system

Abstract

We provide the system. [Solution] A means for receiving information requested by a user and generating a search query based on said information, A means for automatically searching internal information resources and obtaining relevant information based on the generated search query, A means of organizing the acquired information and generating it as a document in a format that the user can understand, Means for providing the aforementioned materials to the user, A means of accumulating knowledge gained during the search process and utilizing it in future searches, An information acquisition system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is 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 modern large-scale organizations, there is a huge amount of information resources, and there is a problem that it is difficult to quickly and efficiently obtain the required information. In particular, a great deal of time and trial and error are required to obtain information, which causes a decrease in business efficiency. Also, in order to appropriately present the obtained information to users, the organization and formatting of information are important, and this process is also inefficient. Therefore, there is a need to develop a system that can quickly search for the information required by users, organize the obtained information, and provide it to users.

Means for Solving the Problems

[0005] This invention provides a means for efficiently obtaining necessary information from internal information resources by automatically analyzing user-specified information requests and generating relevant search queries. Furthermore, it dramatically improves the efficiency of information provision by organizing the obtained information in a user-friendly format and generating it as a document. In addition, it enables further improvements in search efficiency in subsequent searches by utilizing the know-how accumulated during the search process to improve search accuracy. In this way, the process of information acquisition and utilization is automated, reducing the workload on users and significantly improving the efficiency of information utilization.

[0006] A "user" is an entity that uses a system to request information and obtain the necessary data.

[0007] "Information" refers to the data and knowledge that users wish to acquire, and is necessary for a specific purpose.

[0008] A "search query" is a statement of inquiry that includes instructions and conditions generated by a system to retrieve information.

[0009] "Internal information resources" refer to information sources such as databases and documents that exist within the organization.

[0010] "Related information" refers to information obtained in response to a user's request and that is suitable for the user's purpose.

[0011] "Documents" refer to documents and reports that have been compiled and processed into a format that is easy for users to understand.

[0012] "Accumulating knowledge" refers to saving experience and data gained from past search processes and results, and using that information for future searches.

[0013] An "information acquisition system" refers to the entire system that has the function of searching for, organizing, and providing information based on user requests. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. 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).

[0021] 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 A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 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.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] The 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.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is a system for efficiently acquiring information requested by users, and its embodiments are described in detail below.

[0036] The user first enters a request to obtain specific information through their terminal. For example, they might request "detailed information about the base station deployment in a specific area." The user's request is sent from the terminal to the server, which then parses the request. Based on the parsing results, the server automatically generates relevant search queries and issues these queries to the company's information resources.

[0037] The server retrieves necessary information from internal databases and documents and integrates the relevant information. The retrieved information is organized by the server and generated as a document in a user-friendly format. The document is sent to the terminal, and the user can view it through the terminal.

[0038] Furthermore, the server accumulates search know-how gained during processing and utilizes it in subsequent searches. This accumulation of knowledge improves the accuracy and speed of information retrieval by the system.

[0039] As a concrete example, consider a case where a user wants to obtain "sales data for a specific product over the past year." In this case, the terminal sends a request to the server, and the server generates the optimal query to retrieve the necessary data. It then collects all relevant sales data and generates a report including a graph that shows the sales trend by month and year at a glance, and sends it to the terminal. The user can easily review this report and easily access the information they need.

[0040] Thus, the present invention enables users to quickly and efficiently obtain necessary information from a vast amount of data, thereby enhancing the effectiveness of information utilization. The automated processes of the system contribute to improved work efficiency and significantly reduce the cumbersome information retrieval tasks in daily operations.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user uses a device to input the information they want to retrieve. This includes specific datasets and detailed requirements.

[0044] Step 2:

[0045] The terminal processes the user's request and sends the request to the server via the API. This request is structured in a data format such as JSON.

[0046] Step 3:

[0047] The server analyzes incoming requests and automatically generates search queries related to the requested information. Natural language processing technology is used for the analysis to accurately understand the user's request.

[0048] Step 4:

[0049] The server executes the generated queries against internal databases and information resources. It identifies and accesses the most suitable database tables and documents to retrieve the necessary information.

[0050] Step 5:

[0051] The server analyzes and organizes the acquired information. This analysis includes a process to verify the consistency and accuracy of the data.

[0052] Step 6:

[0053] The server organizes the analyzed information and generates a document. The document is formatted to be easily understood by the user and can include visual elements and graphs as needed.

[0054] Step 7:

[0055] The server sends the generated data to the terminal, providing information to the user.

[0056] Step 8:

[0057] Users can view and review the materials provided via their device. If they need any missing or additional information, they can submit a request again.

[0058] Step 9:

[0059] The server accumulates the results and learning from each search process, and uses this to improve the efficiency of subsequent information retrieval. This accumulation enables continuous improvement of the system's performance.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] In today's information society, efficiently retrieving necessary data from vast amounts of information is crucial. However, there are problems such as users not being able to easily access the information they want, and systems not being able to effectively utilize the knowledge gained in the process. Conventional search systems often have inappropriate query generation or the information is not organized in a way that is easy for users to understand, making efficient information retrieval difficult.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes means for receiving information requested by the user, analyzing the information to extract relevant keywords, generating an optimal search query based on the keywords using a generative AI model, and automatically searching for information resources and obtaining relevant information based on the generated search query. This allows the user to quickly obtain the desired information, and the system can utilize the knowledge gained through the search process in subsequent searches.

[0065] A "user" is an individual or organization that uses a system to obtain information.

[0066] An "information request" is a request that a user communicates to the system via their device to obtain specific information.

[0067] "Analysis" is the process of understanding the content of a received information request and extracting important elements and related keywords.

[0068] A "generative AI model" is software that uses machine learning algorithms to automatically generate appropriate search queries based on input data.

[0069] A "search query" is a set of instructions used to retrieve relevant data from an information resource, containing specific conditions for searching.

[0070] "Information resources" refer to a collection of information containing necessary data, such as internal company databases and documents.

[0071] "Information organization" is the process of structuring acquired information and processing it into a format that is easy for users to understand.

[0072] "Documents" are the final documents provided to users, visualizing organized information using charts, graphs, and text.

[0073] "Knowledge accumulation" refers to the method of saving know-how and patterns obtained during the search process so that they can be used in subsequent search processes.

[0074] The invention will now be described in terms of embodiments. This system is designed to allow users to efficiently obtain specific information. The user inputs an information retrieval request using a terminal, and this request is sent to a server. The server analyzes the request and uses a generative AI model to extract relevant keywords. This model automatically generates the most suitable search query for the user's request.

[0075] Subsequently, the server uses the generated search query to search for information resources and retrieve relevant information. These resources include internal databases and various documents. The retrieved information is then organized by the server into a user-friendly format. This organization process includes information integration and prioritization based on importance.

[0076] The server generates data based on organized information. This data often includes graphs and tables to visually represent the information. The generated data is sent to the terminal, where the user can view it and quickly access the necessary information. The server then accumulates the knowledge gained from the search process and uses that knowledge in subsequent searches to improve the accuracy of the system.

[0077] For example, if a user wants to know "details about the base station deployment in a specific area," they would enter the prompt "Please tell me the details of the base station deployment in a specific area" on their terminal. In response to this request, the server collects the relevant information and provides an organized report to the terminal. This allows the user to obtain the necessary information in a short amount of time.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The user uses a terminal to input a request for information retrieval. This request includes specific prompt statements regarding the particular information. The input request is sent from the terminal to the server. The input at this time is the "prompt statement," and the output is the "request data sent to the server."

[0081] Step 2:

[0082] The server analyzes the received request data and extracts keywords based on the request content. Using a generative AI model, it automatically generates search queries based on these keywords. The input is the "request data," and the output is the "automatically generated search query."

[0083] Step 3:

[0084] The server uses the generated search query to search for information resources. Specifically, it refers to internal databases and related documents to collect the necessary information. The input is the "search query," and the output is the "recovered information data."

[0085] Step 4:

[0086] The server organizes the acquired information data and generates user-friendly materials. These materials include integration based on the importance of the information, as well as visual elements such as graphs and tables. The input is "information data," and the output is "organized materials."

[0087] Step 5:

[0088] The server sends organized data to the terminal, making it available for the user to view. The terminal displays the received data, helping the user easily access the information. The input is "organized data," and the output is "display data viewable by the user."

[0089] Step 6:

[0090] The server accumulates knowledge gained through the search process and uses it to improve the accuracy of future searches. This accumulation of knowledge makes subsequent searches faster and more accurate. The input is "information obtained through the search process," and the output is "accumulated knowledge data."

[0091] (Application Example 1)

[0092] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] Conventional information retrieval systems require manual searching to quickly and efficiently obtain the information users need, a process that is time-consuming and labor-intensive. Furthermore, when using voice-based information retrieval, there are challenges regarding speech recognition accuracy, information analysis, and the naturalness of the output.

[0094] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0095] In this invention, the server includes means for receiving information requested by a user and generating a search query based on said information; means for automatically searching for information resources based on the generated search query and obtaining relevant information; means for organizing the obtained information and generating it as information fragments in a format that the user can understand; means for receiving voice input and converting it to text using speech recognition technology; means for analyzing the texted information request and providing the necessary information as an answer using artificial intelligence; and means for providing the answer in voice using speech synthesis technology. As a result, users can easily and efficiently obtain and use information using voice.

[0096] A "user" is someone who uses an information system to obtain specific information.

[0097] "Information" refers to data, knowledge, or related content that a user wishes to acquire.

[0098] A "search query" is a set of instructions or strings of characters generated in response to a user's request to retrieve information.

[0099] "Information resources" refer to databases, data stores, and other structures where necessary information is stored and accessible.

[0100] An "information fragment" is a collection of data that is organized and presented in a format that is easy for the user to understand.

[0101] "Voice input" is a method of requesting information or giving instructions to a system through the voice that the user speaks.

[0102] "Speech recognition technology" is a technology that converts spoken audio from a user into text format.

[0103] Artificial intelligence is a computer system that has the ability to analyze information requests and generate optimal responses.

[0104] "Speech synthesis technology" is a technology for reproducing text information in audio format.

[0105] This invention provides a system that allows users to easily obtain information by voice at home or in the workplace. The system includes speech recognition technology for voice-based user interaction and further uses speech synthesis technology to convert the acquired information from text to speech. For speech recognition, it utilizes platforms such as Google® Cloud Speech-to-Text to transcribe voice commands in real time, and for speech synthesis, it uses Amazon Polly.

[0106] Users provide voice input through home robots or smart devices. For example, they might issue a voice command such as, "Tell me the weather tomorrow." This voice is recognized by the device and sent to the server. The server converts the voice input into text and uses natural language processing techniques to identify relevant information in order to process the received request. If information is needed to meet the request, the server accesses appropriate data sources to collect and analyze the information.

[0107] The acquired information is integrated into a human-readable format and then provided as speech output through speech synthesis. This allows users to easily check and utilize the information by voice. An example of the prompt text mentioned above is a specific information request such as "Tell me the latest sports news," and the corresponding result can be obtained in voice.

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The user inputs information requests into the voice device using voice input. The voice input is a prompt phrase, such as "Tell me the weather tomorrow."

[0111] Step 2:

[0112] The terminal captures the input audio as a digital signal and converts it into text data using speech recognition technology such as Google Cloud Speech-to-Text. In this step, the input is audio data, and the output is the corresponding text data. Specifically, the microphone captures the audio and performs digital conversion for transmission to the server.

[0113] Step 3:

[0114] The server receives a text-based information request and parses it using a natural language processing engine. It extracts keywords from the request and identifies what information should be retrieved. The input for this step is text data, and the output is the information structure necessary for generating the search query. Specifically, this involves text analysis and interpretation of meaning based on context.

[0115] Step 4:

[0116] The server generates appropriate search queries based on the analyzed information and automatically issues queries to information resources. Here, it collects necessary information by referencing databases and external APIs. The input to this step is the information structure, and the output is the relevant information data. Specific operations include verifying database access credentials and sending and receiving API requests.

[0117] Step 5:

[0118] The server organizes the collected information data and integrates it into information fragments in a user-friendly format. These fragments, such as a weather forecast summary, are the output of that step. This allows users to intuitively understand the information. Specific operations include data filtering and formatting adjustments.

[0119] Step 6:

[0120] The server converts the integrated information fragments into speech data using speech synthesis technology such as Amazon Polly and sends it to the terminal. The input for this step is information fragments, and the output is speech data. Specifically, this involves speech synthesis processing to convert text into speech.

[0121] Step 7:

[0122] The terminal plays the received audio data to the user, providing information in audio format. This allows the user to access information without relying solely on visual cues. The input for this step is audio data, and the output is audio output. Specifically, audio playback is performed through the speaker.

[0123] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0124] This invention relates to an information acquisition system that combines an emotion engine that recognizes user emotions, and its embodiments are described below. This system not only acquires the information that the user needs, but also takes into account the user's emotional state, enabling the provision of more personalized and appropriate information.

[0125] First, the user uses the device to input the information or questions they want to obtain. The device incorporates an emotion engine that analyzes the user's voice and text to determine their emotions. The emotion engine identifies emotions such as joy, anger, and sadness from the input data, and determines the user's current emotional state.

[0126] Requests from the terminal are sent to the server, which parses the request and generates a search query. In this generation process, emotional information identified by the emotion engine is considered, and appropriate keywords and information are filtered according to the user's emotions. For example, if an urgent emotion is detected, relevant searches are prioritized.

[0127] The server searches internal information resources and retrieves the requested information. The retrieved information is organized into documents that reflect the user's emotional state. For example, if the emotion engine detects that the user is in a calm state, detailed and comprehensive information is provided, while if a stressed state is detected, the information is adjusted to convey only the essential information concisely.

[0128] The server sends personalized materials to the user's device. The user receives this information via their device, reviews the content, and can then request further details or additional information.

[0129] As a concrete example, consider a case where a user requests "data on market trends for a new product." If the device's emotion engine determines that the user's stress level is high, the server will generate a concise report focusing on basic statistical data and key trend information. This allows the user to quickly obtain the information they need without being overwhelmed by unnecessary information.

[0130] Thus, the system of the present invention can improve the accuracy and adaptability of information acquisition and provide an efficient and effective solution for addressing the emotional challenges faced by users.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] Users use their devices to input the information or questions they want to obtain. Input includes voice input and text input.

[0134] Step 2:

[0135] The device sends the input voice and text data to the emotion engine, which analyzes the user's emotions. The emotion engine uses natural language processing technology to identify emotional states such as joy, anger, and stress.

[0136] Step 3:

[0137] The device sends user requests and analyzed sentiment data to the server. The data sent includes specific information requests and metadata representing the user's sentiment state.

[0138] Step 4:

[0139] The server analyzes the received information request and generates search queries, taking sentiment data into consideration. Based on the sentiment, it adjusts the query priority and keyword filtering.

[0140] Step 5:

[0141] The server executes generated queries against internal databases and information resources to retrieve the requested information. Prioritized searches ensure that relevant information is retrieved efficiently.

[0142] Step 6:

[0143] The server analyzes the acquired information and creates materials based on the user's emotions. If the user is emotionally calm, comprehensive details are prioritized; if they are stressed, concise and clear information is prioritized.

[0144] Step 7:

[0145] The server sends the generated materials to the terminal and provides them to the user. The materials are formatted with emotionally appropriate language and style, making it easier for the user to understand the information.

[0146] Step 8:

[0147] Users view the materials provided through their device and request additional information as needed. These requests are then processed again by the sentiment engine, which performs a more detailed search process.

[0148] This entire process allows users to efficiently acquire information and obtain the necessary information in an emotionally sensitive manner.

[0149] (Example 2)

[0150] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0151] When users search for information, their emotional state is not taken into consideration, which can result in the information provided being unsuitable for them. Furthermore, when users are experiencing stress or emotional burden, complex information can further increase their burden. Additionally, filtering and providing information based on user emotions is difficult, highlighting the need for improved information services that cater to individual needs.

[0152] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0153] In this invention, the server includes means for receiving information requested by the user, generating a search query based on the information, and adjusting keywords considering the user's emotional state; means for automatically searching accumulated knowledge resources based on the generated search query and obtaining relevant information; and means for organizing the information obtained based on the emotional state and generating it as material in a format that the user can understand. This makes it possible to provide optimal information tailored to the emotional state of each individual user.

[0154] A "user" refers to an individual or legal entity that seeks to obtain information and is the entity that uses the system based on their request.

[0155] "Emotional state" refers to the psychological or emotional condition a user exhibits when requesting information, and includes emotions such as joy, sadness, and anger.

[0156] A "search query" refers to a query generated to retrieve information, which includes keywords that are tailored based on the user's needs and emotional state.

[0157] "Knowledge resources" refer to databases or information repositories that store information, which servers use to search and retrieve necessary information.

[0158] An "emotion engine" refers to software or hardware that identifies emotions from a user's voice or text data, and utilizes natural language processing and machine learning techniques.

[0159] "Filtering" refers to the process of selecting necessary or relevant parts of given information based on specific criteria.

[0160] This invention is a system that provides personalized and adaptive information based on the user's information requests, taking into account their emotional state.

[0161] Users input information using a terminal. The terminal has an interface that allows for voice and text input, as well as an emotion engine that analyzes the user's emotions. This emotion engine analyzes the input data using a natural language processing library and a machine learning model to identify the user's emotional state.

[0162] The terminal transmits information and emotional states entered by the user to the server. The server generates search queries based on the received data. The generated search queries are adjusted with the most appropriate keywords, taking into account the user's emotional state. The server automatically searches internal and external knowledge resources to retrieve highly relevant information.

[0163] The acquired information is organized to match the user's emotional state. The server uses a generative AI model to summarize the information and generate prompts, ensuring the information is presented in a way that best suits the user's needs and situation. These prompts might be phrased as, for example, "Please tell me the basic statistics and key trends regarding the market trends of the new product." During this process, especially if a stressful state is detected, the information is provided concisely and to the point, reducing the user's burden.

[0164] The server sends organized information to the terminal and provides it to the user. The user reviews the provided information and makes additional requests if further information is needed. The emotion engine works again on these new requests, providing information that takes into account the user's current emotional state. This allows the user to quickly and easily obtain the most relevant information for their situation.

[0165] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0166] Step 1:

[0167] The user uses the device to input the information they want to obtain via voice or text. This input is passed to an emotion engine that recognizes the user's emotional state. The input data contains specific details of the information to be obtained, and the device receives this information and performs preprocessing for emotion analysis.

[0168] Step 2:

[0169] The device uses an emotion engine to analyze user input data. Specifically, it extracts features from the input text using a natural language processing library and classifies emotions through a machine learning model. This process identifies the user's emotional state, such as joy, anger, or sadness, and generates emotion data as an analysis result.

[0170] Step 3:

[0171] The terminal sends the user's information request and sentiment data to the server. The server receives this data and begins the process of generating a search query based on the requested information. Here, keywords are automatically adjusted according to the entered sentiment, and the optimal query that reflects the sentiment is created.

[0172] Step 4:

[0173] The server uses the generated search query to search for knowledge resources. This search process accesses internal databases and external sources to prioritize extracting information that aligns with the user's needs and sentiments. The search results gather information that is highly relevant to the user.

[0174] Step 5:

[0175] The server organizes the acquired information and generates materials tailored to the user's emotions. For example, if the user is relaxed, it generates a document with comprehensive details, while if they are stressed, it generates a summary of the key points. A generative AI model is used here to design the prompts.

[0176] Step 6:

[0177] The server sends the generated information to the terminal. The terminal displays this information to the user, allowing the user to immediately review it. If the user requires further information based on the provided information, they can make additional requests. At this point, the emotion engine reactivates, and information based on the user's current emotional state continues to be provided.

[0178] (Application Example 2)

[0179] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0180] This invention aims to prevent information overload or insufficiency and enable users to acquire information without stress by providing information that takes into account the user's emotional state when they seek information. Currently, a large amount of information is provided, making it difficult for users to quickly obtain the information they need. Furthermore, providing information without considering the user's emotional state may reduce user satisfaction.

[0181] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0182] In this invention, the server includes means for receiving information requested by the user and generating a search query based on said information; means for analyzing the user's emotions from their voice or text and identifying their emotional state; and means for filtering information based on the generated search query and the identified emotional state and obtaining relevant information. This makes it possible to provide optimal information according to the user's emotional state.

[0183] A "user" is a person who uses an information system to seek information, and whose emotional state is taken into consideration.

[0184] "Information" refers to the specific content and data requested by the user, and is provided according to their emotional state.

[0185] A "search query" is data generated based on a user's request, containing conditions and keywords for exploring information resources.

[0186] An "emotion engine" is software that analyzes and identifies emotions such as joy, anger, and sadness from the user's voice and text data.

[0187] "Emotional state" is a concept that refers to the user's current mental state as identified by the emotion engine.

[0188] "Filtering" is the process of selecting acquired information based on specific conditions or criteria to provide the most appropriate content.

[0189] "Materials" refer to documents or data in which acquired information is organized and presented in a format that is easy for the user to understand.

[0190] "Accumulation" refers to the act of saving knowledge and data obtained from past search processes and making them available for use in subsequent searches.

[0191] To implement this invention, the following system and program will be constructed. The system will receive voice or text input from the user, analyze their emotional state, and provide appropriate information.

[0192] The server uses speech recognition software (e.g., a speech conversion tool) to convert the user's speech into text data. This text data is then passed to sentiment analysis software (e.g., a sentiment analysis engine) to identify the user's emotional state. Based on the user's emotional information and the requested information, a search query is generated.

[0193] The terminal sends the generated search query to the server and instructs it to retrieve relevant information from its built-in or connected database. The server searches the information resources and filters the retrieved information based on the user's emotional state.

[0194] Specifically, if an emotional state is identified as being under stress, the server will organize only the essential information into a concise document. On the other hand, if a relaxed state is determined, the server will provide a document that includes more detailed and comprehensive information.

[0195] If a user requests information about dinner recipes and is detected as being stressed, the server will immediately provide information on simple dishes. This allows users to avoid complexity and obtain information quickly.

[0196] In utilizing generative AI models, an example of a prompt would be, "Considering my desire to know about simple cooking, please suggest simple and easy recipes." This prompt provides the foundation for the AI ​​to generate more appropriate information.

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] The user inputs their information request into the terminal via voice or text. The input voice is converted into text data by speech recognition software. Here, the input is the user's voice or text, and the output is the recognized text data.

[0200] Step 2:

[0201] The device sends the converted text data to the sentiment analysis engine. The sentiment analysis engine analyzes this text data to identify the emotional state and outputs emotional information. In this step, the input is text data, and the output is data on the user's emotional state.

[0202] Step 3:

[0203] The terminal combines the user's request with identified sentiment information to generate a search query for the server. The input here is the user's request and sentiment state, and the output is the search query.

[0204] Step 4:

[0205] The server searches the database based on the received search query and retrieves relevant information. The input is the search query, and the output is a list of relevant information.

[0206] Step 5:

[0207] The server filters the acquired information according to the user's emotional state. It adjusts the information to be concise if the user is stressed, and detailed if they are relaxed. The input is a list of relevant information and the emotional state, and the output is the filtered information.

[0208] Step 6:

[0209] The server organizes the filtered information into a user-friendly format and sends it to the terminal. The input is filtered information, and the output is a formalized document.

[0210] Step 7:

[0211] Users can review the materials provided through the terminal and request further details or additional information as needed. The input is formalized material, and the output is the user's new request.

[0212] 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.

[0213] Data generation model 58 is a 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> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0214] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] 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.

[0218] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0219] 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.

[0220] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0221] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0222] 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.

[0223] 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 using the processor 28. The storage 32 stores the specific processing program 56.

[0224] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0225] The 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.

[0226] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0227] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0228] This invention is a system for efficiently acquiring information requested by users, and its embodiments are described in detail below.

[0229] The user first enters a request to obtain specific information through their terminal. For example, they might request "detailed information about the base station deployment in a specific area." The user's request is sent from the terminal to the server, which then parses the request. Based on the parsing results, the server automatically generates relevant search queries and issues these queries to the company's information resources.

[0230] The server retrieves necessary information from internal databases and documents and integrates the relevant information. The retrieved information is organized by the server and generated as a document in a user-friendly format. The document is sent to the terminal, and the user can view it through the terminal.

[0231] Furthermore, the server accumulates search know-how gained during processing and utilizes it in subsequent searches. This accumulation of knowledge improves the accuracy and speed of information retrieval by the system.

[0232] As a concrete example, consider a case where a user wants to obtain "sales data for a specific product over the past year." In this case, the terminal sends a request to the server, and the server generates the optimal query to retrieve the necessary data. It then collects all relevant sales data and generates a report including a graph that shows the sales trend by month and year at a glance, and sends it to the terminal. The user can easily review this report and easily access the information they need.

[0233] Thus, the present invention enables users to quickly and efficiently obtain necessary information from a vast amount of data, thereby enhancing the effectiveness of information utilization. The automated processes of the system contribute to improved work efficiency and significantly reduce the cumbersome information retrieval tasks in daily operations.

[0234] The following describes the processing flow.

[0235] Step 1:

[0236] The user uses a device to input the information they want to retrieve. This includes specific datasets and detailed requirements.

[0237] Step 2:

[0238] The terminal processes the user's request and sends the request to the server via the API. This request is structured in a data format such as JSON.

[0239] Step 3:

[0240] The server analyzes incoming requests and automatically generates search queries related to the requested information. Natural language processing technology is used for the analysis to accurately understand the user's request.

[0241] Step 4:

[0242] The server executes the generated queries against internal databases and information resources. It identifies and accesses the most suitable database tables and documents to retrieve the necessary information.

[0243] Step 5:

[0244] The server analyzes and organizes the acquired information. This analysis includes a process to verify the consistency and accuracy of the data.

[0245] Step 6:

[0246] The server organizes the analyzed information and generates a document. The document is formatted to be easily understood by the user and can include visual elements and graphs as needed.

[0247] Step 7:

[0248] The server sends the generated data to the terminal, providing information to the user.

[0249] Step 8:

[0250] Users can view and review the materials provided via their device. If they need any missing or additional information, they can submit a request again.

[0251] Step 9:

[0252] The server accumulates the results and learning from each search process, and uses this to improve the efficiency of subsequent information retrieval. This accumulation enables continuous improvement of the system's performance.

[0253] (Example 1)

[0254] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0255] In today's information society, efficiently retrieving necessary data from vast amounts of information is crucial. However, there are problems such as users not being able to easily access the information they want, and systems not being able to effectively utilize the knowledge gained in the process. Conventional search systems often have inappropriate query generation or the information is not organized in a way that is easy for users to understand, making efficient information retrieval difficult.

[0256] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0257] In this invention, the server includes means for receiving information requested by the user, analyzing the information to extract relevant keywords, generating an optimal search query based on the keywords using a generative AI model, and automatically searching for information resources and obtaining relevant information based on the generated search query. This allows the user to quickly obtain the desired information, and the system can utilize the knowledge gained through the search process in subsequent searches.

[0258] A "user" is an individual or organization that uses a system to obtain information.

[0259] An "information request" is a request that a user communicates to the system via their device to obtain specific information.

[0260] "Analysis" is the process of understanding the content of a received information request and extracting important elements and related keywords.

[0261] A "generative AI model" is software that uses machine learning algorithms to automatically generate appropriate search queries based on input data.

[0262] A "search query" is a set of instructions used to retrieve relevant data from an information resource, containing specific conditions for searching.

[0263] "Information resources" refer to a collection of information containing necessary data, such as internal company databases and documents.

[0264] "Information organization" is the process of structuring acquired information and processing it into a format that is easy for users to understand.

[0265] "Documents" are the final documents provided to users, visualizing organized information using charts, graphs, and text.

[0266] "Knowledge accumulation" refers to the method of saving know-how and patterns obtained during the search process so that they can be used in subsequent search processes.

[0267] The invention will now be described in terms of embodiments. This system is designed to allow users to efficiently obtain specific information. The user inputs an information retrieval request using a terminal, and this request is sent to a server. The server analyzes the request and uses a generative AI model to extract relevant keywords. This model automatically generates the most suitable search query for the user's request.

[0268] Subsequently, the server uses the generated search query to search for information resources and retrieve relevant information. These resources include internal databases and various documents. The retrieved information is then organized by the server into a user-friendly format. This organization process includes information integration and prioritization based on importance.

[0269] The server generates data based on organized information. This data often includes graphs and tables to visually represent the information. The generated data is sent to the terminal, where the user can view it and quickly access the necessary information. The server then accumulates the knowledge gained from the search process and uses that knowledge in subsequent searches to improve the accuracy of the system.

[0270] For example, if a user wants to know "details about the base station deployment in a specific area," they would enter the prompt "Please tell me the details of the base station deployment in a specific area" on their terminal. In response to this request, the server collects the relevant information and provides an organized report to the terminal. This allows the user to obtain the necessary information in a short amount of time.

[0271] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0272] Step 1:

[0273] The user uses a terminal to input a request for information retrieval. This request includes specific prompt statements regarding the particular information. The input request is sent from the terminal to the server. The input at this time is the "prompt statement," and the output is the "request data sent to the server."

[0274] Step 2:

[0275] The server analyzes the received request data and extracts keywords based on the request content. Using a generative AI model, it automatically generates search queries based on these keywords. The input is the "request data," and the output is the "automatically generated search query."

[0276] Step 3:

[0277] The server searches for information resources using the generated search query. Specifically, it refers to the in-house database and related documents to collect the necessary information. The input is the "search query", and the output is the "acquired information data".

[0278] Step 4:

[0279] The server organizes the acquired information data and generates materials that are easy for the user to understand. The materials include integration based on the importance of the information and visual elements such as graphs and tables. The input is the "information data", and the output is the "organized materials".

[0280] Step 5:

[0281] The server sends the organized materials to the terminal so that the user can view them. The terminal displays the received materials and assists the user in easily checking the information. The input is the "organized materials", and the output is the "display data that can be viewed by the user".

[0282] Step 6:

[0283] The server accumulates the knowledge obtained through the search process and uses it to improve the accuracy of future search processes. This knowledge accumulation makes the next search faster and more accurate. The input is the "information obtained in the search process", and the output is the "accumulated knowledge data".

[0284] (Application Example 1)

[0285] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0286] In a conventional information retrieval system, in order to quickly and efficiently obtain the information required by the user, manual retrieval is necessary, and there are problems that it takes a lot of time and effort in the process. In addition, when obtaining information using voice, there are problems with speech recognition accuracy, information analysis, and naturalness of output.

[0287] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following means.

[0288] In this invention, the server includes means for receiving the information required by the user and generating a search query based on the information, means for automatically searching information resources based on the generated search query and obtaining relevant information, means for organizing the obtained information and generating it as information pieces in a form understandable by the user, means for receiving voice input and converting it into text using speech recognition technology, means for analyzing the texturized information request and answering the necessary information using artificial intelligence, and means for providing the answer in voice using speech synthesis technology. As a result, the user can easily and efficiently obtain and use information using voice.

[0289] A "user" is a person who attempts to obtain specific information using an information system.

[0290] "Information" is data, knowledge, or related content that the user wants to obtain.

[0291] A "search query" is an instruction or character string generated to search for information in response to a user's request.

[0292] "Information resources" are databases, data stores, etc. where necessary information is accumulated and accessible.

[0293] "Information pieces" are a set of data provided by organizing the obtained information in a form easy for the user to understand.

[0294] "Voice input" is a method of requesting information or giving instructions to a system through the voice that the user speaks.

[0295] "Speech recognition technology" is a technology that converts spoken audio from a user into text format.

[0296] Artificial intelligence is a computer system that has the ability to analyze information requests and generate optimal responses.

[0297] "Speech synthesis technology" is a technology for reproducing text information in audio format.

[0298] This invention provides a system that allows users to easily obtain information by voice at home or in the workplace. The system includes speech recognition technology for voice-based user interaction and further uses speech synthesis technology to convert the acquired information from text to speech. For speech recognition, it utilizes a platform such as Google Cloud Speech-to-Text to transcribe voice commands in real time, and for speech synthesis, it uses Amazon Polly.

[0299] Users provide voice input through home robots or smart devices. For example, they might issue a voice command such as, "Tell me the weather tomorrow." This voice is recognized by the device and sent to the server. The server converts the voice input into text and uses natural language processing techniques to identify relevant information in order to process the received request. If information is needed to meet the request, the server accesses appropriate data sources to collect and analyze the information.

[0300] The acquired information is integrated into a human-readable format and then provided as speech output through speech synthesis. This allows users to easily check and utilize the information by voice. An example of the prompt text mentioned above is a specific information request such as "Tell me the latest sports news," and the corresponding result can be obtained in voice.

[0301] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0302] Step 1:

[0303] The user inputs an information request as voice to the voice device. The input voice is a prompt sentence such as "Tell me the weather for tomorrow".

[0304] Step 2:

[0305] The terminal captures the input voice as a digital signal and converts it into text data using a speech recognition technology such as Google Cloud Speech-to-Text. The input of this step is voice data, and the output is the corresponding text data. As a specific operation, the microphone captures the voice and performs digital conversion for transmission to the server.

[0306] Step 3:

[0307] The server receives the texturized information request and analyzes it with a natural language processing engine. It extracts the keywords contained in the request and identifies what information should be obtained. The input of this step is text data, and the output is the information structure necessary for generating a search query. As a specific operation, there is text analysis and interpretation of the meaning according to the context.

[0308] Step 4:

[0309] The server generates an appropriate search query based on the analyzed information and automatically issues a query to the information resource. Here, it refers to a database or an external API to collect the necessary information. The input of this step is the information structure, and the output is the relevant information data. As specific operations, there are confirmation of database access credentials and sending and receiving of API requests.

[0310] Step 5:

[0311] The server organizes the collected information data and integrates it into information fragments in a user-friendly format. These fragments, such as a weather forecast summary, are the output of that step. This allows users to intuitively understand the information. Specific operations include data filtering and formatting adjustments.

[0312] Step 6:

[0313] The server converts the integrated information fragments into speech data using speech synthesis technology such as Amazon Polly and sends it to the terminal. The input for this step is information fragments, and the output is speech data. Specifically, this involves speech synthesis processing to convert text into speech.

[0314] Step 7:

[0315] The terminal plays the received audio data to the user, providing information in audio format. This allows the user to access information without relying solely on visual cues. The input for this step is audio data, and the output is audio output. Specifically, audio playback is performed through the speaker.

[0316] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0317] This invention relates to an information acquisition system that combines an emotion engine that recognizes user emotions, and its embodiments are described below. This system not only acquires the information that the user needs, but also takes into account the user's emotional state, enabling the provision of more personalized and appropriate information.

[0318] First, the user uses the device to input the information or questions they want to obtain. The device incorporates an emotion engine that analyzes the user's voice and text to determine their emotions. The emotion engine identifies emotions such as joy, anger, and sadness from the input data, and determines the user's current emotional state.

[0319] Requests from the terminal are sent to the server, which parses the request and generates a search query. In this generation process, emotional information identified by the emotion engine is considered, and appropriate keywords and information are filtered according to the user's emotions. For example, if an urgent emotion is detected, relevant searches are prioritized.

[0320] The server searches internal information resources and retrieves the requested information. The retrieved information is organized into documents that reflect the user's emotional state. For example, if the emotion engine detects that the user is in a calm state, detailed and comprehensive information is provided, while if a stressed state is detected, the information is adjusted to convey only the essential information concisely.

[0321] The server sends personalized materials to the user's device. The user receives this information via their device, reviews the content, and can then request further details or additional information.

[0322] As a concrete example, consider a case where a user requests "data on market trends for a new product." If the device's emotion engine determines that the user's stress level is high, the server will generate a concise report focusing on basic statistical data and key trend information. This allows the user to quickly obtain the information they need without being overwhelmed by unnecessary information.

[0323] Thus, the system of the present invention can improve the accuracy and adaptability of information acquisition and provide an efficient and effective solution for addressing the emotional challenges faced by users.

[0324] The following describes the processing flow.

[0325] Step 1:

[0326] Users use their devices to input the information or questions they want to obtain. Input includes voice input and text input.

[0327] Step 2:

[0328] The device sends the input voice and text data to the emotion engine, which analyzes the user's emotions. The emotion engine uses natural language processing technology to identify emotional states such as joy, anger, and stress.

[0329] Step 3:

[0330] The device sends user requests and analyzed sentiment data to the server. The data sent includes specific information requests and metadata representing the user's sentiment state.

[0331] Step 4:

[0332] The server analyzes the received information request and generates search queries, taking sentiment data into consideration. Based on the sentiment, it adjusts the query priority and keyword filtering.

[0333] Step 5:

[0334] The server executes generated queries against internal databases and information resources to retrieve the requested information. Prioritized searches ensure that relevant information is retrieved efficiently.

[0335] Step 6:

[0336] The server analyzes the acquired information and creates materials based on the user's emotions. If the user is emotionally calm, comprehensive details are prioritized; if they are stressed, concise and clear information is prioritized.

[0337] Step 7:

[0338] The server sends the generated materials to the terminal and provides them to the user. The materials are formatted with emotionally appropriate language and style, making it easier for the user to understand the information.

[0339] Step 8:

[0340] Users view the materials provided through their device and request additional information as needed. These requests are then processed again by the sentiment engine, which performs a more detailed search process.

[0341] This entire process allows users to efficiently acquire information and obtain the necessary information in an emotionally sensitive manner.

[0342] (Example 2)

[0343] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0344] When users search for information, their emotional state is not taken into consideration, which can result in the information provided being unsuitable for them. Furthermore, when users are experiencing stress or emotional burden, complex information can further increase their burden. Additionally, filtering and providing information based on user emotions is difficult, highlighting the need for improved information services that cater to individual needs.

[0345] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0346] In this invention, the server includes means for receiving information requested by the user, generating a search query based on the information, and adjusting keywords considering the user's emotional state; means for automatically searching accumulated knowledge resources based on the generated search query and obtaining relevant information; and means for organizing the information obtained based on the emotional state and generating it as material in a format that the user can understand. This makes it possible to provide optimal information tailored to the emotional state of each individual user.

[0347] A "user" refers to an individual or legal entity that seeks to obtain information and is the entity that uses the system based on their request.

[0348] "Emotional state" refers to the psychological or emotional condition a user exhibits when requesting information, and includes emotions such as joy, sadness, and anger.

[0349] A "search query" refers to a query generated to retrieve information, which includes keywords that are tailored based on the user's needs and emotional state.

[0350] "Knowledge resources" refer to databases or information repositories that store information, which servers use to search and retrieve necessary information.

[0351] An "emotion engine" refers to software or hardware that identifies emotions from a user's voice or text data, and utilizes natural language processing and machine learning techniques.

[0352] "Filtering" refers to the process of selecting necessary or relevant parts of given information based on specific criteria.

[0353] This invention is a system that provides personalized and adaptive information based on the user's information requests, taking into account their emotional state.

[0354] Users input information using a terminal. The terminal has an interface that allows for voice and text input, as well as an emotion engine that analyzes the user's emotions. This emotion engine analyzes the input data using a natural language processing library and a machine learning model to identify the user's emotional state.

[0355] The terminal transmits information and emotional states entered by the user to the server. The server generates search queries based on the received data. The generated search queries are adjusted with the most appropriate keywords, taking into account the user's emotional state. The server automatically searches internal and external knowledge resources to retrieve highly relevant information.

[0356] The acquired information is organized to match the user's emotional state. The server uses a generative AI model to summarize the information and generate prompts, ensuring the information is presented in a way that best suits the user's needs and situation. These prompts might be phrased as, for example, "Please tell me the basic statistics and key trends regarding the market trends of the new product." During this process, especially if a stressful state is detected, the information is provided concisely and to the point, reducing the user's burden.

[0357] The server sends organized information to the terminal and provides it to the user. The user reviews the provided information and makes additional requests if further information is needed. The emotion engine works again on these new requests, providing information that takes into account the user's current emotional state. This allows the user to quickly and easily obtain the most relevant information for their situation.

[0358] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0359] Step 1:

[0360] The user uses the device to input the information they want to obtain via voice or text. This input is passed to an emotion engine that recognizes the user's emotional state. The input data contains specific details of the information to be obtained, and the device receives this information and performs preprocessing for emotion analysis.

[0361] Step 2:

[0362] The device uses an emotion engine to analyze user input data. Specifically, it extracts features from the input text using a natural language processing library and classifies emotions through a machine learning model. This process identifies the user's emotional state, such as joy, anger, or sadness, and generates emotion data as an analysis result.

[0363] Step 3:

[0364] The terminal sends the user's information request and sentiment data to the server. The server receives this data and begins the process of generating a search query based on the requested information. Here, keywords are automatically adjusted according to the entered sentiment, and the optimal query that reflects the sentiment is created.

[0365] Step 4:

[0366] The server uses the generated search query to search for knowledge resources. This search process accesses internal databases and external sources to prioritize extracting information that aligns with the user's needs and sentiments. The search results gather information that is highly relevant to the user.

[0367] Step 5:

[0368] The server organizes the acquired information and generates materials tailored to the user's emotions. For example, if the user is relaxed, it generates a document with comprehensive details, while if they are stressed, it generates a summary of the key points. A generative AI model is used here to design the prompts.

[0369] Step 6:

[0370] The server sends the generated information to the terminal. The terminal displays this information to the user, allowing the user to immediately review it. If the user requires further information based on the provided information, they can make additional requests. At this point, the emotion engine reactivates, and information based on the user's current emotional state continues to be provided.

[0371] (Application Example 2)

[0372] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0373] This invention aims to prevent information overload or insufficiency and enable users to acquire information without stress by providing information that takes into account the user's emotional state when they seek information. Currently, a large amount of information is provided, making it difficult for users to quickly obtain the information they need. Furthermore, providing information without considering the user's emotional state may reduce user satisfaction.

[0374] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0375] In this invention, the server includes means for receiving information requested by the user and generating a search query based on said information; means for analyzing the user's emotions from their voice or text and identifying their emotional state; and means for filtering information based on the generated search query and the identified emotional state and obtaining relevant information. This makes it possible to provide optimal information according to the user's emotional state.

[0376] A "user" is a person who uses an information system to seek information, and whose emotional state is taken into consideration.

[0377] "Information" refers to the specific content and data requested by the user, and is provided according to their emotional state.

[0378] A "search query" is data generated based on a user's request, containing conditions and keywords for exploring information resources.

[0379] An "emotion engine" is software that analyzes and identifies emotions such as joy, anger, and sadness from the user's voice and text data.

[0380] "Emotional state" is a concept that refers to the user's current mental state as identified by the emotion engine.

[0381] "Filtering" is the process of selecting acquired information based on specific conditions or criteria to provide the most appropriate content.

[0382] "Materials" refer to documents or data in which acquired information is organized and presented in a format that is easy for the user to understand.

[0383] "Accumulation" refers to the act of saving knowledge and data obtained from past search processes and making them available for use in subsequent searches.

[0384] To implement this invention, the following system and program will be constructed. The system will receive voice or text input from the user, analyze their emotional state, and provide appropriate information.

[0385] The server uses speech recognition software (e.g., a speech conversion tool) to convert the user's speech into text data. This text data is then passed to sentiment analysis software (e.g., a sentiment analysis engine) to identify the user's emotional state. Based on the user's emotional information and the requested information, a search query is generated.

[0386] The terminal sends the generated search query to the server and instructs it to retrieve relevant information from its built-in or connected database. The server searches the information resources and filters the retrieved information based on the user's emotional state.

[0387] Specifically, if an emotional state is identified as being under stress, the server will organize only the essential information into a concise document. On the other hand, if a relaxed state is determined, the server will provide a document that includes more detailed and comprehensive information.

[0388] If a user requests information about dinner recipes and is detected as being stressed, the server will immediately provide information on simple dishes. This allows users to avoid complexity and obtain information quickly.

[0389] In utilizing generative AI models, an example of a prompt would be, "Considering my desire to know about simple cooking, please suggest simple and easy recipes." This prompt provides the foundation for the AI ​​to generate more appropriate information.

[0390] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0391] Step 1:

[0392] The user inputs their information request into the terminal via voice or text. The input voice is converted into text data by speech recognition software. Here, the input is the user's voice or text, and the output is the recognized text data.

[0393] Step 2:

[0394] The device sends the converted text data to the sentiment analysis engine. The sentiment analysis engine analyzes this text data to identify the emotional state and outputs emotional information. In this step, the input is text data, and the output is data on the user's emotional state.

[0395] Step 3:

[0396] The terminal combines the user's request with identified sentiment information to generate a search query for the server. The input here is the user's request and sentiment state, and the output is the search query.

[0397] Step 4:

[0398] The server searches the database based on the received search query and retrieves relevant information. The input is the search query, and the output is a list of relevant information.

[0399] Step 5:

[0400] The server filters the acquired information according to the user's emotional state. It adjusts the information to be concise if the user is stressed, and detailed if they are relaxed. The input is a list of relevant information and the emotional state, and the output is the filtered information.

[0401] Step 6:

[0402] The server organizes the filtered information into a user-friendly format and sends it to the terminal. The input is filtered information, and the output is a formalized document.

[0403] Step 7:

[0404] Users can review the materials provided through the terminal and request further details or additional information as needed. The input is formalized material, and the output is the user's new request.

[0405] 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.

[0406] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0407] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0408] [Third Embodiment]

[0409] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0410] 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.

[0411] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0412] 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.

[0413] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0414] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0415] 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.

[0416] 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.

[0417] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0418] The 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.

[0419] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0420] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0421] This invention is a system for efficiently acquiring information requested by users, and its embodiments are described in detail below.

[0422] The user first enters a request to obtain specific information through their terminal. For example, they might request "detailed information about the base station deployment in a specific area." The user's request is sent from the terminal to the server, which then parses the request. Based on the parsing results, the server automatically generates relevant search queries and issues these queries to the company's information resources.

[0423] The server retrieves necessary information from internal databases and documents and integrates the relevant information. The retrieved information is organized by the server and generated as a document in a user-friendly format. The document is sent to the terminal, and the user can view it through the terminal.

[0424] Furthermore, the server accumulates search know-how gained during processing and utilizes it in subsequent searches. This accumulation of knowledge improves the accuracy and speed of information retrieval by the system.

[0425] As a concrete example, consider a case where a user wants to obtain "sales data for a specific product over the past year." In this case, the terminal sends a request to the server, and the server generates the optimal query to retrieve the necessary data. It then collects all relevant sales data and generates a report including a graph that shows the sales trend by month and year at a glance, and sends it to the terminal. The user can easily review this report and easily access the information they need.

[0426] Thus, the present invention enables users to quickly and efficiently obtain necessary information from a vast amount of data, thereby enhancing the effectiveness of information utilization. The automated processes of the system contribute to improved work efficiency and significantly reduce the cumbersome information retrieval tasks in daily operations.

[0427] The following describes the processing flow.

[0428] Step 1:

[0429] The user uses a device to input the information they want to retrieve. This includes specific datasets and detailed requirements.

[0430] Step 2:

[0431] The terminal processes the user's request and sends the request to the server via the API. This request is structured in a data format such as JSON.

[0432] Step 3:

[0433] The server analyzes incoming requests and automatically generates search queries related to the requested information. Natural language processing technology is used for the analysis to accurately understand the user's request.

[0434] Step 4:

[0435] The server executes the generated queries against internal databases and information resources. It identifies and accesses the most suitable database tables and documents to retrieve the necessary information.

[0436] Step 5:

[0437] The server analyzes and organizes the acquired information. This analysis includes a process to verify the consistency and accuracy of the data.

[0438] Step 6:

[0439] The server organizes the analyzed information and generates a document. The document is formatted to be easily understood by the user and can include visual elements and graphs as needed.

[0440] Step 7:

[0441] The server sends the generated data to the terminal, providing information to the user.

[0442] Step 8:

[0443] Users can view and review the materials provided via their device. If they need any missing or additional information, they can submit a request again.

[0444] Step 9:

[0445] The server accumulates the results and learning from each search process, and uses this to improve the efficiency of subsequent information retrieval. This accumulation enables continuous improvement of the system's performance.

[0446] (Example 1)

[0447] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0448] In today's information society, efficiently retrieving necessary data from vast amounts of information is crucial. However, there are problems such as users not being able to easily access the information they want, and systems not being able to effectively utilize the knowledge gained in the process. Conventional search systems often have inappropriate query generation or the information is not organized in a way that is easy for users to understand, making efficient information retrieval difficult.

[0449] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0450] In this invention, the server includes means for receiving information requested by the user, analyzing the information to extract relevant keywords, generating an optimal search query based on the keywords using a generative AI model, and automatically searching for information resources and obtaining relevant information based on the generated search query. This allows the user to quickly obtain the desired information, and the system can utilize the knowledge gained through the search process in subsequent searches.

[0451] A "user" is an individual or organization that uses a system to obtain information.

[0452] An "information request" is a request that a user communicates to the system via their device to obtain specific information.

[0453] "Analysis" is the process of understanding the content of a received information request and extracting important elements and related keywords.

[0454] A "generative AI model" is software that uses machine learning algorithms to automatically generate appropriate search queries based on input data.

[0455] A "search query" is a set of instructions used to retrieve relevant data from an information resource, containing specific conditions for searching.

[0456] "Information resources" refer to a collection of information containing necessary data, such as internal company databases and documents.

[0457] "Information organization" is the process of structuring acquired information and processing it into a format that is easy for users to understand.

[0458] "Documents" are the final documents provided to users, visualizing organized information using charts, graphs, and text.

[0459] "Knowledge accumulation" refers to the method of saving know-how and patterns obtained during the search process so that they can be used in subsequent search processes.

[0460] The invention will now be described in terms of embodiments. This system is designed to allow users to efficiently obtain specific information. The user inputs an information retrieval request using a terminal, and this request is sent to a server. The server analyzes the request and uses a generative AI model to extract relevant keywords. This model automatically generates the most suitable search query for the user's request.

[0461] Subsequently, the server uses the generated search query to search for information resources and retrieve relevant information. These resources include internal databases and various documents. The retrieved information is then organized by the server into a user-friendly format. This organization process includes information integration and prioritization based on importance.

[0462] The server generates data based on organized information. This data often includes graphs and tables to visually represent the information. The generated data is sent to the terminal, where the user can view it and quickly access the necessary information. The server then accumulates the knowledge gained from the search process and uses that knowledge in subsequent searches to improve the accuracy of the system.

[0463] For example, if a user wants to know "details about the base station deployment in a specific area," they would enter the prompt "Please tell me the details of the base station deployment in a specific area" on their terminal. In response to this request, the server collects the relevant information and provides an organized report to the terminal. This allows the user to obtain the necessary information in a short amount of time.

[0464] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0465] Step 1:

[0466] The user uses a terminal to input a request for information retrieval. This request includes specific prompt statements regarding the particular information. The input request is sent from the terminal to the server. The input at this time is the "prompt statement," and the output is the "request data sent to the server."

[0467] Step 2:

[0468] The server analyzes the received request data and extracts keywords based on the request content. Using a generative AI model, it automatically generates search queries based on these keywords. The input is the "request data," and the output is the "automatically generated search query."

[0469] Step 3:

[0470] The server uses the generated search query to search for information resources. Specifically, it refers to internal databases and related documents to collect the necessary information. The input is the "search query," and the output is the "recovered information data."

[0471] Step 4:

[0472] The server organizes the acquired information data and generates user-friendly materials. These materials include integration based on the importance of the information, as well as visual elements such as graphs and tables. The input is "information data," and the output is "organized materials."

[0473] Step 5:

[0474] The server sends organized data to the terminal, making it available for the user to view. The terminal displays the received data, helping the user easily access the information. The input is "organized data," and the output is "display data viewable by the user."

[0475] Step 6:

[0476] The server accumulates knowledge gained through the search process and uses it to improve the accuracy of future searches. This accumulation of knowledge makes subsequent searches faster and more accurate. The input is "information obtained through the search process," and the output is "accumulated knowledge data."

[0477] (Application Example 1)

[0478] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0479] Conventional information retrieval systems require manual searching to quickly and efficiently obtain the information users need, a process that is time-consuming and labor-intensive. Furthermore, when using voice-based information retrieval, there are challenges regarding speech recognition accuracy, information analysis, and the naturalness of the output.

[0480] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0481] In this invention, the server includes means for receiving information requested by a user and generating a search query based on said information; means for automatically searching for information resources based on the generated search query and obtaining relevant information; means for organizing the obtained information and generating it as information fragments in a format that the user can understand; means for receiving voice input and converting it to text using speech recognition technology; means for analyzing the texted information request and providing the necessary information as an answer using artificial intelligence; and means for providing the answer in voice using speech synthesis technology. As a result, users can easily and efficiently obtain and use information using voice.

[0482] A "user" is someone who uses an information system to obtain specific information.

[0483] "Information" refers to data, knowledge, or related content that a user wishes to acquire.

[0484] A "search query" is a set of instructions or strings of characters generated in response to a user's request to retrieve information.

[0485] "Information resources" refer to databases, data stores, and other structures where necessary information is stored and accessible.

[0486] An "information fragment" is a collection of data that is organized and presented in a format that is easy for the user to understand.

[0487] "Voice input" is a method of requesting information or giving instructions to a system through the voice that the user speaks.

[0488] "Speech recognition technology" is a technology that converts spoken audio from a user into text format.

[0489] Artificial intelligence is a computer system that has the ability to analyze information requests and generate optimal responses.

[0490] "Speech synthesis technology" is a technology for reproducing text information in audio format.

[0491] This invention provides a system that allows users to easily obtain information by voice at home or in the workplace. The system includes speech recognition technology for voice-based user interaction and further uses speech synthesis technology to convert the acquired information from text to speech. For speech recognition, it utilizes a platform such as Google Cloud Speech-to-Text to transcribe voice commands in real time, and for speech synthesis, it uses Amazon Polly.

[0492] Users provide voice input through home robots or smart devices. For example, they might issue a voice command such as, "Tell me the weather tomorrow." This voice is recognized by the device and sent to the server. The server converts the voice input into text and uses natural language processing techniques to identify relevant information in order to process the received request. If information is needed to meet the request, the server accesses appropriate data sources to collect and analyze the information.

[0493] The acquired information is integrated into a human-readable format and then provided as speech output through speech synthesis. This allows users to easily check and utilize the information by voice. An example of the prompt text mentioned above is a specific information request such as "Tell me the latest sports news," and the corresponding result can be obtained in voice.

[0494] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0495] Step 1:

[0496] The user inputs information requests into the voice device using voice input. The voice input is a prompt phrase, such as "Tell me the weather tomorrow."

[0497] Step 2:

[0498] The terminal captures the input audio as a digital signal and converts it into text data using speech recognition technology such as Google Cloud Speech-to-Text. In this step, the input is audio data, and the output is the corresponding text data. Specifically, the microphone captures the audio and performs digital conversion for transmission to the server.

[0499] Step 3:

[0500] The server receives a text-based information request and parses it using a natural language processing engine. It extracts keywords from the request and identifies what information should be retrieved. The input for this step is text data, and the output is the information structure necessary for generating the search query. Specifically, this involves text analysis and interpretation of meaning based on context.

[0501] Step 4:

[0502] The server generates appropriate search queries based on the analyzed information and automatically issues queries to information resources. Here, it collects necessary information by referencing databases and external APIs. The input to this step is the information structure, and the output is the relevant information data. Specific operations include verifying database access credentials and sending and receiving API requests.

[0503] Step 5:

[0504] The server organizes the collected information data and integrates it into information fragments in a user-friendly format. These fragments, such as a weather forecast summary, are the output of that step. This allows users to intuitively understand the information. Specific operations include data filtering and formatting adjustments.

[0505] Step 6:

[0506] The server converts the integrated information fragments into speech data using speech synthesis technology such as Amazon Polly and sends it to the terminal. The input for this step is information fragments, and the output is speech data. Specifically, this involves speech synthesis processing to convert text into speech.

[0507] Step 7:

[0508] The terminal plays the received audio data to the user, providing information in audio format. This allows the user to access information without relying solely on visual cues. The input for this step is audio data, and the output is audio output. Specifically, audio playback is performed through the speaker.

[0509] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0510] This invention relates to an information acquisition system that combines an emotion engine that recognizes user emotions, and its embodiments are described below. This system not only acquires the information that the user needs, but also takes into account the user's emotional state, enabling the provision of more personalized and appropriate information.

[0511] First, the user uses the device to input the information or questions they want to obtain. The device incorporates an emotion engine that analyzes the user's voice and text to determine their emotions. The emotion engine identifies emotions such as joy, anger, and sadness from the input data, and determines the user's current emotional state.

[0512] Requests from the terminal are sent to the server, which parses the request and generates a search query. In this generation process, emotional information identified by the emotion engine is considered, and appropriate keywords and information are filtered according to the user's emotions. For example, if an urgent emotion is detected, relevant searches are prioritized.

[0513] The server searches internal information resources and retrieves the requested information. The retrieved information is organized into documents that reflect the user's emotional state. For example, if the emotion engine detects that the user is in a calm state, detailed and comprehensive information is provided, while if a stressed state is detected, the information is adjusted to convey only the essential information concisely.

[0514] The server sends personalized materials to the user's device. The user receives this information via their device, reviews the content, and can then request further details or additional information.

[0515] As a concrete example, consider a case where a user requests "data on market trends for a new product." If the device's emotion engine determines that the user's stress level is high, the server will generate a concise report focusing on basic statistical data and key trend information. This allows the user to quickly obtain the information they need without being overwhelmed by unnecessary information.

[0516] Thus, the system of the present invention can improve the accuracy and adaptability of information acquisition and provide an efficient and effective solution for addressing the emotional challenges faced by users.

[0517] The following describes the processing flow.

[0518] Step 1:

[0519] Users use their devices to input the information or questions they want to obtain. Input includes voice input and text input.

[0520] Step 2:

[0521] The device sends the input voice and text data to the emotion engine, which analyzes the user's emotions. The emotion engine uses natural language processing technology to identify emotional states such as joy, anger, and stress.

[0522] Step 3:

[0523] The device sends user requests and analyzed sentiment data to the server. The data sent includes specific information requests and metadata representing the user's sentiment state.

[0524] Step 4:

[0525] The server analyzes the received information request and generates search queries, taking sentiment data into consideration. Based on the sentiment, it adjusts the query priority and keyword filtering.

[0526] Step 5:

[0527] The server executes generated queries against internal databases and information resources to retrieve the requested information. Prioritized searches ensure that relevant information is retrieved efficiently.

[0528] Step 6:

[0529] The server analyzes the acquired information and creates materials based on the user's emotions. If the user is emotionally calm, comprehensive details are prioritized; if they are stressed, concise and clear information is prioritized.

[0530] Step 7:

[0531] The server sends the generated materials to the terminal and provides them to the user. The materials are formatted with emotionally appropriate language and style, making it easier for the user to understand the information.

[0532] Step 8:

[0533] Users view the materials provided through their device and request additional information as needed. These requests are then processed again by the sentiment engine, which performs a more detailed search process.

[0534] This entire process allows users to efficiently acquire information and obtain the necessary information in an emotionally sensitive manner.

[0535] (Example 2)

[0536] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0537] When users search for information, their emotional state is not taken into consideration, which can result in the information provided being unsuitable for them. Furthermore, when users are experiencing stress or emotional burden, complex information can further increase their burden. Additionally, filtering and providing information based on user emotions is difficult, highlighting the need for improved information services that cater to individual needs.

[0538] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0539] In this invention, the server includes means for receiving information requested by the user, generating a search query based on the information, and adjusting keywords considering the user's emotional state; means for automatically searching accumulated knowledge resources based on the generated search query and obtaining relevant information; and means for organizing the information obtained based on the emotional state and generating it as material in a format that the user can understand. This makes it possible to provide optimal information tailored to the emotional state of each individual user.

[0540] A "user" refers to an individual or legal entity that seeks to obtain information and is the entity that uses the system based on their request.

[0541] "Emotional state" refers to the psychological or emotional condition a user exhibits when requesting information, and includes emotions such as joy, sadness, and anger.

[0542] A "search query" refers to a query generated to retrieve information, which includes keywords that are tailored based on the user's needs and emotional state.

[0543] "Knowledge resources" refer to databases or information repositories that store information, which servers use to search and retrieve necessary information.

[0544] An "emotion engine" refers to software or hardware that identifies emotions from a user's voice or text data, and utilizes natural language processing and machine learning techniques.

[0545] "Filtering" refers to the process of selecting necessary or relevant parts of given information based on specific criteria.

[0546] This invention is a system that provides personalized and adaptive information based on the user's information requests, taking into account their emotional state.

[0547] Users input information using a terminal. The terminal has an interface that allows for voice and text input, as well as an emotion engine that analyzes the user's emotions. This emotion engine analyzes the input data using a natural language processing library and a machine learning model to identify the user's emotional state.

[0548] The terminal transmits information and emotional states entered by the user to the server. The server generates search queries based on the received data. The generated search queries are adjusted with the most appropriate keywords, taking into account the user's emotional state. The server automatically searches internal and external knowledge resources to retrieve highly relevant information.

[0549] The acquired information is organized to match the user's emotional state. The server uses a generative AI model to summarize the information and generate prompts, ensuring the information is presented in a way that best suits the user's needs and situation. These prompts might be phrased as, for example, "Please tell me the basic statistics and key trends regarding the market trends of the new product." During this process, especially if a stressful state is detected, the information is provided concisely and to the point, reducing the user's burden.

[0550] The server sends organized information to the terminal and provides it to the user. The user reviews the provided information and makes additional requests if further information is needed. The emotion engine works again on these new requests, providing information that takes into account the user's current emotional state. This allows the user to quickly and easily obtain the most relevant information for their situation.

[0551] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0552] Step 1:

[0553] The user uses the device to input the information they want to obtain via voice or text. This input is passed to an emotion engine that recognizes the user's emotional state. The input data contains specific details of the information to be obtained, and the device receives this information and performs preprocessing for emotion analysis.

[0554] Step 2:

[0555] The device uses an emotion engine to analyze user input data. Specifically, it extracts features from the input text using a natural language processing library and classifies emotions through a machine learning model. This process identifies the user's emotional state, such as joy, anger, or sadness, and generates emotion data as an analysis result.

[0556] Step 3:

[0557] The terminal sends the user's information request and sentiment data to the server. The server receives this data and begins the process of generating a search query based on the requested information. Here, keywords are automatically adjusted according to the entered sentiment, and the optimal query that reflects the sentiment is created.

[0558] Step 4:

[0559] The server uses the generated search query to search for knowledge resources. This search process accesses internal databases and external sources to prioritize extracting information that aligns with the user's needs and sentiments. The search results gather information that is highly relevant to the user.

[0560] Step 5:

[0561] The server organizes the acquired information and generates materials tailored to the user's emotions. For example, if the user is relaxed, it generates a document with comprehensive details, while if they are stressed, it generates a summary of the key points. A generative AI model is used here to design the prompts.

[0562] Step 6:

[0563] The server sends the generated information to the terminal. The terminal displays this information to the user, allowing the user to immediately review it. If the user requires further information based on the provided information, they can make additional requests. At this point, the emotion engine reactivates, and information based on the user's current emotional state continues to be provided.

[0564] (Application Example 2)

[0565] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0566] This invention aims to prevent information overload or insufficiency and enable users to acquire information without stress by providing information that takes into account the user's emotional state when they seek information. Currently, a large amount of information is provided, making it difficult for users to quickly obtain the information they need. Furthermore, providing information without considering the user's emotional state may reduce user satisfaction.

[0567] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0568] In this invention, the server includes means for receiving information requested by the user and generating a search query based on said information; means for analyzing the user's emotions from their voice or text and identifying their emotional state; and means for filtering information based on the generated search query and the identified emotional state and obtaining relevant information. This makes it possible to provide optimal information according to the user's emotional state.

[0569] A "user" is a person who uses an information system to seek information, and whose emotional state is taken into consideration.

[0570] "Information" refers to the specific content and data requested by the user, and is provided according to their emotional state.

[0571] A "search query" is data generated based on a user's request, containing conditions and keywords for exploring information resources.

[0572] An "emotion engine" is software that analyzes and identifies emotions such as joy, anger, and sadness from the user's voice and text data.

[0573] "Emotional state" is a concept that refers to the user's current mental state as identified by the emotion engine.

[0574] "Filtering" is the process of selecting acquired information based on specific conditions or criteria to provide the most appropriate content.

[0575] "Materials" refer to documents or data in which acquired information is organized and presented in a format that is easy for the user to understand.

[0576] "Accumulation" refers to the act of saving knowledge and data obtained from past search processes and making them available for use in subsequent searches.

[0577] To implement this invention, the following system and program will be constructed. The system will receive voice or text input from the user, analyze their emotional state, and provide appropriate information.

[0578] The server uses speech recognition software (e.g., a speech conversion tool) to convert the user's speech into text data. This text data is then passed to sentiment analysis software (e.g., a sentiment analysis engine) to identify the user's emotional state. Based on the user's emotional information and the requested information, a search query is generated.

[0579] The terminal sends the generated search query to the server and instructs it to retrieve relevant information from its built-in or connected database. The server searches the information resources and filters the retrieved information based on the user's emotional state.

[0580] Specifically, if an emotional state is identified as being under stress, the server will organize only the essential information into a concise document. On the other hand, if a relaxed state is determined, the server will provide a document that includes more detailed and comprehensive information.

[0581] If a user requests information about dinner recipes and is detected as being stressed, the server will immediately provide information on simple dishes. This allows users to avoid complexity and obtain information quickly.

[0582] In utilizing generative AI models, an example of a prompt would be, "Considering my desire to know about simple cooking, please suggest simple and easy recipes." This prompt provides the foundation for the AI ​​to generate more appropriate information.

[0583] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0584] Step 1:

[0585] The user inputs their information request into the terminal via voice or text. The input voice is converted into text data by speech recognition software. Here, the input is the user's voice or text, and the output is the recognized text data.

[0586] Step 2:

[0587] The device sends the converted text data to the sentiment analysis engine. The sentiment analysis engine analyzes this text data to identify the emotional state and outputs emotional information. In this step, the input is text data, and the output is data on the user's emotional state.

[0588] Step 3:

[0589] The terminal combines the user's request with identified sentiment information to generate a search query for the server. The input here is the user's request and sentiment state, and the output is the search query.

[0590] Step 4:

[0591] The server searches the database based on the received search query and retrieves relevant information. The input is the search query, and the output is a list of relevant information.

[0592] Step 5:

[0593] The server filters the acquired information according to the user's emotional state. It adjusts the information to be concise if the user is stressed, and detailed if they are relaxed. The input is a list of relevant information and the emotional state, and the output is the filtered information.

[0594] Step 6:

[0595] The server organizes the filtered information into a user-friendly format and sends it to the terminal. The input is filtered information, and the output is a formalized document.

[0596] Step 7:

[0597] Users can review the materials provided through the terminal and request further details or additional information as needed. The input is formalized material, and the output is the user's new request.

[0598] 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.

[0599] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0600] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0601] [Fourth Embodiment]

[0602] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0603] 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.

[0604] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0605] 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.

[0606] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0607] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0608] 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.

[0609] 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. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0610] 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.

[0611] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0612] The 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.

[0613] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0614] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0615] This invention is a system for efficiently acquiring information requested by users, and its embodiments are described in detail below.

[0616] The user first enters a request to obtain specific information through their terminal. For example, they might request "detailed information about the base station deployment in a specific area." The user's request is sent from the terminal to the server, which then parses the request. Based on the parsing results, the server automatically generates relevant search queries and issues these queries to the company's information resources.

[0617] The server retrieves necessary information from internal databases and documents and integrates the relevant information. The retrieved information is organized by the server and generated as a document in a user-friendly format. The document is sent to the terminal, and the user can view it through the terminal.

[0618] Furthermore, the server accumulates search know-how gained during processing and utilizes it in subsequent searches. This accumulation of knowledge improves the accuracy and speed of information retrieval by the system.

[0619] As a concrete example, consider a case where a user wants to obtain "sales data for a specific product over the past year." In this case, the terminal sends a request to the server, and the server generates the optimal query to retrieve the necessary data. It then collects all relevant sales data and generates a report including a graph that shows the sales trend by month and year at a glance, and sends it to the terminal. The user can easily review this report and easily access the information they need.

[0620] Thus, the present invention enables users to quickly and efficiently obtain necessary information from a vast amount of data, thereby enhancing the effectiveness of information utilization. The automated processes of the system contribute to improved work efficiency and significantly reduce the cumbersome information retrieval tasks in daily operations.

[0621] The following describes the processing flow.

[0622] Step 1:

[0623] The user uses a device to input the information they want to retrieve. This includes specific datasets and detailed requirements.

[0624] Step 2:

[0625] The terminal processes the user's request and sends the request to the server via the API. This request is structured in a data format such as JSON.

[0626] Step 3:

[0627] The server analyzes incoming requests and automatically generates search queries related to the requested information. Natural language processing technology is used for the analysis to accurately understand the user's request.

[0628] Step 4:

[0629] The server executes the generated queries against internal databases and information resources. It identifies and accesses the most suitable database tables and documents to retrieve the necessary information.

[0630] Step 5:

[0631] The server analyzes and organizes the acquired information. This analysis includes a process to verify the consistency and accuracy of the data.

[0632] Step 6:

[0633] The server organizes the analyzed information and generates a document. The document is formatted to be easily understood by the user and can include visual elements and graphs as needed.

[0634] Step 7:

[0635] The server sends the generated data to the terminal, providing information to the user.

[0636] Step 8:

[0637] Users can view and review the materials provided via their device. If they need any missing or additional information, they can submit a request again.

[0638] Step 9:

[0639] The server accumulates the results and learning from each search process, and uses this to improve the efficiency of subsequent information retrieval. This accumulation enables continuous improvement of the system's performance.

[0640] (Example 1)

[0641] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0642] In today's information society, efficiently retrieving necessary data from vast amounts of information is crucial. However, there are problems such as users not being able to easily access the information they want, and systems not being able to effectively utilize the knowledge gained in the process. Conventional search systems often have inappropriate query generation or the information is not organized in a way that is easy for users to understand, making efficient information retrieval difficult.

[0643] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0644] In this invention, the server includes means for receiving information requested by the user, analyzing the information to extract relevant keywords, generating an optimal search query based on the keywords using a generative AI model, and automatically searching for information resources and obtaining relevant information based on the generated search query. This allows the user to quickly obtain the desired information, and the system can utilize the knowledge gained through the search process in subsequent searches.

[0645] A "user" is an individual or organization that uses a system to obtain information.

[0646] An "information request" is a request that a user communicates to the system via their device to obtain specific information.

[0647] "Analysis" is the process of understanding the content of a received information request and extracting important elements and related keywords.

[0648] A "generative AI model" is software that uses machine learning algorithms to automatically generate appropriate search queries based on input data.

[0649] A "search query" is a set of instructions used to retrieve relevant data from an information resource, containing specific conditions for searching.

[0650] "Information resources" refer to a collection of information containing necessary data, such as internal company databases and documents.

[0651] "Information organization" is the process of structuring acquired information and processing it into a format that is easy for users to understand.

[0652] "Documents" are the final documents provided to users, visualizing organized information using charts, graphs, and text.

[0653] "Knowledge accumulation" refers to the method of saving know-how and patterns obtained during the search process so that they can be used in subsequent search processes.

[0654] The invention will now be described in terms of embodiments. This system is designed to allow users to efficiently obtain specific information. The user inputs an information retrieval request using a terminal, and this request is sent to a server. The server analyzes the request and uses a generative AI model to extract relevant keywords. This model automatically generates the most suitable search query for the user's request.

[0655] Subsequently, the server uses the generated search query to search for information resources and retrieve relevant information. These resources include internal databases and various documents. The retrieved information is then organized by the server into a user-friendly format. This organization process includes information integration and prioritization based on importance.

[0656] The server generates data based on organized information. This data often includes graphs and tables to visually represent the information. The generated data is sent to the terminal, where the user can view it and quickly access the necessary information. The server then accumulates the knowledge gained from the search process and uses that knowledge in subsequent searches to improve the accuracy of the system.

[0657] For example, if a user wants to know "details about the base station deployment in a specific area," they would enter the prompt "Please tell me the details of the base station deployment in a specific area" on their terminal. In response to this request, the server collects the relevant information and provides an organized report to the terminal. This allows the user to obtain the necessary information in a short amount of time.

[0658] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0659] Step 1:

[0660] The user uses a terminal to input a request for information retrieval. This request includes specific prompt statements regarding the particular information. The input request is sent from the terminal to the server. The input at this time is the "prompt statement," and the output is the "request data sent to the server."

[0661] Step 2:

[0662] The server analyzes the received request data and extracts keywords based on the request content. Using a generative AI model, it automatically generates search queries based on these keywords. The input is the "request data," and the output is the "automatically generated search query."

[0663] Step 3:

[0664] The server uses the generated search query to search for information resources. Specifically, it refers to internal databases and related documents to collect the necessary information. The input is the "search query," and the output is the "recovered information data."

[0665] Step 4:

[0666] The server organizes the acquired information data and generates user-friendly materials. These materials include integration based on the importance of the information, as well as visual elements such as graphs and tables. The input is "information data," and the output is "organized materials."

[0667] Step 5:

[0668] The server sends organized data to the terminal, making it available for the user to view. The terminal displays the received data, helping the user easily access the information. The input is "organized data," and the output is "display data viewable by the user."

[0669] Step 6:

[0670] The server accumulates knowledge gained through the search process and uses it to improve the accuracy of future searches. This accumulation of knowledge makes subsequent searches faster and more accurate. The input is "information obtained through the search process," and the output is "accumulated knowledge data."

[0671] (Application Example 1)

[0672] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0673] Conventional information retrieval systems require manual searching to quickly and efficiently obtain the information users need, a process that is time-consuming and labor-intensive. Furthermore, when using voice-based information retrieval, there are challenges regarding speech recognition accuracy, information analysis, and the naturalness of the output.

[0674] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0675] In this invention, the server includes means for receiving information requested by a user and generating a search query based on said information; means for automatically searching for information resources based on the generated search query and obtaining relevant information; means for organizing the obtained information and generating it as information fragments in a format that the user can understand; means for receiving voice input and converting it to text using speech recognition technology; means for analyzing the texted information request and providing the necessary information as an answer using artificial intelligence; and means for providing the answer in voice using speech synthesis technology. As a result, users can easily and efficiently obtain and use information using voice.

[0676] A "user" is someone who uses an information system to obtain specific information.

[0677] "Information" refers to data, knowledge, or related content that a user wishes to acquire.

[0678] A "search query" is a set of instructions or strings of characters generated in response to a user's request to retrieve information.

[0679] "Information resources" refer to databases, data stores, and other structures where necessary information is stored and accessible.

[0680] An "information fragment" is a collection of data that is organized and presented in a format that is easy for the user to understand.

[0681] "Voice input" is a method of requesting information or giving instructions to a system through the voice that the user speaks.

[0682] "Speech recognition technology" is a technology that converts spoken audio from a user into text format.

[0683] Artificial intelligence is a computer system that has the ability to analyze information requests and generate optimal responses.

[0684] "Speech synthesis technology" is a technology for reproducing text information in audio format.

[0685] This invention provides a system that allows users to easily obtain information by voice at home or in the workplace. The system includes speech recognition technology for voice-based user interaction and further uses speech synthesis technology to convert the acquired information from text to speech. For speech recognition, it utilizes a platform such as Google Cloud Speech-to-Text to transcribe voice commands in real time, and for speech synthesis, it uses Amazon Polly.

[0686] Users provide voice input through home robots or smart devices. For example, they might issue a voice command such as, "Tell me the weather tomorrow." This voice is recognized by the device and sent to the server. The server converts the voice input into text and uses natural language processing techniques to identify relevant information in order to process the received request. If information is needed to meet the request, the server accesses appropriate data sources to collect and analyze the information.

[0687] The acquired information is integrated into a human-readable format and then provided as speech output through speech synthesis. This allows users to easily check and utilize the information by voice. An example of the prompt text mentioned above is a specific information request such as "Tell me the latest sports news," and the corresponding result can be obtained in voice.

[0688] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0689] Step 1:

[0690] The user inputs information requests into the voice device using voice input. The voice input is a prompt phrase, such as "Tell me the weather tomorrow."

[0691] Step 2:

[0692] The terminal captures the input audio as a digital signal and converts it into text data using speech recognition technology such as Google Cloud Speech-to-Text. In this step, the input is audio data, and the output is the corresponding text data. Specifically, the microphone captures the audio and performs digital conversion for transmission to the server.

[0693] Step 3:

[0694] The server receives a text-based information request and parses it using a natural language processing engine. It extracts keywords from the request and identifies what information should be retrieved. The input for this step is text data, and the output is the information structure necessary for generating the search query. Specifically, this involves text analysis and interpretation of meaning based on context.

[0695] Step 4:

[0696] The server generates appropriate search queries based on the analyzed information and automatically issues queries to information resources. Here, it collects necessary information by referencing databases and external APIs. The input to this step is the information structure, and the output is the relevant information data. Specific operations include verifying database access credentials and sending and receiving API requests.

[0697] Step 5:

[0698] The server organizes the collected information data and integrates it into information fragments in a user-friendly format. These fragments, such as a weather forecast summary, are the output of that step. This allows users to intuitively understand the information. Specific operations include data filtering and formatting adjustments.

[0699] Step 6:

[0700] The server converts the integrated information fragments into speech data using speech synthesis technology such as Amazon Polly and sends it to the terminal. The input for this step is information fragments, and the output is speech data. Specifically, this involves speech synthesis processing to convert text into speech.

[0701] Step 7:

[0702] The terminal plays the received audio data to the user, providing information in audio format. This allows the user to access information without relying solely on visual cues. The input for this step is audio data, and the output is audio output. Specifically, audio playback is performed through the speaker.

[0703] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0704] This invention relates to an information acquisition system that combines an emotion engine that recognizes user emotions, and its embodiments are described below. This system not only acquires the information that the user needs, but also takes into account the user's emotional state, enabling the provision of more personalized and appropriate information.

[0705] First, the user uses the device to input the information or questions they want to obtain. The device incorporates an emotion engine that analyzes the user's voice and text to determine their emotions. The emotion engine identifies emotions such as joy, anger, and sadness from the input data, and determines the user's current emotional state.

[0706] Requests from the terminal are sent to the server, which parses the request and generates a search query. In this generation process, emotional information identified by the emotion engine is considered, and appropriate keywords and information are filtered according to the user's emotions. For example, if an urgent emotion is detected, relevant searches are prioritized.

[0707] The server searches internal information resources and retrieves the requested information. The retrieved information is organized into documents that reflect the user's emotional state. For example, if the emotion engine detects that the user is in a calm state, detailed and comprehensive information is provided, while if a stressed state is detected, the information is adjusted to convey only the essential information concisely.

[0708] The server sends personalized materials to the user's device. The user receives this information via their device, reviews the content, and can then request further details or additional information.

[0709] As a concrete example, consider a case where a user requests "data on market trends for a new product." If the device's emotion engine determines that the user's stress level is high, the server will generate a concise report focusing on basic statistical data and key trend information. This allows the user to quickly obtain the information they need without being overwhelmed by unnecessary information.

[0710] Thus, the system of the present invention can improve the accuracy and adaptability of information acquisition and provide an efficient and effective solution for addressing the emotional challenges faced by users.

[0711] The following describes the processing flow.

[0712] Step 1:

[0713] Users use their devices to input the information or questions they want to obtain. Input includes voice input and text input.

[0714] Step 2:

[0715] The device sends the input voice and text data to the emotion engine, which analyzes the user's emotions. The emotion engine uses natural language processing technology to identify emotional states such as joy, anger, and stress.

[0716] Step 3:

[0717] The device sends user requests and analyzed sentiment data to the server. The data sent includes specific information requests and metadata representing the user's sentiment state.

[0718] Step 4:

[0719] The server analyzes the received information request and generates search queries, taking sentiment data into consideration. Based on the sentiment, it adjusts the query priority and keyword filtering.

[0720] Step 5:

[0721] The server executes generated queries against internal databases and information resources to retrieve the requested information. Prioritized searches ensure that relevant information is retrieved efficiently.

[0722] Step 6:

[0723] The server analyzes the acquired information and creates materials based on the user's emotions. If the user is emotionally calm, comprehensive details are prioritized; if they are stressed, concise and clear information is prioritized.

[0724] Step 7:

[0725] The server sends the generated materials to the terminal and provides them to the user. The materials are formatted with emotionally appropriate language and style, making it easier for the user to understand the information.

[0726] Step 8:

[0727] Users view the materials provided through their device and request additional information as needed. These requests are then processed again by the sentiment engine, which performs a more detailed search process.

[0728] This entire process allows users to efficiently acquire information and obtain the necessary information in an emotionally sensitive manner.

[0729] (Example 2)

[0730] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0731] When users search for information, their emotional state is not taken into consideration, which can result in the information provided being unsuitable for them. Furthermore, when users are experiencing stress or emotional burden, complex information can further increase their burden. Additionally, filtering and providing information based on user emotions is difficult, highlighting the need for improved information services that cater to individual needs.

[0732] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0733] In this invention, the server includes means for receiving information requested by the user, generating a search query based on the information, and adjusting keywords considering the user's emotional state; means for automatically searching accumulated knowledge resources based on the generated search query and obtaining relevant information; and means for organizing the information obtained based on the emotional state and generating it as material in a format that the user can understand. This makes it possible to provide optimal information tailored to the emotional state of each individual user.

[0734] A "user" refers to an individual or legal entity that seeks to obtain information and is the entity that uses the system based on their request.

[0735] "Emotional state" refers to the psychological or emotional condition a user exhibits when requesting information, and includes emotions such as joy, sadness, and anger.

[0736] A "search query" refers to a query generated to retrieve information, which includes keywords that are tailored based on the user's needs and emotional state.

[0737] "Knowledge resources" refer to databases or information repositories that store information, which servers use to search and retrieve necessary information.

[0738] An "emotion engine" refers to software or hardware that identifies emotions from a user's voice or text data, and utilizes natural language processing and machine learning techniques.

[0739] "Filtering" refers to the process of selecting necessary or relevant parts of given information based on specific criteria.

[0740] This invention is a system that provides personalized and adaptive information based on the user's information requests, taking into account their emotional state.

[0741] Users input information using a terminal. The terminal has an interface that allows for voice and text input, as well as an emotion engine that analyzes the user's emotions. This emotion engine analyzes the input data using a natural language processing library and a machine learning model to identify the user's emotional state.

[0742] The terminal transmits information and emotional states entered by the user to the server. The server generates search queries based on the received data. The generated search queries are adjusted with the most appropriate keywords, taking into account the user's emotional state. The server automatically searches internal and external knowledge resources to retrieve highly relevant information.

[0743] The acquired information is organized to match the user's emotional state. The server uses a generative AI model to summarize the information and generate prompts, ensuring the information is presented in a way that best suits the user's needs and situation. These prompts might be phrased as, for example, "Please tell me the basic statistics and key trends regarding the market trends of the new product." During this process, especially if a stressful state is detected, the information is provided concisely and to the point, reducing the user's burden.

[0744] The server sends organized information to the terminal and provides it to the user. The user reviews the provided information and makes additional requests if further information is needed. The emotion engine works again on these new requests, providing information that takes into account the user's current emotional state. This allows the user to quickly and easily obtain the most relevant information for their situation.

[0745] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0746] Step 1:

[0747] The user uses the device to input the information they want to obtain via voice or text. This input is passed to an emotion engine that recognizes the user's emotional state. The input data contains specific details of the information to be obtained, and the device receives this information and performs preprocessing for emotion analysis.

[0748] Step 2:

[0749] The device uses an emotion engine to analyze user input data. Specifically, it extracts features from the input text using a natural language processing library and classifies emotions through a machine learning model. This process identifies the user's emotional state, such as joy, anger, or sadness, and generates emotion data as an analysis result.

[0750] Step 3:

[0751] The terminal sends the user's information request and sentiment data to the server. The server receives this data and begins the process of generating a search query based on the requested information. Here, keywords are automatically adjusted according to the entered sentiment, and the optimal query that reflects the sentiment is created.

[0752] Step 4:

[0753] The server uses the generated search query to search for knowledge resources. This search process accesses internal databases and external sources to prioritize extracting information that aligns with the user's needs and sentiments. The search results gather information that is highly relevant to the user.

[0754] Step 5:

[0755] The server organizes the acquired information and generates materials tailored to the user's emotions. For example, if the user is relaxed, it generates a document with comprehensive details, while if they are stressed, it generates a summary of the key points. A generative AI model is used here to design the prompts.

[0756] Step 6:

[0757] The server sends the generated information to the terminal. The terminal displays this information to the user, allowing the user to immediately review it. If the user requires further information based on the provided information, they can make additional requests. At this point, the emotion engine reactivates, and information based on the user's current emotional state continues to be provided.

[0758] (Application Example 2)

[0759] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0760] This invention aims to prevent information overload or insufficiency and enable users to acquire information without stress by providing information that takes into account the user's emotional state when they seek information. Currently, a large amount of information is provided, making it difficult for users to quickly obtain the information they need. Furthermore, providing information without considering the user's emotional state may reduce user satisfaction.

[0761] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0762] In this invention, the server includes means for receiving information requested by the user and generating a search query based on said information; means for analyzing the user's emotions from their voice or text and identifying their emotional state; and means for filtering information based on the generated search query and the identified emotional state and obtaining relevant information. This makes it possible to provide optimal information according to the user's emotional state.

[0763] A "user" is a person who uses an information system to seek information, and whose emotional state is taken into consideration.

[0764] "Information" refers to the specific content and data requested by the user, and is provided according to their emotional state.

[0765] A "search query" is data generated based on a user's request, containing conditions and keywords for exploring information resources.

[0766] An "emotion engine" is software that analyzes and identifies emotions such as joy, anger, and sadness from the user's voice and text data.

[0767] "Emotional state" is a concept that refers to the user's current mental state as identified by the emotion engine.

[0768] "Filtering" is the process of selecting acquired information based on specific conditions or criteria to provide the most appropriate content.

[0769] "Materials" refer to documents or data in which acquired information is organized and presented in a format that is easy for the user to understand.

[0770] "Accumulation" refers to the act of saving knowledge and data obtained from past search processes and making them available for use in subsequent searches.

[0771] To implement this invention, the following system and program will be constructed. The system will receive voice or text input from the user, analyze their emotional state, and provide appropriate information.

[0772] The server uses speech recognition software (e.g., a speech conversion tool) to convert the user's speech into text data. This text data is then passed to sentiment analysis software (e.g., a sentiment analysis engine) to identify the user's emotional state. Based on the user's emotional information and the requested information, a search query is generated.

[0773] The terminal sends the generated search query to the server and instructs it to retrieve relevant information from its built-in or connected database. The server searches the information resources and filters the retrieved information based on the user's emotional state.

[0774] Specifically, if an emotional state is identified as being under stress, the server will organize only the essential information into a concise document. On the other hand, if a relaxed state is determined, the server will provide a document that includes more detailed and comprehensive information.

[0775] If a user requests information about dinner recipes and is detected as being stressed, the server will immediately provide information on simple dishes. This allows users to avoid complexity and obtain information quickly.

[0776] In utilizing generative AI models, an example of a prompt would be, "Considering my desire to know about simple cooking, please suggest simple and easy recipes." This prompt provides the foundation for the AI ​​to generate more appropriate information.

[0777] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0778] Step 1:

[0779] The user inputs their information request into the terminal via voice or text. The input voice is converted into text data by speech recognition software. Here, the input is the user's voice or text, and the output is the recognized text data.

[0780] Step 2:

[0781] The device sends the converted text data to the sentiment analysis engine. The sentiment analysis engine analyzes this text data to identify the emotional state and outputs emotional information. In this step, the input is text data, and the output is data on the user's emotional state.

[0782] Step 3:

[0783] The terminal combines the user's request with identified sentiment information to generate a search query for the server. The input here is the user's request and sentiment state, and the output is the search query.

[0784] Step 4:

[0785] The server searches the database based on the received search query and retrieves relevant information. The input is the search query, and the output is a list of relevant information.

[0786] Step 5:

[0787] The server filters the acquired information according to the user's emotional state. It adjusts the information to be concise if the user is stressed, and detailed if they are relaxed. The input is a list of relevant information and the emotional state, and the output is the filtered information.

[0788] Step 6:

[0789] The server organizes the filtered information into a user-friendly format and sends it to the terminal. The input is filtered information, and the output is a formalized document.

[0790] Step 7:

[0791] Users can review the materials provided through the terminal and request further details or additional information as needed. The input is formalized material, and the output is the user's new request.

[0792] 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.

[0793] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0794] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0795] 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.

[0796] Figure 9 shows an 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.

[0797] 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.

[0798] 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.

[0799] 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, motorcycles, etc., 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, for example, based 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.

[0800] 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."

[0801] 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.

[0802] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0803] 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 of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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 this memory.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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 the like 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.

[0812] 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.

[0813] The following is further disclosed regarding the embodiments described above.

[0814] (Claim 1)

[0815] A means for receiving information requested by a user and generating a search query based on said information,

[0816] A means for automatically searching internal information resources and obtaining relevant information based on the generated search query,

[0817] A means of organizing the acquired information and generating it as a document in a format that the user can understand,

[0818] Means for providing the aforementioned materials to the user,

[0819] A means of accumulating knowledge gained during the search process and utilizing it in future searches,

[0820] An information acquisition system that includes this.

[0821] (Claim 2)

[0822] The information acquisition system according to claim 1, further comprising means for analyzing information requests received from a user and extracting relevant keywords.

[0823] (Claim 3)

[0824] The information retrieval system according to claim 1, further comprising means for a server to issue queries to information resources and extract necessary information from a database.

[0825] "Example 1"

[0826] (Claim 1)

[0827] A means for receiving information requested by the user, analyzing the said information, and extracting relevant keywords,

[0828] A means of using a generative AI model to generate the optimal search query based on the aforementioned keywords,

[0829] A means of automatically searching for information resources based on the generated search query and obtaining related information,

[0830] A means of organizing acquired information and generating it as a document in a visual format,

[0831] Means for transmitting the aforementioned materials to a terminal in order to provide them to the user,

[0832] A means of accumulating knowledge gained during the search process and using it to improve the accuracy of subsequent searches,

[0833] A system that includes this.

[0834] (Claim 2)

[0835] The system according to claim 1, further comprising means for analyzing information requests received from a user and effectively extracting relevant keywords using a generative AI model.

[0836] (Claim 3)

[0837] The system according to claim 1, further comprising means for a server to access information resources using automatically generated queries and extract necessary information from data resources.

[0838] "Application Example 1"

[0839] (Claim 1)

[0840] A means for receiving information requested by a user and generating a search query based on said information,

[0841] A means for automatically searching for information resources and obtaining related information based on the generated search query,

[0842] A means of organizing the acquired information and generating it as information fragments in a format that the user can understand,

[0843] Means for providing the aforementioned information fragment to the user,

[0844] A means of accumulating knowledge gained during the search process and utilizing it in future searches,

[0845] A means of receiving voice input and converting it to text using speech recognition technology,

[0846] A means of analyzing textual information requests and providing the necessary information using artificial intelligence,

[0847] A means of providing answers in voice using speech synthesis technology,

[0848] A system that includes this.

[0849] (Claim 2)

[0850] The system according to claim 1, further comprising means for analyzing information requests received from a user and extracting relevant words and phrases.

[0851] (Claim 3)

[0852] The system according to claim 1, further comprising means for issuing automated queries and extracting necessary information from data storage units.

[0853] "Example 2 of combining an emotion engine"

[0854] (Claim 1)

[0855] A means for receiving information requested by the user, generating a search query based on said information, and adjusting keywords while considering the user's emotional state,

[0856] A means for automatically searching the accumulated knowledge resources based on the generated search query and obtaining related information,

[0857] A means of organizing information acquired based on emotional states and generating it as material in a format that users can understand,

[0858] A means of adjusting and providing the aforementioned materials according to the user's emotions,

[0859] A means of analyzing and identifying emotional states from user input data,

[0860] A system that includes this.

[0861] (Claim 2)

[0862] The system according to claim 1, further comprising means for analyzing information requests received from users, extracting relevant keywords, and filtering them according to sentiment.

[0863] (Claim 3)

[0864] The system according to claim 1, further comprising means for optimizing queries to information resources and extracting appropriate information from a database based on the user's emotional state analyzed by an emotion engine.

[0865] "Application example 2 when combining with an emotional engine"

[0866] (Claim 1)

[0867] A means for receiving information requested by a user and generating a search query based on said information,

[0868] A means of analyzing emotions from a user's voice or text and identifying their emotional state,

[0869] A means for filtering information and obtaining relevant information based on the generated search query and identified emotional state,

[0870] A means of generating materials from acquired information in a format that corresponds to the user's emotional state,

[0871] A means of providing the aforementioned materials to the user and presenting information appropriate to their emotional state,

[0872] A means to accumulate knowledge and sentiment data obtained during the search process and utilize it for future searches,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, further comprising means for analyzing information requests received from a user, extracting relevant keywords, and determining the priority of information provision according to the user's emotional state.

[0876] (Claim 3)

[0877] The system according to claim 1, further comprising means for a server to issue queries to information resources, extract necessary information from a database, and filter the extracted information based on the user's sentiment recognition. [Explanation of Symbols]

[0878] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving information requested by a user and generating a search query based on said information, A means for automatically searching internal information resources and obtaining relevant information based on the generated search query, A means of organizing the acquired information and generating it as a document in a format that the user can understand, Means for providing the aforementioned materials to the user, A means of accumulating knowledge gained during the search process and utilizing it in future searches, An information acquisition system that includes this.

2. The information acquisition system according to claim 1, further comprising means for analyzing information requests received from a user and extracting relevant keywords.

3. The information acquisition system according to claim 1, further comprising means for a server to issue queries to information resources and extract necessary information from a database.

Images