a smartphone or car navigation system, this system offers a new search method utilizing multimodal AI functionality in addition to traditional address-based or name-based search methods. For example, when a user enters an ambiguous search query such as "good restaurants nearby" or "children's parks," the multimodal AI analyzes the query and suggests appropriate locations. The multimodal AI then considers contextual information, such as the user's past search history, current location, and time of day, to provide more personalized search results. Furthermore, multimodal AI can also perform searches using multimodal data such as images and audio. For example, when a user uploads a photo taken with their smartphone, the system can search for related places based on the photo. Voice input also allows users to search simply by speaking. This system enables users to discover new places and experiences that could not be found using traditional search methods. The system also collects user feedback and continuously learns to improve the accuracy of search results. For example, when a user rates a suggested place, the rating data is fed back to the multimodal AI and reflected in the next search results. This allows the system to continue to evolve to suit the user's preferences and needs. This allows the system to provide users with the value of new discoveries and encounters. For example, users can discover new places and experiences that they would not have been able to find using traditional search methods, improving user convenience. The system also continues to evolve to suit the user's preferences and needs by collecting user feedback and continuously learning to improve the accuracy of search results.

[0066] A search system according to an embodiment includes a receiving unit, an analysis unit, a suggestion unit, and a learning unit. The receiving unit receives a search query, an image, or a voice from a user. For example, the receiving unit receives a search query in text format entered by a user. The receiving unit can also receive images uploaded by a user. The receiving unit can also receive voice spoken by a user. The analysis unit analyzes the data received by the receiving unit and searches for related places. For example, the analysis unit analyzes images using deep learning technology. The analysis unit can also analyze voice using natural language processing technology. The analysis unit can also provide personalized search results by taking into account context information such as a user's past search history, current location information, and time of day. The suggestion unit suggests search results obtained by the analysis unit to a user. For example, the suggestion unit provides personalized search results by taking into account context information such as a user's past search history, current location information, and time of day. The suggestion unit can also reflect data on places rated by the user in subsequent search results. The learning unit collects user feedback on places suggested by the suggestion unit and uses the feedback as learning data for the analysis unit. For example, the learning unit collects data on users' evaluations of suggested places and uses the evaluation data as learning data for the analysis unit. As a result, the search system according to the embodiment can provide users with new search methods by accepting, analyzing, suggesting, and collecting feedback on users' search queries, images, and voices.

[0067] The reception unit can estimate the user's emotions and adjust the method for receiving search queries based on the estimated user emotions. For example, if the user is feeling stressed, the reception unit can provide a simple interface and minimize input steps. Furthermore, if the user is relaxed, the reception unit can provide detailed input options and suggest customizable input methods. Furthermore, if the user is in a hurry, the reception unit can prioritize voice input to enable quick search query input. This allows for a more appropriate search experience by adjusting the method for receiving search queries according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit can be performed using AI, or without AI. For example, the reception unit can input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0068] The reception unit can analyze the user's past search history and select a reception method. For example, the reception unit can automatically display search queries that the user has frequently input in the past as candidates. The reception unit can also prioritize and suggest input methods (voice, text, etc.) that the user has used in the past. The reception unit can also predict and suggest search queries to be used in a specific time period based on the user's past search history. This makes it possible to provide an optimal reception method by analyzing the user's past search history. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input the user's past search history data into a generation AI and have the generation AI select an optimal reception method.

[0069] The reception unit can perform filtering based on the user's current location information and time period when receiving a search query. For example, the reception unit can prioritize displaying search results that are close to the user's current location. The reception unit can also predict places the user will visit during a specific time period and filter the search results. The reception unit can also provide optimal search results based on the user's current location information. This makes it possible to provide more relevant search results by filtering the search results based on the user's current location information and time period. Some or all of the above-described processing in the reception unit can be performed using, or without, AI, for example. For example, the reception unit can input the user's location information data to a generation AI and have the generation AI perform filtering.

[0070] When receiving a search query, the reception unit can select a reception means according to the user's input method. For example, when the user inputs a search query by voice, the reception unit analyzes the query using voice recognition technology. Furthermore, when the user uploads an image, the reception unit can search for related places using image recognition technology. Furthermore, when the user inputs a search query by text, the reception unit can analyze the query using natural language processing technology. This allows for selecting the optimal reception means according to the user's input method, thereby providing a smoother search experience. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's voice data to a generation AI and have the generation AI perform voice recognition.

[0071] The analysis unit can analyze images using deep learning technology and audio using natural language processing technology. The analysis unit can analyze images using, for example, deep learning technology. For example, the analysis unit can extract image features using a convolutional neural network (CNN) and identify related locations. The analysis unit can also analyze image time series data using a recurrent neural network (RNN). The analysis unit can also analyze audio using natural language processing technology. For example, the analysis unit can convert audio data into text using morphological analysis and perform grammatical analysis. The analysis unit can also understand the meaning of audio data and identify related locations using semantic analysis. This improves the accuracy of image and audio analysis by using deep learning technology and natural language processing technology. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input a user's image data into a generation AI and have the generation AI perform image analysis.

[0072] The suggestion unit can provide personalized search results by taking into account the user's past search history or context information such as current location information and time of day. The suggestion unit can provide personalized search results by taking into account, for example, the user's past search history. For example, the suggestion unit can suggest related places based on data on places the user has previously searched for or rated. The suggestion unit can also provide personalized search results by taking into account the user's current location information. For example, the suggestion unit can prioritize suggesting places close to the user's current location. The suggestion unit can also provide personalized search results by taking into account the user's time of day. For example, the suggestion unit can predict places the user will visit during a specific time of day and suggest related places. This makes it possible to provide more personalized search results by taking into account the user's context information. Some or all of the above-described processing in the suggestion unit can be performed using AI, for example, or without AI. For example, the suggestion unit can input the user's context information into a generation AI and cause the generation AI to generate personalized search results.

[0073] The learning unit can collect user feedback and use it as learning data for the analysis unit. For example, the learning unit can collect data on users' ratings of suggested places and use the rating data as learning data for the analysis unit. The learning unit can also collect user comments and behavioral data and use it as learning data for the analysis unit. For example, the learning unit can collect ratings and comments made by users on suggested places and use the data as learning data for the analysis unit. The learning unit can also collect user behavioral data (e.g., visit history and stay time) and use it as learning data for the analysis unit. In this way, by collecting user feedback, the analysis unit can use it as learning data to improve the accuracy of the system. Some or all of the above-mentioned processing in the learning unit can be performed, for example, using AI or without AI. For example, the learning unit can input user feedback data to the generation AI and cause the generation AI to update the learning data.

[0074] The suggestion unit can reflect the data of places rated by the user in the next search results. The suggestion unit, for example, reflects the data of places rated by the user in the next search results. For example, the suggestion unit prioritizes suggesting places that the user has given a high rating. The suggestion unit can also exclude places that the user has given a low rating from the search results. The suggestion unit can also personalize the next search results based on the user's rating data. For example, the suggestion unit analyzes data of places rated by the user and provides search results tailored to the user's preferences and needs. This enables more accurate suggestions by reflecting the data of places rated by the user in the next search results. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input the user's rating data into a generation AI and cause the generation AI to generate the next search results.

[0075] The reception unit can estimate the user's emotions and determine the priority of search queries to be received based on the estimated user emotions. For example, when the user is excited, the reception unit can prioritize urgent queries. Furthermore, when the user is relaxed, the reception unit can prioritize detailed queries. Furthermore, when the user is stressed, the reception unit can prioritize simple queries. By prioritizing search queries based on the user's emotions, more appropriate search results can be provided. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit can be performed using, for example, an AI, or without an AI. For example, the reception unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0076] When receiving a search query, the reception unit can prioritize receiving highly relevant queries by taking into account the user's geographical location information. For example, the reception unit can prioritize displaying search results that are close to the user's current location. Furthermore, if the user is in a specific area, the reception unit can prioritize receiving queries related to that area. Furthermore, the reception unit can provide optimal search results based on the user's geographical location information. In this way, by taking the user's geographical location information into account, highly relevant queries can be prioritized. Some or all of the above-described processing by the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit can input the user's location information data to a generation AI and cause the generation AI to prioritize highly relevant queries.

[0077] The reception unit can analyze the user's social media activity when receiving a search query and receive related queries. For example, the reception unit can preferentially receive queries related to places where the user has checked in on social media. The reception unit can also analyze the content of the user's social media posts and receive related queries. The reception unit can also receive related queries by referring to the activities of the user's friends on social media. In this way, related queries can be received by analyzing the user's social media activity. Some or all of the above-described processing by the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input the user's social media data into a generation AI and cause the generation AI to receive related queries.

[0078] The reception unit can customize the reception method by reflecting the user's past feedback when receiving a search query. The reception unit can, for example, suggest an optimal reception method based on search results previously evaluated by the user. The reception unit can also analyze the user's past feedback and customize the reception method. The reception unit can also suggest an optimal search query based on the user's past feedback. In this way, the reception method can be customized by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input the user's feedback data into a generation AI and cause the generation AI to customize the reception method.

[0079] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated user's emotions. For example, the analysis unit can provide detailed analysis results when the user is relaxed. The analysis unit can also provide concise analysis results when the user is in a hurry. The analysis unit can also provide visually stimulating analysis results when the user is excited. By adjusting the way the analysis is presented based on the user's emotions, more appropriate analysis results can be provided. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0080] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the search query. For example, the analysis unit provides detailed analysis results for queries with high importance. The analysis unit can also provide concise analysis results for queries with low importance. The analysis unit can also dynamically adjust the level of detail of the analysis according to the importance. This makes it possible to provide more appropriate analysis results by adjusting the level of detail of the analysis based on the importance of the search query. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input importance data of the search query to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0081] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the search query. For example, in the case of a restaurant search, the analysis unit can apply an analysis algorithm that emphasizes user reviews and ratings. In addition, in the case of a park search, the analysis unit can apply an analysis algorithm that emphasizes facility information and access information. In addition, in the case of a shopping search, the analysis unit can apply an analysis algorithm that emphasizes product inventory status and price information. In this way, by applying different analysis algorithms depending on the category of the search query, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input search query category data to the generation AI and cause the generation AI to apply the analysis algorithm.

[0082] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, optimizes the analysis algorithm based on analysis results previously evaluated by the user. The analysis unit can also analyze the user's past analysis results to improve the accuracy of the analysis. The analysis unit can also suggest an optimal analysis method by referring to the user's past analysis results. In this way, the accuracy of the analysis can be improved by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past analysis result data into the generation AI and cause the generation AI to optimize the analysis algorithm.

[0083] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. For example, if the user is in a hurry, the analysis unit can provide a short and concise analysis result. If the user is relaxed, the analysis unit can also provide a detailed analysis result. If the user is excited, the analysis unit can also provide a visually stimulating analysis result. By adjusting the length of the analysis based on the user's emotions, more appropriate analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using AI, or without AI. For example, the analysis unit can input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0084] During analysis, the analysis unit can determine the analysis priority based on the submission time of the search query. For example, the analysis unit prioritizes analysis of queries with high urgency. The analysis unit can also prioritize analysis of queries submitted earlier. The analysis unit can also dynamically adjust the analysis priority based on the submission time. This makes it possible to provide more appropriate analysis results by determining the analysis priority based on the submission time of the search query. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input search query submission time data into the generation AI and have the generation AI determine the analysis priority.

[0085] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the search queries. For example, the analysis unit prioritizes analysis of highly relevant queries. The analysis unit can also postpone analysis of less relevant queries. The analysis unit can also dynamically adjust the order of analysis based on the relevance. This makes it possible to provide more appropriate analysis results by adjusting the order of analysis based on the relevance of the search queries. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input relevance data of the search queries to the generation AI and cause the generation AI to adjust the order of analysis.

[0086] During analysis, the analysis unit can adjust the use of technical terminology in the analysis according to the user's level of expertise. For example, the analysis unit can provide analysis results that use a lot of technical terminology to a user with high levels of expertise. The analysis unit can also provide concise and easy-to-understand analysis results to a user with low levels of expertise. The analysis unit can also dynamically adjust the use of technical terminology in the analysis according to the user's level of expertise. This makes it possible to provide more appropriate analysis results by adjusting the use of technical terminology in the analysis according to the user's level of expertise. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's level of expertise data into a generation AI and have the generation AI execute the use of technical terminology.

[0087] The suggestion unit can estimate the user's emotions and adjust the way the suggestions are expressed based on the estimated user emotions. For example, the suggestion unit can provide detailed suggestions when the user is relaxed. The suggestion unit can also provide concise suggestions when the user is in a hurry. The suggestion unit can also provide visually stimulating suggestions when the user is excited. By adjusting the way the suggestions are expressed based on the user's emotions, more appropriate suggestions can be provided. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the suggestion unit can be performed using, for example, an AI, or without an AI. For example, the suggestion unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0088] The suggestion unit can adjust the level of detail of the suggestion based on the importance of the search result when making a suggestion. For example, the suggestion unit provides a detailed suggestion for a search result with high importance. The suggestion unit can also provide a concise suggestion for a search result with low importance. The suggestion unit can also dynamically adjust the level of detail of the suggestion according to the importance. As a result, by adjusting the level of detail of the suggestion based on the importance of the search result, more appropriate suggestions can be provided. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input importance data of the search result to the generation AI and cause the generation AI to adjust the level of detail of the suggestion.

[0089] When making a suggestion, the suggestion unit can apply different suggestion algorithms depending on the category of the search result. For example, in the case of a restaurant search, the suggestion unit can apply a suggestion algorithm that emphasizes user reviews and ratings. In addition, in the case of a park search, the suggestion unit can apply a suggestion algorithm that emphasizes facility information and access information. In addition, in the case of a shopping search, the suggestion unit can apply a suggestion algorithm that emphasizes product inventory status and price information. In this way, by applying different suggestion algorithms depending on the category of the search result, more appropriate suggestions can be provided. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input category data of the search result to the generation AI and cause the generation AI to apply the suggestion algorithm.

[0090] When making a proposal, the suggestion unit can improve the accuracy of the proposal by referring to the user's past proposal results. The suggestion unit, for example, optimizes the proposal algorithm based on proposal results previously evaluated by the user. The suggestion unit can also analyze the user's past proposal results to improve the accuracy of the proposal. The suggestion unit can also suggest an optimal proposal method by referring to the user's past proposal results. In this way, the accuracy of the proposal can be improved by referring to the user's past proposal results. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input the user's past proposal result data into the generation AI and cause the generation AI to optimize the proposal algorithm.

[0091] The suggestion unit can estimate the user's emotions and adjust the length of the suggestions based on the estimated user emotions. For example, if the user is in a hurry, the suggestion unit can provide short and to-the-point suggestions. If the user is relaxed, the suggestion unit can also provide detailed suggestions. If the user is excited, the suggestion unit can also provide visually stimulating suggestions. By adjusting the length of the suggestions based on the user's emotions, more appropriate suggestions can be provided. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the suggestion unit can be performed using, for example, an AI, or without an AI. For example, the suggestion unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0092] When making a proposal, the suggestion unit can determine the priority of the proposal based on the submission time of the search results. For example, the suggestion unit can prioritize suggesting search results with a high urgency. The suggestion unit can also prioritize suggesting search results that were submitted earlier. The suggestion unit can also dynamically adjust the priority of the proposal based on the submission time. This makes it possible to provide more appropriate proposals by determining the priority of the proposal based on the submission time of the search results. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input data on the submission time of the search results into the generation AI and cause the generation AI to determine the priority of the proposals.

[0093] The suggestion unit can adjust the order of suggestions based on the relevance of search results when making suggestions. For example, the suggestion unit prioritizes suggesting highly relevant search results. The suggestion unit can also postpone less relevant search results. The suggestion unit can also dynamically adjust the order of suggestions based on the relevance. This makes it possible to provide more appropriate suggestions by adjusting the order of suggestions based on the relevance of search results. Some or all of the above-described processing in the suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the suggestion unit can input relevance data of search results to a generation AI and cause the generation AI to adjust the order of suggestions.

[0094] When making a proposal, the suggestion unit can adjust the use of technical terminology in the proposal according to the user's level of expertise. For example, the suggestion unit can provide a proposal that uses a lot of technical terminology to a user with high technical expertise. The suggestion unit can also provide a concise and easy-to-understand proposal to a user with low technical expertise. The suggestion unit can also dynamically adjust the use of technical terminology in the proposal according to the user's level of expertise. This makes it possible to provide more appropriate proposals by adjusting the use of technical terminology in the proposal according to the user's level of expertise. Some or all of the above-described processing in the suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the suggestion unit can input the user's level of expertise data to a generation AI and cause the generation AI to execute the use of technical terminology.

[0095] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, if the user is relaxed, the learning unit can use detailed feedback as training data. Furthermore, if the user is in a hurry, the learning unit can also use brief feedback as training data. Furthermore, if the user is excited, the learning unit can also use visually stimulating feedback as training data. By selecting training data based on the user's emotions, more appropriate training data can be used. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the learning unit can be performed using, for example, an AI, or without an AI. For example, the learning unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0096] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on past learning data. The learning unit can also analyze past learning data to improve the accuracy of the learning algorithm. The learning unit can also dynamically adjust the learning algorithm by referring to past learning data. In this way, the learning algorithm can be optimized by referring to past learning data. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input past learning data into a generation AI and cause the generation AI to optimize the learning algorithm.

[0097] The learning unit can update the learning data by reflecting user feedback during learning. The learning unit updates the learning data based on, for example, feedback evaluated by the user. The learning unit can also analyze the user feedback and improve the accuracy of the learning data. The learning unit can also dynamically update the learning data by referring to the user feedback. In this way, the learning data can be updated by reflecting the user feedback. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input user feedback data into the generation AI and cause the generation AI to update the learning data.

[0098] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user emotions. For example, the learning unit can perform learning more frequently when the user is relaxed. The learning unit can also reduce the frequency of learning when the user is in a hurry. The learning unit can also dynamically adjust the frequency of learning when the user is excited. This allows for more appropriate learning by adjusting the frequency of learning based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the learning unit can be performed using an AI, for example, or without an AI. For example, the learning unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0099] During learning, the learning unit can weight the learning data based on the time of submission of the search query. For example, the learning unit weights the learning data by prioritizing recently submitted search queries. The learning unit can also weight the learning data by disregarding older submitted search queries. The learning unit can also dynamically adjust the weighting of the learning data based on the submission time. This allows for more appropriate learning by weighting the learning data based on the submission time of the search query. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input search query submission time data into the generation AI and cause the generation AI to weight the learning data.

[0100] During learning, the learning unit can integrate information from different data sources to enrich the training data. For example, the learning unit can integrate data from social media to enrich the training data. The learning unit can also integrate information from public databases to enrich the training data. The learning unit can also integrate user feedback to enrich the training data. This allows the training data to be enriched by integrating information from different data sources. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input data from different data sources into the generation AI and cause the generation AI to integrate the data.

[0101] During learning, the learning unit can select learning data based on the user's interests. For example, the learning unit selects data related to topics in which the user is interested as learning data. The learning unit can also select data that is likely to be of interest to the user based on the user's past search history as learning data. The learning unit can also analyze the user's social media activities and select data that is likely to be of interest to the user as learning data. This allows for more appropriate learning by selecting learning data based on the user's interests. Some or all of the above-described processing in the learning unit may be performed using, or without, AI. For example, the learning unit can input the user's interest data into the generation AI and have the generation AI select the learning data. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, suggestion unit, and learning unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives search queries, images, and voice from a user. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the received data and searches for related places. The suggestion unit is realized, for example, by the control unit 46A of the smart device 14 and suggests the analysis results to the user. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and collects user feedback and uses it as learning data for the analysis unit. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, suggestion unit, and learning unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives search queries, images, and voice from a user. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the received data and searches for related locations. The suggestion unit is realized, for example, by the control unit 46A of the smart glasses 214 and suggests the analysis results to the user. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and collects user feedback and uses it as learning data for the analysis unit. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, suggestion unit, and learning unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314 and receives search queries, images, and voice from a user. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the received data and searches for related places. The suggestion unit is realized, for example, by the control unit 46A of the headset type terminal 314 and suggests the analysis results to the user. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and collects user feedback and uses it as learning data for the analysis unit. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, suggestion unit, and learning unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives search queries, images, and voice from a user. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the received data and searches for related places. The suggestion unit is realized, for example, by the control unit 46A of the robot 414 and suggests the analysis results to the user. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and collects user feedback and uses it as learning data for the analysis unit.

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

[0103] When accepting a user's search query, the acceptance unit can adjust the display method of search results taking into account the remaining battery level of the user's device. For example, when the remaining battery level is low, the acceptance unit can display simple search results consisting of only text. When the remaining battery level is sufficient, the acceptance unit can also display rich search results including images and videos. Furthermore, when the remaining battery level is moderate, the acceptance unit can also display search results that combine text and some images. This makes it possible to provide an optimal display method of search results depending on the remaining battery level of the user's device.

[0104] When analyzing a user's search query, the analysis unit can adjust the level of analysis detail taking into account the user's Internet connection speed. For example, if the Internet connection speed is slow, the analysis unit can provide a concise analysis result. If the Internet connection speed is fast, the analysis unit can provide a detailed analysis result. Furthermore, if the Internet connection speed is medium, the analysis unit can provide an analysis result with a moderate level of detail. This allows the analysis unit to provide optimal analysis results according to the user's Internet connection speed.

[0105] When making suggestions for a user's search query, the suggestion unit can adjust how the suggestions are displayed, taking into account the screen size of the user's device. For example, when the screen size is small, the suggestion unit can display simple text-only suggestions. When the screen size is large, the suggestion unit can display rich suggestions that include images and videos. Furthermore, when the screen size is medium, the suggestion unit can display suggestions that combine text and some images. This makes it possible to provide an optimal way to display suggestions depending on the screen size of the user's device.

[0106] When collecting user feedback, the learning unit can adjust the update frequency of the learning data taking into account the frequency of the user feedback. For example, if the frequency of feedback is high, the learning unit can update the learning data frequently. Also, if the frequency of feedback is low, the learning unit can reduce the update frequency of the learning data. Furthermore, if the frequency of feedback is medium, the learning unit can update the learning data at an appropriate frequency. This makes it possible to provide an optimal update frequency of the learning data according to the frequency of user feedback.

[0107] When accepting a user's search query, the accepting unit can adjust the method of accepting the search query by taking into account the user's device usage history. For example, the accepting unit can identify applications frequently used by the user from the device usage history and preferentially accept search queries related to those applications. The accepting unit can also predict applications that the user will use during a specific time period from the device usage history and preferentially accept search queries related to that time period. Furthermore, the accepting unit can analyze the user's preferences from the device usage history and suggest search queries that match the user's preferences. This makes it possible to provide an optimal method of accepting search queries according to the user's device usage history.

[0108] When analyzing a user's search query, the analysis unit can estimate the user's emotions and determine the analysis priority based on the estimated user emotions. For example, if the user is excited, it can prioritize analyzing queries with high urgency. Also, if the user is relaxed, it can prioritize detailed analysis. Furthermore, if the user is stressed, it can prioritize concise analysis. In this way, by determining the analysis priority based on the user's emotions, it is possible to provide more appropriate analysis results.

[0109] When making suggestions in response to a user's search query, the suggestion unit can estimate the user's emotions and adjust the content of the suggestions based on the estimated user emotions. For example, if the user is excited, visually stimulating suggestions can be provided. If the user is relaxed, detailed suggestions can be provided. Furthermore, if the user is stressed, concise suggestions can be provided. In this way, by adjusting the content of the suggestions based on the user's emotions, more appropriate suggestions can be provided.

[0110] When collecting user feedback, the learning unit can estimate the user's emotions and adjust the feedback collection method based on the estimated user emotions. For example, if the user is relaxed, detailed feedback can be collected. If the user is in a hurry, brief feedback can be collected. Furthermore, if the user is excited, visually stimulating feedback can be collected. In this way, by adjusting the feedback collection method based on the user's emotions, more appropriate feedback can be collected.

[0111] When accepting a user's search query, the accepting unit can estimate the user's emotions and adjust the method of accepting the search query based on the estimated user emotions. For example, if the user is feeling stressed, a simple interface can be provided to minimize input steps. Alternatively, if the user is relaxed, detailed input options can be provided and a customizable input method can be suggested. Furthermore, if the user is in a hurry, voice input can be prioritized to enable quick input of a search query. In this way, by adjusting the method of accepting a search query according to the user's emotions, a more appropriate search experience can be provided.

[0112] When making suggestions in response to a user's search query, the suggestion unit can estimate the user's emotions and determine the priority of suggestions based on the estimated user emotions. For example, if the user is excited, it can prioritize suggestions with high urgency. Also, if the user is relaxed, it can prioritize detailed suggestions. Furthermore, if the user is stressed, it can prioritize concise suggestions. In this way, by determining the priority of suggestions based on the user's emotions, it is possible to provide more appropriate suggestions.

[0113] The processing flow of the second embodiment will be briefly explained below.

[0114] Step 1: The reception unit receives a search query, an image, or a voice from a user. For example, the reception unit can receive a text search query entered by a user, an uploaded image, or a spoken voice. Step 2: The analysis unit analyzes the data received by the reception unit and searches for related places. For example, it uses deep learning technology to analyze images and natural language processing technology to analyze voice. It can also provide personalized search results by taking into account context information such as the user's past search history, current location, and time of day. Step 3: The suggestion unit suggests the search results obtained by the analysis unit to the user. For example, it provides personalized search results by taking into account the user's past search history, current location, time of day, and other contextual information. It can also reflect the location data rated by the user in the next search results. Step 4: The learning unit collects user feedback on the places suggested by the suggestion unit and uses it as learning data for the analysis unit. For example, data on users' ratings of the suggested places is collected and the rating data is used as learning data for the analysis unit.

[0115] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires 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.

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

[0117] 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.

[0118] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

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

[0121] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, 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.

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

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

[0124] 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).

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

[0126] 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.

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

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

[0129] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0130] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 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.

[0131] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires 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.

[0132] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. 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.

[0133] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may 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.

[0134] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

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

[0137] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, 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.

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

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

[0140] 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).

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

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

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

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

[0145] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0146] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 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.

[0147] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires 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.

[0148] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. 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.

[0149] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may 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.

[0150] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

[0152] 7, 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.

[0153] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, 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.

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

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

[0156] 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).

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

[0158] 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.

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

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

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

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

[0163] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 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.

[0164] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires 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.

[0165] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. 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.

[0166] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may 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.

[0167] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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).

[0172] 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.

[0173] 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."

[0174] 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.

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

[0176] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a 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.

[0177] 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.

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

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0185] 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.

[0186] [Explanation of symbols]

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

Claims

1. a reception unit that receives a search query, an image, or a voice from a user; an analysis unit that analyzes the data received by the reception unit and searches for related locations; a suggestion unit that suggests the search results obtained by the analysis unit to a user; a learning unit that collects user feedback on the places suggested by the suggestion unit and uses the feedback as learning data for an analysis unit; A system characterized by:

2. The reception unit Estimate user sentiment and adjust how search queries are received based on the estimated sentiment 2. The system of claim 1.

3. The reception unit Analyze the user's past search history and select the reception method 2. The system of claim 1.

4. The reception unit When a search query is received, it is filtered based on the user's current location and time of day.

2. The system of claim 1.

5. The reception unit When accepting a search query, select the acceptance method depending on the user's input method.

2. The system of claim 1.

6. The analysis unit Deep learning technology is used to analyze images, and natural language processing technology is used to analyze audio.

2. The system of claim 1.

7. The proposal unit Providing personalized search results by taking into account a user's past search history or contextual information such as their current location or time of day 2. The system of claim 1.

8. The learning unit Collect user feedback and use it as training data for the analysis part 2. The system of claim 1.

Images