system

Abstract

The system according to this embodiment aims to provide contextually appropriate search results in response to the user's query. [Solution] The system according to this embodiment comprises an analysis unit, a search unit, and a provision unit. The analysis unit analyzes the user's query. The search unit provides contextually relevant search results using semantic search based on the query analyzed by the analysis unit. The provision unit provides the search results provided by the search unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to provide appropriate search results according to the context for a user's query.

[0005] The system according to the embodiment aims to provide appropriate search results according to the context for a user's query.

Means for Solving the Problems

[0006] The system according to the embodiment includes an analysis unit, a search unit, and a provision unit. The analysis unit analyzes a user's query. The search unit provides search results adapted to the context using semantic search based on the query analyzed by the analysis unit. The provision unit provides the search results provided by the search unit. [Effects of the Invention]

[0007] The system according to this embodiment can provide contextually appropriate search results in response to the user's query. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The AI ​​assistant document search support tool using natural language processing according to an embodiment of the present invention is a system that analyzes the user's query and searches for relevant documents and information at high speed. This system has a mechanism in which the user inputs a query, the AI ​​assistant analyzes the query, and provides contextually relevant search results using semantic search. For example, if the user inputs a query such as "Please tell me about papers on the latest AI technology," the AI ​​assistant analyzes the query and extracts relevant keywords and context. Next, the AI ​​assistant uses semantic search to search for relevant documents and information at high speed. Semantic search is a technique that searches for highly relevant information based on context, rather than simply keyword searching. For example, when searching for "papers on the latest AI technology," the AI ​​assistant selects relevant papers and articles based on context and provides them as search results. This mechanism allows the user to obtain the necessary information quickly and accurately. Furthermore, the AI ​​assistant can continuously learn and improve in order to provide appropriate search results for the user's query. For example, by providing feedback on a particular search result, the AI ​​assistant can learn from that feedback and improve the accuracy of future search results. In this way, the AI ​​assistant document search support tool, which utilizes natural language processing, analyzes the user's queries and searches for relevant documents and information at high speed, enabling the user to quickly and accurately obtain the information they need. This allows the AI ​​assistant document search support tool, which utilizes natural language processing, to analyze the user's queries, search for relevant documents and information at high speed, and provide contextually relevant search results.

[0029] The AI ​​assistant document search support tool using natural language processing according to this embodiment comprises an analysis unit, a search unit, and a provision unit. The analysis unit analyzes the user's query. The analysis unit understands the meaning of the query using, for example, natural language processing technology and extracts relevant keywords and context. For example, the analysis unit can extract keywords such as "latest AI technology" and "papers" from the query. The analysis unit can also understand the context of the query and extract relevant information. The search unit provides contextually relevant search results using semantic search based on the query analyzed by the analysis unit. The search unit uses, for example, semantic search technology to quickly search for relevant documents and information. For example, the search unit can select relevant papers and articles based on the query and context and provide them as search results. The provision unit provides the search results provided by the search unit to the user. The provision unit can, for example, display the search results through a web page or mobile application. The provision unit can also send the search results via email. As a result, the AI ​​assistant document search support tool using natural language processing according to the embodiment can analyze the user's query, quickly search for relevant documents and information, and provide contextually relevant search results. Some or all of the above-described processes in the analysis unit, search unit, and provision unit may be performed using AI, for example, or without AI. For example, the analysis unit can input a query into the AI, which can understand the meaning of the query and extract relevant keywords and context. The search unit can perform a semantic search using AI to quickly search for relevant documents and information. The provision unit can provide search results using AI.

[0030] The analysis unit analyzes the user's query. For example, the analysis unit uses natural language processing technology to understand the meaning of the query and extract relevant keywords and context. Specifically, the analysis unit tokenizes the query and performs morphological analysis to identify the part of speech and meaning of each word. Furthermore, to understand the context, it performs sentence structure analysis to clarify the relationships between subjects, predicates, objects, etc. For example, in response to the query "I am looking for papers on the latest AI technology," the analysis unit extracts keywords such as "latest," "AI technology," and "papers," and understands how these keywords are related. In addition, to understand the intent of the query, the analysis unit performs contextual analysis to identify the type and scope of information the user is seeking. For example, if the user is looking for "papers" on "the latest AI technology," the analysis unit can instruct it to prioritize searching for papers on the latest research results and technological trends. Furthermore, the analysis unit can perform more accurate analysis by referring to past queries and search history and learning the user's search patterns and interests. This allows the analysis unit to accurately understand the user's query and extract relevant keywords and context, thereby providing appropriate instructions to the search unit.

[0031] The search unit provides contextually relevant search results using semantic search based on queries analyzed by the analysis unit. For example, the search unit uses semantic search techniques to quickly search for relevant documents and information. Specifically, the search unit searches for documents within the database based on keywords and contextual information provided by the analysis unit. Semantic search techniques go beyond simple keyword matching, considering context and meaning to identify highly relevant documents. For example, in response to the query "papers on the latest AI technology," the search unit prioritizes searching for the latest research papers and technical reports on AI technology, selecting the most relevant documents. The search unit also ranks the search results, displaying the most relevant documents at the top. Factors such as document content, publication date, and citation count are considered in the ranking. Furthermore, the search unit can provide the latest information by utilizing a real-time updated database. For example, if newly published papers or articles are added to the database, the search unit can immediately reflect this information in the search results. This allows the search unit to quickly and accurately search for relevant documents and information based on the user's query, providing contextually relevant search results.

[0032] The service provider provides users with the search results provided by the search unit. The service provider can, for example, display search results through web pages or mobile applications. Specifically, the service provider provides an interface for visually clear display of search results. For example, it can display search results in a list format, along with information such as the title, author, publication date, and summary of each document. The service provider also provides a filtering function, allowing users to narrow down search results based on specific criteria. For example, search results can be filtered by publication date, author name, keywords, etc. Furthermore, the service provider also provides a function to send search results via email. This allows users to review search results later or share them with others. The service provider also provides a function to save search results, allowing users to review them again later. For example, it provides a function for users to bookmark specific search results for easy later access. This enables the service provider to visually clear display of search results and allow users to efficiently utilize information.

[0033] The learning unit can improve search results by learning from user feedback. For example, the learning unit can learn from the feedback a user provides regarding a particular search result and improve the accuracy of subsequent search results. For example, the learning unit can adjust the search algorithm based on the search results evaluated by the user. The learning unit can also analyze the user's click history and prioritize providing highly relevant information. In this way, the accuracy of search results can be improved by learning from user feedback. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user feedback into AI, which can learn the feedback and adjust the search algorithm.

[0034] The optimization unit can perform optimizations to improve the accuracy of search results. For example, the optimization unit can adjust the search algorithm and tune its parameters. For instance, the optimization unit can adjust the algorithm parameters to improve the accuracy of search results. The optimization unit can also review the evaluation criteria for search results and provide the most optimal search results. This improves the accuracy of search results. Some or all of the above-described processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input the adjustments to the search algorithm into the AI, which can then find the optimal parameters.

[0035] The analysis unit can understand the meaning of a query using natural language processing techniques and extract relevant keywords and context. For example, the analysis unit can decompose the query using morphological analysis and understand the meaning of each word. It can also analyze the structure of the query using grammatical analysis and understand the context. Furthermore, the analysis unit can understand the intent of the query using semantic analysis and extract relevant information. This improves the accuracy of the analysis by understanding the meaning of the query and extracting relevant keywords and context. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input a query into an AI, which can understand the meaning of the query and extract relevant keywords and context.

[0036] The search unit can retrieve highly relevant information based on context. For example, it can use semantic search techniques to understand the context of a query and retrieve relevant information. For instance, it can select relevant documents or articles based on the query and provide them as search results. Furthermore, it can use relevance scoring to prioritize the display of the most relevant information. This improves search accuracy by searching for relevant information based on context. Some or all of the above processing in the search unit may be performed using AI, or without AI. For example, the search unit can input a query into an AI, which can understand the context and retrieve relevant information.

[0037] The service provider can provide search results to users. For example, the service provider can display search results through a webpage or mobile application. It can also send search results via email. Furthermore, the service provider can make search results available for download in PDF format. This allows for rapid information provision by providing search results to users. Some or all of the above processing in the service provider may be performed using AI, or not. For example, the service provider can input search results into an AI, which can then provide them in the most optimal format.

[0038] The analysis unit can improve the accuracy of a query by referring to the user's past search history. For example, the analysis unit can increase the relevance of the current query based on keywords the user has searched for in the past. The analysis unit can also analyze the user's past search patterns and apply the most suitable analysis method to similar queries. Furthermore, the analysis unit can improve the accuracy of the analysis results by referring to search results the user has clicked on in the past. In this way, the accuracy of the analysis is improved by referring to past search history. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's past search history into AI, which can then analyze past search patterns to improve the accuracy of the current query's analysis.

[0039] The analysis unit can customize the analysis results when analyzing queries, taking into account the user's level of expertise. For example, if the user is an expert, the analysis unit can provide detailed analysis results including technical terms. Alternatively, if the user is a novice, the analysis unit can provide concise and easy-to-understand analysis results. Furthermore, the analysis unit can adjust the appropriate depth and scope of information according to the user's level of expertise. This allows for the provision of more relevant information by customizing the analysis results according to the user's level of expertise. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's level of expertise into the AI, which can then customize the analysis results.

[0040] The analysis unit can prioritize analyzing highly relevant information by considering the user's geographical location when analyzing queries. For example, if the user is in a specific region, the analysis unit will prioritize analyzing information related to that region. The analysis unit can also prioritize providing nearby information based on the user's current location. Furthermore, if the user is traveling, the analysis unit can prioritize analyzing information related to their travel destination. In this way, highly relevant information can be provided by considering geographical location. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's geographical location information into AI, which can then prioritize analyzing highly relevant information.

[0041] The analysis unit can analyze the user's social media activity and extract relevant keywords when analyzing queries. For example, the analysis unit can reflect keywords that the user frequently uses on social media in its analysis. The analysis unit can also prioritize the analysis of relevant information based on the user's interests on social media. Furthermore, the analysis unit can analyze the user's social media activity history and extract the most relevant keywords. In this way, highly relevant keywords can be extracted by analyzing social media activity. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's social media activity into AI, and the AI ​​can extract relevant keywords.

[0042] The search unit can improve search accuracy by referring to the user's past search results during a search. For example, the search unit can increase the relevance of current search results based on search results the user has clicked on in the past. The search unit can also analyze the user's past search patterns and provide the best search results for similar queries. Furthermore, the search unit can improve search accuracy by referring to search results the user has rated in the past. In this way, search accuracy is improved by referring to past search results. Some or all of the above processes in the search unit may be performed using AI, for example, or not using AI. For example, the search unit can input the user's past search results into AI, which can then analyze past search patterns and improve the accuracy of current search results.

[0043] The search function can customize search results by taking into account the user's level of expertise. For example, if the user is an expert, the search function will prioritize displaying specialized information. It can also prioritize displaying basic information if the user is a beginner. Furthermore, the search function can adjust the appropriate depth and scope of information according to the user's level of expertise. This allows for the provision of more relevant information by customizing search results according to the user's level of expertise. Some or all of the above processing in the search function may be performed using AI, for example, or without AI. For example, the search function can input the user's level of expertise into the AI, which can then customize the search results.

[0044] The search unit can prioritize searching for highly relevant information by considering the user's geographical location during a search. For example, if the user is in a specific region, the search unit will prioritize searching for information related to that region. The search unit can also prioritize providing nearby information based on the user's current location. Furthermore, if the user is traveling, the search unit can prioritize searching for information related to their travel destination. In this way, highly relevant information can be provided by considering geographical location. Some or all of the above processing in the search unit may be performed using AI, for example, or without AI. For example, the search unit can input the user's geographical location information into AI, which can then prioritize searching for highly relevant information.

[0045] The search unit can analyze the user's social media activity during a search and retrieve relevant information. For example, the search unit can incorporate keywords that the user frequently uses on social media into the search results. The search unit can also prioritize searching for relevant information based on the user's interests on social media. Furthermore, the search unit can analyze the user's social media activity history and retrieve the most relevant information. This allows the system to provide highly relevant information by analyzing social media activity. Some or all of the above processing in the search unit may be performed using AI, for example, or without AI. For example, the search unit can input the user's social media activity into AI, which can then search for relevant information.

[0046] The delivery unit can optimize its delivery method by referring to the user's past feedback when providing search results. For example, the delivery unit can select the optimal delivery method based on search results that the user has previously rated. The delivery unit can also analyze the user's past feedback and improve the delivery method. Furthermore, the delivery unit can select the optimal delivery method by referring to how the user has previously been presented with search results. In this way, the delivery method can be optimized by referring to past feedback. Some or all of the above processes in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery unit can input the user's past feedback into AI, and the AI ​​can optimize the delivery method.

[0047] The information provider can customize the search results provided, taking into account the user's level of expertise. For example, if the user is an expert, the provider will prioritize providing specialized information. Conversely, if the user is a beginner, the provider can prioritize providing basic information. Furthermore, the provider can adjust the appropriate depth and scope of information according to the user's level of expertise. This allows for the provision of more relevant information by customizing the search results according to the user's level of expertise. Some or all of the above processing in the information provider may be performed using AI, for example, or without AI. For example, the provider can input the user's level of expertise into the AI, which can then customize the search results.

[0048] The information provider can prioritize providing highly relevant information by considering the user's geographical location when providing search results. For example, if the user is in a specific region, the information provider can prioritize providing information related to that region. The information provider can also prioritize providing nearby information based on the user's current location. Furthermore, if the user is traveling, the information provider can prioritize providing information related to their travel destination. In this way, highly relevant information can be provided by considering geographical location. Some or all of the above processing in the information provider may be performed using AI, for example, or without AI. For example, the information provider can input the user's geographical location information into AI, which can then prioritize providing highly relevant information.

[0049] The service provider can analyze the user's social media activity and provide relevant information when providing search results. For example, the service provider can reflect keywords that the user frequently uses on social media in its recommendations. The service provider can also prioritize providing relevant information based on the user's interests on social media. Furthermore, the service provider can analyze the user's social media activity history and provide optimal information. This allows the service provider to provide highly relevant information by analyzing social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or not. For example, the service provider can input the user's social media activity into AI, which can then provide relevant information.

[0050] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also analyze past learning results to improve the accuracy of the algorithm. Furthermore, the learning unit can improve the learning algorithm by referring to past learning data. As a result, the accuracy of the learning algorithm is improved by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into AI, which can then select the optimal learning algorithm and improve the accuracy of the algorithm.

[0051] The learning unit can weight the training data based on the user's search history during training. For example, the learning unit can increase the weight of the training data for keywords that the user frequently searches for. The learning unit can also analyze the user's past search history and weight the data that is most relevant. Furthermore, the learning unit can adjust the weight of the training data based on the search results evaluated by the user. This improves the accuracy of training by weighting the training data based on the search history. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the user's search history into the AI, which can then weight the data that is most relevant.

[0052] The optimization unit can improve optimization accuracy by referring to the user's past feedback during optimization. For example, the optimization unit adjusts the optimization algorithm based on search results that the user has evaluated in the past. The optimization unit can also analyze the user's past feedback to improve optimization accuracy. Furthermore, the optimization unit can improve the optimization algorithm by referring to how the user has displayed search results in the past. In this way, optimization accuracy is improved by referring to past feedback. Some or all of the above processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input the user's past feedback into AI, and the AI ​​can adjust the optimization algorithm to improve optimization accuracy.

[0053] The optimization unit can perform optimization while considering the user's geographical location information. For example, if the user is in a specific region, the optimization unit will prioritize optimizing information related to that region. The optimization unit can also prioritize providing nearby information based on the user's current location. Furthermore, if the user is traveling, the optimization unit can prioritize optimizing information related to the travel destination. In this way, by considering geographical location information, highly relevant information can be provided. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input the user's geographical location information into AI, and the AI ​​can prioritize optimizing information with high relevance.

[0054] The optimization unit can analyze the user's social media activity and optimize relevant information during the optimization process. For example, the optimization unit can reflect keywords frequently used by the user on social media in the optimization. The optimization unit can also prioritize and optimize relevant information based on the user's interests on social media. Furthermore, the optimization unit can analyze the user's social media activity history and optimize the most relevant information. This allows the system to provide highly relevant information by analyzing social media activity. Some or all of the above-described processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input the user's social media activity into AI, which can then optimize the relevant information.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The search function can provide relevant images and videos as search results in response to the user's query. For example, if a user searches for "papers on the latest AI technology," the search function will provide not only relevant papers but also relevant images and videos as search results. Furthermore, the search function can reflect the user's click history on images and videos in future search results. In addition, the search function can analyze the user's past search history and prioritize displaying highly relevant images and videos. This diversifies the information users can obtain by providing search results that include images and videos.

[0057] The service provider can adjust the display method of search results according to the type of device the user is using. For example, if the user is using a smartphone, the service provider can adopt a mobile-friendly display method to improve visibility. If the user is using a tablet, the service provider can adopt a display method suitable for a large screen to improve the readability of the information. Furthermore, if the user is using a desktop computer, the service provider can adopt a display method that includes detailed information. By providing a display method tailored to the device, the service provider improves user convenience.

[0058] The analysis unit can adjust its analysis method to account for the user's input speed and method when analyzing the user's query. For example, if the user is typing quickly, the analysis unit will perform a rapid analysis and provide results quickly. Conversely, if the user is typing slowly, the analysis unit can perform a more detailed analysis and provide more relevant information. Furthermore, if the user is using voice input, the analysis unit can use speech recognition technology to convert the speech into text and analyze the query based on that text. This improves user convenience by providing an analysis method tailored to the user's input speed and method.

[0059] The search function can provide relevant news articles as search results for the user's query. For example, if a user searches for "papers on the latest AI technology," the search function will provide not only relevant papers but also relevant news articles as search results. Furthermore, the search function can reflect the user's click history on news articles in future search results. In addition, the search function can analyze the user's past search history and prioritize displaying highly relevant news articles. By providing search results that include news articles, the information users can obtain becomes more diverse.

[0060] The service provider can optimize its search result delivery method by referring to users' past feedback. For example, it can select the optimal delivery method based on search results that users have previously rated. Furthermore, the service provider can analyze users' past feedback and improve its delivery method. In addition, it can select the optimal delivery method by referring to how users have previously displayed search results. This allows for optimization of the delivery method by referencing past feedback.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The analysis unit analyzes the user's query. The analysis unit uses natural language processing technology to understand the meaning of the query and extract relevant keywords and context. For example, the analysis unit can extract keywords such as "latest AI technology" and "papers" from the query. It can also understand the context of the query and extract relevant information. Step 2: The search unit provides contextually relevant search results using semantic search based on the query analyzed by the analysis unit. The search unit uses semantic search technology to quickly search for relevant documents and information. For example, it can select relevant papers and articles based on the query and provide them as search results. Step 3: The service provider provides the user with the search results provided by the search unit. The service provider can display the search results through a web page or mobile application. It can also send the search results via email.

[0063] (Example of form 2) The AI ​​assistant document search support tool using natural language processing according to an embodiment of the present invention is a system that analyzes the user's query and searches for relevant documents and information at high speed. This system has a mechanism in which the user inputs a query, the AI ​​assistant analyzes the query, and provides contextually relevant search results using semantic search. For example, if the user inputs a query such as "Please tell me about papers on the latest AI technology," the AI ​​assistant analyzes the query and extracts relevant keywords and context. Next, the AI ​​assistant uses semantic search to search for relevant documents and information at high speed. Semantic search is a technique that searches for highly relevant information based on context, rather than simply keyword searching. For example, when searching for "papers on the latest AI technology," the AI ​​assistant selects relevant papers and articles based on context and provides them as search results. This mechanism allows the user to obtain the necessary information quickly and accurately. Furthermore, the AI ​​assistant can continuously learn and improve in order to provide appropriate search results for the user's query. For example, by providing feedback on a particular search result, the AI ​​assistant can learn from that feedback and improve the accuracy of future search results. In this way, the AI ​​assistant document search support tool, which utilizes natural language processing, analyzes the user's queries and searches for relevant documents and information at high speed, enabling the user to quickly and accurately obtain the information they need. This allows the AI ​​assistant document search support tool, which utilizes natural language processing, to analyze the user's queries, search for relevant documents and information at high speed, and provide contextually relevant search results.

[0064] The AI ​​assistant document search support tool using natural language processing according to this embodiment comprises an analysis unit, a search unit, and a provision unit. The analysis unit analyzes the user's query. The analysis unit understands the meaning of the query using, for example, natural language processing technology and extracts relevant keywords and context. For example, the analysis unit can extract keywords such as "latest AI technology" and "papers" from the query. The analysis unit can also understand the context of the query and extract relevant information. The search unit provides contextually relevant search results using semantic search based on the query analyzed by the analysis unit. The search unit uses, for example, semantic search technology to quickly search for relevant documents and information. For example, the search unit can select relevant papers and articles based on the query and context and provide them as search results. The provision unit provides the search results provided by the search unit to the user. The provision unit can, for example, display the search results through a web page or mobile application. The provision unit can also send the search results via email. As a result, the AI ​​assistant document search support tool using natural language processing according to the embodiment can analyze the user's query, quickly search for relevant documents and information, and provide contextually relevant search results. Some or all of the above-described processes in the analysis unit, search unit, and provision unit may be performed using AI, for example, or without AI. For example, the analysis unit can input a query into the AI, which can understand the meaning of the query and extract relevant keywords and context. The search unit can perform a semantic search using AI to quickly search for relevant documents and information. The provision unit can provide search results using AI.

[0065] The analysis unit analyzes the user's query. For example, the analysis unit uses natural language processing technology to understand the meaning of the query and extract relevant keywords and context. Specifically, the analysis unit tokenizes the query and performs morphological analysis to identify the part of speech and meaning of each word. Furthermore, to understand the context, it performs sentence structure analysis to clarify the relationships between subjects, predicates, objects, etc. For example, in response to the query "I am looking for papers on the latest AI technology," the analysis unit extracts keywords such as "latest," "AI technology," and "papers," and understands how these keywords are related. In addition, to understand the intent of the query, the analysis unit performs contextual analysis to identify the type and scope of information the user is seeking. For example, if the user is looking for "papers" on "the latest AI technology," the analysis unit can instruct it to prioritize searching for papers on the latest research results and technological trends. Furthermore, the analysis unit can perform more accurate analysis by referring to past queries and search history and learning the user's search patterns and interests. This allows the analysis unit to accurately understand the user's query and extract relevant keywords and context, thereby providing appropriate instructions to the search unit.

[0066] The search unit provides contextually relevant search results using semantic search based on queries analyzed by the analysis unit. For example, the search unit uses semantic search techniques to quickly search for relevant documents and information. Specifically, the search unit searches for documents within the database based on keywords and contextual information provided by the analysis unit. Semantic search techniques go beyond simple keyword matching, considering context and meaning to identify highly relevant documents. For example, in response to the query "papers on the latest AI technology," the search unit prioritizes searching for the latest research papers and technical reports on AI technology, selecting the most relevant documents. The search unit also ranks the search results, displaying the most relevant documents at the top. Factors such as document content, publication date, and citation count are considered in the ranking. Furthermore, the search unit can provide the latest information by utilizing a real-time updated database. For example, if newly published papers or articles are added to the database, the search unit can immediately reflect this information in the search results. This allows the search unit to quickly and accurately search for relevant documents and information based on the user's query, providing contextually relevant search results.

[0067] The service provider provides users with the search results provided by the search unit. The service provider can, for example, display search results through web pages or mobile applications. Specifically, the service provider provides an interface for visually clear display of search results. For example, it can display search results in a list format, along with information such as the title, author, publication date, and summary of each document. The service provider also provides a filtering function, allowing users to narrow down search results based on specific criteria. For example, search results can be filtered by publication date, author name, keywords, etc. Furthermore, the service provider also provides a function to send search results via email. This allows users to review search results later or share them with others. The service provider also provides a function to save search results, allowing users to review them again later. For example, it provides a function for users to bookmark specific search results for easy later access. This enables the service provider to visually clear display of search results and allow users to efficiently utilize information.

[0068] The learning unit can improve search results by learning from user feedback. For example, the learning unit can learn from the feedback a user provides regarding a particular search result and improve the accuracy of subsequent search results. For example, the learning unit can adjust the search algorithm based on the search results evaluated by the user. The learning unit can also analyze the user's click history and prioritize providing highly relevant information. In this way, the accuracy of search results can be improved by learning from user feedback. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user feedback into AI, which can learn the feedback and adjust the search algorithm.

[0069] The optimization unit can perform optimizations to improve the accuracy of search results. For example, the optimization unit can adjust the search algorithm and tune its parameters. For instance, the optimization unit can adjust the algorithm parameters to improve the accuracy of search results. The optimization unit can also review the evaluation criteria for search results and provide the most optimal search results. This improves the accuracy of search results. Some or all of the above-described processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input the adjustments to the search algorithm into the AI, which can then find the optimal parameters.

[0070] The analysis unit can understand the meaning of a query using natural language processing techniques and extract relevant keywords and context. For example, the analysis unit can decompose the query using morphological analysis and understand the meaning of each word. It can also analyze the structure of the query using grammatical analysis and understand the context. Furthermore, the analysis unit can understand the intent of the query using semantic analysis and extract relevant information. This improves the accuracy of the analysis by understanding the meaning of the query and extracting relevant keywords and context. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input a query into an AI, which can understand the meaning of the query and extract relevant keywords and context.

[0071] The search unit can retrieve highly relevant information based on context. For example, it can use semantic search techniques to understand the context of a query and retrieve relevant information. For instance, it can select relevant documents or articles based on the query and provide them as search results. Furthermore, it can use relevance scoring to prioritize the display of the most relevant information. This improves search accuracy by searching for relevant information based on context. Some or all of the above processing in the search unit may be performed using AI, or without AI. For example, the search unit can input a query into an AI, which can understand the context and retrieve relevant information.

[0072] The service provider can provide search results to users. For example, the service provider can display search results through a webpage or mobile application. It can also send search results via email. Furthermore, the service provider can make search results available for download in PDF format. This allows for rapid information provision by providing search results to users. Some or all of the above processing in the service provider may be performed using AI, or not. For example, the service provider can input search results into an AI, which can then provide them in the most optimal format.

[0073] The analysis unit can estimate the user's emotions and adjust the query analysis method based on the estimated emotions. For example, if the user is stressed, the analysis unit can employ a concise analysis method and provide results quickly. If the user is relaxed, the analysis unit can perform a detailed analysis and provide more relevant information. Furthermore, if the user is in a hurry, the analysis unit can focus on the most important keywords. This allows for more appropriate analysis results by adjusting the query analysis method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into an AI, which can estimate emotions and adjust the query analysis method.

[0074] The analysis unit can improve the accuracy of a query by referring to the user's past search history. For example, the analysis unit can increase the relevance of the current query based on keywords the user has searched for in the past. The analysis unit can also analyze the user's past search patterns and apply the most suitable analysis method to similar queries. Furthermore, the analysis unit can improve the accuracy of the analysis results by referring to search results the user has clicked on in the past. In this way, the accuracy of the analysis is improved by referring to past search history. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's past search history into AI, which can then analyze past search patterns to improve the accuracy of the current query's analysis.

[0075] The analysis unit can customize the analysis results when analyzing queries, taking into account the user's level of expertise. For example, if the user is an expert, the analysis unit can provide detailed analysis results including technical terms. Alternatively, if the user is a novice, the analysis unit can provide concise and easy-to-understand analysis results. Furthermore, the analysis unit can adjust the appropriate depth and scope of information according to the user's level of expertise. This allows for the provision of more relevant information by customizing the analysis results according to the user's level of expertise. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's level of expertise into the AI, which can then customize the analysis results.

[0076] The analysis unit can estimate the user's emotions and prioritize the analysis results based on the estimated emotions. For example, if the user is stressed, the analysis unit will prioritize displaying the most relevant results. If the user is relaxed, the analysis unit can also provide a wider range of relevant information and increase the number of options. Furthermore, if the user is in a hurry, the analysis unit can display the most important information first. This allows for the provision of more appropriate information by prioritizing the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not using AI. For example, the analysis unit can input the user's emotion data into an AI, which can estimate the emotions and determine the priority of the analysis results.

[0077] The analysis unit can prioritize analyzing highly relevant information by considering the user's geographical location when analyzing queries. For example, if the user is in a specific region, the analysis unit will prioritize analyzing information related to that region. The analysis unit can also prioritize providing nearby information based on the user's current location. Furthermore, if the user is traveling, the analysis unit can prioritize analyzing information related to their travel destination. In this way, highly relevant information can be provided by considering geographical location. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's geographical location information into AI, which can then prioritize analyzing highly relevant information.

[0078] The analysis unit can analyze the user's social media activity and extract relevant keywords when analyzing queries. For example, the analysis unit can reflect keywords that the user frequently uses on social media in its analysis. The analysis unit can also prioritize the analysis of relevant information based on the user's interests on social media. Furthermore, the analysis unit can analyze the user's social media activity history and extract the most relevant keywords. In this way, highly relevant keywords can be extracted by analyzing social media activity. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's social media activity into AI, and the AI ​​can extract relevant keywords.

[0079] The search unit can estimate the user's emotions and adjust the search algorithm based on the estimated emotions. For example, if the user is stressed, the search unit may use an algorithm that provides concise and quick search results. If the user is relaxed, the search unit may also use an algorithm that provides search results with more detailed information. Furthermore, if the user is in a hurry, the search unit may use an algorithm that prioritizes displaying the most relevant information. This allows for more appropriate search results by adjusting the search algorithm according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the search unit may be performed using AI or not using AI. For example, the search unit can input user emotion data into an AI, which can estimate the emotions and adjust the search algorithm.

[0080] The search unit can improve search accuracy by referring to the user's past search results during a search. For example, the search unit can increase the relevance of current search results based on search results the user has clicked on in the past. The search unit can also analyze the user's past search patterns and provide the best search results for similar queries. Furthermore, the search unit can improve search accuracy by referring to search results the user has rated in the past. In this way, search accuracy is improved by referring to past search results. Some or all of the above processes in the search unit may be performed using AI, for example, or not using AI. For example, the search unit can input the user's past search results into AI, which can then analyze past search patterns and improve the accuracy of current search results.

[0081] The search function can customize search results by taking into account the user's level of expertise. For example, if the user is an expert, the search function will prioritize displaying specialized information. It can also prioritize displaying basic information if the user is a beginner. Furthermore, the search function can adjust the appropriate depth and scope of information according to the user's level of expertise. This allows for the provision of more relevant information by customizing search results according to the user's level of expertise. Some or all of the above processing in the search function may be performed using AI, for example, or without AI. For example, the search function can input the user's level of expertise into the AI, which can then customize the search results.

[0082] The search unit can estimate the user's emotions and adjust the display order of search results based on the estimated emotions. For example, if the user is stressed, the search unit can display the most relevant results first. If the user is relaxed, the search unit can also provide a wider range of relevant information and increase the number of options. Furthermore, if the user is in a hurry, the search unit can display the most important information first. In this way, by adjusting the display order of search results according to the user's emotions, more appropriate information can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the search unit may be performed using AI or not using AI. For example, the search unit can input user emotion data into AI, which can estimate emotions and adjust the display order of search results.

[0083] The search unit can prioritize searching for highly relevant information by considering the user's geographical location during a search. For example, if the user is in a specific region, the search unit will prioritize searching for information related to that region. The search unit can also prioritize providing nearby information based on the user's current location. Furthermore, if the user is traveling, the search unit can prioritize searching for information related to their travel destination. In this way, highly relevant information can be provided by considering geographical location. Some or all of the above processing in the search unit may be performed using AI, for example, or without AI. For example, the search unit can input the user's geographical location information into AI, which can then prioritize searching for highly relevant information.

[0084] The search unit can analyze the user's social media activity during a search and retrieve relevant information. For example, the search unit can incorporate keywords that the user frequently uses on social media into the search results. The search unit can also prioritize searching for relevant information based on the user's interests on social media. Furthermore, the search unit can analyze the user's social media activity history and retrieve the most relevant information. This allows the system to provide highly relevant information by analyzing social media activity. Some or all of the above processing in the search unit may be performed using AI, for example, or without AI. For example, the search unit can input the user's social media activity into AI, which can then search for relevant information.

[0085] The service provider can estimate the user's emotions and adjust the display method of search results based on the estimated emotions. For example, if the user is stressed, the service provider can provide a concise and highly visible display method. If the user is relaxed, the service provider can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the service provider can provide a concise display method. By adjusting the display method of search results according to the user's emotions, more appropriate information can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI or not using AI. For example, the service provider can input user emotion data into AI, which can estimate emotions and adjust the display method of search results.

[0086] The delivery unit can optimize its delivery method by referring to the user's past feedback when providing search results. For example, the delivery unit can select the optimal delivery method based on search results that the user has previously rated. The delivery unit can also analyze the user's past feedback and improve the delivery method. Furthermore, the delivery unit can select the optimal delivery method by referring to how the user has previously been presented with search results. In this way, the delivery method can be optimized by referring to past feedback. Some or all of the above processes in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery unit can input the user's past feedback into AI, and the AI ​​can optimize the delivery method.

[0087] The information provider can customize the search results provided, taking into account the user's level of expertise. For example, if the user is an expert, the provider will prioritize providing specialized information. Conversely, if the user is a beginner, the provider can prioritize providing basic information. Furthermore, the provider can adjust the appropriate depth and scope of information according to the user's level of expertise. This allows for the provision of more relevant information by customizing the search results according to the user's level of expertise. Some or all of the above processing in the information provider may be performed using AI, for example, or without AI. For example, the provider can input the user's level of expertise into the AI, which can then customize the search results.

[0088] The service provider can estimate the user's emotions and prioritize search results based on the estimated emotions. For example, if the user is stressed, the service provider will prioritize displaying the most relevant results. If the user is relaxed, the service provider can also provide a wider range of relevant information and increase the number of options. Furthermore, if the user is in a hurry, the service provider can display the most important information first. This allows for the provision of more appropriate information by prioritizing search results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input user emotion data into an AI, which can estimate the emotions and determine the priority of search results.

[0089] The information provider can prioritize providing highly relevant information by considering the user's geographical location when providing search results. For example, if the user is in a specific region, the information provider can prioritize providing information related to that region. The information provider can also prioritize providing nearby information based on the user's current location. Furthermore, if the user is traveling, the information provider can prioritize providing information related to their travel destination. In this way, highly relevant information can be provided by considering geographical location. Some or all of the above processing in the information provider may be performed using AI, for example, or without AI. For example, the information provider can input the user's geographical location information into AI, which can then prioritize providing highly relevant information.

[0090] The service provider can analyze the user's social media activity and provide relevant information when providing search results. For example, the service provider can reflect keywords that the user frequently uses on social media in its recommendations. The service provider can also prioritize providing relevant information based on the user's interests on social media. Furthermore, the service provider can analyze the user's social media activity history and provide optimal information. This allows the service provider to provide highly relevant information by analyzing social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or not. For example, the service provider can input the user's social media activity into AI, which can then provide relevant information.

[0091] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is stressed, the learning unit will prioritize learning concise and easy-to-understand data. If the user is relaxed, the learning unit can also learn detailed data to provide broad knowledge. Furthermore, if the user is in a hurry, the learning unit can prioritize learning the most important data. This allows for more appropriate learning by selecting training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI or not using AI. For example, the learning unit can input the user's emotion data into an AI, which can estimate the emotions and select training data.

[0092] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also analyze past learning results to improve the accuracy of the algorithm. Furthermore, the learning unit can improve the learning algorithm by referring to past learning data. As a result, the accuracy of the learning algorithm is improved by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into AI, which can then select the optimal learning algorithm and improve the accuracy of the algorithm.

[0093] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is stressed, the learning unit can reduce the learning frequency to alleviate the burden. Conversely, if the user is relaxed, the learning unit can increase the learning frequency to learn more data. Furthermore, if the user is in a hurry, the learning unit can adjust the learning frequency to focus on important data. This allows for more appropriate learning by adjusting the learning frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI or not using AI. For example, the learning unit can input the user's emotion data into an AI, which can estimate the emotions and adjust the learning frequency.

[0094] The learning unit can weight the training data based on the user's search history during training. For example, the learning unit can increase the weight of the training data for keywords that the user frequently searches for. The learning unit can also analyze the user's past search history and weight the data that is most relevant. Furthermore, the learning unit can adjust the weight of the training data based on the search results evaluated by the user. This improves the accuracy of training by weighting the training data based on the search history. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the user's search history into the AI, which can then weight the data that is most relevant.

[0095] The optimization unit can estimate the user's emotions and adjust the optimization algorithm based on the estimated emotions. For example, if the user is stressed, the optimization unit uses a concise and rapid optimization algorithm. If the user is relaxed, the optimization unit can also use an optimization algorithm that includes detailed information. Furthermore, if the user is in a hurry, the optimization unit can use an optimization algorithm that prioritizes displaying the most relevant information. This allows for more appropriate optimization by adjusting the optimization algorithm according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the optimization unit may be performed using AI or not using AI. For example, the optimization unit can input user emotion data into an AI, which can estimate the emotions and adjust the optimization algorithm.

[0096] The optimization unit can improve optimization accuracy by referring to the user's past feedback during optimization. For example, the optimization unit adjusts the optimization algorithm based on search results that the user has evaluated in the past. The optimization unit can also analyze the user's past feedback to improve optimization accuracy. Furthermore, the optimization unit can improve the optimization algorithm by referring to how the user has displayed search results in the past. In this way, optimization accuracy is improved by referring to past feedback. Some or all of the above processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input the user's past feedback into AI, and the AI ​​can adjust the optimization algorithm to improve optimization accuracy.

[0097] The optimization unit can estimate the user's emotions and determine optimization priorities based on the estimated emotions. For example, if the user is stressed, the optimization unit will prioritize displaying the most relevant results. If the user is relaxed, the optimization unit can also provide a wider range of relevant information and increase the number of options. Furthermore, if the user is in a hurry, the optimization unit can display the most important information first. This allows for the provision of more appropriate information by determining optimization priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the optimization unit may be performed using AI or not using AI. For example, the optimization unit can input user emotion data into an AI, which can estimate the emotions and determine optimization priorities.

[0098] The optimization unit can perform optimization while considering the user's geographical location information. For example, if the user is in a specific region, the optimization unit will prioritize optimizing information related to that region. The optimization unit can also prioritize providing nearby information based on the user's current location. Furthermore, if the user is traveling, the optimization unit can prioritize optimizing information related to the travel destination. In this way, by considering geographical location information, highly relevant information can be provided. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input the user's geographical location information into AI, and the AI ​​can prioritize optimizing information with high relevance.

[0099] The optimization unit can analyze the user's social media activity and optimize relevant information during the optimization process. For example, the optimization unit can reflect keywords frequently used by the user on social media in the optimization. The optimization unit can also prioritize and optimize relevant information based on the user's interests on social media. Furthermore, the optimization unit can analyze the user's social media activity history and optimize the most relevant information. This allows the system to provide highly relevant information by analyzing social media activity. Some or all of the above-described processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input the user's social media activity into AI, which can then optimize the relevant information.

[0100] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0101] The analysis unit can also analyze the user's voice input when analyzing the user's queries. For example, if the user says, "Please tell me about papers on the latest AI technology," the analysis unit will use speech recognition technology to convert the voice into text and analyze the query based on that text. The analysis unit can also estimate the user's emotions from the intonation and speed of the voice input and adjust the analysis method based on those emotions. For example, if the user is in a hurry, it can perform a concise analysis and provide results quickly. In this way, analyzing voice input improves user convenience.

[0102] The search function can provide relevant images and videos as search results in response to the user's query. For example, if a user searches for "papers on the latest AI technology," the search function will provide not only relevant papers but also relevant images and videos as search results. Furthermore, the search function can reflect the user's click history on images and videos in future search results. In addition, the search function can analyze the user's past search history and prioritize displaying highly relevant images and videos. This diversifies the information users can obtain by providing search results that include images and videos.

[0103] The service provider can adjust the display method of search results according to the type of device the user is using. For example, if the user is using a smartphone, the service provider can adopt a mobile-friendly display method to improve visibility. If the user is using a tablet, the service provider can adopt a display method suitable for a large screen to improve the readability of the information. Furthermore, if the user is using a desktop computer, the service provider can adopt a display method that includes detailed information. By providing a display method tailored to the device, the service provider improves user convenience.

[0104] The analysis unit can adjust its analysis method to account for the user's input speed and method when analyzing the user's query. For example, if the user is typing quickly, the analysis unit will perform a rapid analysis and provide results quickly. Conversely, if the user is typing slowly, the analysis unit can perform a more detailed analysis and provide more relevant information. Furthermore, if the user is using voice input, the analysis unit can use speech recognition technology to convert the speech into text and analyze the query based on that text. This improves user convenience by providing an analysis method tailored to the user's input speed and method.

[0105] The search function can provide relevant news articles as search results for the user's query. For example, if a user searches for "papers on the latest AI technology," the search function will provide not only relevant papers but also relevant news articles as search results. Furthermore, the search function can reflect the user's click history on news articles in future search results. In addition, the search function can analyze the user's past search history and prioritize displaying highly relevant news articles. By providing search results that include news articles, the information users can obtain becomes more diverse.

[0106] The analysis unit can estimate the user's emotions and adjust the query analysis method based on the estimated emotions. For example, if the user is stressed, it can employ a concise analysis method to provide results quickly. If the user is relaxed, it can perform a detailed analysis to provide more relevant information. Furthermore, if the user is in a hurry, it can focus the analysis on the most important keywords. In this way, by adjusting the query analysis method according to the user's emotions, more appropriate analysis results can be provided.

[0107] The search engine can estimate the user's emotions when providing search results and adjust the display method based on those emotions. For example, if the user is stressed, it can provide a concise and easily readable display. If the user is relaxed, it can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, it can provide a display method that gets straight to the point. By adjusting the display method of search results according to the user's emotions, it is possible to provide more appropriate information.

[0108] The learning unit can estimate the user's emotions and select training data based on those emotions. For example, if the user is stressed, it will prioritize learning concise and easy-to-understand data. If the user is relaxed, it can learn detailed data to provide a broad range of knowledge. Furthermore, if the user is in a hurry, it can prioritize learning the most important data. This allows for more appropriate learning by selecting training data according to the user's emotions.

[0109] The optimization unit can estimate the user's emotions and adjust the optimization algorithm based on those emotions. For example, if the user is stressed, it can use a concise and rapid optimization algorithm. If the user is relaxed, it can use an optimization algorithm that includes detailed information. Furthermore, if the user is in a hurry, it can use an optimization algorithm that prioritizes displaying the most relevant information. By adjusting the optimization algorithm according to the user's emotions, more appropriate optimization can be achieved.

[0110] The service provider can optimize its search result delivery method by referring to users' past feedback. For example, it can select the optimal delivery method based on search results that users have previously rated. Furthermore, the service provider can analyze users' past feedback and improve its delivery method. In addition, it can select the optimal delivery method by referring to how users have previously displayed search results. This allows for optimization of the delivery method by referencing past feedback.

[0111] The following briefly describes the processing flow for example form 2.

[0112] Step 1: The analysis unit analyzes the user's query. The analysis unit uses natural language processing technology to understand the meaning of the query and extract relevant keywords and context. For example, the analysis unit can extract keywords such as "latest AI technology" and "papers" from the query. It can also understand the context of the query and extract relevant information. Step 2: The search unit provides contextually relevant search results using semantic search based on the query analyzed by the analysis unit. The search unit uses semantic search technology to quickly search for relevant documents and information. For example, it can select relevant papers and articles based on the query and provide them as search results. Step 3: The service provider provides the user with the search results provided by the search unit. The service provider can display the search results through a web page or mobile application. It can also send the search results via email.

[0113] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0114] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0115] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0116] For example, the analysis unit is implemented by the processor 46 of the smart device 14 or the processor 28 of the data processing unit 12. For example, the search unit is implemented by the processor 46 of the smart device 14 or the processor 28 of the data processing unit 12. For example, the providing unit is implemented via the output device 40 of the smart device 14 or the communication I / F 26 of the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12. For example, the optimization unit is implemented by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0117] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0118] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0119] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0120] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0121] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0123] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0124] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0125] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0126] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0127] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0129] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0131] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0132] For example, the analysis unit is implemented by the processor 46 of the smart glasses 214 or the processor 28 of the data processing unit 12. For example, the search unit is implemented by the processor 46 of the smart glasses 214 or the processor 28 of the data processing unit 12. For example, the providing unit is implemented via the speaker 240 of the smart glasses 214 or the communication I / F 26 of the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12. For example, the optimization unit is implemented by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0133] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0134] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0135] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0136] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0137] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0139] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0140] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0141] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0142] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0143] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0144] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0145] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0147] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0148] For example, the analysis unit is implemented by the processor 46 of the headset terminal 314 or the processor 28 of the data processing unit 12. For example, the search unit is implemented by the processor 46 of the headset terminal 314 or the processor 28 of the data processing unit 12. For example, the provision unit is implemented via the display 343 of the headset terminal 314 or the communication I / F 26 of the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12. For example, the optimization unit is implemented by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0149] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0150] As shown in Figure 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.

[0151] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0152] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0153] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0155] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0156] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0157] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0158] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0159] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0160] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0161] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0162] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0163] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0164] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0165] For example, the analysis unit is implemented by the processor 46 of the robot 414 or the processor 28 of the data processing unit 12. For example, the search unit is implemented by the processor 46 of the robot 414 or the processor 28 of the data processing unit 12. For example, the providing unit is implemented via the speaker 240 of the robot 414 or the communication I / F 26 of the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12. For example, the optimization unit is implemented by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0166] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0167] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0168] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0169] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0170] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0171] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0172] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0173] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0174] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0175] 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.

[0176] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0177] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0178] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0179] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0180] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0181] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0182] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0183] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0184] (Note 1) An analysis unit that analyzes the user's queries, A search unit provides contextually relevant search results using semantic search based on queries analyzed by the aforementioned analysis unit, The system comprises a providing unit that provides the search results provided by the search unit. A system characterized by the following features. (Note 2) It includes a learning unit that learns from user feedback to improve search results. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes an optimization unit to improve the accuracy of search results. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned analysis unit, We use natural language processing techniques to understand the meaning of queries and extract relevant keywords and context. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned search unit, Search for relevant information based on context. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned supply unit is, Provide search results to the user. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, It estimates the user's emotions and adjusts the query analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, When parsing queries, we improve parsing accuracy by referencing the user's past search history. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, When parsing queries, the analysis results are customized to take into account the user's level of expertise. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, The system estimates the user's emotions and prioritizes the analysis results based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, When parsing queries, the system prioritizes analyzing highly relevant information by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, When analyzing queries, the system analyzes the user's social media activity and extracts relevant keywords. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned search unit, The system estimates the user's emotions and adjusts the search algorithm based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned search unit, When searching, the system improves search accuracy by referencing the user's past search results. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned search unit, When searching, the search results are customized to take into account the user's level of expertise. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned search unit, It estimates the user's emotions and adjusts the display order of search results based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned search unit, When searching, the system prioritizes finding highly relevant information by taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned search unit, When you search, the system analyzes your social media activity and searches for relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned supply unit is, We estimate the user's emotions and adjust how search results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned supply unit is, When providing search results, we optimize the delivery method by referring to users' past feedback. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, When providing search results, customize the content to take into account the user's level of expertise. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, The system estimates the user's emotions and prioritizes search results based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, When providing search results, we prioritize providing highly relevant information by taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, When providing search results, we analyze the user's social media activity and provide relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 26) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 2, characterized by the features described herein. (Note 27) The aforementioned learning unit, It estimates the user's emotions and adjusts the frequency of learning based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned learning unit, During training, the training data is weighted based on the user's search history. The system described in Appendix 2, characterized by the features described herein. (Note 29) The optimization unit, It estimates the user's emotions and adjusts the optimization algorithm based on the estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 30) The optimization unit, During optimization, we improve optimization accuracy by referring to past user feedback. The system described in Appendix 3, characterized by the features described herein. (Note 31) The optimization unit, It estimates the user's emotions and determines optimization priorities based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 32) The optimization unit, During optimization, the user's geographical location information is taken into consideration. The system described in Appendix 3, characterized by the features described herein. (Note 33) The optimization unit, During optimization, the system analyzes the user's social media activity and optimizes relevant information. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0185] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An analysis unit that analyzes the user's queries, A search unit provides contextually relevant search results using semantic search based on queries analyzed by the aforementioned analysis unit, The system comprises a providing unit that provides the search results provided by the search unit. A system characterized by the following features.

2. It includes a learning unit that learns from user feedback to improve search results. The system according to feature 1.

3. It includes an optimization unit to improve the accuracy of search results. The system according to feature 1.

4. The aforementioned analysis unit, We use natural language processing techniques to understand the meaning of queries and extract relevant keywords and context. The system according to feature 1.

5. The aforementioned search unit, Search for relevant information based on context. The system according to feature 1.

6. The aforementioned analysis unit, It estimates the user's emotions and adjusts the query analysis method based on the estimated user emotions. The system according to feature 1.

7. The aforementioned analysis unit, When parsing queries, we improve parsing accuracy by referencing the user's past search history. The system according to feature 1.

8. The aforementioned analysis unit, When parsing queries, the analysis results are customized to take into account the user's level of expertise. The system according to feature 1.

Images