system

Abstract

Provide a system. 【Solution means】 Means for a user to input a search query for obtaining specific information, Means for receiving the search query, Means for sending the received search query to a generative artificial intelligence, Means for the generative artificial intelligence to optimize the search query, Means for sending the optimized query to a search engine, Means for the search engine to generate search results based on the optimized query, Means for displaying the generated search results to the user, A system including means for automatically making an inquiry to a support chat when the search results are insufficient.

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 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] When searching for information using Cruise Navi at the site, it is difficult for the user to quickly obtain the desired information due to low search ability. Also, when the search results are insufficient, an inquiry is made to the support chat, but this process also takes time, resulting in a problem of poor overall time efficiency. As a result, there are problems of reduced business productivity and increased user stress.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides the following means: The user inputs a search query to obtain specific information and sends the query to a generative artificial intelligence. The generative artificial intelligence optimizes the query, converts it into more appropriate search terms, and sends them to a search engine. Based on this optimized query, the search engine generates search results and displays them to the user. Furthermore, if the search results are insufficient, the system provides means to automatically contact support chat and provide additional information. As a result, the user can obtain information quickly and appropriately, and the inquiry process is streamlined, improving time efficiency and increasing business productivity.

[0006] A "user" refers to an individual or organization that uses the system to perform search activities.

[0007] A "search query" refers to a linguistic expression that a user enters to obtain specific information.

[0008] "Generative artificial intelligence" refers to artificial intelligence technology that analyzes input search queries and generates optimized search terms.

[0009] "Means of receiving" refers to the system's function for receiving search queries entered by users.

[0010] "Means of transmission" refers to the system's functionality for forwarding received search queries to other components or external services.

[0011] "Optimization methods" refer to the process by which generative artificial intelligence analyzes search queries and converts them into more appropriate search terms.

[0012] A "search engine" refers to a program used to extract information from databases and other sources.

[0013] "Means of display" refers to the system's function for visually showing search results on the user's device.

[0014] "Support Chat" refers to an online chat system where users can seek additional questions or support.

[0015] "Means of making an inquiry" refers to a system function for automatically sending a request to the support chat when the search results are insufficient.

Brief Description of Drawings

[0016] [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 multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple 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 the 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 the emotion engine is combined.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, the 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.

[0020] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the 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, etc.

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] overview

[0038] This invention relates to a system that efficiently provides information by optimizing search queries using generative artificial intelligence when a user is retrieving specific information. The system receives a query entered by the user and transmits it to the generative artificial intelligence. The generative artificial intelligence optimizes the query and sends the optimized query to a search engine to retrieve information. The system also includes a function to automatically contact support chat if the search results are insufficient. This allows users to obtain information quickly and accurately.

[0039] System Configuration

[0040] The system consists of the following main components:

[0041] 1. User terminal

[0042] It includes an interface where the user enters search queries to retrieve specific information. The user terminal is used to receive queries and send them to the generative artificial intelligence.

[0043] 2. Generative Artificial Intelligence (AI) Module

[0044] This module receives user queries and generates optimized search terms. Specifically, it parses the input query and optimizes it based on the context.

[0045] 3. Search Engine

[0046] A search engine receives an optimized query, searches its database for relevant information, and generates results. These search results are ultimately provided to the user.

[0047] 4. Support Chat System

[0048] If the search results are insufficient, this system will automatically receive the user's inquiry, and a support representative will provide additional information.

[0049] Operation details

[0050] The following describes the specific operation of the system.

[0051] 1. The user enters a search query.

[0052] The user enters a query into the terminal's search bar to obtain specific information. For example, they might enter "Machine A instruction manual".

[0053] 2. The terminal receives the query.

[0054] The user terminal receives the entered query. The query is converted to the appropriate format within the terminal and prepared to be sent to the generative artificial intelligence module.

[0055] 3. The terminal sends a query to the generative artificial intelligence.

[0056] The terminal sends the received query to a generative artificial intelligence module. The generative AI module analyzes the query and optimizes it into a more effective search term. For example, it might be transformed into something like "Machine A instruction manual latest version".

[0057] 4. Generative artificial intelligence optimizes queries.

[0058] Generative artificial intelligence analyzes queries, understands the context and meaning, and then generates optimized queries. These optimized queries can better meet user requests.

[0059] 5. The device sends optimized queries to the search engine.

[0060] The optimized query is sent to the search engine. The search engine uses this query to search its database and retrieve relevant information.

[0061] 6. The server returns the search results.

[0062] Search results are generated by the search engine and sent back to the user's device. For example, they may include a link to or content of "the latest version of the instruction manual for machine A."

[0063] 7. The device displays the search results.

[0064] The user's device displays the received search results, allowing the user to verify the information.

[0065] 8. If the search results are insufficient, an automated inquiry will be sent to support chat.

[0066] If the search results are insufficient, the device will automatically contact the support chat system. For example, it might ask, "I'm looking for more details on how to perform a specific operation."

[0067] 9. Support chat will assist you.

[0068] The support chat system receives inquiries, and support staff respond to user questions, providing additional information and specific instructions.

[0069] Specific example

[0070] For example, consider a scenario where a user searches for "Machine A User Manual" on CrewNavi. In this case, the user enters a search query, which the terminal receives and sends to a generative artificial intelligence (AI). The AI ​​optimizes the query, and the search engine searches for relevant information. Based on the optimized query, the search engine finds "Latest Version User Manual for Machine A" and returns it to the user. If the user does not find the information they expect, the terminal automatically contacts support chat and is prompted to provide additional information.

[0071] The system of this invention aims to improve work productivity by enabling users to efficiently obtain the necessary information. This significantly reduces the time spent searching for information and alleviates user stress.

[0072] The following describes the processing flow.

[0073] Step 1:

[0074] The user enters a search query into the CrewNavi search bar.

[0075] Specific action: The user enters "Machine A User Manual" and clicks the search button.

[0076] Step 2:

[0077] The device receives a search query from the user.

[0078] Specific operation: The terminal receives the string "Machine A Instruction Manual" and processes it appropriately according to the data format.

[0079] Step 3:

[0080] The terminal sends the received search query to the generative artificial intelligence.

[0081] Specific operation: The terminal sends a request containing the query "Machine A User Manual" to the generative artificial intelligence API endpoint.

[0082] Step 4:

[0083] Generative artificial intelligence optimizes search queries.

[0084] Specific operation: The generative artificial intelligence analyzes "Machine A Instruction Manual," understands its context and meaning, and generates a more effective search term, "Machine A Instruction Manual Latest Version."

[0085] Step 5:

[0086] The device sends optimized queries to CrewNavi's search engine.

[0087] Specific operation: The terminal sends the optimized query "Machine A Instruction Manual Latest Version," which was returned by the generative artificial intelligence, to the CrewNavi search engine.

[0088] Step 6:

[0089] The server generates search results based on the query.

[0090] Specific operation: The search engine searches the database, extracts information from the "Latest Version of the User Manual for Machine A," and generates results.

[0091] Step 7:

[0092] The server sends the search results back to the terminal.

[0093] Specific action: Send the generated search results to the user's device.

[0094] Step 8:

[0095] The device displays search results to the user.

[0096] Specific operation: The search results received by the terminal are displayed on the user's screen. Specifically, a link and content of the "Latest version of the instruction manual for Machine A" are displayed.

[0097] Step 9:

[0098] If the search results are insufficient, the device will automatically contact support chat.

[0099] Specific operation: If the user cannot find specific information, the device will send an automated inquiry, such as "I am looking for specific instructions on how to operate machine A," to the support chat API.

[0100] Step 10:

[0101] The support chat receives and responds to inquiries.

[0102] Specific operation: The support chat system automatically receives inquiries, and support staff provide specific steps and additional documentation in response to the user's request for information.

[0103] (Example 1)

[0104] 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."

[0105] In modern information retrieval systems, the search queries that users enter to obtain specific information are not always optimized, often resulting in insufficient search results. Furthermore, when search results are insufficient, users have to make further inquiries or enter additional queries, which is a time-consuming and troublesome process.

[0106] 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.

[0107] In this invention, the server includes means for a user to input a search query to obtain specific information, means for receiving the search query, means for transmitting the received search query to a generative artificial intelligence, means for the generative artificial intelligence to optimize the search query, means for transmitting the optimized query to a search engine, means for the search engine to generate search results based on the optimized query, means for displaying the generated search results to the user, means for automatically querying a text-based interactive support system if the search results are insufficient, and means for analyzing the query content and providing appropriate supplementary information. As a result, the user can efficiently use the optimized search query to perform highly accurate information retrieval and quickly obtain additional information even if the search results are insufficient.

[0108] A "user" refers to someone who enters a search query and performs an information retrieval operation in order to obtain specific information.

[0109] A "search query" refers to a sentence or phrase that a user enters into a search engine to request specific information.

[0110] "Generative artificial intelligence" refers to artificial intelligence that analyzes input search queries, understands the context and meaning, and then generates optimized search terms.

[0111] A "search engine" refers to a system that searches a database based on an entered search query and extracts relevant information.

[0112] A "text-based interactive support system" refers to a system that automatically responds to user inquiries and inputs in text format, providing appropriate support information.

[0113] "Reception" means that a means or device takes in data or signals sent from another source.

[0114] "Transmission" means that a means or device sends specific data or signals to another party.

[0115] "Optimization" refers to the process of modifying something to its optimal state or configuration for a particular purpose.

[0116] "Analysis" refers to the process of thoroughly examining input data and information to understand its meaning and structure.

[0117] "Supplementary information" refers to additional information provided to complement the main information that the user is seeking.

[0118] System Overview and Configuration

[0119] This invention provides a system that efficiently delivers information by optimizing search queries using generative artificial intelligence when a user retrieves specific information. The system receives the user's search query, the generative artificial intelligence optimizes it, and then sends the optimized query to a search engine to retrieve information. It also includes a function to automatically query a text-based interactive support system if the search results are insufficient.

[0120] Hardware and software to be used

[0121] User terminal: Used by the user to enter search queries. This includes typical personal computers, smartphones, and tablets.

[0122] Generative artificial intelligence module: Analyzes user queries and generates optimized search terms. Examples of AI models used include high-performance natural language processing models such as GPT-4®.

[0123] Search engine: Searches for relevant information based on optimized queries. Common search engine technologies include Elasticsearch® and Solr.

[0124] Text-based interactive support systems: These systems automatically respond to user inquiries and provide supplementary information. Examples include chatbot systems and FAQ systems.

[0125] Explanation of the program's processing

[0126] When a user enters a search query, it is received by the terminal. The terminal sends the received query to a generative artificial intelligence module, which analyzes the query, understands its context and meaning, and then optimizes it. Next, the terminal sends the optimized query to a search engine, which searches its database based on this query and generates relevant information. The generated search results are sent back to the user's terminal by the server and displayed for the user to review.

[0127] If the search results are insufficient, the device automatically contacts a text-based interactive support system. This system provides the user with additional assistance information based on the support staff and pre-configured scenarios.

[0128] Examples of specific scenarios and prompts

[0129] For example, consider a case where a user searches for "Machine A instruction manual." The user enters this query into a terminal, which then sends it to a generative artificial intelligence module. The generative AI optimizes the query, for example, transforming it into "Machine A instruction manual latest version." The search engine then searches for relevant information based on the optimized query and returns the results to the user's terminal. If the user reviews the information and makes further inquiries as needed, a text-based interactive support system will handle it.

[0130] Example of a prompt

[0131] "Receive search queries submitted by users and generate optimized search terms. Submit these optimized queries to search engines to retrieve relevant information. Finally, advise on the best way to present the retrieved information to users."

[0132] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0133] Step 1:

[0134] The user enters a search query. The user enters a query such as "Machine A Instruction Manual" into the search bar to retrieve specific information. The entered query is sent to the terminal.

[0135] Step 2:

[0136] The terminal receives the search query. The terminal receives the query entered by the user and stores it in its internal data format. The received query, "Machine A User Manual," is ready to be passed on to the next process.

[0137] Step 3:

[0138] The terminal sends a search query to the generative artificial intelligence. The terminal sends the received query to the generative artificial intelligence module, along with providing contextual information. The "Machine A User Manual" is passed to the generative artificial intelligence as input.

[0139] Step 4:

[0140] Generative artificial intelligence optimizes the search query. Generative artificial intelligence analyzes the query, understands its context and meaning, and performs optimization. In this process, the query is transformed into "Machine A Instruction Manual Latest Version". The input query "Machine A Instruction Manual" is transformed into the optimized output query "Machine A Instruction Manual Latest Version".

[0141] Step 5:

[0142] The terminal sends an optimized query to the search engine. The terminal receives the optimized query and sends it to the search engine. "Machine A Instruction Manual Latest Version" is sent to the search engine as input.

[0143] Step 6:

[0144] The search engine generates search results. The search engine searches its internal database based on the optimized query and collects relevant information. For example, links and related documents for "Machine A Instruction Manual Latest Version" are extracted. The input to the search engine is "Machine A Instruction Manual Latest Version," and the output is a list of related information.

[0145] Step 7:

[0146] The server returns the search results. The server sends the search results obtained from the search engine back to the user's terminal. For example, a link to "Machine A Instruction Manual Latest Version" is sent to the user's terminal.

[0147] Step 8:

[0148] The user terminal displays the search results. The user terminal displays the received search results to the user. The user can obtain the necessary information based on the displayed links and information. The input is the search results from the server, and the output is what is displayed to the user.

[0149] Step 9:

[0150] If the search results are insufficient, the device automatically queries a text-based interactive support system. If the search results do not meet the user's expectations, the device sends a message to the text-based interactive support system, for example, "I would like to know more information about a specific operation."

[0151] Step 10:

[0152] A text-based interactive support system interacts with the user. The system receives inquiries and provides additional information and specific steps. For example, a support staff member might provide the user with additional materials or instructions. Input is the inquiry from the user's terminal, and output is the provision of supplementary information.

[0153] (Application Example 1)

[0154] 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."

[0155] The problem that this invention aims to solve is to facilitate the rapid and accurate acquisition of specific information by users. In particular, it aims to enable users of autonomous vehicles to easily acquire information about the area around their destination and vehicle handling information while driving or stopped, and to quickly acquire additional information if necessary information is missing. Another important issue is to enable voice input, allowing users to safely enter queries even while driving.

[0156] 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.

[0157] In this invention, the server includes means for a user to input a search query to obtain specific information, means for receiving the search query, means for transmitting the received search query to a generative artificial intelligence, means for the generative artificial intelligence to optimize the search query, means for transmitting the optimized query to a search engine, means for the search engine to generate search results based on the optimized query, means for displaying the generated search results to the user, voice input means, means for converting the voice-input query to text, and means for automatically contacting support chat if the search results are insufficient. This enables the user to safely search for information by voice even while driving and efficiently obtain the necessary information through optimized queries. Furthermore, it becomes possible to automatically use the support chat system as needed to quickly obtain additional information.

[0158] A "search query" is a string of characters that a user enters to retrieve specific information.

[0159] "Means of receiving data" refers to the system for importing search queries entered by users.

[0160] "Generative artificial intelligence" is a type of artificial intelligence that analyzes search queries entered by users and optimizes them based on context.

[0161] "Optimization methods" refer to the process by which generative artificial intelligence transforms search queries into more effective search terms.

[0162] A "search engine" is a system that searches a database for relevant information based on optimized queries and generates results.

[0163] "Means of displaying search results" refers to an interface that displays information in a way that allows users to easily verify the information they have obtained.

[0164] A "voice input method" is a mechanism that allows users to input queries using their voice.

[0165] "Means of converting to text" refers to the process of converting voice-input queries into text format.

[0166] "Support chat" is a system that automatically makes inquiries and provides additional information when search results are insufficient.

[0167] "Automated inquiry methods" refer to the process by which users can contact support chat without manual intervention when they need additional information.

[0168] The embodiments for carrying out the present invention are described in detail below. The system for realizing this invention is designed to allow passengers of an autonomous vehicle to easily obtain specific information using voice input. The system consists of four main components: a user terminal, a generative artificial intelligence module, a search engine, and a support chat system.

[0169] First, the user enters a search query through the in-vehicle voice input device. The user terminal receives this via voice input and converts it into text using speech recognition software. Specifically, the SpeechRecognition library is used. If the user enters "What are some good Japanese restaurants nearby?", this voice is converted into text.

[0170] Next, the stringified search query is sent to a generative artificial intelligence module for optimization. This process uses a GPT-3® model with Hugging Face's Transformers library. The generative AI analyzes the query and, based on context, transforms it into more effective search terms such as "highly-rated Japanese restaurants within 3km of my current location."

[0171] The optimized query is then sent to a search engine, which retrieves relevant information from its database. The search results are returned to the user's device and presented to them via the vehicle's display or audio system. This allows the user to quickly obtain information on highly-rated restaurants near their destination.

[0172] Furthermore, if the retrieved search results are insufficient, an automated inquiry is made to the support chat system. At this stage, the Requests library is used to perform an automated inquiry to obtain additional information. Based on the inquiry received by the support chat, the necessary details are provided. For example, allergen information for a specific restaurant is provided to the user in real time.

[0173] As a concrete example, consider a case where a user voice-inputs "What are some good Japanese restaurants near me?", and this is optimized to show "highly-rated Japanese restaurants within 3km of the user's current location." This optimized query is sent to the search engine, and relevant information is returned. If the information obtained is insufficient, an automated inquiry is sent to the support chat asking, "What is the allergen information for this particular Japanese restaurant?"

[0174] Examples of prompts for a generative AI model include the following:

[0175] A user is searching for nearby restaurants. Please generate the most suitable search terms based on the user's specified criteria. Example: "Japanese food," "delicious," "within 3km."

[0176] Thus, the system of the present invention is designed to enable users to obtain information quickly and safely. The collaboration between generative artificial intelligence and speech recognition technology makes it possible to provide highly accurate and convenient information.

[0177] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0178] Step 1: The user enters the search query by voice.

[0179] Users use a voice input device in the autonomous vehicle to enter search queries by voice to obtain specific information. For example, the input might be "What are some good Japanese restaurants nearby?"

[0180] Step 2: The device receives the voice input and converts it to text.

[0181] The device converts the user's voice input into text using speech recognition software (e.g., the SpeechRecognition library). The input is voice data, and the output is text data such as "What are some good Japanese restaurants nearby?"

[0182] Step 3: The device sends text data to the generative artificial intelligence.

[0183] The terminal sends the converted text data to a generative artificial intelligence module. In this process, the input is the text data entered by the user, and the output is the input data for the generative artificial intelligence.

[0184] Step 4: Generative artificial intelligence optimizes the query

[0185] Generative artificial intelligence analyzes incoming queries and optimizes them into more effective search terms. For example, a GPT-3 model using Hugging Face's Transformers library is used. The input is the original query "What are some good Japanese restaurants near me?", and the output is "Highly-rated Japanese restaurants within 3km of my current location".

[0186] Step 5: The device sends an optimized query to the search engine.

[0187] The device sends an optimized query to the search engine. In this process, the input is a query optimized by generative artificial intelligence, and the output is a query request to the search engine.

[0188] Step 6: The search engine generates relevant information and responds.

[0189] A search engine retrieves relevant information from a database based on an optimized query and generates results. The input is the optimized query, and the output is the search results. For example, it might include "information about highly-rated Japanese restaurants within 3km of my current location."

[0190] Step 7: The device displays the search results to the user.

[0191] The terminal displays search results to the user. This display is done through the vehicle's display or audio system. The input is the search results from the search engine, and the output is the presentation of information to the user.

[0192] Step 8: If the search results are insufficient, the device will automatically contact support chat.

[0193] If the search results do not meet the user's requirements, the device automatically contacts the support chat system. The input consists of the missing search results and additional queries, and the output is the inquiry request to the support chat system.

[0194] Step 9: Support chat will provide additional information.

[0195] The support chat system receives inquiries and provides necessary additional information. The input is the content of the inquiry to the support chat, and the output is additional information for the user. Specifically, this may include "allergen information for a particular restaurant."

[0196] 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.

[0197] overview

[0198] This invention relates to a system that optimizes search queries by combining generative artificial intelligence and an emotion engine when a user retrieves specific information, and provides information tailored to the user's emotional state. The system receives a query entered by the user and analyzes the user's emotions using the emotion engine. The generative artificial intelligence optimizes the query and sends the optimized query to a search engine to retrieve information. If the search results are insufficient, the system includes a function to automatically contact support chat. Furthermore, the emotion engine transmits the user's emotional state to the support chat system to help support staff provide more appropriate responses.

[0199] System Configuration

[0200] The system consists of the following main components:

[0201] 1. User terminal

[0202] It includes an interface where the user enters search queries to retrieve specific information. The user terminal is used to receive queries and send them to the generative artificial intelligence and emotion engine.

[0203] 2. Generative Artificial Intelligence (AI) Module

[0204] This module receives user queries and generates optimized search terms. Specifically, it parses the input query and optimizes it based on the context.

[0205] 3. Emotional Engine

[0206] The emotion engine analyzes the user's emotional state and provides the analysis results to other components. For example, if the user is anxious or dissatisfied, this information is reflected and provided to generative artificial intelligence and the support chat system.

[0207] 4. Search Engine

[0208] A search engine receives an optimized query, searches its database for relevant information, and generates results. These search results are ultimately provided to the user.

[0209] 5. Support Chat System

[0210] If the search results are insufficient, the system automatically receives the user's inquiry, and a support representative provides additional information. Based on the user's sentiment information from the sentiment engine, the support representative takes appropriate action.

[0211] Operation details

[0212] The following describes the specific operation of the system.

[0213] 1. The user enters a search query.

[0214] The user enters a query into the terminal's search bar to obtain specific information. For example, they might enter "Machine A instruction manual" and click the search button.

[0215] 2. The terminal receives the query.

[0216] The user terminal receives the entered query. The query is converted to the appropriate format within the terminal and then prepared to be sent to the sentiment engine.

[0217] 3. The device sends the query to the sentiment engine.

[0218] The device sends the received query and user interaction data (keystrokes, mouse movements, etc.) to the emotion engine. The emotion engine analyzes this data to determine the user's emotional state.

[0219] 4. The emotion engine analyzes the user's emotions.

[0220] The emotion engine receives queries and analyzes the user's emotional state. For example, it determines whether the user is anxious, angry, or calm.

[0221] 5. The terminal sends an optimization query to the generative artificial intelligence.

[0222] Based on the analysis results from the emotion engine, the device sends a request to the generative artificial intelligence to optimize the search query according to the user's emotions. The generative AI receives this request and optimizes the query.

[0223] 6. Generative artificial intelligence optimizes queries.

[0224] Generative artificial intelligence analyzes queries, understands the context and emotional state, and then generates optimized queries. These optimized queries can better meet user requests.

[0225] 7. The device sends optimized queries to the search engine.

[0226] The optimized query is sent to the search engine. The search engine uses this query to search its database and retrieve relevant information.

[0227] 8. The server returns the search results.

[0228] Search results are generated by the search engine and sent back to the user's device. For example, they may include a link to or content of "the latest version of the instruction manual for machine A."

[0229] 9. The device displays search results to the user.

[0230] The user's device displays the received search results, allowing the user to verify the information.

[0231] 10. If search results are insufficient, the system will automatically contact support chat via the sentiment engine.

[0232] If the search results are insufficient, the device will send an automated inquiry via the emotion engine to the support chat API, such as "I am looking for specific instructions on how to operate machine A."

[0233] 11. The support chat receives the inquiry and responds.

[0234] The support chat system receives inquiries, and support staff respond to user questions. They provide additional information and specific steps. Based on emotional information provided by the emotion engine, support staff provide the most appropriate response for the user's situation.

[0235] Specific example

[0236] For example, consider a scenario where a user searches for "Machine A instruction manual." In this case, the user enters a search query, which the device receives and sends to the emotion engine. The emotion engine analyzes the user's emotional state and sends the results to the generative artificial intelligence. The generative AI optimizes the query, and the search engine searches for relevant information. Based on the optimized query, the search engine finds "the latest version of the Machine A instruction manual" and returns it to the user. If the user does not find the information they expect, the device automatically contacts support chat via the emotion engine and is prompted to provide additional information.

[0237] The system of this invention aims to improve work productivity by enabling users to efficiently obtain the information they need. This significantly reduces information retrieval time and alleviates user stress. Furthermore, by incorporating an emotion engine, it can provide optimal responses tailored to the user's emotional state, offering a more fulfilling user experience.

[0238] The following describes the processing flow.

[0239] Step 1:

[0240] The user enters a search query into the CrewNavi search bar.

[0241] Specific action: The user enters "Machine A User Manual" and clicks the search button.

[0242] Step 2:

[0243] The device receives a search query from the user.

[0244] Specific operation: The terminal receives the string "Machine A Instruction Manual" and processes it appropriately according to the data format.

[0245] Step 3:

[0246] The device sends the received search queries and interaction data to the sentiment engine.

[0247] Specific operation: The device sends the search query along with interaction data such as the user's keystrokes and mouse movements to the sentiment engine's API endpoint.

[0248] Step 4:

[0249] The emotion engine analyzes the user's emotions.

[0250] Specific operation: The emotion engine analyzes keystroke speed, mouse movements, input content, etc., to identify the user's emotional state (anxiety, anger, calmness, etc.).

[0251] Step 5:

[0252] The terminal sends queries and sentiment analysis results to the generative artificial intelligence.

[0253] Specific operation: The terminal sends an optimization query request, including the emotion analysis results, to the generative artificial intelligence API.

[0254] Step 6:

[0255] Generative artificial intelligence optimizes queries.

[0256] Specific operation: The generative artificial intelligence analyzes the "Machine A User Manual" and optimizes it, taking into account emotional states, to create something like the "Machine A User Manual Latest Version."

[0257] Step 7:

[0258] The device sends optimized queries to the search engine.

[0259] Specific operation: The terminal sends the optimized query "Machine A Instruction Manual Latest Version," which was returned by the generative artificial intelligence, to the CrewNavi search engine.

[0260] Step 8:

[0261] The server generates search results based on the query.

[0262] Specific operation: The search engine searches the database, extracts information from the "Latest Version of the User Manual for Machine A," and generates results.

[0263] Step 9:

[0264] The server sends the search results back to the terminal.

[0265] Specific action: Send the generated search results to the user's device.

[0266] Step 10:

[0267] The device displays search results to the user.

[0268] Specific operation: The search results received by the terminal are displayed on the user's screen. Specifically, a link and content of the "Latest version of the instruction manual for Machine A" are displayed.

[0269] Step 11:

[0270] If the search results are insufficient, an automated inquiry will be sent to support chat via the emotion engine.

[0271] Specific operation: If the user cannot find specific information, the device will send an automated inquiry, such as "I am looking for specific instructions on how to operate machine A," via the emotion engine to the support chat API.

[0272] Step 12:

[0273] The support chat receives and responds to inquiries.

[0274] Specific operation: The support chat system automatically receives inquiries, and a support representative provides specific steps and additional documentation in response to the user's request. Based on the emotional information provided by the emotion engine, the support representative provides the most appropriate response to the user's situation.

[0275] (Example 2)

[0276] 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".

[0277] Traditional search systems often failed to provide optimal information for user-entered search queries, resulting in decreased user satisfaction. In particular, the lack of appropriate information tailored to the user's emotional state could reduce search efficiency and increase stress. Furthermore, the process of users seeking additional information when search results were insufficient was cumbersome.

[0278] 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.

[0279] In this invention, the server includes means for a user to input a search query to obtain specific information, means for receiving the search query, means for transmitting the received search query to an emotion analysis module, means for the emotion analysis module to analyze the user's emotional state, means for transmitting the search query to a generative artificial intelligence based on the emotion analysis results, means for the generative artificial intelligence to optimize the search query, means for transmitting the optimized query to a search engine, means for the search engine to generate search results based on the optimized query, means for displaying the generated search results to the user, and means for automatically querying a support system via the emotion analysis module if the search results are insufficient. This enables the provision of optimal information according to the user's emotional state, improves search efficiency, and reduces user stress. Furthermore, if the search results are insufficient, a query is automatically made to the support system, allowing the user to quickly obtain additional information.

[0280] "User" refers to a person who uses this system to obtain specific information.

[0281] A "search query" is a combination of strings or words that a user enters to specify the information they want to retrieve.

[0282] "Interface" refers to the means of communication between the user and the system for the user to input a search query and display the results.

[0283] "Sentiment analysis module" or "sentiment engine" refers to a software component for analyzing the user's emotional state, which determines the emotion based on the user's interaction data.

[0284] "Generative artificial intelligence" refers to an artificial intelligence module that generates an optimized search query based on the received search query and the sentiment analysis result.

[0285] "Search engine" refers to a system for searching relevant information from web pages and databases.

[0286] "Search results" refer to a list of information corresponding to the user's search query generated by the search engine.

[0287] "Support system" or "support chat" refers to an automatic inquiry system and response system for providing additional information required by the user.

[0288] "Sentiment analysis result" refers to the analysis result of the user's emotional state obtained by the sentiment analysis module based on the user's interaction data.

[0289] "Optimized query" refers to the most appropriate combination of search terms generated by the generative artificial intelligence based on the user's search query and the sentiment analysis result.

[0290] "Interaction data" refers to the data generated when the user interacts with the system (e.g., keystrokes, mouse movements).

[0291] These definitions clarify each component of the system related to the present invention and its functions.

[0292] Modes for carrying out the invention

[0293] This invention relates to a system that optimizes search queries by combining generative artificial intelligence and an emotion analysis module when a user retrieves specific information, and provides information tailored to the user's emotional state. This system mainly consists of the following key components.

[0294] System Configuration

[0295] 1. User terminal

[0296] It includes an interface where the user enters search queries to retrieve specific information. The user terminal is used to receive queries and send them to generative artificial intelligence and sentiment analysis modules.

[0297] 2. Generative Artificial Intelligence (AI) Module

[0298] This module receives user queries and generates optimized search terms. Specifically, it analyzes the input query and optimizes it based on context and sentiment.

[0299] 3. Emotion Analysis Module (Emotion Engine)

[0300] The emotion analysis module analyzes the user's emotional state and provides the analysis results to other components. For example, if the user is anxious or dissatisfied, this information is reflected in the generative artificial intelligence and support chat system.

[0301] 4. Search Engine

[0302] A search engine receives an optimized query, searches its database for relevant information, and generates results. These search results are ultimately provided to the user.

[0303] 5. Support Chat System

[0304] If the search results are insufficient, this system automatically accepts the user's inquiry, and the support staff provides additional information. Based on the user's sentiment information from the sentiment engine, the support staff takes appropriate actions.

[0305] How the system operates

[0306] Overview of program processing

[0307] The system first receives the search query entered by the user. The received query is sent to the sentiment analysis module, and the user's sentiment state is analyzed. Then, based on the analysis result, the query is optimized by the generative artificial intelligence. The optimized query is sent to the search engine, and relevant search results are generated. The generated search results are displayed to the user. If the search results are insufficient, an inquiry is automatically made to the support chat system. Based on the sentiment information provided by the sentiment analysis module, the support staff provides the user with an optimal response.

[0308] Specific example

[0309] For example, consider a scenario where a user searches for "Machine A Handling Manual". In this case, the user enters a search query, and the terminal receives it and sends it to the sentiment analysis module. The sentiment analysis module analyzes the user's sentiment state and sends the result to the generative artificial intelligence. The generative artificial intelligence optimizes the query, and the search engine searches for relevant information. Based on the optimized query, the search engine searches for the "Latest Edition Handling Manual of Machine A" and returns it to the user. If the information the user expects is not obtained, the terminal automatically makes an inquiry to the support chat system via the sentiment analysis module to provide additional information.

[0310] Specific examples of prompt sentences

[0311] "The user searched for 'Machine A User Manual,' but the emotion engine detected an emotion of impatience. Please generate the most suitable search query for the user and automatically contact support chat if necessary."

[0312] This invention is designed to allow users to efficiently obtain the information they need, aiming to improve work productivity. By introducing an emotion analysis module, it becomes possible to provide optimal responses tailored to the user's emotional state, thereby offering a more enriching user experience.

[0313] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0314] The program's processing flow is divided into processing steps.

[0315] Step 1: The user enters a search query.

[0316] To obtain specific information, the user enters a query into the terminal's search bar. An example of such a query is "Machine A Instruction Manual". The input data here is the string "Machine A Instruction Manual" entered by the user.

[0317] Step 2: The terminal receives the query.

[0318] The terminal receives the query entered by the user. The received query ("Machine A User Manual") is converted into an appropriate data format and prepared to be sent to the sentiment analysis module. The input data here is the user's query, which is the output of step 1. The output data is the query data ready for sentiment analysis.

[0319] Step 3: The device sends query and interaction data to the sentiment analysis module.

[0320] The terminal sends the received query along with user interaction data (e.g., keyboard input speed, mouse movements, etc.) to the sentiment analysis module. The input data consists of the query string "Machine A Instruction Manual" and the interaction data. The output data is the data sent to the sentiment analysis module.

[0321] Step 4: The emotion analysis module analyzes the user's emotional state.

[0322] The emotion analysis module determines the user's emotional state (e.g., anxious, angry, calm) based on the received data. The input data consists of the query and interaction data sent in step 3. The output data is the analyzed user's emotional state.

[0323] Step 5: The device sends queries and sentiment analysis results to the generative artificial intelligence.

[0324] The terminal sends a query along with the emotion analysis results (e.g., state of anxiety) to the generative artificial intelligence. The input data consists of the query and the emotion analysis results. The output data is the request for optimization query generation that was sent to the generative artificial intelligence.

[0325] Step 6: Generative AI optimizes the query.

[0326] Generative artificial intelligence receives a query and sentiment analysis results, and generates an optimized query considering the context and emotional state (e.g., "Download the latest version of the instruction manual for machine A"). The input data is the original query and sentiment analysis results. The output data is the optimized query.

[0327] Step 7: The device sends the optimized query to the search engine.

[0328] The device sends an optimized query to the search engine. The input data is the optimized query. The output data is the query sent to the search engine.

[0329] Step 8: The server returns the search results.

[0330] A server with a search engine receives an optimized query, searches its database, and retrieves relevant information (e.g., "Latest version of the instruction manual for machine A"). The retrieved information is sent back to the terminal as search results. The input data is the optimized query, and the output data is the search results.

[0331] Step 9: The device displays the search results to the user.

[0332] The terminal displays search results received from the server to the user. For example, a link or summary of "the latest version of the instruction manual for machine A" is displayed on the user's screen. The input data is the search results, and the output data is the information displayed to the user.

[0333] Step 10: If the search results are insufficient, send an automated inquiry to the support chat.

[0334] If the user cannot obtain the information they expect, the device will automatically contact the support chat system based on the sentiment analysis results (e.g., "I am looking for specific instructions on how to operate machine A"). The input data consists of insufficient search results and sentiment analysis results, while the output data is the content of the inquiry sent to the support chat.

[0335] Step 11: Support chat receives and responds to the inquiry.

[0336] The support chat system receives inquiries, and support staff respond to user questions. Based on sentiment analysis results, responses are tailored to the user's state. The input data is the content of the inquiry sent to the support chat, and the output data is additional information provided by the support staff.

[0337] This allows users to efficiently obtain the information they need, and to quickly acquire additional information even if the search results are insufficient.

[0338] (Application Example 2)

[0339] 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".

[0340] Current information retrieval systems often fail to provide search results quickly and accurately, as they do not take into account the user's emotional state. This is particularly problematic in the security field, where providing appropriate information in situations where security personnel are under pressure and anxiety is crucial, but current systems do not adequately address this. Furthermore, the lack of automated systems for additional actions when search results are insufficient places a significant burden on users.

[0341] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting a search query for a user to obtain specific information, means for receiving the search query, means for transmitting the received search query to a generative artificial intelligence, means for the generative artificial intelligence to optimize the search query, means for transmitting the optimized query to a search engine, means for the search engine to generate search results based on the optimized query, means for displaying the generated search results to the user, means for automatically contacting a support chat if the search results are insufficient, means for capturing a frame with an image capture device and analyzing the user's emotional state using an emotion recognition engine, and means for generating a warning message based on the emotional state. This not only enables the provision of optimal information according to the user's emotional state, but also reduces the burden on the user by automatically taking additional action if the search results are insufficient.

[0342] A "user" is an individual or organization that enters a search query to obtain information.

[0343] A "search query" is a set of sentences or words that a user enters in order to obtain specific information.

[0344] "Generative artificial intelligence" is an artificial intelligence technology that analyzes input search queries and optimizes them based on context.

[0345] "Optimization" is the process of analyzing an entered search query and converting it into search terms that best meet the user's needs.

[0346] A "search engine" is a system that searches a database based on optimized queries and generates relevant information.

[0347] "Search results" are a collection of information generated by a search engine that a user is looking for.

[0348] A "support chat" is a system that automatically responds to user inquiries and provides additional information when search results are insufficient.

[0349] An "emotion recognition engine" is a technology used to analyze a user's emotional state, and it has the function of determining a user's emotions by analyzing their voice and facial expressions.

[0350] An "image capture device" is a device used to capture images or videos in real time.

[0351] A "warning message" is information or instructions designed to draw attention to a user's emotional state.

[0352] To implement the invention, the following hardware and software components are required. First, the user terminal has an interface for the user to input search queries to obtain specific information. This terminal is used for receiving queries and transmitting them to a generative artificial intelligence and emotion engine.

[0353] When a user enters a search query, the device receives the query, converts it to an appropriate format, and sends it to a generative artificial intelligence (AI). The AI ​​analyzes this query and optimizes it to best meet the user's needs. The optimized query is then sent to a search engine. The search engine searches its database for relevant information, generates search results, and returns them to the user.

[0354] If the search results are insufficient, the system will automatically contact the support chat system. This support chat system will answer the user's additional questions and provide more specific information.

[0355] Furthermore, the system includes an emotion recognition engine that analyzes the user's emotional state in real time. This engine captures frames using an image capture device and determines the user's emotional state from their facial expressions and voice. Based on this analysis, the emotion recognition engine generates a warning message and provides it to the user.

[0356] As a concrete example, let's consider a scenario where a user is performing monitoring duties. When the user searches for "emergency reporting procedures" in an emergency, the system receives the search query, and generative artificial intelligence optimizes it before sending it to the search engine. For example, it might be optimized as "on-site emergency reporting procedures." If the search results are not appropriate (for example, if no specific reporting procedures are found), the system automatically contacts the support chat system and provides additional specific response procedures.

[0357] Furthermore, the emotion recognition engine analyzes the user's emotional state and, if it detects that the user is anxious, generates an appropriate warning message. For example, it might display, "Please calm down and review the following steps." This allows the user to continue acting calmly.

[0358] The hardware and software used include:

[0359] Hardware: Cameras (surveillance cameras, webcams), user devices (PCs, smartphones, etc.)

[0360] Software: OpenCV (for camera frame capture), emotion recognition engine (e.g., Facial Emotion Recognition module), generative artificial intelligence (GPT-3 API, etc.)

[0361] The example prompt is as follows:

[0362] "The security team is in a state of panic. Please generate the most appropriate warning message."

[0363] The introduction of this system allows users to efficiently obtain necessary information and reduce stress and anxiety through emotion recognition. Furthermore, if search results are insufficient, additional actions are taken immediately, ensuring smooth task completion.

[0364] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0365] Step 1:

[0366] The user enters a search query to obtain specific information. The user enters the query in the search bar of their device and sends the entered query. For example, they might enter "emergency call procedure".

[0367] Step 2:

[0368] The terminal receives the search query. The terminal receives the query entered by the user and converts it to an appropriate format. The input data is a text-based query, and the converted data is also in text format.

[0369] Step 3:

[0370] The terminal sends the received search query to the generative artificial intelligence. The terminal then sends the pre-processed query to the generative AI module and waits for the result to be received. The input data is a search query in text format, and an optimized query is output.

[0371] Step 4:

[0372] Generative artificial intelligence optimizes search queries. The generative AI module analyzes the received query and transforms it into the most appropriate form based on the context. For example, it might specify "emergency call procedure" as "on-site emergency call procedure." The input data is the search query, and the output data is the optimized query.

[0373] Step 5:

[0374] The device sends an optimized query to the search engine. The input data is an optimized query, and the output data is a query in the form of a request to the search engine.

[0375] Step 6:

[0376] A search engine generates search results based on an optimized query. The search engine searches its database based on the received query and retrieves relevant information. The input data is the optimized query, and the output data is the search results.

[0377] Step 7:

[0378] The server displays the generated search results to the user. The server sends the search results obtained from the search engine back to the user's terminal. The user's terminal displays the received search results to the user. The input data is the search results, and the output data is the information displayed on the screen.

[0379] Step 8:

[0380] If search results are insufficient, the system automatically initiates a support chat inquiry. If the user cannot obtain the necessary information, the device automatically sends an inquiry to the support chat. The input data is a query for the missing information, and the output data is the request to the support chat.

[0381] Step 9:

[0382] The support chat receives the inquiry and provides additional information. The support chat system receives the user's inquiry, and a support representative provides additional information. The input data is the inquiry, and the output data is the additional information provided.

[0383] Step 10:

[0384] The system captures frames using an image capture device and analyzes the user's emotional state using an emotion recognition engine. It performs facial recognition and voice analysis to determine the emotional state in real time. Input data consists of camera frames and audio data, while output data is the result of the emotional state analysis.

[0385] Step 11:

[0386] The emotion recognition engine generates warning messages based on the user's emotional state. The engine presents an appropriate warning message based on the analysis results. For example, if the user is feeling anxious, it might generate a message such as, "Please calm down and review the following steps." The input data is the analysis result of the emotional state, and the output data is the warning message.

[0387] 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.

[0388] 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.

[0389] 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.

[0390] [Second Embodiment]

[0391] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0392] 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.

[0393] 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).

[0394] 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.

[0395] 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.

[0396] 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).

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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".

[0403] overview

[0404] This invention relates to a system that efficiently provides information by optimizing search queries using generative artificial intelligence when a user is retrieving specific information. The system receives a query entered by the user and transmits it to the generative artificial intelligence. The generative artificial intelligence optimizes the query and sends the optimized query to a search engine to retrieve information. The system also includes a function to automatically contact support chat if the search results are insufficient. This allows users to obtain information quickly and accurately.

[0405] System Configuration

[0406] The system consists of the following main components:

[0407] 1. User terminal

[0408] It includes an interface where the user enters search queries to retrieve specific information. The user terminal is used to receive queries and send them to the generative artificial intelligence.

[0409] 2. Generative Artificial Intelligence (AI) Module

[0410] This module receives user queries and generates optimized search terms. Specifically, it parses the input query and optimizes it based on the context.

[0411] 3. Search Engine

[0412] A search engine receives an optimized query, searches its database for relevant information, and generates results. These search results are ultimately provided to the user.

[0413] 4. Support Chat System

[0414] If the search results are insufficient, this system will automatically receive the user's inquiry, and a support representative will provide additional information.

[0415] Operation details

[0416] The following describes the specific operation of the system.

[0417] 1. The user enters a search query.

[0418] The user enters a query into the terminal's search bar to obtain specific information. For example, they might enter "Machine A instruction manual".

[0419] 2. The terminal receives the query.

[0420] The user terminal receives the entered query. The query is converted to the appropriate format within the terminal and prepared to be sent to the generative artificial intelligence module.

[0421] 3. The terminal sends a query to the generative artificial intelligence.

[0422] The terminal sends the received query to a generative artificial intelligence module. The generative AI module analyzes the query and optimizes it into a more effective search term. For example, it might be transformed into something like "Machine A instruction manual latest version".

[0423] 4. Generative artificial intelligence optimizes queries.

[0424] Generative artificial intelligence analyzes queries, understands the context and meaning, and then generates optimized queries. These optimized queries can better meet user requests.

[0425] 5. The device sends optimized queries to the search engine.

[0426] The optimized query is sent to the search engine. The search engine uses this query to search its database and retrieve relevant information.

[0427] 6. The server returns the search results.

[0428] Search results are generated by the search engine and sent back to the user's device. For example, they may include a link to or content of "the latest version of the instruction manual for machine A."

[0429] 7. The device displays the search results.

[0430] The user's device displays the received search results, allowing the user to verify the information.

[0431] 8. If the search results are insufficient, an automated inquiry will be sent to support chat.

[0432] If the search results are insufficient, the device will automatically contact the support chat system. For example, it might ask, "I'm looking for more details on how to perform a specific operation."

[0433] 9. Support chat will assist you.

[0434] The support chat system receives inquiries, and support staff respond to user questions, providing additional information and specific instructions.

[0435] Specific example

[0436] For example, consider a scenario where a user searches for "Machine A User Manual" on CrewNavi. In this case, the user enters a search query, which the terminal receives and sends to a generative artificial intelligence (AI). The AI ​​optimizes the query, and the search engine searches for relevant information. Based on the optimized query, the search engine finds "Latest Version User Manual for Machine A" and returns it to the user. If the user does not find the information they expect, the terminal automatically contacts support chat and is prompted to provide additional information.

[0437] The system of this invention aims to improve work productivity by enabling users to efficiently obtain the necessary information. This significantly reduces the time spent searching for information and alleviates user stress.

[0438] The following describes the processing flow.

[0439] Step 1:

[0440] The user enters a search query into the CrewNavi search bar.

[0441] Specific action: The user enters "Machine A User Manual" and clicks the search button.

[0442] Step 2:

[0443] The device receives a search query from the user.

[0444] Specific operation: The terminal receives the string "Machine A Instruction Manual" and processes it appropriately according to the data format.

[0445] Step 3:

[0446] The terminal sends the received search query to the generative artificial intelligence.

[0447] Specific operation: The terminal sends a request containing the query "Machine A User Manual" to the generative artificial intelligence API endpoint.

[0448] Step 4:

[0449] Generative artificial intelligence optimizes search queries.

[0450] Specific operation: The generative artificial intelligence analyzes "Machine A Instruction Manual," understands its context and meaning, and generates a more effective search term, "Machine A Instruction Manual Latest Version."

[0451] Step 5:

[0452] The device sends optimized queries to CrewNavi's search engine.

[0453] Specific operation: The terminal sends the optimized query "Machine A Instruction Manual Latest Version," which was returned by the generative artificial intelligence, to the CrewNavi search engine.

[0454] Step 6:

[0455] The server generates search results based on the query.

[0456] Specific operation: The search engine searches the database, extracts information from the "Latest Version of the User Manual for Machine A," and generates results.

[0457] Step 7:

[0458] The server sends the search results back to the terminal.

[0459] Specific action: Send the generated search results to the user's device.

[0460] Step 8:

[0461] The device displays search results to the user.

[0462] Specific operation: The search results received by the terminal are displayed on the user's screen. Specifically, a link and content of the "Latest version of the instruction manual for Machine A" are displayed.

[0463] Step 9:

[0464] If the search results are insufficient, the device will automatically contact support chat.

[0465] Specific operation: If the user cannot find specific information, the device will send an automated inquiry, such as "I am looking for specific instructions on how to operate machine A," to the support chat API.

[0466] Step 10:

[0467] The support chat receives and responds to inquiries.

[0468] Specific operation: The support chat system automatically receives inquiries, and support staff provide specific steps and additional documentation in response to the user's request for information.

[0469] (Example 1)

[0470] 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."

[0471] In modern information retrieval systems, the search queries that users enter to obtain specific information are not always optimized, often resulting in insufficient search results. Furthermore, when search results are insufficient, users have to make further inquiries or enter additional queries, which is a time-consuming and troublesome process.

[0472] 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.

[0473] In this invention, the server includes means for a user to input a search query to obtain specific information, means for receiving the search query, means for transmitting the received search query to a generative artificial intelligence, means for the generative artificial intelligence to optimize the search query, means for transmitting the optimized query to a search engine, means for the search engine to generate search results based on the optimized query, means for displaying the generated search results to the user, means for automatically querying a text-based interactive support system if the search results are insufficient, and means for analyzing the query content and providing appropriate supplementary information. As a result, the user can efficiently use the optimized search query to perform highly accurate information retrieval and quickly obtain additional information even if the search results are insufficient.

[0474] A "user" refers to someone who enters a search query and performs an information retrieval operation in order to obtain specific information.

[0475] A "search query" refers to a sentence or phrase that a user enters into a search engine to request specific information.

[0476] "Generative artificial intelligence" refers to artificial intelligence that analyzes input search queries, understands the context and meaning, and then generates optimized search terms.

[0477] A "search engine" refers to a system that searches a database based on an entered search query and extracts relevant information.

[0478] A "text-based interactive support system" refers to a system that automatically responds to user inquiries and inputs in text format, providing appropriate support information.

[0479] "Reception" means that a means or device takes in data or signals sent from another source.

[0480] "Transmission" means that a means or device sends specific data or signals to another party.

[0481] "Optimization" refers to the process of modifying something to its optimal state or configuration for a particular purpose.

[0482] "Analysis" refers to the process of thoroughly examining input data and information to understand its meaning and structure.

[0483] "Supplementary information" refers to additional information provided to complement the main information that the user is seeking.

[0484] System Overview and Configuration

[0485] This invention provides a system that efficiently delivers information by optimizing search queries using generative artificial intelligence when a user retrieves specific information. The system receives the user's search query, the generative artificial intelligence optimizes it, and then sends the optimized query to a search engine to retrieve information. It also includes a function to automatically query a text-based interactive support system if the search results are insufficient.

[0486] Hardware and software to be used

[0487] User terminal: Used by the user to enter search queries. This includes typical personal computers, smartphones, and tablets.

[0488] Generative artificial intelligence module: Analyzes user queries and generates optimized search terms. Examples of AI models used include high-performance natural language processing models such as GPT-4.

[0489] Search engine: Searches for relevant information based on optimized queries. Common search engine technologies include Elasticsearch and Solr.

[0490] Text-based interactive support systems: These systems automatically respond to user inquiries and provide supplementary information. Examples include chatbot systems and FAQ systems.

[0491] Explanation of the program's processing

[0492] When a user enters a search query, it is received by the terminal. The terminal sends the received query to a generative artificial intelligence module, which analyzes the query, understands its context and meaning, and then optimizes it. Next, the terminal sends the optimized query to a search engine, which searches its database based on this query and generates relevant information. The generated search results are sent back to the user's terminal by the server and displayed for the user to review.

[0493] If the search results are insufficient, the device automatically contacts a text-based interactive support system. This system provides the user with additional assistance information based on the support staff and pre-configured scenarios.

[0494] Examples of specific scenarios and prompts

[0495] For example, consider a case where a user searches for "Machine A instruction manual." The user enters this query into a terminal, which then sends it to a generative artificial intelligence module. The generative AI optimizes the query, for example, transforming it into "Machine A instruction manual latest version." The search engine then searches for relevant information based on the optimized query and returns the results to the user's terminal. If the user reviews the information and makes further inquiries as needed, a text-based interactive support system will handle it.

[0496] Example of a prompt

[0497] "Receive search queries submitted by users and generate optimized search terms. Submit these optimized queries to search engines to retrieve relevant information. Finally, advise on the best way to present the retrieved information to users."

[0498] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0499] Step 1:

[0500] The user enters a search query. The user enters a query such as "Machine A Instruction Manual" into the search bar to retrieve specific information. The entered query is sent to the terminal.

[0501] Step 2:

[0502] The terminal receives the search query. The terminal receives the query entered by the user and stores it in its internal data format. The received query, "Machine A User Manual," is ready to be passed on to the next process.

[0503] Step 3:

[0504] The terminal sends a search query to the generative artificial intelligence. The terminal sends the received query to the generative artificial intelligence module, along with providing contextual information. The "Machine A User Manual" is passed to the generative artificial intelligence as input.

[0505] Step 4:

[0506] Generative artificial intelligence optimizes the search query. Generative artificial intelligence analyzes the query, understands its context and meaning, and performs optimization. In this process, the query is transformed into "Machine A Instruction Manual Latest Version". The input query "Machine A Instruction Manual" is transformed into the optimized output query "Machine A Instruction Manual Latest Version".

[0507] Step 5:

[0508] The terminal sends an optimized query to the search engine. The terminal receives the optimized query and sends it to the search engine. "Machine A Instruction Manual Latest Version" is sent to the search engine as input.

[0509] Step 6:

[0510] The search engine generates search results. The search engine searches its internal database based on the optimized query and collects relevant information. For example, links and related documents for "Machine A Instruction Manual Latest Version" are extracted. The input to the search engine is "Machine A Instruction Manual Latest Version," and the output is a list of related information.

[0511] Step 7:

[0512] The server returns the search results. The server sends the search results obtained from the search engine back to the user's terminal. For example, a link to "Machine A Instruction Manual Latest Version" is sent to the user's terminal.

[0513] Step 8:

[0514] The user terminal displays the search results. The user terminal displays the received search results to the user. The user can obtain the necessary information based on the displayed links and information. The input is the search results from the server, and the output is what is displayed to the user.

[0515] Step 9:

[0516] If the search results are insufficient, the device automatically queries a text-based interactive support system. If the search results do not meet the user's expectations, the device sends a message to the text-based interactive support system, for example, "I would like to know more information about a specific operation."

[0517] Step 10:

[0518] A text-based interactive support system interacts with the user. The system receives inquiries and provides additional information and specific steps. For example, a support staff member might provide the user with additional materials or instructions. Input is the inquiry from the user's terminal, and output is the provision of supplementary information.

[0519] (Application Example 1)

[0520] 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 glasses 214 will be referred to as the "terminal."

[0521] The problem that this invention aims to solve is to facilitate the rapid and accurate acquisition of specific information by users. In particular, it aims to enable users of autonomous vehicles to easily acquire information about the area around their destination and vehicle handling information while driving or stopped, and to quickly acquire additional information if necessary information is missing. Another important issue is to enable voice input, allowing users to safely enter queries even while driving.

[0522] 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.

[0523] In this invention, the server includes means for a user to input a search query to obtain specific information, means for receiving the search query, means for transmitting the received search query to a generative artificial intelligence, means for the generative artificial intelligence to optimize the search query, means for transmitting the optimized query to a search engine, means for the search engine to generate search results based on the optimized query, means for displaying the generated search results to the user, voice input means, means for converting the voice-input query to text, and means for automatically contacting support chat if the search results are insufficient. This enables the user to safely search for information by voice even while driving and efficiently obtain the necessary information through optimized queries. Furthermore, it becomes possible to automatically use the support chat system as needed to quickly obtain additional information.

[0524] A "search query" is a string of characters that a user enters to retrieve specific information.

[0525] "Means of receiving data" refers to the system for importing search queries entered by users.

[0526] "Generative artificial intelligence" is a type of artificial intelligence that analyzes search queries entered by users and optimizes them based on context.

[0527] "Optimization methods" refer to the process by which generative artificial intelligence transforms search queries into more effective search terms.

[0528] A "search engine" is a system that searches a database for relevant information based on optimized queries and generates results.

[0529] "Means of displaying search results" refers to an interface that displays information in a way that allows users to easily verify the information they have obtained.

[0530] A "voice input method" is a mechanism that allows users to input queries using their voice.

[0531] "Means of converting to text" refers to the process of converting voice-input queries into text format.

[0532] "Support chat" is a system that automatically makes inquiries and provides additional information when search results are insufficient.

[0533] "Automated inquiry methods" refer to the process by which users can contact support chat without manual intervention when they need additional information.

[0534] The embodiments for carrying out the present invention are described in detail below. The system for realizing this invention is designed to allow passengers of an autonomous vehicle to easily obtain specific information using voice input. The system consists of four main components: a user terminal, a generative artificial intelligence module, a search engine, and a support chat system.

[0535] First, the user enters a search query through the in-vehicle voice input device. The user terminal receives this via voice input and converts it into text using speech recognition software. Specifically, the SpeechRecognition library is used. If the user enters "What are some good Japanese restaurants nearby?", this voice is converted into text.

[0536] Next, the stringified search query is sent to a generative artificial intelligence module for query optimization. This process uses a GPT-3 model with Hugging Face's Transformers library. The generative AI analyzes the query and, based on context, transforms it into more effective search terms such as "highly-rated Japanese restaurants within 3km of my current location."

[0537] The optimized query is then sent to a search engine, which retrieves relevant information from its database. The search results are returned to the user's device and presented to them via the vehicle's display or audio system. This allows the user to quickly obtain information on highly-rated restaurants near their destination.

[0538] Furthermore, if the retrieved search results are insufficient, an automated inquiry is made to the support chat system. At this stage, the Requests library is used to perform an automated inquiry to obtain additional information. Based on the inquiry received by the support chat, the necessary details are provided. For example, allergen information for a specific restaurant is provided to the user in real time.

[0539] As a concrete example, consider a case where a user voice-inputs "What are some good Japanese restaurants near me?", and this is optimized to show "highly-rated Japanese restaurants within 3km of the user's current location." This optimized query is sent to the search engine, and relevant information is returned. If the information obtained is insufficient, an automated inquiry is sent to the support chat asking, "What is the allergen information for this particular Japanese restaurant?"

[0540] Examples of prompts for a generative AI model include the following:

[0541] A user is searching for nearby restaurants. Please generate the most suitable search terms based on the user's specified criteria. Example: "Japanese food," "delicious," "within 3km."

[0542] Thus, the system of the present invention is designed to enable users to obtain information quickly and safely. The collaboration between generative artificial intelligence and speech recognition technology makes it possible to provide highly accurate and convenient information.

[0543] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0544] Step 1: The user enters the search query by voice.

[0545] Users use a voice input device in the autonomous vehicle to enter search queries by voice to obtain specific information. For example, the input might be "What are some good Japanese restaurants nearby?"

[0546] Step 2: The device receives the voice input and converts it to text.

[0547] The device converts the user's voice input into text using speech recognition software (e.g., the SpeechRecognition library). The input is voice data, and the output is text data such as "What are some good Japanese restaurants nearby?"

[0548] Step 3: The device sends text data to the generative artificial intelligence.

[0549] The terminal sends the converted text data to a generative artificial intelligence module. In this process, the input is the text data entered by the user, and the output is the input data for the generative artificial intelligence.

[0550] Step 4: Generative artificial intelligence optimizes the query

[0551] Generative artificial intelligence analyzes incoming queries and optimizes them into more effective search terms. For example, a GPT-3 model using Hugging Face's Transformers library is used. The input is the original query "What are some good Japanese restaurants near me?", and the output is "Highly-rated Japanese restaurants within 3km of my current location".

[0552] Step 5: The device sends an optimized query to the search engine.

[0553] The device sends an optimized query to the search engine. In this process, the input is a query optimized by generative artificial intelligence, and the output is a query request to the search engine.

[0554] Step 6: The search engine generates relevant information and responds.

[0555] A search engine retrieves relevant information from a database based on an optimized query and generates results. The input is the optimized query, and the output is the search results. For example, it might include "information about highly-rated Japanese restaurants within 3km of my current location."

[0556] Step 7: The device displays the search results to the user.

[0557] The terminal displays search results to the user. This display is done through the vehicle's display or audio system. The input is the search results from the search engine, and the output is the presentation of information to the user.

[0558] Step 8: If the search results are insufficient, the device will automatically contact support chat.

[0559] If the search results do not meet the user's requirements, the device automatically contacts the support chat system. The input consists of the missing search results and additional queries, and the output is the inquiry request to the support chat system.

[0560] Step 9: Support chat will provide additional information.

[0561] The support chat system receives inquiries and provides necessary additional information. The input is the content of the inquiry to the support chat, and the output is additional information for the user. Specifically, this may include "allergen information for a particular restaurant."

[0562] 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.

[0563] overview

[0564] This invention relates to a system that optimizes search queries by combining generative artificial intelligence and an emotion engine when a user retrieves specific information, and provides information tailored to the user's emotional state. The system receives a query entered by the user and analyzes the user's emotions using the emotion engine. The generative artificial intelligence optimizes the query and sends the optimized query to a search engine to retrieve information. If the search results are insufficient, the system includes a function to automatically contact support chat. Furthermore, the emotion engine transmits the user's emotional state to the support chat system to help support staff provide more appropriate responses.

[0565] System Configuration

[0566] The system consists of the following main components:

[0567] 1. User terminal

[0568] It includes an interface where the user enters search queries to retrieve specific information. The user terminal is used to receive queries and send them to the generative artificial intelligence and emotion engine.

[0569] 2. Generative Artificial Intelligence (AI) Module

[0570] This module receives user queries and generates optimized search terms. Specifically, it parses the input query and optimizes it based on the context.

[0571] 3. Emotional Engine

[0572] The emotion engine analyzes the user's emotional state and provides the analysis results to other components. For example, if the user is anxious or dissatisfied, this information is reflected and provided to generative artificial intelligence and the support chat system.

[0573] 4. Search Engine

[0574] A search engine receives an optimized query, searches its database for relevant information, and generates results. These search results are ultimately provided to the user.

[0575] 5. Support Chat System

[0576] If the search results are insufficient, the system automatically receives the user's inquiry, and a support representative provides additional information. Based on the user's sentiment information from the sentiment engine, the support representative takes appropriate action.

[0577] Operation details

[0578] The following describes the specific operation of the system.

[0579] 1. The user enters a search query.

[0580] The user enters a query into the terminal's search bar to obtain specific information. For example, they might enter "Machine A instruction manual" and click the search button.

[0581] 2. The terminal receives the query.

[0582] The user terminal receives the entered query. The query is converted to the appropriate format within the terminal and then prepared to be sent to the sentiment engine.

[0583] 3. The device sends the query to the sentiment engine.

[0584] The device sends the received query and user interaction data (keystrokes, mouse movements, etc.) to the emotion engine. The emotion engine analyzes this data to determine the user's emotional state.

[0585] 4. The emotion engine analyzes the user's emotions.

[0586] The emotion engine receives queries and analyzes the user's emotional state. For example, it determines whether the user is anxious, angry, or calm.

[0587] 5. The terminal sends an optimization query to the generative artificial intelligence.

[0588] Based on the analysis results from the emotion engine, the device sends a request to the generative artificial intelligence to optimize the search query according to the user's emotions. The generative AI receives this request and optimizes the query.

[0589] 6. Generative artificial intelligence optimizes queries.

[0590] Generative artificial intelligence analyzes queries, understands the context and emotional state, and then generates optimized queries. These optimized queries can better meet user requests.

[0591] 7. The device sends optimized queries to the search engine.

[0592] The optimized query is sent to the search engine. The search engine uses this query to search its database and retrieve relevant information.

[0593] 8. The server returns the search results.

[0594] Search results are generated by the search engine and sent back to the user's device. For example, they may include a link to or content of "the latest version of the instruction manual for machine A."

[0595] 9. The device displays search results to the user.

[0596] The user's device displays the received search results, allowing the user to verify the information.

[0597] 10. If search results are insufficient, the system will automatically contact support chat via the sentiment engine.

[0598] If the search results are insufficient, the device will send an automated inquiry via the emotion engine to the support chat API, such as "I am looking for specific instructions on how to operate machine A."

[0599] 11. The support chat receives the inquiry and responds.

[0600] The support chat system receives inquiries, and support staff respond to user questions. They provide additional information and specific steps. Based on emotional information provided by the emotion engine, support staff provide the most appropriate response for the user's situation.

[0601] Specific example

[0602] For example, consider a scenario where a user searches for "Machine A instruction manual." In this case, the user enters a search query, which the device receives and sends to the emotion engine. The emotion engine analyzes the user's emotional state and sends the results to the generative artificial intelligence. The generative AI optimizes the query, and the search engine searches for relevant information. Based on the optimized query, the search engine finds "the latest version of the Machine A instruction manual" and returns it to the user. If the user does not find the information they expect, the device automatically contacts support chat via the emotion engine and is prompted to provide additional information.

[0603] The system of this invention aims to improve work productivity by enabling users to efficiently obtain the information they need. This significantly reduces information retrieval time and alleviates user stress. Furthermore, by incorporating an emotion engine, it can provide optimal responses tailored to the user's emotional state, offering a more fulfilling user experience.

[0604] The following describes the processing flow.

[0605] Step 1:

[0606] The user enters a search query into the CrewNavi search bar.

[0607] Specific action: The user enters "Machine A User Manual" and clicks the search button.

[0608] Step 2:

[0609] The device receives a search query from the user.

[0610] Specific operation: The terminal receives the string "Machine A Instruction Manual" and processes it appropriately according to the data format.

[0611] Step 3:

[0612] The device sends the received search queries and interaction data to the sentiment engine.

[0613] Specific operation: The device sends the search query along with interaction data such as the user's keystrokes and mouse movements to the sentiment engine's API endpoint.

[0614] Step 4:

[0615] The emotion engine analyzes the user's emotions.

[0616] Specific operation: The emotion engine analyzes keystroke speed, mouse movements, input content, etc., to identify the user's emotional state (anxiety, anger, calmness, etc.).

[0617] Step 5:

[0618] The terminal sends queries and sentiment analysis results to the generative artificial intelligence.

[0619] Specific operation: The terminal sends an optimization query request, including the emotion analysis results, to the generative artificial intelligence API.

[0620] Step 6:

[0621] Generative artificial intelligence optimizes queries.

[0622] Specific operation: The generative artificial intelligence analyzes the "Machine A User Manual" and optimizes it, taking into account emotional states, to create something like the "Machine A User Manual Latest Version."

[0623] Step 7:

[0624] The device sends optimized queries to the search engine.

[0625] Specific operation: The terminal sends the optimized query "Machine A Instruction Manual Latest Version," which was returned by the generative artificial intelligence, to the CrewNavi search engine.

[0626] Step 8:

[0627] The server generates search results based on the query.

[0628] Specific operation: The search engine searches the database, extracts information from the "Latest Version of the User Manual for Machine A," and generates results.

[0629] Step 9:

[0630] The server sends the search results back to the terminal.

[0631] Specific action: Send the generated search results to the user's device.

[0632] Step 10:

[0633] The device displays search results to the user.

[0634] Specific operation: The search results received by the terminal are displayed on the user's screen. Specifically, a link and content of the "Latest version of the instruction manual for Machine A" are displayed.

[0635] Step 11:

[0636] If the search results are insufficient, an automated inquiry will be sent to support chat via the emotion engine.

[0637] Specific operation: If the user cannot find specific information, the device will send an automated inquiry, such as "I am looking for specific instructions on how to operate machine A," via the emotion engine to the support chat API.

[0638] Step 12:

[0639] The support chat receives and responds to inquiries.

[0640] Specific operation: The support chat system automatically receives inquiries, and a support representative provides specific steps and additional documentation in response to the user's request. Based on the emotional information provided by the emotion engine, the support representative provides the most appropriate response to the user's situation.

[0641] (Example 2)

[0642] 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".

[0643] Traditional search systems often failed to provide optimal information for user-entered search queries, resulting in decreased user satisfaction. In particular, the lack of appropriate information tailored to the user's emotional state could reduce search efficiency and increase stress. Furthermore, the process of users seeking additional information when search results were insufficient was cumbersome.

[0644] 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.

[0645] In this invention, the server includes means for a user to input a search query to obtain specific information, means for receiving the search query, means for transmitting the received search query to an emotion analysis module, means for the emotion analysis module to analyze the user's emotional state, means for transmitting the search query to a generative artificial intelligence based on the emotion analysis results, means for the generative artificial intelligence to optimize the search query, means for transmitting the optimized query to a search engine, means for the search engine to generate search results based on the optimized query, means for displaying the generated search results to the user, and means for automatically querying a support system via the emotion analysis module if the search results are insufficient. This enables the provision of optimal information according to the user's emotional state, improves search efficiency, and reduces user stress. Furthermore, if the search results are insufficient, a query is automatically made to the support system, allowing the user to quickly obtain additional information.

[0646] "User" refers to a person who uses this system to obtain specific information.

[0647] A "search query" is a combination of strings or words that a user enters to specify the information they want to retrieve.

[0648] An "interface" is a means of communication between the user and the system that allows the user to enter a search query and display the results.

[0649] An "emotion analysis module" or "emotion engine" is a software component that analyzes a user's emotional state, determining emotions based on user interaction data.

[0650] "Generative artificial intelligence" refers to an artificial intelligence module that generates optimized search queries based on received search queries and sentiment analysis results.

[0651] A "search engine" is a system used to search for relevant information from web pages and databases.

[0652] "Search results" are a list of information generated by a search engine that corresponds to a user's search query.

[0653] A "support system" or "support chat" is an automated inquiry and response system designed to provide users with additional information they may need.

[0654] "Emotional analysis results" refer to the results of an analysis of the user's emotional state obtained by the emotional analysis module based on the user's interaction data.

[0655] An "optimized query" is the most appropriate combination of search terms generated by a generative artificial intelligence system based on the user's search query and sentiment analysis results.

[0656] "Interaction data" refers to data generated when a user interacts with a system (e.g., keystrokes, mouse movements).

[0657] These definitions clarify each component of the system relating to the present invention and its function.

[0658] Modes for carrying out the invention

[0659] This invention relates to a system that optimizes search queries by combining generative artificial intelligence and an emotion analysis module when a user retrieves specific information, and provides information tailored to the user's emotional state. This system mainly consists of the following key components.

[0660] System Configuration

[0661] 1. User terminal

[0662] It includes an interface where the user enters search queries to retrieve specific information. The user terminal is used to receive queries and send them to generative artificial intelligence and sentiment analysis modules.

[0663] 2. Generative Artificial Intelligence (AI) Module

[0664] This module receives user queries and generates optimized search terms. Specifically, it analyzes the input query and optimizes it based on context and sentiment.

[0665] 3. Emotion Analysis Module (Emotion Engine)

[0666] The emotion analysis module analyzes the user's emotional state and provides the analysis results to other components. For example, if the user is anxious or dissatisfied, this information is reflected in the generative artificial intelligence and support chat system.

[0667] 4. Search Engine

[0668] A search engine receives an optimized query, searches its database for relevant information, and generates results. These search results are ultimately provided to the user.

[0669] 5. Support Chat System

[0670] If the search results are insufficient, the system automatically receives the user's inquiry, and a support representative provides additional information. Based on the user's sentiment information from the sentiment engine, the support representative takes appropriate action.

[0671] How the system works

[0672] Program Processing Overview

[0673] The system first receives the search query entered by the user. The received query is sent to an emotion analysis module, which analyzes the user's emotional state. Then, based on the analysis results, the query is optimized by generative artificial intelligence. The optimized query is sent to a search engine, and relevant search results are generated. The generated search results are displayed to the user, but if the search results are insufficient, an inquiry is automatically sent to the support chat system. Based on the emotional information provided by the emotion analysis module, a support representative provides the most appropriate response to the user.

[0674] Specific example

[0675] For example, consider a scenario where a user searches for "Machine A instruction manual." In this case, the user enters a search query, which the terminal receives and sends to an emotion analysis module. The emotion analysis module analyzes the user's emotional state and sends the results to a generative artificial intelligence (AI). The AI ​​optimizes the query, and the search engine searches for relevant information. Based on the optimized query, the search engine finds "the latest version of the Machine A instruction manual" and returns it to the user. If the user does not find the information they expect, the terminal automatically contacts a support chat system via the emotion analysis module to provide additional information.

[0676] Examples of prompt statements

[0677] "The user searched for 'Machine A User Manual,' but the emotion engine detected an anxious emotion. Please generate the most suitable search query for the user and automatically contact support chat if necessary."

[0678] This invention is designed to allow users to efficiently obtain the information they need, aiming to improve work productivity. By introducing an emotion analysis module, it becomes possible to provide optimal responses tailored to the user's emotional state, thereby offering a more enriching user experience.

[0679] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0680] The program's processing flow is divided into processing steps.

[0681] Step 1: The user enters a search query.

[0682] To obtain specific information, the user enters a query into the terminal's search bar. An example of such a query is "Machine A Instruction Manual". The input data here is the string "Machine A Instruction Manual" entered by the user.

[0683] Step 2: The terminal receives the query.

[0684] The terminal receives the query entered by the user. The received query ("Machine A User Manual") is converted into an appropriate data format and prepared to be sent to the sentiment analysis module. The input data here is the user's query, which is the output of step 1. The output data is the query data ready for sentiment analysis.

[0685] Step 3: The device sends query and interaction data to the sentiment analysis module.

[0686] The terminal sends the received query along with user interaction data (e.g., keyboard input speed, mouse movements, etc.) to the sentiment analysis module. The input data consists of the query string "Machine A Instruction Manual" and the interaction data. The output data is the data sent to the sentiment analysis module.

[0687] Step 4: The emotion analysis module analyzes the user's emotional state.

[0688] The emotion analysis module determines the user's emotional state (e.g., anxious, angry, calm) based on the received data. The input data consists of the query and interaction data sent in step 3. The output data is the analyzed user's emotional state.

[0689] Step 5: The device sends queries and sentiment analysis results to the generative artificial intelligence.

[0690] The terminal sends a query along with the emotion analysis results (e.g., state of anxiety) to the generative artificial intelligence. The input data consists of the query and the emotion analysis results. The output data is the request for optimization query generation that was sent to the generative artificial intelligence.

[0691] Step 6: Generative AI optimizes the query.

[0692] Generative artificial intelligence receives a query and sentiment analysis results, and generates an optimized query considering the context and emotional state (e.g., "Download the latest version of the instruction manual for machine A"). The input data is the original query and sentiment analysis results. The output data is the optimized query.

[0693] Step 7: The device sends the optimized query to the search engine.

[0694] The device sends an optimized query to the search engine. The input data is the optimized query. The output data is the query sent to the search engine.

[0695] Step 8: The server returns the search results.

[0696] A server with a search engine receives an optimized query, searches its database, and retrieves relevant information (e.g., "Latest version of the instruction manual for machine A"). The retrieved information is sent back to the terminal as search results. The input data is the optimized query, and the output data is the search results.

[0697] Step 9: The device displays the search results to the user.

[0698] The terminal displays search results received from the server to the user. For example, a link or summary of "the latest version of the instruction manual for machine A" is displayed on the user's screen. The input data is the search results, and the output data is the information displayed to the user.

[0699] Step 10: If the search results are insufficient, send an automated inquiry to the support chat.

[0700] If the user cannot obtain the information they expect, the device will automatically contact the support chat system based on the sentiment analysis results (e.g., "I am looking for specific instructions on how to operate machine A"). The input data consists of insufficient search results and sentiment analysis results, while the output data is the content of the inquiry sent to the support chat.

[0701] Step 11: Support chat receives and responds to the inquiry.

[0702] The support chat system receives inquiries, and support staff respond to user questions. Based on sentiment analysis results, responses are tailored to the user's state. The input data is the content of the inquiry sent to the support chat, and the output data is additional information provided by the support staff.

[0703] This allows users to efficiently obtain the information they need, and to quickly acquire additional information even if the search results are insufficient.

[0704] (Application Example 2)

[0705] 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."

[0706] Current information retrieval systems often fail to provide search results quickly and accurately, as they do not take into account the user's emotional state. This is particularly problematic in the security field, where providing appropriate information in situations where security personnel are under pressure and anxiety is crucial, but current systems do not adequately address this. Furthermore, the lack of automated systems for additional actions when search results are insufficient places a significant burden on users.

[0707] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting a search query for a user to obtain specific information, means for receiving the search query, means for transmitting the received search query to a generative artificial intelligence, means for the generative artificial intelligence to optimize the search query, means for transmitting the optimized query to a search engine, means for the search engine to generate search results based on the optimized query, means for displaying the generated search results to the user, means for automatically contacting a support chat if the search results are insufficient, means for capturing a frame with an image capture device and analyzing the user's emotional state using an emotion recognition engine, and means for generating a warning message based on the emotional state. This not only enables the provision of optimal information according to the user's emotional state, but also reduces the burden on the user by automatically taking additional action if the search results are insufficient.

[0708] A "user" is an individual or organization that enters a search query to obtain information.

[0709] A "search query" is a set of sentences or words that a user enters in order to obtain specific information.

[0710] "Generative artificial intelligence" is an artificial intelligence technology that analyzes input search queries and optimizes them based on context.

[0711] "Optimization" is the process of analyzing an entered search query and converting it into search terms that best meet the user's needs.

[0712] A "search engine" is a system that searches a database based on optimized queries and generates relevant information.

[0713] "Search results" are a collection of information generated by a search engine that a user is looking for.

[0714] A "support chat" is a system that automatically responds to user inquiries and provides additional information when search results are insufficient.

[0715] An "emotion recognition engine" is a technology used to analyze a user's emotional state, and it has the function of determining a user's emotions by analyzing their voice and facial expressions.

[0716] An "image capture device" is a device used to capture images or videos in real time.

[0717] A "warning message" is information or instructions designed to draw attention to a user's emotional state.

[0718] To implement the invention, the following hardware and software components are required. First, the user terminal has an interface for the user to input search queries to obtain specific information. This terminal is used for receiving queries and transmitting them to a generative artificial intelligence and emotion engine.

[0719] When a user enters a search query, the device receives the query, converts it to an appropriate format, and sends it to a generative artificial intelligence (AI). The AI ​​analyzes this query and optimizes it to best meet the user's needs. The optimized query is then sent to a search engine. The search engine searches its database for relevant information, generates search results, and returns them to the user.

[0720] If the search results are insufficient, the system will automatically contact the support chat system. This support chat system will answer the user's additional questions and provide more specific information.

[0721] Furthermore, the system includes an emotion recognition engine that analyzes the user's emotional state in real time. This engine captures frames using an image capture device and determines the user's emotional state from their facial expressions and voice. Based on this analysis, the emotion recognition engine generates a warning message and provides it to the user.

[0722] As a concrete example, let's consider a scenario where a user is performing monitoring duties. When the user searches for "emergency reporting procedures" in an emergency, the system receives the search query, and generative artificial intelligence optimizes it before sending it to the search engine. For example, it might be optimized as "on-site emergency reporting procedures." If the search results are not appropriate (for example, if no specific reporting procedures are found), the system automatically contacts the support chat system and provides additional specific response procedures.

[0723] Furthermore, the emotion recognition engine analyzes the user's emotional state and, if it detects that the user is anxious, generates an appropriate warning message. For example, it might display, "Please calm down and review the following steps." This allows the user to continue acting calmly.

[0724] The hardware and software used include:

[0725] Hardware: Cameras (surveillance cameras, webcams), user devices (PCs, smartphones, etc.)

[0726] Software: OpenCV (for camera frame capture), emotion recognition engine (e.g., Facial Emotion Recognition module), generative artificial intelligence (GPT-3 API, etc.)

[0727] The example prompt is as follows:

[0728] "The security team is in a state of panic. Please generate the most appropriate warning message."

[0729] The introduction of this system allows users to efficiently obtain necessary information and reduce stress and anxiety through emotion recognition. Furthermore, if search results are insufficient, additional actions are taken immediately, ensuring smooth task completion.

[0730] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0731] Step 1:

[0732] The user enters a search query to obtain specific information. The user enters the query in the search bar of their device and sends the entered query. For example, they might enter "emergency call procedure".

[0733] Step 2:

[0734] The terminal receives the search query. The terminal receives the query entered by the user and converts it to an appropriate format. The input data is a text-based query, and the converted data is also in text format.

[0735] Step 3:

[0736] The terminal sends the received search query to the generative artificial intelligence. The terminal then sends the pre-processed query to the generative AI module and waits for the result to be received. The input data is a search query in text format, and an optimized query is output.

[0737] Step 4:

[0738] Generative artificial intelligence optimizes search queries. The generative AI module analyzes the received query and transforms it into the most appropriate form based on the context. For example, it might specify "emergency call procedure" as "on-site emergency call procedure." The input data is the search query, and the output data is the optimized query.

[0739] Step 5:

[0740] The device sends an optimized query to the search engine. The input data is an optimized query, and the output data is a query in the form of a request to the search engine.

[0741] Step 6:

[0742] A search engine generates search results based on an optimized query. The search engine searches its database based on the received query and retrieves relevant information. The input data is the optimized query, and the output data is the search results.

[0743] Step 7:

[0744] The server displays the generated search results to the user. The server sends the search results obtained from the search engine back to the user's terminal. The user's terminal displays the received search results to the user. The input data is the search results, and the output data is the information displayed on the screen.

[0745] Step 8:

[0746] If search results are insufficient, the system automatically initiates a support chat inquiry. If the user cannot obtain the necessary information, the device automatically sends an inquiry to the support chat. The input data is a query for the missing information, and the output data is the request to the support chat.

[0747] Step 9:

[0748] The support chat receives the inquiry and provides additional information. The support chat system receives the user's inquiry, and a support representative provides additional information. The input data is the inquiry, and the output data is the additional information provided.

[0749] Step 10:

[0750] The system captures frames using an image capture device and analyzes the user's emotional state using an emotion recognition engine. It performs facial recognition and voice analysis to determine the emotional state in real time. Input data consists of camera frames and audio data, while output data is the result of the emotional state analysis.

[0751] Step 11:

[0752] The emotion recognition engine generates warning messages based on the user's emotional state. The engine presents an appropriate warning message based on the analysis results. For example, if the user is feeling anxious, it might generate a message such as, "Please calm down and review the following steps." The input data is the analysis result of the emotional state, and the output data is the warning message.

[0753] 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.

[0754] 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.

[0755] 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.

[0756] [Third Embodiment]

[0757] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0758] 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.

[0759] 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).

[0760] 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.

[0761] 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.

[0762] 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).

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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".

[0769] overview

[0770] This invention relates to a system that efficiently provides information by optimizing search queries using generative artificial intelligence when a user is retrieving specific information. The system receives a query entered by the user and transmits it to the generative artificial intelligence. The generative artificial intelligence optimizes the query and sends the optimized query to a search engine to retrieve information. The system also includes a function to automatically contact support chat if the search results are insufficient. This allows users to obtain information quickly and accurately.

[0771] System Configuration

[0772] The system consists of the following main components:

[0773] 1. User terminal

[0774] It includes an interface where the user enters search queries to retrieve specific information. The user terminal is used to receive queries and send them to the generative artificial intelligence.

[0775] 2. Generative Artificial Intelligence (AI) Module

[0776] This module receives user queries and generates optimized search terms. Specifically, it parses the input query and optimizes it based on the context.

[0777] 3. Search Engine

[0778] A search engine receives an optimized query, searches its database for relevant information, and generates results. These search results are ultimately provided to the user.

[0779] 4. Support Chat System

[0780] If the search results are insufficient, this system will automatically receive the user's inquiry, and a support representative will provide additional information.

[0781] Operation details

[0782] The following describes the specific operation of the system.

[0783] 1. The user enters a search query.

[0784] The user enters a query into the terminal's search bar to obtain specific information. For example, they might enter "Machine A instruction manual".

[0785] 2. The terminal receives the query.

[0786] The user terminal receives the entered query. The query is converted to the appropriate format within the terminal and prepared to be sent to the generative artificial intelligence module.

[0787] 3. The terminal sends a query to the generative artificial intelligence.

[0788] The terminal sends the received query to a generative artificial intelligence module. The generative AI module analyzes the query and optimizes it into a more effective search term. For example, it might be transformed into something like "Machine A instruction manual latest version".

[0789] 4. Generative artificial intelligence optimizes queries.

[0790] Generative artificial intelligence analyzes queries, understands the context and meaning, and then generates optimized queries. These optimized queries can better meet user requests.

[0791] 5. The device sends optimized queries to the search engine.

[0792] The optimized query is sent to the search engine. The search engine uses this query to search its database and retrieve relevant information.

[0793] 6. The server returns the search results.

[0794] Search results are generated by the search engine and sent back to the user's device. For example, they may include a link to or content of "the latest version of the instruction manual for machine A."

[0795] 7. The device displays the search results.

[0796] The user's device displays the received search results, allowing the user to verify the information.

[0797] 8. If the search results are insufficient, an automated inquiry will be sent to support chat.

[0798] If the search results are insufficient, the device will automatically contact the support chat system. For example, it might ask, "I'm looking for more details on how to perform a specific operation."

[0799] 9. Support chat will assist you.

[0800] The support chat system receives inquiries, and support staff respond to user questions, providing additional information and specific instructions.

[0801] Specific example

[0802] For example, consider a scenario where a user searches for "Machine A User Manual" on CrewNavi. In this case, the user enters a search query, which the terminal receives and sends to a generative artificial intelligence (AI). The AI ​​optimizes the query, and the search engine searches for relevant information. Based on the optimized query, the search engine finds "Latest Version User Manual for Machine A" and returns it to the user. If the user does not find the information they expect, the terminal automatically contacts support chat and is prompted to provide additional information.

[0803] The system of this invention aims to improve work productivity by enabling users to efficiently obtain the necessary information. This significantly reduces the time spent searching for information and alleviates user stress.

[0804] The following describes the processing flow.

[0805] Step 1:

[0806] The user enters a search query into the CrewNavi search bar.

[0807] Specific action: The user enters "Machine A User Manual" and clicks the search button.

[0808] Step 2:

[0809] The device receives a search query from the user.

[0810] Specific operation: The terminal receives the string "Machine A Instruction Manual" and processes it appropriately according to the data format.

[0811] Step 3:

[0812] The terminal sends the received search query to the generative artificial intelligence.

[0813] Specific operation: The terminal sends a request containing the query "Machine A User Manual" to the generative artificial intelligence API endpoint.

[0814] Step 4:

[0815] Generative artificial intelligence optimizes search queries.

[0816] Specific operation: The generative artificial intelligence analyzes "Machine A Instruction Manual," understands its context and meaning, and generates a more effective search term, "Machine A Instruction Manual Latest Version."

[0817] Step 5:

[0818] The device sends optimized queries to CrewNavi's search engine.

[0819] Specific operation: The terminal sends the optimized query "Machine A Instruction Manual Latest Version," which was returned by the generative artificial intelligence, to the CrewNavi search engine.

[0820] Step 6:

[0821] The server generates search results based on the query.

[0822] Specific operation: The search engine searches the database, extracts information from the "Latest Version of the User Manual for Machine A," and generates results.

[0823] Step 7:

[0824] The server sends the search results back to the terminal.

[0825] Specific action: Send the generated search results to the user's device.

[0826] Step 8:

[0827] The device displays search results to the user.

[0828] Specific operation: The search results received by the terminal are displayed on the user's screen. Specifically, a link and content of the "Latest version of the instruction manual for Machine A" are displayed.

[0829] Step 9:

[0830] If the search results are insufficient, the device will automatically contact support chat.

[0831] Specific operation: If the user cannot find specific information, the device will send an automated inquiry, such as "I am looking for specific instructions on how to operate machine A," to the support chat API.

[0832] Step 10:

[0833] The support chat receives and responds to inquiries.

[0834] Specific operation: The support chat system automatically receives inquiries, and support staff provide specific steps and additional documentation in response to the user's request for information.

[0835] (Example 1)

[0836] 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."

[0837] In modern information retrieval systems, the search queries that users enter to obtain specific information are not always optimized, often resulting in insufficient search results. Furthermore, when search results are insufficient, users have to make further inquiries or enter additional queries, which is a time-consuming and troublesome process.

[0838] 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.

[0839] In this invention, the server includes means for a user to input a search query to obtain specific information, means for receiving the search query, means for transmitting the received search query to a generative artificial intelligence, means for the generative artificial intelligence to optimize the search query, means for transmitting the optimized query to a search engine, means for the search engine to generate search results based on the optimized query, means for displaying the generated search results to the user, means for automatically querying a text-based interactive support system if the search results are insufficient, and means for analyzing the query content and providing appropriate supplementary information. As a result, the user can efficiently use the optimized search query to perform highly accurate information retrieval and quickly obtain additional information even if the search results are insufficient.

[0840] A "user" refers to someone who enters a search query and performs an information retrieval operation in order to obtain specific information.

[0841] A "search query" refers to a sentence or phrase that a user enters into a search engine to request specific information.

[0842] "Generative artificial intelligence" refers to artificial intelligence that analyzes input search queries, understands the context and meaning, and then generates optimized search terms.

[0843] A "search engine" refers to a system that searches a database based on an entered search query and extracts relevant information.

[0844] A "text-based interactive support system" refers to a system that automatically responds to user inquiries and inputs in text format, providing appropriate support information.

[0845] "Reception" means that a means or device takes in data or signals sent from another source.

[0846] "Transmission" means that a means or device sends specific data or signals to another party.

[0847] "Optimization" refers to the process of modifying something to its optimal state or configuration for a particular purpose.

[0848] "Analysis" refers to the process of thoroughly examining input data and information to understand its meaning and structure.

[0849] "Supplementary information" refers to additional information provided to complement the main information that the user is seeking.

[0850] System Overview and Configuration

[0851] This invention provides a system that efficiently delivers information by optimizing search queries using generative artificial intelligence when a user retrieves specific information. The system receives the user's search query, the generative artificial intelligence optimizes it, and then sends the optimized query to a search engine to retrieve information. It also includes a function to automatically query a text-based interactive support system if the search results are insufficient.

[0852] Hardware and software to be used

[0853] User terminal: Used by the user to enter search queries. This includes typical personal computers, smartphones, and tablets.

[0854] Generative artificial intelligence module: Analyzes user queries and generates optimized search terms. Examples of AI models used include high-performance natural language processing models such as GPT-4.

[0855] Search engine: Searches for relevant information based on optimized queries. Common search engine technologies include Elasticsearch and Solr.

[0856] Text-based interactive support systems: These systems automatically respond to user inquiries and provide supplementary information. Examples include chatbot systems and FAQ systems.

[0857] Explanation of the program's processing

[0858] When a user enters a search query, it is received by the terminal. The terminal sends the received query to a generative artificial intelligence module, which analyzes the query, understands its context and meaning, and then optimizes it. Next, the terminal sends the optimized query to a search engine, which searches its database based on this query and generates relevant information. The generated search results are sent back to the user's terminal by the server and displayed for the user to review.

[0859] If the search results are insufficient, the device automatically contacts a text-based interactive support system. This system provides the user with additional assistance information based on the support staff and pre-configured scenarios.

[0860] Examples of specific scenarios and prompts

[0861] For example, consider a case where a user searches for "Machine A instruction manual." The user enters this query into a terminal, which then sends it to a generative artificial intelligence module. The generative AI optimizes the query, for example, transforming it into "Machine A instruction manual latest version." The search engine then searches for relevant information based on the optimized query and returns the results to the user's terminal. If the user reviews the information and makes further inquiries as needed, a text-based interactive support system will handle it.

[0862] Example of a prompt

[0863] "Receive search queries submitted by users and generate optimized search terms. Submit these optimized queries to search engines to retrieve relevant information. Finally, advise on the best way to present the retrieved information to users."

[0864] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0865] Step 1:

[0866] The user enters a search query. The user enters a query such as "Machine A Instruction Manual" into the search bar to retrieve specific information. The entered query is sent to the terminal.

[0867] Step 2:

[0868] The terminal receives the search query. The terminal receives the query entered by the user and stores it in its internal data format. The received query, "Machine A User Manual," is ready to be passed on to the next process.

[0869] Step 3:

[0870] The terminal sends a search query to the generative artificial intelligence. The terminal sends the received query to the generative artificial intelligence module, along with providing contextual information. The "Machine A User Manual" is passed to the generative artificial intelligence as input.

[0871] Step 4:

[0872] Generative artificial intelligence optimizes the search query. Generative artificial intelligence analyzes the query, understands its context and meaning, and performs optimization. In this process, the query is transformed into "Machine A Instruction Manual Latest Version". The input query "Machine A Instruction Manual" is transformed into the optimized output query "Machine A Instruction Manual Latest Version".

[0873] Step 5:

[0874] The terminal sends an optimized query to the search engine. The terminal receives the optimized query and sends it to the search engine. "Machine A Instruction Manual Latest Version" is sent to the search engine as input.

[0875] Step 6:

[0876] The search engine generates search results. The search engine searches its internal database based on the optimized query and collects relevant information. For example, links and related documents for "Machine A Instruction Manual Latest Version" are extracted. The input to the search engine is "Machine A Instruction Manual Latest Version," and the output is a list of related information.

[0877] Step 7:

[0878] The server returns the search results. The server sends the search results obtained from the search engine back to the user's terminal. For example, a link to "Machine A Instruction Manual Latest Version" is sent to the user's terminal.

[0879] Step 8:

[0880] The user terminal displays the search results. The user terminal displays the received search results to the user. The user can obtain the necessary information based on the displayed links and information. The input is the search results from the server, and the output is what is displayed to the user.

[0881] Step 9:

[0882] If the search results are insufficient, the device automatically queries a text-based interactive support system. If the search results do not meet the user's expectations, the device sends a message to the text-based interactive support system, for example, "I would like to know more information about a specific operation."

[0883] Step 10:

[0884] A text-based interactive support system interacts with the user. The system receives inquiries and provides additional information and specific steps. For example, a support staff member might provide the user with additional materials or instructions. Input is the inquiry from the user's terminal, and output is the provision of supplementary information.

[0885] (Application Example 1)

[0886] 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."

[0887] The problem that this invention aims to solve is to facilitate the rapid and accurate acquisition of specific information by users. In particular, it aims to enable users of autonomous vehicles to easily acquire information about the area around their destination and vehicle handling information while driving or stopped, and to quickly acquire additional information if necessary information is missing. Another important issue is to enable voice input, allowing users to safely enter queries even while driving.

[0888] 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.

[0889] In this invention, the server includes means for a user to input a search query to obtain specific information, means for receiving the search query, means for transmitting the received search query to a generative artificial intelligence, means for the generative artificial intelligence to optimize the search query, means for transmitting the optimized query to a search engine, means for the search engine to generate search results based on the optimized query, means for displaying the generated search results to the user, voice input means, means for converting the voice-input query to text, and means for automatically contacting support chat if the search results are insufficient. This enables the user to safely search for information by voice even while driving and efficiently obtain the necessary information through optimized queries. Furthermore, it becomes possible to automatically use the support chat system as needed to quickly obtain additional information.

[0890] A "search query" is a string of characters that a user enters to retrieve specific information.

[0891] "Means of receiving data" refers to the system for importing search queries entered by users.

[0892] "Generative artificial intelligence" is a type of artificial intelligence that analyzes search queries entered by users and optimizes them based on context.

[0893] "Optimization methods" refer to the process by which generative artificial intelligence transforms search queries into more effective search terms.

[0894] A "search engine" is a system that searches a database for relevant information based on optimized queries and generates results.

[0895] "Means of displaying search results" refers to an interface that displays information in a way that allows users to easily verify the information they have obtained.

[0896] A "voice input method" is a mechanism that allows users to input queries using their voice.

[0897] "Means of converting to text" refers to the process of converting voice-input queries into text format.

[0898] "Support chat" is a system that automatically makes inquiries and provides additional information when search results are insufficient.

[0899] "Automated inquiry methods" refer to the process by which users can contact support chat without manual intervention when they need additional information.

[0900] The embodiments for carrying out the present invention are described in detail below. The system for realizing this invention is designed to allow passengers of an autonomous vehicle to easily obtain specific information using voice input. The system consists of four main components: a user terminal, a generative artificial intelligence module, a search engine, and a support chat system.

[0901] First, the user enters a search query through the in-vehicle voice input device. The user terminal receives this via voice input and converts it into text using speech recognition software. Specifically, the SpeechRecognition library is used. If the user enters "What are some good Japanese restaurants nearby?", this voice is converted into text.

[0902] Next, the stringified search query is sent to a generative artificial intelligence module for query optimization. This process uses a GPT-3 model with Hugging Face's Transformers library. The generative AI analyzes the query and, based on context, transforms it into more effective search terms such as "highly-rated Japanese restaurants within 3km of my current location."

[0903] The optimized query is then sent to a search engine, which retrieves relevant information from its database. The search results are returned to the user's device and presented to them via the vehicle's display or audio system. This allows the user to quickly obtain information on highly-rated restaurants near their destination.

[0904] Furthermore, if the retrieved search results are insufficient, an automated inquiry is made to the support chat system. At this stage, the Requests library is used to perform an automated inquiry to obtain additional information. Based on the inquiry received by the support chat, the necessary details are provided. For example, allergen information for a specific restaurant is provided to the user in real time.

[0905] As a concrete example, consider a case where a user voice-inputs "What are some good Japanese restaurants near me?", and this is optimized to show "highly-rated Japanese restaurants within 3km of the user's current location." This optimized query is sent to the search engine, and relevant information is returned. If the information obtained is insufficient, an automated inquiry is sent to the support chat asking, "What is the allergen information for this particular Japanese restaurant?"

[0906] Examples of prompts for a generative AI model include the following:

[0907] A user is searching for nearby restaurants. Please generate the most suitable search terms based on the user's specified criteria. Example: "Japanese food," "delicious," "within 3km."

[0908] Thus, the system of the present invention is designed to enable users to obtain information quickly and safely. The collaboration between generative artificial intelligence and speech recognition technology makes it possible to provide highly accurate and convenient information.

[0909] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0910] Step 1: The user enters the search query by voice.

[0911] Users use a voice input device in the autonomous vehicle to enter search queries by voice to obtain specific information. For example, the input might be "What are some good Japanese restaurants nearby?"

[0912] Step 2: The device receives the voice input and converts it to text.

[0913] The device converts the user's voice input into text using speech recognition software (e.g., the SpeechRecognition library). The input is voice data, and the output is text data such as "What are some good Japanese restaurants nearby?"

[0914] Step 3: The device sends text data to the generative artificial intelligence.

[0915] The terminal sends the converted text data to a generative artificial intelligence module. In this process, the input is the text data entered by the user, and the output is the input data for the generative artificial intelligence.

[0916] Step 4: Generative artificial intelligence optimizes the query

[0917] Generative artificial intelligence analyzes incoming queries and optimizes them into more effective search terms. For example, a GPT-3 model using Hugging Face's Transformers library is used. The input is the original query "What are some good Japanese restaurants near me?", and the output is "Highly-rated Japanese restaurants within 3km of my current location".

[0918] Step 5: The device sends an optimized query to the search engine.

[0919] The device sends an optimized query to the search engine. In this process, the input is a query optimized by generative artificial intelligence, and the output is a query request to the search engine.

[0920] Step 6: The search engine generates relevant information and responds.

[0921] A search engine retrieves relevant information from a database based on an optimized query and generates results. The input is the optimized query, and the output is the search results. For example, it might include "information about highly-rated Japanese restaurants within 3km of my current location."

[0922] Step 7: The device displays the search results to the user.

[0923] The terminal displays search results to the user. This display is done through the vehicle's display or audio system. The input is the search results from the search engine, and the output is the presentation of information to the user.

[0924] Step 8: If the search results are insufficient, the device will automatically contact support chat.

[0925] If the search results do not meet the user's requirements, the device automatically contacts the support chat system. The input consists of the missing search results and additional queries, and the output is the inquiry request to the support chat system.

[0926] Step 9: Support chat will provide additional information.

[0927] The support chat system receives inquiries and provides necessary additional information. The input is the content of the inquiry to the support chat, and the output is additional information for the user. Specifically, this may include "allergen information for a particular restaurant."

[0928] 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.

[0929] overview

[0930] This invention relates to a system that optimizes search queries by combining generative artificial intelligence and an emotion engine when a user retrieves specific information, and provides information tailored to the user's emotional state. The system receives a query entered by the user and analyzes the user's emotions using the emotion engine. The generative artificial intelligence optimizes the query and sends the optimized query to a search engine to retrieve information. If the search results are insufficient, the system includes a function to automatically contact support chat. Furthermore, the emotion engine transmits the user's emotional state to the support chat system to help support staff provide more appropriate responses.

[0931] System Configuration

[0932] The system consists of the following main components:

[0933] 1. User terminal

[0934] It includes an interface where the user enters search queries to retrieve specific information. The user terminal is used to receive queries and send them to the generative artificial intelligence and emotion engine.

[0935] 2. Generative Artificial Intelligence (AI) Module

[0936] This module receives user queries and generates optimized search terms. Specifically, it parses the input query and optimizes it based on the context.

[0937] 3. Emotional Engine

[0938] The emotion engine analyzes the user's emotional state and provides the analysis results to other components. For example, if the user is anxious or dissatisfied, this information is reflected and provided to generative artificial intelligence and the support chat system.

[0939] 4. Search Engine

[0940] A search engine receives an optimized query, searches its database for relevant information, and generates results. These search results are ultimately provided to the user.

[0941] 5. Support Chat System

[0942] If the search results are insufficient, the system automatically receives the user's inquiry, and a support representative provides additional information. Based on the user's sentiment information from the sentiment engine, the support representative takes appropriate action.

[0943] Operation details

[0944] The following describes the specific operation of the system.

[0945] 1. The user enters a search query.

[0946] The user enters a query into the terminal's search bar to obtain specific information. For example, they might enter "Machine A instruction manual" and click the search button.

[0947] 2. The terminal receives the query.

[0948] The user terminal receives the entered query. The query is converted to the appropriate format within the terminal and then prepared to be sent to the sentiment engine.

[0949] 3. The device sends the query to the sentiment engine.

[0950] The device sends the received query and user interaction data (keystrokes, mouse movements, etc.) to the emotion engine. The emotion engine analyzes this data to determine the user's emotional state.

[0951] 4. The emotion engine analyzes the user's emotions.

[0952] The emotion engine receives queries and analyzes the user's emotional state. For example, it determines whether the user is anxious, angry, or calm.

[0953] 5. The terminal sends an optimization query to the generative artificial intelligence.

[0954] Based on the analysis results from the emotion engine, the device sends a request to the generative artificial intelligence to optimize the search query according to the user's emotions. The generative AI receives this request and optimizes the query.

[0955] 6. Generative artificial intelligence optimizes queries.

[0956] Generative artificial intelligence analyzes queries, understands the context and emotional state, and then generates optimized queries. These optimized queries can better meet user requests.

[0957] 7. The device sends optimized queries to the search engine.

[0958] The optimized query is sent to the search engine. The search engine uses this query to search its database and retrieve relevant information.

[0959] 8. The server returns the search results.

[0960] Search results are generated by the search engine and sent back to the user's device. For example, they may include a link to or content of "the latest version of the instruction manual for machine A."

[0961] 9. The device displays search results to the user.

[0962] The user's device displays the received search results, allowing the user to verify the information.

[0963] 10. If search results are insufficient, the system will automatically contact support chat via the sentiment engine.

[0964] If the search results are insufficient, the device will send an automated inquiry via the emotion engine to the support chat API, such as "I am looking for specific instructions on how to operate machine A."

[0965] 11. The support chat receives the inquiry and responds.

[0966] The support chat system receives inquiries, and support staff respond to user questions. They provide additional information and specific steps. Based on emotional information provided by the emotion engine, support staff provide the most appropriate response for the user's situation.

[0967] Specific example

[0968] For example, consider a scenario where a user searches for "Machine A instruction manual." In this case, the user enters a search query, which the device receives and sends to the emotion engine. The emotion engine analyzes the user's emotional state and sends the results to the generative artificial intelligence. The generative AI optimizes the query, and the search engine searches for relevant information. Based on the optimized query, the search engine finds "the latest version of the Machine A instruction manual" and returns it to the user. If the user does not find the information they expect, the device automatically contacts support chat via the emotion engine and is prompted to provide additional information.

[0969] The system of this invention aims to improve work productivity by enabling users to efficiently obtain the information they need. This significantly reduces information retrieval time and alleviates user stress. Furthermore, by incorporating an emotion engine, it can provide optimal responses tailored to the user's emotional state, offering a more fulfilling user experience.

[0970] The following describes the processing flow.

[0971] Step 1:

[0972] The user enters a search query into the CrewNavi search bar.

[0973] Specific action: The user enters "Machine A User Manual" and clicks the search button.

[0974] Step 2:

[0975] The device receives a search query from the user.

[0976] Specific operation: The terminal receives the string "Machine A Instruction Manual" and processes it appropriately according to the data format.

[0977] Step 3:

[0978] The device sends the received search queries and interaction data to the sentiment engine.

[0979] Specific operation: The device sends the search query along with interaction data such as the user's keystrokes and mouse movements to the sentiment engine's API endpoint.

[0980] Step 4:

[0981] The emotion engine analyzes the user's emotions.

[0982] Specific operation: The emotion engine analyzes keystroke speed, mouse movements, input content, etc., to identify the user's emotional state (anxiety, anger, calmness, etc.).

[0983] Step 5:

[0984] The terminal sends queries and sentiment analysis results to the generative artificial intelligence.

[0985] Specific operation: The terminal sends an optimization query request, including the emotion analysis results, to the generative artificial intelligence API.

[0986] Step 6:

[0987] Generative artificial intelligence optimizes queries.

[0988] Specific operation: The generative artificial intelligence analyzes the "Machine A User Manual" and optimizes it, taking into account emotional states, to create something like the "Machine A User Manual Latest Version."

[0989] Step 7:

[0990] The device sends optimized queries to the search engine.

[0991] Specific operation: The terminal sends the optimized query "Machine A Instruction Manual Latest Version," which was returned by the generative artificial intelligence, to the CrewNavi search engine.

[0992] Step 8:

[0993] The server generates search results based on the query.

[0994] Specific operation: The search engine searches the database, extracts information from the "Latest Version of the User Manual for Machine A," and generates results.

[0995] Step 9:

[0996] The server sends the search results back to the terminal.

[0997] Specific action: Send the generated search results to the user's device.

[0998] Step 10:

[0999] The device displays search results to the user.

[1000] Specific operation: The search results received by the terminal are displayed on the user's screen. Specifically, a link and content of the "Latest version of the instruction manual for Machine A" are displayed.

[1001] Step 11:

[1002] If the search results are insufficient, an automated inquiry will be sent to support chat via the emotion engine.

[1003] Specific operation: If the user cannot find specific information, the device will send an automated inquiry, such as "I am looking for specific instructions on how to operate machine A," via the emotion engine to the support chat API.

[1004] Step 12:

[1005] The support chat receives and responds to inquiries.

[1006] Specific operation: The support chat system automatically receives inquiries, and a support representative provides specific steps and additional documentation in response to the user's request. Based on the emotional information provided by the emotion engine, the support representative provides the most appropriate response to the user's situation.

[1007] (Example 2)

[1008] 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."

[1009] Traditional search systems often failed to provide optimal information for user-entered search queries, resulting in decreased user satisfaction. In particular, the lack of appropriate information tailored to the user's emotional state could reduce search efficiency and increase stress. Furthermore, the process of users seeking additional information when search results were insufficient was cumbersome.

[1010] 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.

[1011] In this invention, the server includes means for a user to input a search query to obtain specific information, means for receiving the search query, means for transmitting the received search query to an emotion analysis module, means for the emotion analysis module to analyze the user's emotional state, means for transmitting the search query to a generative artificial intelligence based on the emotion analysis results, means for the generative artificial intelligence to optimize the search query, means for transmitting the optimized query to a search engine, means for the search engine to generate search results based on the optimized query, means for displaying the generated search results to the user, and means for automatically querying a support system via the emotion analysis module if the search results are insufficient. This enables the provision of optimal information according to the user's emotional state, improves search efficiency, and reduces user stress. Furthermore, if the search results are insufficient, a query is automatically made to the support system, allowing the user to quickly obtain additional information.

[1012] "User" refers to a person who uses this system to obtain specific information.

[1013] A "search query" is a combination of strings or words that a user enters to specify the information they want to retrieve.

[1014] An "interface" is a means of communication between the user and the system that allows the user to enter a search query and display the results.

[1015] An "emotion analysis module" or "emotion engine" is a software component that analyzes a user's emotional state, determining emotions based on user interaction data.

[1016] "Generative artificial intelligence" refers to an artificial intelligence module that generates optimized search queries based on received search queries and sentiment analysis results.

[1017] A "search engine" is a system used to search for relevant information from web pages and databases.

[1018] "Search results" are a list of information generated by a search engine that corresponds to a user's search query.

[1019] A "support system" or "support chat" is an automated inquiry and response system designed to provide users with additional information they may need.

[1020] "Emotional analysis results" refer to the results of an analysis of the user's emotional state obtained by the emotional analysis module based on the user's interaction data.

[1021] An "optimized query" is the most appropriate combination of search terms generated by a generative artificial intelligence system based on the user's search query and sentiment analysis results.

[1022] "Interaction data" refers to data generated when a user interacts with a system (e.g., keystrokes, mouse movements).

[1023] These definitions clarify each component of the system relating to the present invention and its function.

[1024] Modes for carrying out the invention

[1025] This invention relates to a system that optimizes search queries by combining generative artificial intelligence and an emotion analysis module when a user retrieves specific information, and provides information tailored to the user's emotional state. This system mainly consists of the following key components.

[1026] System Configuration

[1027] 1. User terminal

[1028] It includes an interface where the user enters search queries to retrieve specific information. The user terminal is used to receive queries and send them to generative artificial intelligence and sentiment analysis modules.

[1029] 2. Generative Artificial Intelligence (AI) Module

[1030] This module receives user queries and generates optimized search terms. Specifically, it analyzes the input query and optimizes it based on context and sentiment.

[1031] 3. Emotion Analysis Module (Emotion Engine)

[1032] The emotion analysis module analyzes the user's emotional state and provides the analysis results to other components. For example, if the user is anxious or dissatisfied, this information is reflected in the generative artificial intelligence and support chat system.

[1033] 4. Search Engine

[1034] A search engine receives an optimized query, searches its database for relevant information, and generates results. These search results are ultimately provided to the user.

[1035] 5. Support Chat System

[1036] If the search results are insufficient, the system automatically receives the user's inquiry, and a support representative provides additional information. Based on the user's sentiment information from the sentiment engine, the support representative takes appropriate action.

[1037] How the system works

[1038] Program Processing Overview

[1039] The system first receives the search query entered by the user. The received query is sent to an emotion analysis module, which analyzes the user's emotional state. Then, based on the analysis results, the query is optimized by generative artificial intelligence. The optimized query is sent to a search engine, and relevant search results are generated. The generated search results are displayed to the user, but if the search results are insufficient, an inquiry is automatically sent to the support chat system. Based on the emotional information provided by the emotion analysis module, a support representative provides the most appropriate response to the user.

[1040] Specific example

[1041] For example, consider a scenario where a user searches for "Machine A instruction manual." In this case, the user enters a search query, which the terminal receives and sends to an emotion analysis module. The emotion analysis module analyzes the user's emotional state and sends the results to a generative artificial intelligence (AI). The AI ​​optimizes the query, and the search engine searches for relevant information. Based on the optimized query, the search engine finds "the latest version of the Machine A instruction manual" and returns it to the user. If the user does not find the information they expect, the terminal automatically contacts a support chat system via the emotion analysis module to provide additional information.

[1042] Examples of prompt statements

[1043] "The user searched for 'Machine A User Manual,' but the emotion engine detected an anxious emotion. Please generate the most suitable search query for the user and automatically contact support chat if necessary."

[1044] This invention is designed to allow users to efficiently obtain the information they need, aiming to improve work productivity. By introducing an emotion analysis module, it becomes possible to provide optimal responses tailored to the user's emotional state, thereby offering a more enriching user experience.

[1045] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1046] The program's processing flow is divided into processing steps.

[1047] Step 1: The user enters a search query.

[1048] To obtain specific information, the user enters a query into the terminal's search bar. An example of such a query is "Machine A Instruction Manual". The input data here is the string "Machine A Instruction Manual" entered by the user.

[1049] Step 2: The terminal receives the query.

[1050] The terminal receives the query entered by the user. The received query ("Machine A User Manual") is converted into an appropriate data format and prepared to be sent to the sentiment analysis module. The input data here is the user's query, which is the output of step 1. The output data is the query data ready for sentiment analysis.

[1051] Step 3: The device sends query and interaction data to the sentiment analysis module.

[1052] The terminal sends the received query along with user interaction data (e.g., keyboard input speed, mouse movements, etc.) to the sentiment analysis module. The input data consists of the query string "Machine A Instruction Manual" and the interaction data. The output data is the data sent to the sentiment analysis module.

[1053] Step 4: The emotion analysis module analyzes the user's emotional state.

[1054] The emotion analysis module determines the user's emotional state (e.g., anxious, angry, calm) based on the received data. The input data consists of the query and interaction data sent in step 3. The output data is the analyzed user's emotional state.

[1055] Step 5: The device sends queries and sentiment analysis results to the generative artificial intelligence.

[1056] The terminal sends a query along with the emotion analysis results (e.g., state of anxiety) to the generative artificial intelligence. The input data consists of the query and the emotion analysis results. The output data is the request for optimization query generation that was sent to the generative artificial intelligence.

[1057] Step 6: Generative AI optimizes the query.

[1058] Generative artificial intelligence receives a query and sentiment analysis results, and generates an optimized query considering the context and emotional state (e.g., "Download the latest version of the instruction manual for machine A"). The input data is the original query and sentiment analysis results. The output data is the optimized query.

[1059] Step 7: The device sends the optimized query to the search engine.

[1060] The device sends an optimized query to the search engine. The input data is the optimized query. The output data is the query sent to the search engine.

[1061] Step 8: The server returns the search results.

[1062] A server with a search engine receives an optimized query, searches its database, and retrieves relevant information (e.g., "Latest version of the instruction manual for machine A"). The retrieved information is sent back to the terminal as search results. The input data is the optimized query, and the output data is the search results.

[1063] Step 9: The device displays the search results to the user.

[1064] The terminal displays search results received from the server to the user. For example, a link or summary of "the latest version of the instruction manual for machine A" is displayed on the user's screen. The input data is the search results, and the output data is the information displayed to the user.

[1065] Step 10: If the search results are insufficient, send an automated inquiry to the support chat.

[1066] If the user cannot obtain the information they expect, the device will automatically contact the support chat system based on the sentiment analysis results (e.g., "I am looking for specific instructions on how to operate machine A"). The input data consists of insufficient search results and sentiment analysis results, while the output data is the content of the inquiry sent to the support chat.

[1067] Step 11: Support chat receives and responds to the inquiry.

[1068] The support chat system receives inquiries, and support staff respond to user questions. Based on sentiment analysis results, responses are tailored to the user's state. The input data is the content of the inquiry sent to the support chat, and the output data is additional information provided by the support staff.

[1069] This allows users to efficiently obtain the information they need, and to quickly acquire additional information even if the search results are insufficient.

[1070] (Application Example 2)

[1071] 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."

[1072] Current information retrieval systems often fail to provide search results quickly and accurately, as they do not take into account the user's emotional state. This is particularly problematic in the security field, where providing appropriate information in situations where security personnel are under pressure and anxiety is crucial, but current systems do not adequately address this. Furthermore, the lack of automated systems for additional actions when search results are insufficient places a significant burden on users.

[1073] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting a search query for a user to obtain specific information, means for receiving the search query, means for transmitting the received search query to a generative artificial intelligence, means for the generative artificial intelligence to optimize the search query, means for transmitting the optimized query to a search engine, means for the search engine to generate search results based on the optimized query, means for displaying the generated search results to the user, means for automatically contacting a support chat if the search results are insufficient, means for capturing a frame with an image capture device and analyzing the user's emotional state using an emotion recognition engine, and means for generating a warning message based on the emotional state. This not only enables the provision of optimal information according to the user's emotional state, but also reduces the burden on the user by automatically taking additional action if the search results are insufficient.

[1074] A "user" is an individual or organization that enters a search query to obtain information.

[1075] A "search query" is a set of sentences or words that a user enters in order to obtain specific information.

[1076] "Generative artificial intelligence" is an artificial intelligence technology that analyzes input search queries and optimizes them based on context.

[1077] "Optimization" is the process of analyzing an entered search query and converting it into search terms that best meet the user's needs.

[1078] A "search engine" is a system that searches a database based on optimized queries and generates relevant information.

[1079] "Search results" are a collection of information generated by a search engine that a user is looking for.

[1080] A "support chat" is a system that automatically responds to user inquiries and provides additional information when search results are insufficient.

[1081] An "emotion recognition engine" is a technology used to analyze a user's emotional state, and it has the function of determining a user's emotions by analyzing their voice and facial expressions.

[1082] An "image capture device" is a device used to capture images or videos in real time.

[1083] A "warning message" is information or instructions designed to draw attention to a user's emotional state.

[1084] To implement the invention, the following hardware and software components are required. First, the user terminal has an interface for the user to input search queries to obtain specific information. This terminal is used for receiving queries and transmitting them to a generative artificial intelligence and emotion engine.

[1085] When a user enters a search query, the device receives the query, converts it to an appropriate format, and sends it to a generative artificial intelligence (AI). The AI ​​analyzes this query and optimizes it to best meet the user's needs. The optimized query is then sent to a search engine. The search engine searches its database for relevant information, generates search results, and returns them to the user.

[1086] If the search results are insufficient, the system will automatically contact the support chat system. This support chat system will answer the user's additional questions and provide more specific information.

[1087] Furthermore, the system includes an emotion recognition engine that analyzes the user's emotional state in real time. This engine captures frames using an image capture device and determines the user's emotional state from their facial expressions and voice. Based on this analysis, the emotion recognition engine generates a warning message and provides it to the user.

[1088] As a concrete example, let's consider a scenario where a user is performing monitoring duties. When the user searches for "emergency reporting procedures" in an emergency, the system receives the search query, and generative artificial intelligence optimizes it before sending it to the search engine. For example, it might be optimized as "on-site emergency reporting procedures." If the search results are not appropriate (for example, if no specific reporting procedures are found), the system automatically contacts the support chat system and provides additional specific response procedures.

[1089] Furthermore, the emotion recognition engine analyzes the user's emotional state and, if it detects that the user is anxious, generates an appropriate warning message. For example, it might display, "Please calm down and review the following steps." This allows the user to continue acting calmly.

[1090] The hardware and software used include:

[1091] Hardware: Cameras (surveillance cameras, webcams), user devices (PCs, smartphones, etc.)

[1092] Software: OpenCV (for camera frame capture), emotion recognition engine (e.g., Facial Emotion Recognition module), generative artificial intelligence (GPT-3 API, etc.)

[1093] The example prompt is as follows:

[1094] "The security team is in a state of panic. Please generate the most appropriate warning message."

[1095] The introduction of this system allows users to efficiently obtain necessary information and reduce stress and anxiety through emotion recognition. Furthermore, if search results are insufficient, additional actions are taken immediately, ensuring smooth task completion.

[1096] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1097] Step 1:

[1098] The user enters a search query to obtain specific information. The user enters the query in the search bar of their device and sends the entered query. For example, they might enter "emergency call procedure".

[1099] Step 2:

[1100] The terminal receives the search query. The terminal receives the query entered by the user and converts it to an appropriate format. The input data is a text-based query, and the converted data is also in text format.

[1101] Step 3:

[1102] The terminal sends the received search query to the generative artificial intelligence. The terminal then sends the pre-processed query to the generative AI module and waits for the result to be received. The input data is a search query in text format, and an optimized query is output.

[1103] Step 4:

[1104] Generative artificial intelligence optimizes search queries. The generative AI module analyzes the received query and transforms it into the most appropriate form based on the context. For example, it might specify "emergency call procedure" as "on-site emergency call procedure." The input data is the search query, and the output data is the optimized query.

[1105] Step 5:

[1106] The device sends an optimized query to the search engine. The input data is an optimized query, and the output data is a query in the form of a request to the search engine.

[1107] Step 6:

[1108] A search engine generates search results based on an optimized query. The search engine searches its database based on the received query and retrieves relevant information. The input data is the optimized query, and the output data is the search results.

[1109] Step 7:

[1110] The server displays the generated search results to the user. The server sends the search results obtained from the search engine back to the user's terminal. The user's terminal displays the received search results to the user. The input data is the search results, and the output data is the information displayed on the screen.

[1111] Step 8:

[1112] If search results are insufficient, the system automatically initiates a support chat inquiry. If the user cannot obtain the necessary information, the device automatically sends an inquiry to the support chat. The input data is a query for the missing information, and the output data is the request to the support chat.

[1113] Step 9:

[1114] The support chat receives the inquiry and provides additional information. The support chat system receives the user's inquiry, and a support representative provides additional information. The input data is the inquiry, and the output data is the additional information provided.

[1115] Step 10:

[1116] The system captures frames using an image capture device and analyzes the user's emotional state using an emotion recognition engine. It performs facial recognition and voice analysis to determine the emotional state in real time. Input data consists of camera frames and audio data, while output data is the result of the emotional state analysis.

[1117] Step 11:

[1118] The emotion recognition engine generates warning messages based on the user's emotional state. The engine presents an appropriate warning message based on the analysis results. For example, if the user is feeling anxious, it might generate a message such as, "Please calm down and review the following steps." The input data is the analysis result of the emotional state, and the output data is the warning message.

[1119] 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.

[1120] 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.

[1121] 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.

[1122] [Fourth Embodiment]

[1123] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1124] 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.

[1125] 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).

[1126] 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.

[1127] 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.

[1128] 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).

[1129] 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.

[1130] 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.

[1131] 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.

[1132] 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.

[1133] 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.

[1134] 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.

[1135] 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".

[1136] overview

[1137] This invention relates to a system that efficiently provides information by optimizing search queries using generative artificial intelligence when a user is retrieving specific information. The system receives a query entered by the user and transmits it to the generative artificial intelligence. The generative artificial intelligence optimizes the query and sends the optimized query to a search engine to retrieve information. The system also includes a function to automatically contact support chat if the search results are insufficient. This allows users to obtain information quickly and accurately.

[1138] System Configuration

[1139] The system consists of the following main components:

[1140] 1. User terminal

[1141] It includes an interface where the user enters search queries to retrieve specific information. The user terminal is used to receive queries and send them to the generative artificial intelligence.

[1142] 2. Generative Artificial Intelligence (AI) Module

[1143] This module receives user queries and generates optimized search terms. Specifically, it parses the input query and optimizes it based on the context.

[1144] 3. Search Engine

[1145] A search engine receives an optimized query, searches its database for relevant information, and generates results. These search results are ultimately provided to the user.

[1146] 4. Support Chat System

[1147] If the search results are insufficient, this system will automatically receive the user's inquiry, and a support representative will provide additional information.

[1148] Operation details

[1149] The following describes the specific operation of the system.

[1150] 1. The user enters a search query.

[1151] The user enters a query into the terminal's search bar to obtain specific information. For example, they might enter "Machine A instruction manual".

[1152] 2. The terminal receives the query.

[1153] The user terminal receives the entered query. The query is converted to the appropriate format within the terminal and prepared to be sent to the generative artificial intelligence module.

[1154] 3. The terminal sends a query to the generative artificial intelligence.

[1155] The terminal sends the received query to a generative artificial intelligence module. The generative AI module analyzes the query and optimizes it into a more effective search term. For example, it might be transformed into something like "Machine A instruction manual latest version".

[1156] 4. Generative artificial intelligence optimizes queries.

[1157] Generative artificial intelligence analyzes queries, understands the context and meaning, and then generates optimized queries. These optimized queries can better meet user requests.

[1158] 5. The device sends optimized queries to the search engine.

[1159] The optimized query is sent to the search engine. The search engine uses this query to search its database and retrieve relevant information.

[1160] 6. The server returns the search results.

[1161] Search results are generated by the search engine and sent back to the user's device. For example, they may include a link to or content of "the latest version of the instruction manual for machine A."

[1162] 7. The device displays the search results.

[1163] The user's device displays the received search results, allowing the user to verify the information.

[1164] 8. If the search results are insufficient, an automated inquiry will be sent to support chat.

[1165] If the search results are insufficient, the device will automatically contact the support chat system. For example, it might ask, "I'm looking for more details on how to perform a specific operation."

[1166] 9. Support chat will assist you.

[1167] The support chat system receives inquiries, and support staff respond to user questions, providing additional information and specific instructions.

[1168] Specific example

[1169] For example, consider a scenario where a user searches for "Machine A User Manual" on CrewNavi. In this case, the user enters a search query, which the terminal receives and sends to a generative artificial intelligence (AI). The AI ​​optimizes the query, and the search engine searches for relevant information. Based on the optimized query, the search engine finds "Latest Version User Manual for Machine A" and returns it to the user. If the user does not find the information they expect, the terminal automatically contacts support chat and is prompted to provide additional information.

[1170] The system of this invention aims to improve work productivity by enabling users to efficiently obtain the necessary information. This significantly reduces the time spent searching for information and alleviates user stress.

[1171] The following describes the processing flow.

[1172] Step 1:

[1173] The user enters a search query into the CrewNavi search bar.

[1174] Specific action: The user enters "Machine A User Manual" and clicks the search button.

[1175] Step 2:

[1176] The device receives a search query from the user.

[1177] Specific operation: The terminal receives the string "Machine A Instruction Manual" and processes it appropriately according to the data format.

[1178] Step 3:

[1179] The terminal sends the received search query to the generative artificial intelligence.

[1180] Specific operation: The terminal sends a request containing the query "Machine A User Manual" to the generative artificial intelligence API endpoint.

[1181] Step 4:

[1182] Generative artificial intelligence optimizes search queries.

[1183] Specific operation: The generative artificial intelligence analyzes "Machine A Instruction Manual," understands its context and meaning, and generates a more effective search term, "Machine A Instruction Manual Latest Version."

[1184] Step 5:

[1185] The device sends optimized queries to CrewNavi's search engine.

[1186] Specific operation: The terminal sends the optimized query "Machine A Instruction Manual Latest Version," which was returned by the generative artificial intelligence, to the CrewNavi search engine.

[1187] Step 6:

[1188] The server generates search results based on the query.

[1189] Specific operation: The search engine searches the database, extracts information from the "Latest Version of the User Manual for Machine A," and generates results.

[1190] Step 7:

[1191] The server sends the search results back to the terminal.

[1192] Specific action: Send the generated search results to the user's device.

[1193] Step 8:

[1194] The device displays search results to the user.

[1195] Specific operation: The search results received by the terminal are displayed on the user's screen. Specifically, a link and content of the "Latest version of the instruction manual for Machine A" are displayed.

[1196] Step 9:

[1197] If the search results are insufficient, the device will automatically contact support chat.

[1198] Specific operation: If the user cannot find specific information, the device will send an automated inquiry, such as "I am looking for specific instructions on how to operate machine A," to the support chat API.

[1199] Step 10:

[1200] The support chat receives and responds to inquiries.

[1201] Specific operation: The support chat system automatically receives inquiries, and support staff provide specific steps and additional documentation in response to the user's request for information.

[1202] (Example 1)

[1203] 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".

[1204] In modern information retrieval systems, the search queries that users enter to obtain specific information are not always optimized, often resulting in insufficient search results. Furthermore, when search results are insufficient, users have to make further inquiries or enter additional queries, which is a time-consuming and troublesome process.

[1205] 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.

[1206] In this invention, the server includes means for a user to input a search query to obtain specific information, means for receiving the search query, means for transmitting the received search query to a generative artificial intelligence, means for the generative artificial intelligence to optimize the search query, means for transmitting the optimized query to a search engine, means for the search engine to generate search results based on the optimized query, means for displaying the generated search results to the user, means for automatically querying a text-based interactive support system if the search results are insufficient, and means for analyzing the query content and providing appropriate supplementary information. As a result, the user can efficiently use the optimized search query to perform highly accurate information retrieval and quickly obtain additional information even if the search results are insufficient.

[1207] A "user" refers to someone who enters a search query and performs an information retrieval operation in order to obtain specific information.

[1208] A "search query" refers to a sentence or phrase that a user enters into a search engine to request specific information.

[1209] "Generative artificial intelligence" refers to artificial intelligence that analyzes input search queries, understands the context and meaning, and then generates optimized search terms.

[1210] A "search engine" refers to a system that searches a database based on an entered search query and extracts relevant information.

[1211] A "text-based interactive support system" refers to a system that automatically responds to user inquiries and inputs in text format, providing appropriate support information.

[1212] "Reception" means that a means or device takes in data or signals sent from another source.

[1213] "Transmission" means that a means or device sends specific data or signals to another party.

[1214] "Optimization" refers to the process of modifying something to its optimal state or configuration for a particular purpose.

[1215] "Analysis" refers to the process of thoroughly examining input data and information to understand its meaning and structure.

[1216] "Supplementary information" refers to additional information provided to complement the main information that the user is seeking.

[1217] System Overview and Configuration

[1218] This invention provides a system that efficiently delivers information by optimizing search queries using generative artificial intelligence when a user retrieves specific information. The system receives the user's search query, the generative artificial intelligence optimizes it, and then sends the optimized query to a search engine to retrieve information. It also includes a function to automatically query a text-based interactive support system if the search results are insufficient.

[1219] Hardware and software to be used

[1220] User terminal: Used by the user to enter search queries. This includes typical personal computers, smartphones, and tablets.

[1221] Generative artificial intelligence module: Analyzes user queries and generates optimized search terms. Examples of AI models used include high-performance natural language processing models such as GPT-4.

[1222] Search engine: Searches for relevant information based on optimized queries. Common search engine technologies include Elasticsearch and Solr.

[1223] Text-based interactive support systems: These systems automatically respond to user inquiries and provide supplementary information. Examples include chatbot systems and FAQ systems.

[1224] Explanation of the program's processing

[1225] When a user enters a search query, it is received by the terminal. The terminal sends the received query to a generative artificial intelligence module, which analyzes the query, understands its context and meaning, and then optimizes it. Next, the terminal sends the optimized query to a search engine, which searches its database based on this query and generates relevant information. The generated search results are sent back to the user's terminal by the server and displayed for the user to review.

[1226] If the search results are insufficient, the device automatically contacts a text-based interactive support system. This system provides the user with additional assistance information based on the support staff and pre-configured scenarios.

[1227] Examples of specific scenarios and prompts

[1228] For example, consider a case where a user searches for "Machine A instruction manual." The user enters this query into a terminal, which then sends it to a generative artificial intelligence module. The generative AI optimizes the query, for example, transforming it into "Machine A instruction manual latest version." The search engine then searches for relevant information based on the optimized query and returns the results to the user's terminal. If the user reviews the information and makes further inquiries as needed, a text-based interactive support system will handle it.

[1229] Example of a prompt

[1230] "Receive search queries submitted by users and generate optimized search terms. Submit these optimized queries to search engines to retrieve relevant information. Finally, advise on the best way to present the retrieved information to users."

[1231] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1232] Step 1:

[1233] The user enters a search query. The user enters a query such as "Machine A Instruction Manual" into the search bar to retrieve specific information. The entered query is sent to the terminal.

[1234] Step 2:

[1235] The terminal receives the search query. The terminal receives the query entered by the user and stores it in its internal data format. The received query, "Machine A User Manual," is ready to be passed on to the next process.

[1236] Step 3:

[1237] The terminal sends a search query to the generative artificial intelligence. The terminal sends the received query to the generative artificial intelligence module, along with providing contextual information. The "Machine A User Manual" is passed to the generative artificial intelligence as input.

[1238] Step 4:

[1239] Generative artificial intelligence optimizes the search query. Generative artificial intelligence analyzes the query, understands its context and meaning, and performs optimization. In this process, the query is transformed into "Machine A Instruction Manual Latest Version". The input query "Machine A Instruction Manual" is transformed into the optimized output query "Machine A Instruction Manual Latest Version".

[1240] Step 5:

[1241] The terminal sends an optimized query to the search engine. The terminal receives the optimized query and sends it to the search engine. "Machine A Instruction Manual Latest Version" is sent to the search engine as input.

[1242] Step 6:

[1243] The search engine generates search results. The search engine searches its internal database based on the optimized query and collects relevant information. For example, links and related documents for "Machine A Instruction Manual Latest Version" are extracted. The input to the search engine is "Machine A Instruction Manual Latest Version," and the output is a list of related information.

[1244] Step 7:

[1245] The server returns the search results. The server sends the search results obtained from the search engine back to the user's terminal. For example, a link to "Machine A Instruction Manual Latest Version" is sent to the user's terminal.

[1246] Step 8:

[1247] The user terminal displays the search results. The user terminal displays the received search results to the user. The user can obtain the necessary information based on the displayed links and information. The input is the search results from the server, and the output is what is displayed to the user.

[1248] Step 9:

[1249] If the search results are insufficient, the device automatically queries a text-based interactive support system. If the search results do not meet the user's expectations, the device sends a message to the text-based interactive support system, for example, "I would like to know more information about a specific operation."

[1250] Step 10:

[1251] A text-based interactive support system interacts with the user. The system receives inquiries and provides additional information and specific steps. For example, a support staff member might provide the user with additional materials or instructions. Input is the inquiry from the user's terminal, and output is the provision of supplementary information.

[1252] (Application Example 1)

[1253] 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".

[1254] The problem that this invention aims to solve is to facilitate the rapid and accurate acquisition of specific information by users. In particular, it aims to enable users of autonomous vehicles to easily acquire information about the area around their destination and vehicle handling information while driving or stopped, and to quickly acquire additional information if necessary information is missing. Another important issue is to enable voice input, allowing users to safely enter queries even while driving.

[1255] 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.

[1256] In this invention, the server includes means for a user to input a search query to obtain specific information, means for receiving the search query, means for transmitting the received search query to a generative artificial intelligence, means for the generative artificial intelligence to optimize the search query, means for transmitting the optimized query to a search engine, means for the search engine to generate search results based on the optimized query, means for displaying the generated search results to the user, voice input means, means for converting the voice-input query to text, and means for automatically contacting support chat if the search results are insufficient. This enables the user to safely search for information by voice even while driving and efficiently obtain the necessary information through optimized queries. Furthermore, it becomes possible to automatically use the support chat system as needed to quickly obtain additional information.

[1257] A "search query" is a string of characters that a user enters to retrieve specific information.

[1258] "Means of receiving data" refers to the system for importing search queries entered by users.

[1259] "Generative artificial intelligence" is a type of artificial intelligence that analyzes search queries entered by users and optimizes them based on context.

[1260] "Optimization methods" refer to the process by which generative artificial intelligence transforms search queries into more effective search terms.

[1261] A "search engine" is a system that searches a database for relevant information based on optimized queries and generates results.

[1262] "Means of displaying search results" refers to an interface that displays information in a way that allows users to easily verify the information they have obtained.

[1263] A "voice input method" is a mechanism that allows users to input queries using their voice.

[1264] "Means of converting to text" refers to the process of converting voice-input queries into text format.

[1265] "Support chat" is a system that automatically makes inquiries and provides additional information when search results are insufficient.

[1266] "Automated inquiry methods" refer to the process by which users can contact support chat without manual intervention when they need additional information.

[1267] The embodiments for carrying out the present invention are described in detail below. The system for realizing this invention is designed to allow passengers of an autonomous vehicle to easily obtain specific information using voice input. The system consists of four main components: a user terminal, a generative artificial intelligence module, a search engine, and a support chat system.

[1268] First, the user enters a search query through the in-vehicle voice input device. The user terminal receives this via voice input and converts it into text using speech recognition software. Specifically, the SpeechRecognition library is used. If the user enters "What are some good Japanese restaurants nearby?", this voice is converted into text.

[1269] Next, the stringified search query is sent to a generative artificial intelligence module for query optimization. This process uses a GPT-3 model with Hugging Face's Transformers library. The generative AI analyzes the query and, based on context, transforms it into more effective search terms such as "highly-rated Japanese restaurants within 3km of my current location."

[1270] The optimized query is then sent to a search engine, which retrieves relevant information from its database. The search results are returned to the user's device and presented to them via the vehicle's display or audio system. This allows the user to quickly obtain information on highly-rated restaurants near their destination.

[1271] Furthermore, if the retrieved search results are insufficient, an automated inquiry is made to the support chat system. At this stage, the Requests library is used to perform an automated inquiry to obtain additional information. Based on the inquiry received by the support chat, the necessary details are provided. For example, allergen information for a specific restaurant is provided to the user in real time.

[1272] As a concrete example, consider a case where a user voice-inputs "What are some good Japanese restaurants near me?", and this is optimized to show "highly-rated Japanese restaurants within 3km of the user's current location." This optimized query is sent to the search engine, and relevant information is returned. If the information obtained is insufficient, an automated inquiry is sent to the support chat asking, "What is the allergen information for this particular Japanese restaurant?"

[1273] Examples of prompts for a generative AI model include the following:

[1274] A user is searching for nearby restaurants. Please generate the most suitable search terms based on the user's specified criteria. Example: "Japanese food," "delicious," "within 3km."

[1275] Thus, the system of the present invention is designed to enable users to obtain information quickly and safely. The collaboration between generative artificial intelligence and speech recognition technology makes it possible to provide highly accurate and convenient information.

[1276] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1277] Step 1: The user enters the search query by voice.

[1278] Users use a voice input device in the autonomous vehicle to enter search queries by voice to obtain specific information. For example, the input might be "What are some good Japanese restaurants nearby?"

[1279] Step 2: The device receives the voice input and converts it to text.

[1280] The device converts the user's voice input into text using speech recognition software (e.g., the SpeechRecognition library). The input is voice data, and the output is text data such as "What are some good Japanese restaurants nearby?"

[1281] Step 3: The device sends text data to the generative artificial intelligence.

[1282] The terminal sends the converted text data to a generative artificial intelligence module. In this process, the input is the text data entered by the user, and the output is the input data for the generative artificial intelligence.

[1283] Step 4: Generative artificial intelligence optimizes the query

[1284] Generative artificial intelligence analyzes incoming queries and optimizes them into more effective search terms. For example, a GPT-3 model using Hugging Face's Transformers library is used. The input is the original query "What are some good Japanese restaurants near me?", and the output is "Highly-rated Japanese restaurants within 3km of my current location".

[1285] Step 5: The device sends an optimized query to the search engine.

[1286] The device sends an optimized query to the search engine. In this process, the input is a query optimized by generative artificial intelligence, and the output is a query request to the search engine.

[1287] Step 6: The search engine generates relevant information and responds.

[1288] A search engine retrieves relevant information from a database based on an optimized query and generates results. The input is the optimized query, and the output is the search results. For example, it might include "information about highly-rated Japanese restaurants within 3km of my current location."

[1289] Step 7: The device displays the search results to the user.

[1290] The terminal displays search results to the user. This display is done through the vehicle's display or audio system. The input is the search results from the search engine, and the output is the presentation of information to the user.

[1291] Step 8: If the search results are insufficient, the device will automatically contact support chat.

[1292] If the search results do not meet the user's requirements, the device automatically contacts the support chat system. The input consists of the missing search results and additional queries, and the output is the inquiry request to the support chat system.

[1293] Step 9: Support chat will provide additional information.

[1294] The support chat system receives inquiries and provides necessary additional information. The input is the content of the inquiry to the support chat, and the output is additional information for the user. Specifically, this may include "allergen information for a particular restaurant."

[1295] 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.

[1296] overview

[1297] This invention relates to a system that optimizes search queries by combining generative artificial intelligence and an emotion engine when a user retrieves specific information, and provides information tailored to the user's emotional state. The system receives a query entered by the user and analyzes the user's emotions using the emotion engine. The generative artificial intelligence optimizes the query and sends the optimized query to a search engine to retrieve information. If the search results are insufficient, the system includes a function to automatically contact support chat. Furthermore, the emotion engine transmits the user's emotional state to the support chat system to help support staff provide more appropriate responses.

[1298] System Configuration

[1299] The system consists of the following main components:

[1300] 1. User terminal

[1301] It includes an interface where the user enters search queries to retrieve specific information. The user terminal is used to receive queries and send them to the generative artificial intelligence and emotion engine.

[1302] 2. Generative Artificial Intelligence (AI) Module

[1303] This module receives user queries and generates optimized search terms. Specifically, it parses the input query and optimizes it based on the context.

[1304] 3. Emotional Engine

[1305] The emotion engine analyzes the user's emotional state and provides the analysis results to other components. For example, if the user is anxious or dissatisfied, this information is reflected and provided to generative artificial intelligence and the support chat system.

[1306] 4. Search Engine

[1307] A search engine receives an optimized query, searches its database for relevant information, and generates results. These search results are ultimately provided to the user.

[1308] 5. Support Chat System

[1309] If the search results are insufficient, the system automatically receives the user's inquiry, and a support representative provides additional information. Based on the user's sentiment information from the sentiment engine, the support representative takes appropriate action.

[1310] Operation details

[1311] The following describes the specific operation of the system.

[1312] 1. The user enters a search query.

[1313] The user enters a query into the terminal's search bar to obtain specific information. For example, they might enter "Machine A instruction manual" and click the search button.

[1314] 2. The terminal receives the query.

[1315] The user terminal receives the entered query. The query is converted to the appropriate format within the terminal and then prepared to be sent to the sentiment engine.

[1316] 3. The device sends the query to the sentiment engine.

[1317] The device sends the received query and user interaction data (keystrokes, mouse movements, etc.) to the emotion engine. The emotion engine analyzes this data to determine the user's emotional state.

[1318] 4. The emotion engine analyzes the user's emotions.

[1319] The emotion engine receives queries and analyzes the user's emotional state. For example, it determines whether the user is anxious, angry, or calm.

[1320] 5. The terminal sends an optimization query to the generative artificial intelligence.

[1321] Based on the analysis results from the emotion engine, the device sends a request to the generative artificial intelligence to optimize the search query according to the user's emotions. The generative AI receives this request and optimizes the query.

[1322] 6. Generative artificial intelligence optimizes queries.

[1323] Generative artificial intelligence analyzes queries, understands the context and emotional state, and then generates optimized queries. These optimized queries can better meet user requests.

[1324] 7. The device sends optimized queries to the search engine.

[1325] The optimized query is sent to the search engine. The search engine uses this query to search its database and retrieve relevant information.

[1326] 8. The server returns the search results.

[1327] Search results are generated by the search engine and sent back to the user's device. For example, they may include a link to or content of "the latest version of the instruction manual for machine A."

[1328] 9. The device displays search results to the user.

[1329] The user's device displays the received search results, allowing the user to verify the information.

[1330] 10. If search results are insufficient, the system will automatically contact support chat via the sentiment engine.

[1331] If the search results are insufficient, the device will send an automated inquiry via the emotion engine to the support chat API, such as "I am looking for specific instructions on how to operate machine A."

[1332] 11. The support chat receives the inquiry and responds.

[1333] The support chat system receives inquiries, and support staff respond to user questions. They provide additional information and specific steps. Based on emotional information provided by the emotion engine, support staff provide the most appropriate response for the user's situation.

[1334] Specific example

[1335] For example, consider a scenario where a user searches for "Machine A instruction manual." In this case, the user enters a search query, which the device receives and sends to the emotion engine. The emotion engine analyzes the user's emotional state and sends the results to the generative artificial intelligence. The generative AI optimizes the query, and the search engine searches for relevant information. Based on the optimized query, the search engine finds "the latest version of the Machine A instruction manual" and returns it to the user. If the user does not find the information they expect, the device automatically contacts support chat via the emotion engine and is prompted to provide additional information.

[1336] The system of this invention aims to improve work productivity by enabling users to efficiently obtain the information they need. This significantly reduces information retrieval time and alleviates user stress. Furthermore, by incorporating an emotion engine, it can provide optimal responses tailored to the user's emotional state, offering a more fulfilling user experience.

[1337] The following describes the processing flow.

[1338] Step 1:

[1339] The user enters a search query into the CrewNavi search bar.

[1340] Specific action: The user enters "Machine A User Manual" and clicks the search button.

[1341] Step 2:

[1342] The device receives a search query from the user.

[1343] Specific operation: The terminal receives the string "Machine A Instruction Manual" and processes it appropriately according to the data format.

[1344] Step 3:

[1345] The device sends the received search queries and interaction data to the sentiment engine.

[1346] Specific operation: The device sends the search query along with interaction data such as the user's keystrokes and mouse movements to the sentiment engine's API endpoint.

[1347] Step 4:

[1348] The emotion engine analyzes the user's emotions.

[1349] Specific operation: The emotion engine analyzes keystroke speed, mouse movements, input content, etc., to identify the user's emotional state (anxiety, anger, calmness, etc.).

[1350] Step 5:

[1351] The terminal sends queries and sentiment analysis results to the generative artificial intelligence.

[1352] Specific operation: The terminal sends an optimization query request, including the emotion analysis results, to the generative artificial intelligence API.

[1353] Step 6:

[1354] Generative artificial intelligence optimizes queries.

[1355] Specific operation: The generative artificial intelligence analyzes the "Machine A User Manual" and optimizes it, taking into account emotional states, to create something like the "Machine A User Manual Latest Version."

[1356] Step 7:

[1357] The device sends optimized queries to the search engine.

[1358] Specific operation: The terminal sends the optimized query "Machine A Instruction Manual Latest Version," which was returned by the generative artificial intelligence, to the CrewNavi search engine.

[1359] Step 8:

[1360] The server generates search results based on the query.

[1361] Specific operation: The search engine searches the database, extracts information from the "Latest Version of the User Manual for Machine A," and generates results.

[1362] Step 9:

[1363] The server sends the search results back to the terminal.

[1364] Specific action: Send the generated search results to the user's device.

[1365] Step 10:

[1366] The device displays search results to the user.

[1367] Specific operation: The search results received by the terminal are displayed on the user's screen. Specifically, a link and content of the "Latest version of the instruction manual for Machine A" are displayed.

[1368] Step 11:

[1369] If the search results are insufficient, an automated inquiry will be sent to support chat via the emotion engine.

[1370] Specific operation: If the user cannot find specific information, the device will send an automated inquiry, such as "I am looking for specific instructions on how to operate machine A," via the emotion engine to the support chat API.

[1371] Step 12:

[1372] The support chat receives and responds to inquiries.

[1373] Specific operation: The support chat system automatically receives inquiries, and a support representative provides specific steps and additional documentation in response to the user's request. Based on the emotional information provided by the emotion engine, the support representative provides the most appropriate response to the user's situation.

[1374] (Example 2)

[1375] 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".

[1376] Traditional search systems often failed to provide optimal information for user-entered search queries, resulting in decreased user satisfaction. In particular, the lack of appropriate information tailored to the user's emotional state could reduce search efficiency and increase stress. Furthermore, the process of users seeking additional information when search results were insufficient was cumbersome.

[1377] 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.

[1378] In this invention, the server includes means for a user to input a search query to obtain specific information, means for receiving the search query, means for transmitting the received search query to an emotion analysis module, means for the emotion analysis module to analyze the user's emotional state, means for transmitting the search query to a generative artificial intelligence based on the emotion analysis results, means for the generative artificial intelligence to optimize the search query, means for transmitting the optimized query to a search engine, means for the search engine to generate search results based on the optimized query, means for displaying the generated search results to the user, and means for automatically querying a support system via the emotion analysis module if the search results are insufficient. This enables the provision of optimal information according to the user's emotional state, improves search efficiency, and reduces user stress. Furthermore, if the search results are insufficient, a query is automatically made to the support system, allowing the user to quickly obtain additional information.

[1379] "User" refers to a person who uses this system to obtain specific information.

[1380] A "search query" is a combination of strings or words that a user enters to specify the information they want to retrieve.

[1381] An "interface" is a means of communication between the user and the system that allows the user to enter a search query and display the results.

[1382] An "emotion analysis module" or "emotion engine" is a software component that analyzes a user's emotional state, determining emotions based on user interaction data.

[1383] "Generative artificial intelligence" refers to an artificial intelligence module that generates optimized search queries based on received search queries and sentiment analysis results.

[1384] A "search engine" is a system used to search for relevant information from web pages and databases.

[1385] "Search results" are a list of information generated by a search engine that corresponds to a user's search query.

[1386] A "support system" or "support chat" is an automated inquiry and response system designed to provide users with additional information they may need.

[1387] "Emotional analysis results" refer to the results of an analysis of the user's emotional state obtained by the emotional analysis module based on the user's interaction data.

[1388] An "optimized query" is the most appropriate combination of search terms generated by a generative artificial intelligence system based on the user's search query and sentiment analysis results.

[1389] "Interaction data" refers to data generated when a user interacts with a system (e.g., keystrokes, mouse movements).

[1390] These definitions clarify each component of the system relating to the present invention and its function.

[1391] Modes for carrying out the invention

[1392] This invention relates to a system that optimizes search queries by combining generative artificial intelligence and an emotion analysis module when a user retrieves specific information, and provides information tailored to the user's emotional state. This system mainly consists of the following key components.

[1393] System Configuration

[1394] 1. User terminal

[1395] It includes an interface where the user enters search queries to retrieve specific information. The user terminal is used to receive queries and send them to generative artificial intelligence and sentiment analysis modules.

[1396] 2. Generative Artificial Intelligence (AI) Module

[1397] This module receives user queries and generates optimized search terms. Specifically, it analyzes the input query and optimizes it based on context and sentiment.

[1398] 3. Emotion Analysis Module (Emotion Engine)

[1399] The emotion analysis module analyzes the user's emotional state and provides the analysis results to other components. For example, if the user is anxious or dissatisfied, this information is reflected in the generative artificial intelligence and support chat system.

[1400] 4. Search Engine

[1401] A search engine receives an optimized query, searches its database for relevant information, and generates results. These search results are ultimately provided to the user.

[1402] 5. Support Chat System

[1403] If the search results are insufficient, the system automatically receives the user's inquiry, and a support representative provides additional information. Based on the user's sentiment information from the sentiment engine, the support representative takes appropriate action.

[1404] How the system works

[1405] Program Processing Overview

[1406] The system first receives the search query entered by the user. The received query is sent to an emotion analysis module, which analyzes the user's emotional state. Then, based on the analysis results, the query is optimized by generative artificial intelligence. The optimized query is sent to a search engine, and relevant search results are generated. The generated search results are displayed to the user, but if the search results are insufficient, an inquiry is automatically sent to the support chat system. Based on the emotional information provided by the emotion analysis module, a support representative provides the most appropriate response to the user.

[1407] Specific example

[1408] For example, consider a scenario where a user searches for "Machine A instruction manual." In this case, the user enters a search query, which the terminal receives and sends to an emotion analysis module. The emotion analysis module analyzes the user's emotional state and sends the results to a generative artificial intelligence (AI). The AI ​​optimizes the query, and the search engine searches for relevant information. Based on the optimized query, the search engine finds "the latest version of the Machine A instruction manual" and returns it to the user. If the user does not find the information they expect, the terminal automatically contacts a support chat system via the emotion analysis module to provide additional information.

[1409] Examples of prompt statements

[1410] "The user searched for 'Machine A User Manual,' but the emotion engine detected an anxious emotion. Please generate the most suitable search query for the user and automatically contact support chat if necessary."

[1411] This invention is designed to allow users to efficiently obtain the information they need, aiming to improve work productivity. By introducing an emotion analysis module, it becomes possible to provide optimal responses tailored to the user's emotional state, thereby offering a more enriching user experience.

[1412] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1413] The program's processing flow is divided into processing steps.

[1414] Step 1: The user enters a search query.

[1415] To obtain specific information, the user enters a query into the terminal's search bar. An example of such a query is "Machine A Instruction Manual". The input data here is the string "Machine A Instruction Manual" entered by the user.

[1416] Step 2: The terminal receives the query.

[1417] The terminal receives the query entered by the user. The received query ("Machine A User Manual") is converted into an appropriate data format and prepared to be sent to the sentiment analysis module. The input data here is the user's query, which is the output of step 1. The output data is the query data ready for sentiment analysis.

[1418] Step 3: The device sends query and interaction data to the sentiment analysis module.

[1419] The terminal sends the received query along with user interaction data (e.g., keyboard input speed, mouse movements, etc.) to the sentiment analysis module. The input data consists of the query string "Machine A Instruction Manual" and the interaction data. The output data is the data sent to the sentiment analysis module.

[1420] Step 4: The emotion analysis module analyzes the user's emotional state.

[1421] The emotion analysis module determines the user's emotional state (e.g., anxious, angry, calm) based on the received data. The input data consists of the query and interaction data sent in step 3. The output data is the analyzed user's emotional state.

[1422] Step 5: The device sends queries and sentiment analysis results to the generative artificial intelligence.

[1423] The terminal sends a query along with the emotion analysis results (e.g., state of anxiety) to the generative artificial intelligence. The input data consists of the query and the emotion analysis results. The output data is the request for optimization query generation that was sent to the generative artificial intelligence.

[1424] Step 6: Generative AI optimizes the query.

[1425] Generative artificial intelligence receives a query and sentiment analysis results, and generates an optimized query considering the context and emotional state (e.g., "Download the latest version of the instruction manual for machine A"). The input data is the original query and sentiment analysis results. The output data is the optimized query.

[1426] Step 7: The device sends the optimized query to the search engine.

[1427] The device sends an optimized query to the search engine. The input data is the optimized query. The output data is the query sent to the search engine.

[1428] Step 8: The server returns the search results.

[1429] A server with a search engine receives an optimized query, searches its database, and retrieves relevant information (e.g., "Latest version of the instruction manual for machine A"). The retrieved information is sent back to the terminal as search results. The input data is the optimized query, and the output data is the search results.

[1430] Step 9: The device displays the search results to the user.

[1431] The terminal displays search results received from the server to the user. For example, a link or summary of "the latest version of the instruction manual for machine A" is displayed on the user's screen. The input data is the search results, and the output data is the information displayed to the user.

[1432] Step 10: If the search results are insufficient, send an automated inquiry to the support chat.

[1433] If the user cannot obtain the information they expect, the device will automatically contact the support chat system based on the sentiment analysis results (e.g., "I am looking for specific instructions on how to operate machine A"). The input data consists of insufficient search results and sentiment analysis results, while the output data is the content of the inquiry sent to the support chat.

[1434] Step 11: Support chat receives and responds to the inquiry.

[1435] The support chat system receives inquiries, and support staff respond to user questions. Based on sentiment analysis results, responses are tailored to the user's state. The input data is the content of the inquiry sent to the support chat, and the output data is additional information provided by the support staff.

[1436] This allows users to efficiently obtain the information they need, and to quickly acquire additional information even if the search results are insufficient.

[1437] (Application Example 2)

[1438] 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".

[1439] Current information retrieval systems often fail to provide search results quickly and accurately, as they do not take into account the user's emotional state. This is particularly problematic in the security field, where providing appropriate information in situations where security personnel are under pressure and anxiety is crucial, but current systems do not adequately address this. Furthermore, the lack of automated systems for additional actions when search results are insufficient places a significant burden on users.

[1440] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting a search query for a user to obtain specific information, means for receiving the search query, means for transmitting the received search query to a generative artificial intelligence, means for the generative artificial intelligence to optimize the search query, means for transmitting the optimized query to a search engine, means for the search engine to generate search results based on the optimized query, means for displaying the generated search results to the user, means for automatically contacting a support chat if the search results are insufficient, means for capturing a frame with an image capture device and analyzing the user's emotional state using an emotion recognition engine, and means for generating a warning message based on the emotional state. This not only enables the provision of optimal information according to the user's emotional state, but also reduces the burden on the user by automatically taking additional action if the search results are insufficient.

[1441] A "user" is an individual or organization that enters a search query to obtain information.

[1442] A "search query" is a set of sentences or words that a user enters in order to obtain specific information.

[1443] "Generative artificial intelligence" is an artificial intelligence technology that analyzes input search queries and optimizes them based on context.

[1444] "Optimization" is the process of analyzing an entered search query and converting it into search terms that best meet the user's needs.

[1445] A "search engine" is a system that searches a database based on optimized queries and generates relevant information.

[1446] "Search results" are a collection of information generated by a search engine that a user is looking for.

[1447] A "support chat" is a system that automatically responds to user inquiries and provides additional information when search results are insufficient.

[1448] An "emotion recognition engine" is a technology used to analyze a user's emotional state, and it has the function of determining a user's emotions by analyzing their voice and facial expressions.

[1449] An "image capture device" is a device used to capture images or videos in real time.

[1450] A "warning message" is information or instructions designed to draw attention to a user's emotional state.

[1451] To implement the invention, the following hardware and software components are required. First, the user terminal has an interface for the user to input search queries to obtain specific information. This terminal is used for receiving queries and transmitting them to a generative artificial intelligence and emotion engine.

[1452] When a user enters a search query, the device receives the query, converts it to an appropriate format, and sends it to a generative artificial intelligence (AI). The AI ​​analyzes this query and optimizes it to best meet the user's needs. The optimized query is then sent to a search engine. The search engine searches its database for relevant information, generates search results, and returns them to the user.

[1453] If the search results are insufficient, the system will automatically contact the support chat system. This support chat system will answer the user's additional questions and provide more specific information.

[1454] Furthermore, the system includes an emotion recognition engine that analyzes the user's emotional state in real time. This engine captures frames using an image capture device and determines the user's emotional state from their facial expressions and voice. Based on this analysis, the emotion recognition engine generates a warning message and provides it to the user.

[1455] As a concrete example, let's consider a scenario where a user is performing monitoring duties. When the user searches for "emergency reporting procedures" in an emergency, the system receives the search query, and generative artificial intelligence optimizes it before sending it to the search engine. For example, it might be optimized as "on-site emergency reporting procedures." If the search results are not appropriate (for example, if no specific reporting procedures are found), the system automatically contacts the support chat system and provides additional specific response procedures.

[1456] Furthermore, the emotion recognition engine analyzes the user's emotional state and, if it detects that the user is anxious, generates an appropriate warning message. For example, it might display, "Please calm down and review the following steps." This allows the user to continue acting calmly.

[1457] The hardware and software used include:

[1458] Hardware: Cameras (surveillance cameras, webcams), user devices (PCs, smartphones, etc.)

[1459] Software: OpenCV (for camera frame capture), emotion recognition engine (e.g., Facial Emotion Recognition module), generative artificial intelligence (GPT-3 API, etc.)

[1460] The example prompt is as follows:

[1461] "The security team is in a state of panic. Please generate the most appropriate warning message."

[1462] The introduction of this system allows users to efficiently obtain necessary information and reduce stress and anxiety through emotion recognition. Furthermore, if search results are insufficient, additional actions are taken immediately, ensuring smooth task completion.

[1463] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1464] Step 1:

[1465] The user enters a search query to obtain specific information. The user enters the query in the search bar of their device and sends the entered query. For example, they might enter "emergency call procedure".

[1466] Step 2:

[1467] The terminal receives the search query. The terminal receives the query entered by the user and converts it to an appropriate format. The input data is a text-based query, and the converted data is also in text format.

[1468] Step 3:

[1469] The terminal sends the received search query to the generative artificial intelligence. The terminal then sends the pre-processed query to the generative AI module and waits for the result to be received. The input data is a search query in text format, and an optimized query is output.

[1470] Step 4:

[1471] Generative artificial intelligence optimizes search queries. The generative AI module analyzes the received query and transforms it into the most appropriate form based on the context. For example, it might specify "emergency call procedure" as "on-site emergency call procedure." The input data is the search query, and the output data is the optimized query.

[1472] Step 5:

[1473] The device sends an optimized query to the search engine. The input data is an optimized query, and the output data is a query in the form of a request to the search engine.

[1474] Step 6:

[1475] A search engine generates search results based on an optimized query. The search engine searches its database based on the received query and retrieves relevant information. The input data is the optimized query, and the output data is the search results.

[1476] Step 7:

[1477] The server displays the generated search results to the user. The server sends the search results obtained from the search engine back to the user's terminal. The user's terminal displays the received search results to the user. The input data is the search results, and the output data is the information displayed on the screen.

[1478] Step 8:

[1479] If search results are insufficient, the system automatically initiates a support chat inquiry. If the user cannot obtain the necessary information, the device automatically sends an inquiry to the support chat. The input data is a query for the missing information, and the output data is the request to the support chat.

[1480] Step 9:

[1481] The support chat receives the inquiry and provides additional information. The support chat system receives the user's inquiry, and a support representative provides additional information. The input data is the inquiry, and the output data is the additional information provided.

[1482] Step 10:

[1483] The system captures frames using an image capture device and analyzes the user's emotional state using an emotion recognition engine. It performs facial recognition and voice analysis to determine the emotional state in real time. Input data consists of camera frames and audio data, while output data is the result of the emotional state analysis.

[1484] Step 11:

[1485] The emotion recognition engine generates warning messages based on the user's emotional state. The engine presents an appropriate warning message based on the analysis results. For example, if the user is feeling anxious, it might generate a message such as, "Please calm down and review the following steps." The input data is the analysis result of the emotional state, and the output data is the warning message.

[1486] 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.

[1487] 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.

[1488] 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 robot 414.

[1489] 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.

[1490] 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.

[1491] 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.

[1492] 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.

[1493] 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.

[1494] 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."

[1495] 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.

[1496] 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.

[1497] 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.

[1498] 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.

[1499] 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.

[1500] 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.

[1501] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1502] 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.

[1503] 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.

[1504] 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.

[1505] 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.

[1506] 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 as being incorporated by reference.

[1507] The following is further disclosed regarding the embodiments described above.

[1508] (Claim 1)

[1509] A means for the user to enter a search query to obtain specific information,

[1510] The means for receiving the aforementioned search query,

[1511] A means for transmitting the received search query to a generative artificial intelligence,

[1512] The generative artificial intelligence includes means for optimizing the search query,

[1513] A means for submitting the optimized query to a search engine,

[1514] The search engine provides means for generating search results based on the optimized query,

[1515] Means for displaying the generated search results to the user,

[1516] A system that includes a means of automatically contacting support chat if the aforementioned search results are insufficient.

[1517] (Claim 2)

[1518] The system according to claim 1, further comprising means for analyzing the search query and converting it into more appropriate search terms in order for the generative artificial intelligence to generate an optimized query.

[1519] (Claim 3)

[1520] The system according to claim 1, wherein the support chat includes means for receiving the inquiry and providing additional information.

[1521] "Example 1"

[1522] (Claim 1)

[1523] A means for the user to enter a search query to obtain specific information,

[1524] The means for receiving the aforementioned search query,

[1525] A means for transmitting the received search query to a generative artificial intelligence,

[1526] The generative artificial intelligence includes means for optimizing the search query,

[1527] A means for submitting the optimized query to a search engine,

[1528] The search engine provides means for generating search results based on the optimized query,

[1529] Means for displaying the generated search results to the user,

[1530] A means for automatically querying a text-based interactive support system if the aforementioned search results are insufficient,

[1531] A means for analyzing the content of the aforementioned inquiry and providing appropriate supplementary information,

[1532] A system that includes this.

[1533] (Claim 2)

[1534] The system according to claim 1, wherein the generative artificial intelligence includes means for analyzing the search query, understanding the context and meaning of the search query, and converting it into appropriate search terms in order to generate an optimized query.

[1535] (Claim 3)

[1536] The system according to claim 1, wherein the interactive support system includes means for providing additional information or specific procedures based on the content of the inquiry.

[1537] "Application Example 1"

[1538] (Claim 1)

[1539] A means for the user to enter a search query to obtain specific information,

[1540] The means for receiving the aforementioned search query,

[1541] A means for transmitting the received search query to a generative artificial intelligence,

[1542] The generative artificial intelligence includes means for optimizing the search query,

[1543] A means for submitting the optimized query to a search engine,

[1544] The search engine provides means for generating search results based on the optimized query,

[1545] Means for displaying the generated search results to the user,

[1546] Voice input method,

[1547] means for converting the voice-input query into text,

[1548] A system that includes a means of automatically contacting support chat if the aforementioned search results are insufficient.

[1549] (Claim 2)

[1550] The system according to claim 1, further comprising means for analyzing the search query and converting it into more appropriate search terms in order for the generative artificial intelligence to generate an optimized query.

[1551] (Claim 3)

[1552] The system according to claim 1, wherein the support chat includes means for receiving the inquiry and providing additional information.

[1553] "Example 2 of combining an emotion engine"

[1554] (Claim 1)

[1555] A means for the user to enter a search query to obtain specific information,

[1556] The means for receiving the aforementioned search query,

[1557] Means for sending the received search query to the sentiment analysis module,

[1558] The aforementioned emotion analysis module includes means for analyzing the user's emotional state,

[1559] A means for sending a search query to a generative artificial intelligence based on the emotion analysis results,

[1560] The generative artificial intelligence includes means for optimizing the search query,

[1561] A means for submitting the optimized query to a search engine,

[1562] The search engine provides means for generating search results based on the optimized query,

[1563] Means for displaying the generated search results to the user,

[1564] A system that includes means for automatically querying a support system via an emotion analysis module if the aforementioned search results are insufficient.

[1565] (Claim 2)

[1566] The system according to claim 1, wherein the generative artificial intelligence includes means for analyzing the search query and generating an optimized query that takes into account the context and the user's emotional state.

[1567] (Claim 3)

[1568] The system according to claim 1, wherein the support system receives the inquiry content and provides additional information based on the sentiment analysis results.

[1569] "Application example 2 when combining with an emotional engine"

[1570] (Claim 1)

[1571] A means for the user to enter a search query to obtain specific information,

[1572] The means for receiving the aforementioned search query,

[1573] A means for transmitting the received search query to a generative artificial intelligence,

[1574] The generative artificial intelligence includes means for optimizing the search query,

[1575] A means for submitting the optimized query to a search engine,

[1576] The search engine provides means for generating search results based on the optimized query,

[1577] Means for displaying the generated search results to the user,

[1578] A means of automatically contacting support chat if the aforementioned search results are insufficient,

[1579] A means for capturing frames with an image capture device and analyzing the user's emotional state using an emotion recognition engine,

[1580] A system including means for generating a warning message based on the aforementioned emotional state.

[1581] (Claim 2)

[1582] The system according to claim 1, further comprising means for analyzing the search query and converting it into more appropriate search terms in order for the generative artificial intelligence to generate an optimized query.

[1583] (Claim 3)

[1584] The system according to claim 1, wherein the support chat includes means for receiving the inquiry and providing additional information. [Explanation of Symbols]

[1585] 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 the user to enter a search query to obtain specific information, The means for receiving the aforementioned search query, A means for transmitting the received search query to a generative artificial intelligence, The generative artificial intelligence includes means for optimizing the search query, A means for submitting the optimized query to a search engine, The search engine provides means for generating search results based on the optimized query, Means for displaying the generated search results to the user, A system that includes a means of automatically contacting support chat if the aforementioned search results are insufficient.

2. The system according to claim 1, further comprising means for analyzing the search query and converting it into more appropriate search terms in order for the generative artificial intelligence to generate an optimized query.

3. The system according to claim 1, wherein the support chat includes means for receiving the inquiry and providing additional information.

Images