system

Abstract

We provide the system. [Solution] An input device that receives voice or text input from the user, A conversion means for converting input audio into text data, An analysis means for analyzing the aforementioned character data and recognizing the user's request, A search means for retrieving information based on the aforementioned request, A generation means that generates a response based on the information obtained by the search means, An output device that presents the generated response to the user, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern information society, elderly people who are not used to machines or users who are not good at operating machines cannot fully utilize information terminals such as smartphones. As a result, problems such as information gap and social isolation may occur. In particular, elderly people often have difficulty obtaining the information necessary for their daily lives, and there is a need to solve such a situation.

Means for Solving the Problems

[0005] This invention provides a system that receives voice and text input from users, analyzes this data to understand user requests, and searches for and retrieves necessary information. The system includes a conversion means for converting voice into text data using speech recognition, an analysis means for analyzing requests, a search means for retrieving information, a generation means for generating responses, and an output device for presenting the generated responses to the user. In this way, it realizes information retrieval and retrieval support that can be used intuitively even by the elderly and beginners.

[0006] An "input device" is a device for receiving voice or text input from a user.

[0007] A "conversion means" is a means for converting input audio into corresponding text data.

[0008] "Analysis means" refers to a means of analyzing audio or text data to recognize user requests.

[0009] A "search tool" is a means for retrieving necessary information based on a request recognized by an analysis tool.

[0010] A "generation means" is a means for generating a response to a user based on information obtained through a search means.

[0011] An "output device" is a device that presents the generated response to the user.

[0012] "User" refers to an individual who attempts to operate this system and obtain information.

[0013] "Speech recognition" refers to the technology and process of converting speech into text data.

[0014] "Response" refers to the answer or information provided in response to a user's request. [Brief explanation of the drawing]

[0015] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, the numbered 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.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention is a system that enables users to easily obtain information through information terminals such as smartphones. This system provides comprehensive support to users by coordinating an input device, a conversion means, an analysis means, a search means, a generation means, and an output device.

[0037] First, the user can input a request for information retrieval into the terminal using voice or text. In the case of voice input, the terminal sends the data to the server, where a conversion device converts the voice into text data.

[0038] The server analyzes this text data using parsing tools to understand the user's intent. Based on this understood intent, search tools collect necessary information using the network and internal databases.

[0039] Based on the collected information, the server generates a user-appropriate response through a generation mechanism. This response can be personalized based on the user's attributes and requests.

[0040] The terminal presents the final response in either voice or text. Voice output utilizes speech synthesis, while text output is displayed on the screen. This process allows elderly users and those unfamiliar with technology to intuitively obtain the necessary information.

[0041] For example, if a user voice-inputs "I want to know tomorrow's weather," the terminal sends this voice to the server, and a conversion means converts it into text. Then, an analysis means interprets the user's request as "getting a weather forecast," and a search means retrieves weather information. A generation means creates a response based on that information, such as "It's going to be sunny tomorrow," and the terminal conveys it to the user by voice. This allows the user to receive the information in an easy-to-understand way.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user enters their information request via voice or text. In the case of voice input, the device acquires voice data through the microphone. In the case of text input, it receives character data from the keyboard.

[0045] Step 2:

[0046] The device sends the acquired audio data to the server. The server uses a speech recognition engine to convert the audio data into corresponding text data.

[0047] Step 3:

[0048] The server analyzes the converted text data and inputs it into a generative AI model to understand the user's intent. The model recognizes the user's request and generates a specific information retrieval query.

[0049] Step 4:

[0050] Based on the recognized query, the server searches for the necessary information from the internet or internal databases. Relevant information is collected through the search method.

[0051] Step 5:

[0052] Based on the information collected by the server, a response is generated for the user. The generative AI model creates a response in natural language, and in some cases, it may be personalized according to the user's attributes.

[0053] Step 6:

[0054] The server sends the generated response to the terminal. The terminal receives this data and presents the response to the user using methods such as speech synthesis or text display. In the case of audio output, the audio is played through the speaker.

[0055] Step 7:

[0056] If the user requests further information or wishes to perform a different action, they can return to Step 1 and begin the next input. This process is repeated until the user obtains the information they need.

[0057] (Example 1)

[0058] 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."

[0059] The challenge is to enable users to efficiently acquire information through voice or text input and receive appropriate responses tailored to their individual needs. In particular, it is necessary to provide a system that allows even users unfamiliar with information technology to intuitively acquire information.

[0060] 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.

[0061] In this invention, the server includes data collection means, voice processing means, analysis means, information acquisition means, response generation means, and result output means. This makes it possible to retrieve necessary information from requests entered by the user in voice or text, and to provide responses in voice or visual form that are tailored to the individual characteristics based on the results.

[0062] "Data collection means" refers to a device or function for receiving requests from users in voice or text.

[0063] "Speech processing means" refers to technologies and programs for converting collected speech data into text data.

[0064] "Analysis means" refers to functions and processes for analyzing text data to determine the user's intentions and requests.

[0065] "Information acquisition means" refers to the process of searching for and acquiring necessary information from networks and databases based on the analysis results.

[0066] A "response generation means" refers to a program or function that constructs an appropriate response to the user based on the acquired information.

[0067] "Result output means" refers to a device or technology that presents the generated response to the user in audio or visual form.

[0068] In implementing this invention, a user can first request information acquisition using a terminal such as a smartphone. The user can input the request by voice or text, and in the case of voice input, the terminal sends the voice data to the server. The server converts the voice into text data using voice processing software. In this process, it is conceivable that speech recognition technology such as Google® Cloud Speech-to-Text would be used.

[0069] The converted text data is analyzed by server-side analysis tools to understand the user's intent. Natural language processing techniques are used for this analysis, sometimes including models like Google BERT. This analysis helps to grasp the user's request and prepares the system for obtaining the necessary information in the next step.

[0070] To obtain information, the server collects the necessary data from the network and databases through information acquisition means. Search engines and APIs (e.g., weather forecast APIs) are used to collect relevant information based on user requests.

[0071] Based on the collected information, the server generates an appropriate response to the user using a response generation mechanism. This response generation may utilize AI models such as OpenAI® GPT-3®. Because the response is adjusted based on the user's attributes and characteristics, personalized information provision becomes possible.

[0072] Finally, the response sent from the server is presented to the user via the terminal's result output mechanism. If an audio response is required, speech synthesis software, such as Amazon Polly, is used, and the terminal screen is used for visual presentation.

[0073] For example, if a user inputs "I want to know tomorrow's weather" via voice, the prompt might be "Predict what information the user will request next and generate a response." Following this prompt, the server generates a specific response such as "It is expected to be sunny tomorrow" and provides that information to the user via the terminal. This system allows the user to smoothly obtain the information they need.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The user inputs information requests to a device such as a smartphone via voice or text. For example, the input might be a voice message saying, "I want to know tomorrow's weather." The input data is temporarily stored on the device.

[0077] Step 2:

[0078] When using voice input, the terminal sends the voice data to the server. The server uses voice processing software to convert this voice into text data. Specifically, it uses speech recognition technology to convert "I want to know tomorrow's weather" into the text "I want to know tomorrow's weather". This process converts the voice data into a parseable text format.

[0079] Step 3:

[0080] The server processes the converted text data using an analysis tool. This analysis tool utilizes natural language processing technology to understand the user's intent from the text. Based on the input text data, it extracts a specific request, such as "obtain weather forecast." This process includes keyword extraction and contextual analysis.

[0081] Step 4:

[0082] Based on the analyzed user intent, the server searches for the necessary information using information retrieval methods. In this step, it accesses networks and databases to obtain the required data, such as tomorrow's weather information from a weather forecast API. This collects the specific data needed to satisfy the user's request.

[0083] Step 5:

[0084] The server generates a response to the user using a response generation mechanism based on the collected information. This process uses a generative AI model and may use a prompt such as, "Predict what information the user will ask for next and generate a response." The response generated here would be a specific and natural sentence, such as, "It is expected to be sunny tomorrow."

[0085] Step 6:

[0086] The terminal presents the server-generated response to the user through a result output mechanism. If voice output is specified, speech synthesis software is used to produce a speech response, for example, "It is expected to be sunny tomorrow," which is then played for the user. If text output is specified, it is displayed as text on the terminal's screen. Ultimately, the user can receive a response to their request through either sight or sound.

[0087] (Application Example 1)

[0088] 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."

[0089] In modern cities, residents and tourists need to be able to quickly and appropriately access information about daily life and tourism. However, conventional systems struggle to personalize information based on users' geographical location and individual attributes. Furthermore, there is a need for enhanced systems that allow users to intuitively access information using voice interfaces. This is expected to significantly improve the user experience in cities.

[0090] 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.

[0091] In this invention, the server includes an input unit that receives voice or text input from a user, a conversion unit that converts the input voice into text data, an analysis unit that analyzes the text data to recognize the user's request, a search unit that searches for information based on the request, a generation unit that generates a response based on the information obtained by the search unit, a location information unit that obtains the user's geographical location information, and an output unit that presents the response generated based on the location information to the user. This enables the provision of fast and personalized information to the user based on location information.

[0092] An "input unit" is a device for receiving information acquisition requests from users in the form of voice or text.

[0093] A "conversion unit" is a device that converts audio data into text data.

[0094] An "analysis unit" is a device that analyzes text data and recognizes user requests.

[0095] A "search unit" is a device that searches for information based on the user's request.

[0096] A "generation unit" is a device that generates a response based on information acquired by the exploration unit.

[0097] A "location information unit" is a device used to acquire a user's geographical location information.

[0098] An "output unit" is a device that presents the generated response either audibly or visually.

[0099] The system for carrying out this invention is centered around a terminal device equipped with a user interface that accepts voice or text input. When the server receives voice input, it first uses speech recognition software (for example, Google Cloud Speech-to-Text) to convert the voice data into text data.

[0100] Next, the server parses this text data using a natural language processing API (e.g., Dialogflow) to identify the user's request. In this process, the server utilizes a location unit to obtain the user's geographical location. This location information is used to determine where the user is currently located and whether the requested information is relevant to that location.

[0101] After the analysis is complete, the server searches for information. Specifically, it uses a search unit to collect the requested information from the internet and local databases. Based on the information obtained from this search, a generation unit creates an appropriate response. This response is further personalized based on the user's attributes and location information.

[0102] Finally, the terminal uses an output unit to present a response. The response may be synthesized as speech or displayed as visual text on a screen. For example, if a user asks, "Are there any restaurants nearby?", the system will determine the user's current location and either respond verbally or display a list of nearby restaurants on the screen.

[0103] For example, if a user asks, "What events are currently taking place in a nearby park?", the server can determine the user's location via a location information unit, search for relevant event information, and generate a response such as, "There is currently a music festival taking place in a nearby park."

[0104] Example prompt: "Please provide the most relevant event information based on the user's current location and time of day."

[0105] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0106] Step 1:

[0107] The terminal accepts voice or text input from the user. Voice input is treated as audio data and immediately sent to the next processing step. Text input is passed directly as text data to the next step.

[0108] Step 2:

[0109] When the server receives voice input, it uses speech recognition software to convert the voice data into text data. Specifically, it forwards the voice input to the Google Cloud Speech-to-Text API and retrieves the corresponding string. In this step, the input is voice data, and the output is text data.

[0110] Step 3:

[0111] The server analyzes the generated text data using a natural language processing API to identify the user's request. Dialogflow is used for natural language processing. When analyzing the text data, the user's intent is clarified, and requests based on that intent are sent to the next step.

[0112] Step 4:

[0113] The server uses a location unit to obtain the user's geographical location. This location information is crucial data for determining which region the requested information relates to. In this step, location information is the input, and specific information about the user's current location is the output.

[0114] Step 5:

[0115] Based on the analyzed request and acquired location information, the server uses a search unit to collect necessary information from internet sources and databases. The collected information is specifically related to the user's request and is formatted as search results.

[0116] Step 6:

[0117] The server generates a response based on the search results. The generation unit uses Dialogflow or a similar system to assemble the most suitable response for the user. This response is personalized based on the user's requests, location, and attributes.

[0118] Step 7:

[0119] The terminal receives the generated response and uses an output unit to present the response to the user as audio or text data. Specifically, it generates audio using a speech synthesis API and outputs it through the speaker or displays it as text on the screen. The output in this step presents information in a format that is easy for the user to understand.

[0120] 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.

[0121] The present invention is a system that takes user emotions into consideration, receiving user input, recognizing emotions using an emotion engine, and providing personalized responses to achieve more intuitive and human-like interaction. This system includes an input device that accepts voice or text input, a conversion means for converting voice data, an analysis means for analyzing data, a search means for retrieving information, a generation means for generating responses, an output device for presenting responses, and an emotion engine for recognizing emotions.

[0122] When a user inputs information via voice or text into a device such as a smartphone, the device records the input and, in the case of voice input, converts it into text data using a conversion device. The server analyzes this text data using an analysis device to recognize the user's request.

[0123] Furthermore, an emotion engine extracts emotions from the user's input. This emotion engine recognizes emotions such as joy, sadness, and anger that the user is feeling by analyzing voice tone, speed, and linguistic indicators.

[0124] Based on the user's request obtained by the analysis means and the emotion recognized by the emotion engine, the server uses the search means to collect appropriate information. The generation means considers this information and the emotion to construct an appropriate response that matches the user's mood.

[0125] Finally, the constructed response is presented to the user by the device either as voice or text. For example, if the user asks in a sad voice, "What's the weather like today?", the system generates a caring message such as, "It looks like it's going to be sunny today, so cheer up!" and delivers it aloud. This allows the user to feel reassured and comforted. In this way, the present invention can provide users with more human-like interaction and emotionally responsive support.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] The user enters an information request into the terminal via voice or text. In the case of voice input, the terminal captures the voice data through the microphone. In the case of text input, it receives the string data from the keyboard.

[0129] Step 2:

[0130] The device sends the captured audio data to the server. The server uses a speech recognition engine to convert the audio into text data. This process transforms the audio into usable text information.

[0131] Step 3:

[0132] The server analyzes the converted character data using an analysis tool to recognize the user's request. The analysis tool uses a generative AI model to determine what the user's request is.

[0133] Step 4:

[0134] While the server is analyzing the data, it uses an emotion engine to detect the user's emotions. The emotion engine analyzes the user's input, including their tone of voice, speed, and word choice, to estimate their emotional state.

[0135] Step 5:

[0136] Based on the requests obtained by the analysis tools and the emotional information detected by the emotion engine, the server uses search tools to retrieve relevant information from the web and databases. This ensures that information aligned with the user's requests is gathered.

[0137] Step 6:

[0138] The server considers the information it collects and the user's emotions, and constructs an appropriate response using a generation method. The generation AI model customizes the response using a tone and expression that is appropriate for the user's emotions.

[0139] Step 7:

[0140] The server sends the generated response to the terminal. The terminal converts the received response into speech using speech synthesis technology and either plays it to the user through the speaker or displays it as text on the screen.

[0141] Step 8:

[0142] The user receives a response from the system and asks further questions if necessary. The system continues this process, responding to the user's information requests.

[0143] (Example 2)

[0144] 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".

[0145] Conventional interface systems have a problem in that their responses to user input are simplistic and lack human-like qualities that take emotions into consideration, resulting in users perceiving them as mechanical. In particular, it has been difficult to provide responses that are sensitive to the user's emotions.

[0146] 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.

[0147] In this invention, the server includes emotion recognition means for extracting emotions from user input, search means for retrieving information based on the user's requests and emotions, and response generation means for generating a response that takes the retrieved information and emotions into consideration. This makes it possible to construct and provide to the user a more humane and approachable response that reflects the user's emotions.

[0148] An "input device" is a device for receiving voice or text input from a user.

[0149] A "conversion device" is a device that converts input audio into text data.

[0150] An "analysis device" is a device that analyzes received text data to recognize the user's requests.

[0151] An "emotion recognition device" is a device that extracts emotions from user input.

[0152] A "search device" is a device used to retrieve necessary information based on analyzed requests and extracted emotions.

[0153] A "response generation device" is a device that generates a response to present to the user, taking into account the information and emotions obtained.

[0154] An "output device" is a device that presents the generated response to the user.

[0155] This invention is a system that generates responses while considering the user's emotions, and achieves more intuitive and human-like interaction based on user input. The system can be implemented using the following hardware and software.

[0156] When users input information via voice or text, they use devices such as smartphones or personal computers. These devices function as input devices, and in the case of voice input, they use a voice recognition cloud service (for example, a common voice recognition API) as a conversion device to convert voice data into text data.

[0157] Subsequently, the server uses a natural language processing library (e.g., an open-source natural language processing toolkit) as an analysis device to analyze the text data and extract the user's request. At the same time, it uses an emotion analysis service (a general language analysis API) as an emotion recognition device to identify the user's emotions from their voice tone and input content.

[0158] Based on the information obtained by the analysis device and the emotion recognition device, the server uses a database search engine (e.g., a distributed search engine) as a search device to collect appropriate information. This activates a response generation device that generates a response based on the requested information and emotion. The generation device uses a generation AI model (e.g., a general-purpose AI model) to construct an emotion-appropriate response.

[0159] Finally, the terminal acts as an output device, presenting the generated response in voice or text using a speech synthesis service (e.g., a common speech synthesis API). This process allows the user to receive a friendly, rather than mechanical, response.

[0160] For example, if a user asks "What's the weather like today?" in a sad voice, the system can generate and deliver a comforting message such as "It looks like it's going to be sunny today, so cheer up!" An example of a prompt might be "Give a cheering response when the user asks about the weather in a sad voice."

[0161] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0162] Step 1:

[0163] The user inputs information via voice or text into a device such as a smartphone. The device, acting as an input device, receives this input. The input here is voice data or text data spoken by the user, such as "Tell me the weather tomorrow." The voice data is then converted into text data using a speech recognition API. The output is the converted text data.

[0164] Step 2:

[0165] The server receives the converted character data and performs analysis using a natural language processing library as its parsing device. This analysis identifies the user's request from the character data. By using the converted character data as input and identifying the request, the server can obtain a specific request, such as "weather information inquiry," as output.

[0166] Step 3:

[0167] The server, acting as an emotion recognition device, simultaneously uses an emotion analysis API to analyze the user's emotions from the input data. The input includes voice tone and text, and based on this, it identifies emotions (joy, sadness, anger, etc.) as output. In this example, the output indicates that the user is sad.

[0168] Step 4:

[0169] The server uses a database search engine as its search mechanism to retrieve the necessary information based on the collected requests and sentiment information. The input is the aforementioned request content and sentiment information, and the output is the search results based on this. In this case, the information collected is "Tomorrow's weather will be sunny."

[0170] Step 5:

[0171] The server utilizes a generative AI model as a response generator to produce responses that take into account the information and emotions collected by the search device. The inputs used are search results and emotion information. For example, considering both "sunny" and "the user is sad," it might generate the text response, "It looks like it will be sunny tomorrow, so cheer up!" This is the output of this step.

[0172] Step 6:

[0173] The terminal uses an output device to either play the generated response as audio using a speech synthesis API or display it as text on the screen. The input is the generated response text, which is delivered to the user either as audio output in a soft tone or as text output on the screen. This output is the terminal's final response to the user.

[0174] (Application Example 2)

[0175] 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".

[0176] When users interact with systems, they sometimes respond coldly and mechanically without adequately considering the user's emotions. This problem is particularly important in consumer devices such as home robots, where providing a more user-friendly and enriching experience is crucial. Conventional systems struggle to construct appropriate responses that reflect the user's emotions, often resulting in user dissatisfaction.

[0177] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0178] In this invention, the server includes a reception module that receives information from the user, a data conversion device that converts the input voice into text data, and a data analysis device that analyzes the text data to interpret the user's request. This makes it possible to provide a more human-like interaction that takes the user's emotions into consideration.

[0179] A "reception module for receiving user information" is a component that is responsible for receiving voice and text data input from users.

[0180] A "data conversion device" is a device that performs the process of converting input audio data into text data.

[0181] A "data analysis device" is a device that interprets converted text data and performs processing to understand user requests.

[0182] A "data retrieval tool" is a means of searching for necessary information and knowledge from databases, etc., based on user requests.

[0183] A "response generation module" is a module that has the function of composing a response to the user based on the information that has been searched.

[0184] A "sentiment analysis engine" is an engine that detects emotions from a user's voice or text and evaluates their emotional state, such as joy or sadness.

[0185] A "presentation device" is a device that outputs the generated response to the user as audio or visual information.

[0186] The program for implementing this system is designed to run on a home robot. The user provides input directly to the robot via voice or text. The terminal transmits this input, and in the case of voice input, a data conversion device converts it into text data. The converted text data is sent to a data analysis device, where the user's request is interpreted.

[0187] Next, an emotion analysis engine is implemented to detect emotions from user input. Specifically, it grasps emotional states through voice tone and speed, and the linguistic elements used. This allows it to recognize emotions such as joy, sadness, and anger.

[0188] Subsequently, a data retrieval tool searches for appropriate knowledge based on the analyzed requests and emotional states. During this process, a generative AI model constructs the information necessary to generate a response. Finally, a response generation module organizes this information and shapes a personalized response that takes the user's emotions into consideration. The created response is then conveyed to the user as audio or visual information through a presentation device.

[0189] As a concrete example, consider a case where a user, in a tired voice, types, "Can you recommend a song that will cheer me up?" In this case, the system would determine that the user is fatigued, select and play positive music, and provide an encouraging message such as, "Let's relax together." The system might use prompts like the following:

[0190] User request: "Can you suggest some uplifting music?"

[0191] Emotion detection: Fatigue

[0192] Prompt: Consider the user's fatigue and suggest an uplifting music playlist, providing cheerful music to lift their spirits.

[0193] In this way, the system can provide users with a user-friendly and emotionally resonant experience.

[0194] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0195] Step 1:

[0196] The terminal receives voice or text input from the user. In the case of voice input, the terminal sends this voice data to a data conversion device, which converts it into text data. The output of this step is the converted text data.

[0197] Step 2:

[0198] The server uses a data analysis device to analyze the received text data and interpret the user's request. The input is text data, and natural language processing techniques are used to extract meaning. The output is the analyzed user request.

[0199] Step 3:

[0200] The server uses an emotion analysis engine to analyze the emotions contained in the text data. The input is the text data converted in step 1. It analyzes voice tone and linguistic indicators to extract the user's emotions. The output of this step is the identification result of the emotional state.

[0201] Step 4:

[0202] The server uses data retrieval tools to search for relevant information corresponding to the analyzed request and emotional state. The input used here is the analyzed user request and emotional state. Useful information is retrieved from databases and other sources, and the search results are provided as output.

[0203] Step 5:

[0204] The server uses a generative AI model to construct a response based on the retrieved information. This process generates an emotionally sensitive response by including emotional states as prompts. The input consists of search results and prompts, which are processed by the AI ​​model to produce a generated response as output.

[0205] Step 6:

[0206] The terminal receives the output from the response generation module and presents it to the user in audio or visual form using a presentation device. The input for this step is the response sentence constructed in step 5. The final output is the response presented in a format easily understood by the user.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] [Second Embodiment]

[0211] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0212] 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.

[0213] 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).

[0214] 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.

[0215] 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.

[0216] 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).

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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".

[0223] This invention is a system that enables users to easily obtain information through information terminals such as smartphones. This system provides comprehensive support to users by coordinating an input device, a conversion means, an analysis means, a search means, a generation means, and an output device.

[0224] First, the user can input a request for information retrieval into the terminal using voice or text. In the case of voice input, the terminal sends the data to the server, where a conversion device converts the voice into text data.

[0225] The server analyzes this text data using parsing tools to understand the user's intent. Based on this understood intent, search tools collect necessary information using the network and internal databases.

[0226] Based on the collected information, the server generates a user-appropriate response through a generation mechanism. This response can be personalized based on the user's attributes and requests.

[0227] The terminal presents the final response in either voice or text. Voice output utilizes speech synthesis, while text output is displayed on the screen. This process allows elderly users and those unfamiliar with technology to intuitively obtain the necessary information.

[0228] For example, if a user voice-inputs "I want to know tomorrow's weather," the terminal sends this voice to the server, and a conversion means converts it into text. Then, an analysis means interprets the user's request as "getting a weather forecast," and a search means retrieves weather information. A generation means creates a response based on that information, such as "It's going to be sunny tomorrow," and the terminal conveys it to the user by voice. This allows the user to receive the information in an easy-to-understand way.

[0229] The following describes the processing flow.

[0230] Step 1:

[0231] The user enters their information request via voice or text. In the case of voice input, the device acquires voice data through the microphone. In the case of text input, it receives character data from the keyboard.

[0232] Step 2:

[0233] The device sends the acquired audio data to the server. The server uses a speech recognition engine to convert the audio data into corresponding text data.

[0234] Step 3:

[0235] The server analyzes the converted text data and inputs it into a generative AI model to understand the user's intent. The model recognizes the user's request and generates a specific information retrieval query.

[0236] Step 4:

[0237] Based on the recognized query, the server searches for the necessary information from the internet or internal databases. Relevant information is collected through the search method.

[0238] Step 5:

[0239] Based on the information collected by the server, a response is generated for the user. The generative AI model creates a response in natural language, and in some cases, it may be personalized according to the user's attributes.

[0240] Step 6:

[0241] The server sends the generated response to the terminal. The terminal receives this data and presents the response to the user using methods such as speech synthesis or text display. In the case of audio output, the audio is played through the speaker.

[0242] Step 7:

[0243] If the user requests further information or wishes to perform a different action, they can return to Step 1 and begin the next input. This process is repeated until the user obtains the information they need.

[0244] (Example 1)

[0245] 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."

[0246] The challenge is to enable users to efficiently acquire information through voice or text input and receive appropriate responses tailored to their individual needs. In particular, it is necessary to provide a system that allows even users unfamiliar with information technology to intuitively acquire information.

[0247] 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.

[0248] In this invention, the server includes data collection means, voice processing means, analysis means, information acquisition means, response generation means, and result output means. This makes it possible to retrieve necessary information from requests entered by the user in voice or text, and to provide responses in voice or visual form that are tailored to the individual characteristics based on the results.

[0249] "Data collection means" refers to a device or function for receiving requests from users in voice or text.

[0250] "Speech processing means" refers to technologies and programs for converting collected speech data into text data.

[0251] "Analysis means" refers to functions and processes for analyzing text data to determine the user's intentions and requests.

[0252] "Information acquisition means" refers to the process of searching for and acquiring necessary information from networks and databases based on the analysis results.

[0253] A "response generation means" refers to a program or function that constructs an appropriate response to the user based on the acquired information.

[0254] "Result output means" refers to a device or technology that presents the generated response to the user in audio or visual form.

[0255] In implementing this invention, a user can first request information acquisition using a terminal such as a smartphone. The user can input the request by voice or text, and in the case of voice input, the terminal sends the voice data to the server. The server converts the voice into text data using voice processing software. In this process, it is conceivable that speech recognition technology such as Google Cloud Speech-to-Text would be used.

[0256] The converted text data is analyzed by server-side analysis tools to understand the user's intent. Natural language processing techniques are used for this analysis, sometimes including models like Google BERT. This analysis helps to grasp the user's request and prepares the system for obtaining the necessary information in the next step.

[0257] To obtain information, the server collects the necessary data from the network and databases through information acquisition means. Search engines and APIs (e.g., weather forecast APIs) are used to collect relevant information based on user requests.

[0258] Based on the collected information, the server generates an appropriate response to the user using a response generation mechanism. OpenAI GPT-3, for example, may be used as the generation AI model for this response generation. Because the response is adjusted based on the user's attributes and characteristics, personalized information provision becomes possible.

[0259] Finally, the response sent from the server is presented to the user via the terminal's result output mechanism. If an audio response is required, speech synthesis software, such as Amazon Polly, is used, and the terminal screen is used for visual presentation.

[0260] For example, if a user inputs "I want to know tomorrow's weather" via voice, the prompt might be "Predict what information the user will request next and generate a response." Following this prompt, the server generates a specific response such as "It is expected to be sunny tomorrow" and provides that information to the user via the terminal. This system allows the user to smoothly obtain the information they need.

[0261] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0262] Step 1:

[0263] The user inputs information requests to a device such as a smartphone via voice or text. For example, the input might be a voice message saying, "I want to know tomorrow's weather." The input data is temporarily stored on the device.

[0264] Step 2:

[0265] When using voice input, the terminal sends the voice data to the server. The server uses voice processing software to convert this voice into text data. Specifically, it uses speech recognition technology to convert "I want to know tomorrow's weather" into the text "I want to know tomorrow's weather". This process converts the voice data into a parseable text format.

[0266] Step 3:

[0267] The server processes the converted text data using an analysis tool. This analysis tool utilizes natural language processing technology to understand the user's intent from the text. Based on the input text data, it extracts a specific request, such as "obtain weather forecast." This process includes keyword extraction and contextual analysis.

[0268] Step 4:

[0269] Based on the analyzed user intent, the server searches for the necessary information using information retrieval methods. In this step, it accesses networks and databases to obtain the required data, such as tomorrow's weather information from a weather forecast API. This collects the specific data needed to satisfy the user's request.

[0270] Step 5:

[0271] The server generates a response to the user using a response generation mechanism based on the collected information. This process uses a generative AI model and may use a prompt such as, "Predict what information the user will ask for next and generate a response." The response generated here would be a specific and natural sentence, such as, "It is expected to be sunny tomorrow."

[0272] Step 6:

[0273] The terminal presents the server-generated response to the user through a result output mechanism. If voice output is specified, speech synthesis software is used to produce a speech response, for example, "It is expected to be sunny tomorrow," which is then played for the user. If text output is specified, it is displayed as text on the terminal's screen. Ultimately, the user can receive a response to their request through either sight or sound.

[0274] (Application Example 1)

[0275] 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."

[0276] In modern cities, residents and tourists need to be able to quickly and appropriately access information about daily life and tourism. However, conventional systems struggle to personalize information based on users' geographical location and individual attributes. Furthermore, there is a need for enhanced systems that allow users to intuitively access information using voice interfaces. This is expected to significantly improve the user experience in cities.

[0277] 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.

[0278] In this invention, the server includes an input unit that receives voice or text input from a user, a conversion unit that converts the input voice into text data, an analysis unit that analyzes the text data to recognize the user's request, a search unit that searches for information based on the request, a generation unit that generates a response based on the information obtained by the search unit, a location information unit that obtains the user's geographical location information, and an output unit that presents the response generated based on the location information to the user. This enables the provision of fast and personalized information to the user based on location information.

[0279] An "input unit" is a device for receiving information acquisition requests from users in the form of voice or text.

[0280] A "conversion unit" is a device that converts audio data into text data.

[0281] An "analysis unit" is a device that analyzes text data and recognizes user requests.

[0282] A "search unit" is a device that searches for information based on the user's request.

[0283] A "generation unit" is a device that generates a response based on information acquired by the exploration unit.

[0284] The "Location Information Unit" is a device for acquiring the geographical location information of a user.

[0285] The "Output Unit" is a device for presenting the generated response audibly or visually.

[0286] The system for implementing this invention is centered around a terminal device equipped with a user interface that accepts voice or text input. When the server receives voice input, it first converts the voice data into character data using voice recognition software (e.g., Google Cloud Speech-to-Text).

[0287] Next, the server analyzes this character data using a natural language processing API (e.g., Dialogflow) to identify the user's request. In this process, the server utilizes the Location Information Unit to obtain the geographical location information of the user. The location information is used to identify where the user is currently located and to determine whether the requested information is relevant to that location.

[0288] After the analysis is completed, the server searches for information. Specifically, it uses a search unit to collect information corresponding to the request from the Internet or a local database. Based on the information obtained as a result of this search, a generation unit creates an appropriate response. This response is further personalized based on the user's attributes and location information.

[0289] Finally, the terminal presents the response using the Output Unit. The response may be synthesized as voice or displayed as visual text on a display. For example, when the user asks "Is there a restaurant nearby?", the system checks the user's current location and responds verbally with information about restaurants nearby or displays a list on the screen.

[0290] For example, if a user asks, "What events are currently taking place in a nearby park?", the server can determine the user's location via a location information unit, search for relevant event information, and generate a response such as, "There is currently a music festival taking place in a nearby park."

[0291] Example prompt: "Please provide the most relevant event information based on the user's current location and time of day."

[0292] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0293] Step 1:

[0294] The terminal accepts voice or text input from the user. Voice input is treated as audio data and immediately sent to the next processing step. Text input is passed directly as text data to the next step.

[0295] Step 2:

[0296] When the server receives voice input, it uses speech recognition software to convert the voice data into text data. Specifically, it forwards the voice input to the Google Cloud Speech-to-Text API and retrieves the corresponding string. In this step, the input is voice data, and the output is text data.

[0297] Step 3:

[0298] The server analyzes the generated text data using a natural language processing API to identify the user's request. Dialogflow is used for natural language processing. When analyzing the text data, the user's intent is clarified, and requests based on that intent are sent to the next step.

[0299] Step 4:

[0300] The server uses the location information unit to obtain the geographical location of the user. This location information is important data for determining which region the requested information is related to. In this step, the location information is input, and specific information regarding the user's current location is output.

[0301] Step 5:

[0302] Based on the analyzed request and the obtained location information, the server uses the search unit to collect the necessary information from information sources or databases on the Internet. The information collected is specifically related to the user's request and is formatted as search results.

[0303] Step 6:

[0304] The server generates a response based on the search results. The generation unit uses Dialogflow or a similar system to assemble the optimal response for the user. This response is personalized based on the user's request, location information, and attributes.

[0305] Step 7:

[0306] The terminal receives the generated response and uses the output unit to present the response to the user as voice data or text data. As a specific operation, it uses the text-to-speech API to generate voice and output it from the speaker, or displays it as text on the display. The output of this step is the presentation of information in a format that is easy for the user to understand.

[0307] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0308] The present invention is a system that takes user emotions into consideration, receiving user input, recognizing emotions using an emotion engine, and providing personalized responses to achieve more intuitive and human-like interaction. This system includes an input device that accepts voice or text input, a conversion means for converting voice data, an analysis means for analyzing data, a search means for retrieving information, a generation means for generating responses, an output device for presenting responses, and an emotion engine for recognizing emotions.

[0309] When a user inputs information via voice or text into a device such as a smartphone, the device records the input and, in the case of voice input, converts it into text data using a conversion device. The server analyzes this text data using an analysis device to recognize the user's request.

[0310] Furthermore, an emotion engine extracts emotions from the user's input. This emotion engine recognizes emotions such as joy, sadness, and anger that the user is feeling by analyzing voice tone, speed, and linguistic indicators.

[0311] Based on the user's request obtained by the analysis means and the emotion recognized by the emotion engine, the server uses the search means to collect appropriate information. The generation means considers this information and the emotion to construct an appropriate response that matches the user's mood.

[0312] Finally, the constructed response is presented to the user by the device either as voice or text. For example, if the user asks in a sad voice, "What's the weather like today?", the system generates a caring message such as, "It looks like it's going to be sunny today, so cheer up!" and delivers it aloud. This allows the user to feel reassured and comforted. In this way, the present invention can provide users with more human-like interaction and emotionally responsive support.

[0313] The following describes the processing flow.

[0314] Step 1:

[0315] The user enters an information request into the terminal via voice or text. In the case of voice input, the terminal captures the voice data through the microphone. In the case of text input, it receives the string data from the keyboard.

[0316] Step 2:

[0317] The device sends the captured audio data to the server. The server uses a speech recognition engine to convert the audio into text data. This process transforms the audio into usable text information.

[0318] Step 3:

[0319] The server analyzes the converted character data using an analysis tool to recognize the user's request. The analysis tool uses a generative AI model to determine what the user's request is.

[0320] Step 4:

[0321] While the server is analyzing the data, it uses an emotion engine to detect the user's emotions. The emotion engine analyzes the user's input, including their tone of voice, speed, and word choice, to estimate their emotional state.

[0322] Step 5:

[0323] Based on the requests obtained by the analysis tools and the emotional information detected by the emotion engine, the server uses search tools to retrieve relevant information from the web and databases. This ensures that information aligned with the user's requests is gathered.

[0324] Step 6:

[0325] The server considers the information it collects and the user's emotions, and constructs an appropriate response using a generation method. The generation AI model customizes the response using a tone and expression that is appropriate for the user's emotions.

[0326] Step 7:

[0327] The server sends the generated response to the terminal. The terminal converts the received response into speech using speech synthesis technology and either plays it to the user through the speaker or displays it as text on the screen.

[0328] Step 8:

[0329] The user receives a response from the system and asks further questions if necessary. The system continues this process, responding to the user's information requests.

[0330] (Example 2)

[0331] 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".

[0332] Conventional interface systems have a problem in that their responses to user input are simplistic and lack human-like qualities that take emotions into consideration, resulting in users perceiving them as mechanical. In particular, it has been difficult to provide responses that are sensitive to the user's emotions.

[0333] 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.

[0334] In this invention, the server includes emotion recognition means for extracting emotions from user input, search means for retrieving information based on the user's requests and emotions, and response generation means for generating a response that takes the retrieved information and emotions into consideration. This makes it possible to construct and provide to the user a more humane and approachable response that reflects the user's emotions.

[0335] An "input device" is a device for receiving voice or text input from a user.

[0336] A "conversion device" is a device that converts input audio into text data.

[0337] An "analysis device" is a device that analyzes received text data to recognize the user's requests.

[0338] An "emotion recognition device" is a device that extracts emotions from user input.

[0339] A "search device" is a device used to retrieve necessary information based on analyzed requests and extracted emotions.

[0340] A "response generation device" is a device that generates a response to present to the user, taking into account the information and emotions obtained.

[0341] An "output device" is a device that presents the generated response to the user.

[0342] This invention is a system that generates responses while considering the user's emotions, and achieves more intuitive and human-like interaction based on user input. The system can be implemented using the following hardware and software.

[0343] When users input information via voice or text, they use devices such as smartphones or personal computers. These devices function as input devices, and in the case of voice input, they use a voice recognition cloud service (for example, a common voice recognition API) as a conversion device to convert voice data into text data.

[0344] Subsequently, the server uses a natural language processing library (e.g., an open-source natural language processing toolkit) as an analysis device to analyze the text data and extract the user's request. At the same time, it uses an emotion analysis service (a general language analysis API) as an emotion recognition device to identify the user's emotions from their voice tone and input content.

[0345] Based on the information obtained by the analysis device and the emotion recognition device, the server uses a database search engine (e.g., a distributed search engine) as a search device to collect appropriate information. This activates a response generation device that generates a response based on the requested information and emotion. The generation device uses a generation AI model (e.g., a general-purpose AI model) to construct an emotion-appropriate response.

[0346] Finally, the terminal acts as an output device, presenting the generated response in voice or text using a speech synthesis service (e.g., a common speech synthesis API). This process allows the user to receive a friendly, rather than mechanical, response.

[0347] For example, if a user asks "What's the weather like today?" in a sad voice, the system can generate and deliver a comforting message such as "It looks like it's going to be sunny today, so cheer up!" An example of a prompt might be "Give a cheering response when the user asks about the weather in a sad voice."

[0348] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0349] Step 1:

[0350] The user inputs information via voice or text into a device such as a smartphone. The device, acting as an input device, receives this input. The input here is voice data or text data spoken by the user, such as "Tell me the weather tomorrow." The voice data is then converted into text data using a speech recognition API. The output is the converted text data.

[0351] Step 2:

[0352] The server receives the converted character data and performs analysis using a natural language processing library as its parsing device. This analysis identifies the user's request from the character data. By using the converted character data as input and identifying the request, the server can obtain a specific request, such as "weather information inquiry," as output.

[0353] Step 3:

[0354] The server, acting as an emotion recognition device, simultaneously uses an emotion analysis API to analyze the user's emotions from the input data. The input includes voice tone and text, and based on this, it identifies emotions (joy, sadness, anger, etc.) as output. In this example, the output indicates that the user is sad.

[0355] Step 4:

[0356] The server uses a database search engine as its search mechanism to retrieve the necessary information based on the collected requests and sentiment information. The input is the aforementioned request content and sentiment information, and the output is the search results based on this. In this case, the information collected is "Tomorrow's weather will be sunny."

[0357] Step 5:

[0358] The server utilizes a generative AI model as a response generator to produce responses that take into account the information and emotions collected by the search device. The inputs used are search results and emotion information. For example, considering both "sunny" and "the user is sad," it might generate the text response, "It looks like it will be sunny tomorrow, so cheer up!" This is the output of this step.

[0359] Step 6:

[0360] The terminal uses an output device to either play the generated response as audio using a speech synthesis API or display it as text on the screen. The input is the generated response text, which is delivered to the user either as audio output in a soft tone or as text output on the screen. This output is the terminal's final response to the user.

[0361] (Application Example 2)

[0362] 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."

[0363] When users interact with systems, they sometimes respond coldly and mechanically without adequately considering the user's emotions. This problem is particularly important in consumer devices such as home robots, where providing a more user-friendly and enriching experience is crucial. Conventional systems struggle to construct appropriate responses that reflect the user's emotions, often resulting in user dissatisfaction.

[0364] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0365] In this invention, the server includes a reception module that receives information from the user, a data conversion device that converts the input voice into text data, and a data analysis device that analyzes the text data to interpret the user's request. This makes it possible to provide a more human-like interaction that takes the user's emotions into consideration.

[0366] A "reception module for receiving user information" is a component that is responsible for receiving voice and text data input from users.

[0367] A "data conversion device" is a device that performs the process of converting input audio data into text data.

[0368] A "data analysis device" is a device that interprets converted text data and performs processing to understand user requests.

[0369] A "data retrieval tool" is a means of searching for necessary information and knowledge from databases, etc., based on user requests.

[0370] A "response generation module" is a module that has the function of composing a response to the user based on the information that has been searched.

[0371] A "sentiment analysis engine" is an engine that detects emotions from a user's voice or text and evaluates their emotional state, such as joy or sadness.

[0372] A "presentation device" is a device that outputs the generated response to the user as audio or visual information.

[0373] The program for implementing this system is designed to run on a home robot. The user provides input directly to the robot via voice or text. The terminal transmits this input, and in the case of voice input, a data conversion device converts it into text data. The converted text data is sent to a data analysis device, where the user's request is interpreted.

[0374] Next, an emotion analysis engine is implemented to detect emotions from user input. Specifically, it grasps emotional states through voice tone and speed, and the linguistic elements used. This allows it to recognize emotions such as joy, sadness, and anger.

[0375] Subsequently, a data retrieval tool searches for appropriate knowledge based on the analyzed requests and emotional states. During this process, a generative AI model constructs the information necessary to generate a response. Finally, a response generation module organizes this information and shapes a personalized response that takes the user's emotions into consideration. The created response is then conveyed to the user as audio or visual information through a presentation device.

[0376] As a concrete example, consider a case where a user, in a tired voice, types, "Can you recommend a song that will cheer me up?" In this case, the system would determine that the user is fatigued, select and play positive music, and provide an encouraging message such as, "Let's relax together." The system might use prompts like the following:

[0377] User request: "Can you suggest some uplifting music?"

[0378] Emotion detection: Fatigue

[0379] Prompt: Consider the user's fatigue and suggest an uplifting music playlist, providing cheerful music to lift their spirits.

[0380] In this way, the system can provide users with a user-friendly and emotionally resonant experience.

[0381] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0382] Step 1:

[0383] The terminal receives voice or text input from the user. In the case of voice input, the terminal sends this voice data to a data conversion device, which converts it into text data. The output of this step is the converted text data.

[0384] Step 2:

[0385] The server uses a data analysis device to analyze the received text data and interpret the user's request. The input is text data, and natural language processing techniques are used to extract meaning. The output is the analyzed user request.

[0386] Step 3:

[0387] The server uses an emotion analysis engine to analyze the emotions contained in the text data. The input is the text data converted in step 1. It analyzes voice tone and linguistic indicators to extract the user's emotions. The output of this step is the identification result of the emotional state.

[0388] Step 4:

[0389] The server uses data retrieval tools to search for relevant information corresponding to the analyzed request and emotional state. The input used here is the analyzed user request and emotional state. Useful information is retrieved from databases and other sources, and the search results are provided as output.

[0390] Step 5:

[0391] The server uses a generative AI model to construct a response based on the retrieved information. This process generates an emotionally sensitive response by including emotional states as prompts. The input consists of search results and prompts, which are processed by the AI ​​model to produce a generated response as output.

[0392] Step 6:

[0393] The terminal receives the output from the response generation module and presents it to the user in audio or visual form using a presentation device. The input for this step is the response sentence constructed in step 5. The final output is the response presented in a format easily understood by the user.

[0394] 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.

[0395] 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.

[0396] 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.

[0397] [Third Embodiment]

[0398] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0399] 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.

[0400] 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).

[0401] 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.

[0402] 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.

[0403] 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).

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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".

[0410] This invention is a system that enables users to easily obtain information through information terminals such as smartphones. This system provides comprehensive support to users by coordinating an input device, a conversion means, an analysis means, a search means, a generation means, and an output device.

[0411] First, the user can input a request for information retrieval into the terminal using voice or text. In the case of voice input, the terminal sends the data to the server, where a conversion device converts the voice into text data.

[0412] The server analyzes this text data using parsing tools to understand the user's intent. Based on this understood intent, search tools collect necessary information using the network and internal databases.

[0413] Based on the collected information, the server generates a user-appropriate response through a generation mechanism. This response can be personalized based on the user's attributes and requests.

[0414] The terminal presents the final response in either voice or text. Voice output utilizes speech synthesis, while text output is displayed on the screen. This process allows elderly users and those unfamiliar with technology to intuitively obtain the necessary information.

[0415] For example, if a user voice-inputs "I want to know tomorrow's weather," the terminal sends this voice to the server, and a conversion means converts it into text. Then, an analysis means interprets the user's request as "getting a weather forecast," and a search means retrieves weather information. A generation means creates a response based on that information, such as "It's going to be sunny tomorrow," and the terminal conveys it to the user by voice. This allows the user to receive the information in an easy-to-understand way.

[0416] The following describes the processing flow.

[0417] Step 1:

[0418] The user enters their information request via voice or text. In the case of voice input, the device acquires voice data through the microphone. In the case of text input, it receives character data from the keyboard.

[0419] Step 2:

[0420] The device sends the acquired audio data to the server. The server uses a speech recognition engine to convert the audio data into corresponding text data.

[0421] Step 3:

[0422] The server analyzes the converted text data and inputs it into a generative AI model to understand the user's intent. The model recognizes the user's request and generates a specific information retrieval query.

[0423] Step 4:

[0424] Based on the recognized query, the server searches for the necessary information from the internet or internal databases. Relevant information is collected through the search method.

[0425] Step 5:

[0426] Based on the information collected by the server, a response is generated for the user. The generative AI model creates a response in natural language, and in some cases, it may be personalized according to the user's attributes.

[0427] Step 6:

[0428] The server sends the generated response to the terminal. The terminal receives this data and presents the response to the user using methods such as speech synthesis or text display. In the case of audio output, the audio is played through the speaker.

[0429] Step 7:

[0430] If the user requests further information or wishes to perform a different action, they can return to Step 1 and begin the next input. This process is repeated until the user obtains the information they need.

[0431] (Example 1)

[0432] 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."

[0433] The challenge is to enable users to efficiently acquire information through voice or text input and receive appropriate responses tailored to their individual needs. In particular, it is necessary to provide a system that allows even users unfamiliar with information technology to intuitively acquire information.

[0434] 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.

[0435] In this invention, the server includes data collection means, voice processing means, analysis means, information acquisition means, response generation means, and result output means. This makes it possible to retrieve necessary information from requests entered by the user in voice or text, and to provide responses in voice or visual form that are tailored to the individual characteristics based on the results.

[0436] "Data collection means" refers to a device or function for receiving requests from users in voice or text.

[0437] "Speech processing means" refers to technologies and programs for converting collected speech data into text data.

[0438] "Analysis means" refers to functions and processes for analyzing text data to determine the user's intentions and requests.

[0439] "Information acquisition means" refers to the process of searching for and acquiring necessary information from networks and databases based on the analysis results.

[0440] A "response generation means" refers to a program or function that constructs an appropriate response to the user based on the acquired information.

[0441] "Result output means" refers to a device or technology that presents the generated response to the user in audio or visual form.

[0442] In implementing this invention, a user can first request information acquisition using a terminal such as a smartphone. The user can input the request by voice or text, and in the case of voice input, the terminal sends the voice data to the server. The server converts the voice into text data using voice processing software. In this process, it is conceivable that speech recognition technology such as Google Cloud Speech-to-Text would be used.

[0443] The converted text data is analyzed by server-side analysis tools to understand the user's intent. Natural language processing techniques are used for this analysis, sometimes including models like Google BERT. This analysis helps to grasp the user's request and prepares the system for obtaining the necessary information in the next step.

[0444] To obtain information, the server collects the necessary data from the network and databases through information acquisition means. Search engines and APIs (e.g., weather forecast APIs) are used to collect relevant information based on user requests.

[0445] Based on the collected information, the server generates an appropriate response to the user using a response generation mechanism. OpenAI GPT-3, for example, may be used as the generation AI model for this response generation. Because the response is adjusted based on the user's attributes and characteristics, personalized information provision becomes possible.

[0446] Finally, the response sent from the server is presented to the user via the terminal's result output mechanism. If an audio response is required, speech synthesis software, such as Amazon Polly, is used, and the terminal screen is used for visual presentation.

[0447] For example, if a user inputs "I want to know tomorrow's weather" via voice, the prompt might be "Predict what information the user will request next and generate a response." Following this prompt, the server generates a specific response such as "It is expected to be sunny tomorrow" and provides that information to the user via the terminal. This system allows the user to smoothly obtain the information they need.

[0448] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0449] Step 1:

[0450] The user inputs information requests to a device such as a smartphone via voice or text. For example, the input might be a voice message saying, "I want to know tomorrow's weather." The input data is temporarily stored on the device.

[0451] Step 2:

[0452] When using voice input, the terminal sends the voice data to the server. The server uses voice processing software to convert this voice into text data. Specifically, it uses speech recognition technology to convert "I want to know tomorrow's weather" into the text "I want to know tomorrow's weather". This process converts the voice data into a parseable text format.

[0453] Step 3:

[0454] The server processes the converted text data using an analysis tool. This analysis tool utilizes natural language processing technology to understand the user's intent from the text. Based on the input text data, it extracts a specific request, such as "obtain weather forecast." This process includes keyword extraction and contextual analysis.

[0455] Step 4:

[0456] Based on the analyzed user intent, the server searches for the necessary information using information retrieval methods. In this step, it accesses networks and databases to obtain the required data, such as tomorrow's weather information from a weather forecast API. This collects the specific data needed to satisfy the user's request.

[0457] Step 5:

[0458] The server generates a response to the user using a response generation mechanism based on the collected information. This process uses a generative AI model and may use a prompt such as, "Predict what information the user will ask for next and generate a response." The response generated here would be a specific and natural sentence, such as, "It is expected to be sunny tomorrow."

[0459] Step 6:

[0460] The terminal presents the server-generated response to the user through a result output mechanism. If voice output is specified, speech synthesis software is used to produce a speech response, for example, "It is expected to be sunny tomorrow," which is then played for the user. If text output is specified, it is displayed as text on the terminal's screen. Ultimately, the user can receive a response to their request through either sight or sound.

[0461] (Application Example 1)

[0462] 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."

[0463] In modern cities, residents and tourists need to be able to quickly and appropriately access information about daily life and tourism. However, conventional systems struggle to personalize information based on users' geographical location and individual attributes. Furthermore, there is a need for enhanced systems that allow users to intuitively access information using voice interfaces. This is expected to significantly improve the user experience in cities.

[0464] 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.

[0465] In this invention, the server includes an input unit that receives voice or text input from a user, a conversion unit that converts the input voice into text data, an analysis unit that analyzes the text data to recognize the user's request, a search unit that searches for information based on the request, a generation unit that generates a response based on the information obtained by the search unit, a location information unit that obtains the user's geographical location information, and an output unit that presents the response generated based on the location information to the user. This enables the provision of fast and personalized information to the user based on location information.

[0466] An "input unit" is a device for receiving information acquisition requests from users in the form of voice or text.

[0467] A "conversion unit" is a device that converts audio data into text data.

[0468] An "analysis unit" is a device that analyzes text data and recognizes user requests.

[0469] A "search unit" is a device that searches for information based on the user's request.

[0470] A "generation unit" is a device that generates a response based on information acquired by the exploration unit.

[0471] A "location information unit" is a device used to acquire a user's geographical location information.

[0472] An "output unit" is a device that presents the generated response either audibly or visually.

[0473] The system for carrying out this invention is centered around a terminal device equipped with a user interface that accepts voice or text input. When the server receives voice input, it first uses speech recognition software (for example, Google Cloud Speech-to-Text) to convert the voice data into text data.

[0474] Next, the server parses this text data using a natural language processing API (e.g., Dialogflow) to identify the user's request. In this process, the server utilizes a location unit to obtain the user's geographical location. This location information is used to determine where the user is currently located and whether the requested information is relevant to that location.

[0475] After the analysis is complete, the server searches for information. Specifically, it uses a search unit to collect the requested information from the internet and local databases. Based on the information obtained from this search, a generation unit creates an appropriate response. This response is further personalized based on the user's attributes and location information.

[0476] Finally, the terminal uses an output unit to present a response. The response may be synthesized as speech or displayed as visual text on a screen. For example, if a user asks, "Are there any restaurants nearby?", the system will determine the user's current location and either respond verbally or display a list of nearby restaurants on the screen.

[0477] For example, if a user asks, "What events are currently taking place in a nearby park?", the server can determine the user's location via a location information unit, search for relevant event information, and generate a response such as, "There is currently a music festival taking place in a nearby park."

[0478] Example prompt: "Please provide the most relevant event information based on the user's current location and time of day."

[0479] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0480] Step 1:

[0481] The terminal accepts voice or text input from the user. Voice input is treated as audio data and immediately sent to the next processing step. Text input is passed directly as text data to the next step.

[0482] Step 2:

[0483] When the server receives voice input, it uses speech recognition software to convert the voice data into text data. Specifically, it forwards the voice input to the Google Cloud Speech-to-Text API and retrieves the corresponding string. In this step, the input is voice data, and the output is text data.

[0484] Step 3:

[0485] The server analyzes the generated text data using a natural language processing API to identify the user's request. Dialogflow is used for natural language processing. When analyzing the text data, the user's intent is clarified, and requests based on that intent are sent to the next step.

[0486] Step 4:

[0487] The server uses a location unit to obtain the user's geographical location. This location information is crucial data for determining which region the requested information relates to. In this step, location information is the input, and specific information about the user's current location is the output.

[0488] Step 5:

[0489] Based on the analyzed request and acquired location information, the server uses a search unit to collect necessary information from internet sources and databases. The collected information is specifically related to the user's request and is formatted as search results.

[0490] Step 6:

[0491] The server generates a response based on the search results. The generation unit uses Dialogflow or a similar system to assemble the most suitable response for the user. This response is personalized based on the user's requests, location, and attributes.

[0492] Step 7:

[0493] The terminal receives the generated response and uses an output unit to present the response to the user as audio or text data. Specifically, it generates audio using a speech synthesis API and outputs it through the speaker or displays it as text on the screen. The output in this step presents information in a format that is easy for the user to understand.

[0494] 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.

[0495] The present invention is a system that takes user emotions into consideration, receiving user input, recognizing emotions using an emotion engine, and providing personalized responses to achieve more intuitive and human-like interaction. This system includes an input device that accepts voice or text input, a conversion means for converting voice data, an analysis means for analyzing data, a search means for retrieving information, a generation means for generating responses, an output device for presenting responses, and an emotion engine for recognizing emotions.

[0496] When a user inputs information via voice or text into a device such as a smartphone, the device records the input and, in the case of voice input, converts it into text data using a conversion device. The server analyzes this text data using an analysis device to recognize the user's request.

[0497] Furthermore, an emotion engine extracts emotions from the user's input. This emotion engine recognizes emotions such as joy, sadness, and anger that the user is feeling by analyzing voice tone, speed, and linguistic indicators.

[0498] Based on the user's request obtained by the analysis means and the emotion recognized by the emotion engine, the server uses the search means to collect appropriate information. The generation means considers this information and the emotion to construct an appropriate response that matches the user's mood.

[0499] Finally, the constructed response is presented to the user by the device either as voice or text. For example, if the user asks in a sad voice, "What's the weather like today?", the system generates a caring message such as, "It looks like it's going to be sunny today, so cheer up!" and delivers it aloud. This allows the user to feel reassured and comforted. In this way, the present invention can provide users with more human-like interaction and emotionally responsive support.

[0500] The following describes the processing flow.

[0501] Step 1:

[0502] The user enters an information request into the terminal via voice or text. In the case of voice input, the terminal captures the voice data through the microphone. In the case of text input, it receives the string data from the keyboard.

[0503] Step 2:

[0504] The device sends the captured audio data to the server. The server uses a speech recognition engine to convert the audio into text data. This process transforms the audio into usable text information.

[0505] Step 3:

[0506] The server analyzes the converted character data using an analysis tool to recognize the user's request. The analysis tool uses a generative AI model to determine what the user's request is.

[0507] Step 4:

[0508] While the server is analyzing the data, it uses an emotion engine to detect the user's emotions. The emotion engine analyzes the user's input, including their tone of voice, speed, and word choice, to estimate their emotional state.

[0509] Step 5:

[0510] Based on the requests obtained by the analysis tools and the emotional information detected by the emotion engine, the server uses search tools to retrieve relevant information from the web and databases. This ensures that information aligned with the user's requests is gathered.

[0511] Step 6:

[0512] The server considers the information it collects and the user's emotions, and constructs an appropriate response using a generation method. The generation AI model customizes the response using a tone and expression that is appropriate for the user's emotions.

[0513] Step 7:

[0514] The server sends the generated response to the terminal. The terminal converts the received response into speech using speech synthesis technology and either plays it to the user through the speaker or displays it as text on the screen.

[0515] Step 8:

[0516] The user receives a response from the system and asks further questions if necessary. The system continues this process, responding to the user's information requests.

[0517] (Example 2)

[0518] 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."

[0519] Conventional interface systems have a problem in that their responses to user input are simplistic and lack human-like qualities that take emotions into consideration, resulting in users perceiving them as mechanical. In particular, it has been difficult to provide responses that are sensitive to the user's emotions.

[0520] 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.

[0521] In this invention, the server includes emotion recognition means for extracting emotions from user input, search means for retrieving information based on the user's requests and emotions, and response generation means for generating a response that takes the retrieved information and emotions into consideration. This makes it possible to construct and provide to the user a more humane and approachable response that reflects the user's emotions.

[0522] An "input device" is a device for receiving voice or text input from a user.

[0523] A "conversion device" is a device that converts input audio into text data.

[0524] An "analysis device" is a device that analyzes received text data to recognize the user's requests.

[0525] An "emotion recognition device" is a device that extracts emotions from user input.

[0526] A "search device" is a device used to retrieve necessary information based on analyzed requests and extracted emotions.

[0527] A "response generation device" is a device that generates a response to present to the user, taking into account the information and emotions obtained.

[0528] An "output device" is a device that presents the generated response to the user.

[0529] This invention is a system that generates responses while considering the user's emotions, and achieves more intuitive and human-like interaction based on user input. The system can be implemented using the following hardware and software.

[0530] When users input information via voice or text, they use devices such as smartphones or personal computers. These devices function as input devices, and in the case of voice input, they use a voice recognition cloud service (for example, a common voice recognition API) as a conversion device to convert voice data into text data.

[0531] Subsequently, the server uses a natural language processing library (e.g., an open-source natural language processing toolkit) as an analysis device to analyze the text data and extract the user's request. At the same time, it uses an emotion analysis service (a general language analysis API) as an emotion recognition device to identify the user's emotions from their voice tone and input content.

[0532] Based on the information obtained by the analysis device and the emotion recognition device, the server uses a database search engine (e.g., a distributed search engine) as a search device to collect appropriate information. This activates a response generation device that generates a response based on the requested information and emotion. The generation device uses a generation AI model (e.g., a general-purpose AI model) to construct an emotion-appropriate response.

[0533] Finally, the terminal acts as an output device, presenting the generated response in voice or text using a speech synthesis service (e.g., a common speech synthesis API). This process allows the user to receive a friendly, rather than mechanical, response.

[0534] For example, if a user asks "What's the weather like today?" in a sad voice, the system can generate and deliver a comforting message such as "It looks like it's going to be sunny today, so cheer up!" An example of a prompt might be "Give a cheering response when the user asks about the weather in a sad voice."

[0535] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0536] Step 1:

[0537] The user inputs information via voice or text into a device such as a smartphone. The device, acting as an input device, receives this input. The input here is voice data or text data spoken by the user, such as "Tell me the weather tomorrow." The voice data is then converted into text data using a speech recognition API. The output is the converted text data.

[0538] Step 2:

[0539] The server receives the converted character data and performs analysis using a natural language processing library as its parsing device. This analysis identifies the user's request from the character data. By using the converted character data as input and identifying the request, the server can obtain a specific request, such as "weather information inquiry," as output.

[0540] Step 3:

[0541] The server, acting as an emotion recognition device, simultaneously uses an emotion analysis API to analyze the user's emotions from the input data. The input includes voice tone and text, and based on this, it identifies emotions (joy, sadness, anger, etc.) as output. In this example, the output indicates that the user is sad.

[0542] Step 4:

[0543] The server uses a database search engine as its search mechanism to retrieve the necessary information based on the collected requests and sentiment information. The input is the aforementioned request content and sentiment information, and the output is the search results based on this. In this case, the information collected is "Tomorrow's weather will be sunny."

[0544] Step 5:

[0545] The server utilizes a generative AI model as a response generator to produce responses that take into account the information and emotions collected by the search device. The inputs used are search results and emotion information. For example, considering both "sunny" and "the user is sad," it might generate the text response, "It looks like it will be sunny tomorrow, so cheer up!" This is the output of this step.

[0546] Step 6:

[0547] The terminal uses an output device to either play the generated response as audio using a speech synthesis API or display it as text on the screen. The input is the generated response text, which is delivered to the user either as audio output in a soft tone or as text output on the screen. This output is the terminal's final response to the user.

[0548] (Application Example 2)

[0549] 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."

[0550] When users interact with systems, they sometimes respond coldly and mechanically without adequately considering the user's emotions. This problem is particularly important in consumer devices such as home robots, where providing a more user-friendly and enriching experience is crucial. Conventional systems struggle to construct appropriate responses that reflect the user's emotions, often resulting in user dissatisfaction.

[0551] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0552] In this invention, the server includes a reception module that receives information from the user, a data conversion device that converts the input voice into text data, and a data analysis device that analyzes the text data to interpret the user's request. This makes it possible to provide a more human-like interaction that takes the user's emotions into consideration.

[0553] A "reception module for receiving user information" is a component that is responsible for receiving voice and text data input from users.

[0554] A "data conversion device" is a device that performs the process of converting input audio data into text data.

[0555] A "data analysis device" is a device that interprets converted text data and performs processing to understand user requests.

[0556] A "data retrieval tool" is a means of searching for necessary information and knowledge from databases, etc., based on user requests.

[0557] A "response generation module" is a module that has the function of composing a response to the user based on the information that has been searched.

[0558] A "sentiment analysis engine" is an engine that detects emotions from a user's voice or text and evaluates their emotional state, such as joy or sadness.

[0559] A "presentation device" is a device that outputs the generated response to the user as audio or visual information.

[0560] The program for implementing this system is designed to run on a home robot. The user provides input directly to the robot via voice or text. The terminal transmits this input, and in the case of voice input, a data conversion device converts it into text data. The converted text data is sent to a data analysis device, where the user's request is interpreted.

[0561] Next, an emotion analysis engine is implemented to detect emotions from user input. Specifically, it grasps emotional states through voice tone and speed, and the linguistic elements used. This allows it to recognize emotions such as joy, sadness, and anger.

[0562] Subsequently, a data retrieval tool searches for appropriate knowledge based on the analyzed requests and emotional states. During this process, a generative AI model constructs the information necessary to generate a response. Finally, a response generation module organizes this information and shapes a personalized response that takes the user's emotions into consideration. The created response is then conveyed to the user as audio or visual information through a presentation device.

[0563] As a concrete example, consider a case where a user, in a tired voice, types, "Can you recommend a song that will cheer me up?" In this case, the system would determine that the user is fatigued, select and play positive music, and provide an encouraging message such as, "Let's relax together." The system might use prompts like the following:

[0564] User request: "Can you suggest some uplifting music?"

[0565] Emotion detection: Fatigue

[0566] Prompt: Consider the user's fatigue and suggest an uplifting music playlist, providing cheerful music to lift their spirits.

[0567] In this way, the system can provide users with a user-friendly and emotionally resonant experience.

[0568] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0569] Step 1:

[0570] The terminal receives voice or text input from the user. In the case of voice input, the terminal sends this voice data to a data conversion device, which converts it into text data. The output of this step is the converted text data.

[0571] Step 2:

[0572] The server uses a data analysis device to analyze the received text data and interpret the user's request. The input is text data, and natural language processing techniques are used to extract meaning. The output is the analyzed user request.

[0573] Step 3:

[0574] The server uses an emotion analysis engine to analyze the emotions contained in the text data. The input is the text data converted in step 1. It analyzes voice tone and linguistic indicators to extract the user's emotions. The output of this step is the identification result of the emotional state.

[0575] Step 4:

[0576] The server uses data retrieval tools to search for relevant information corresponding to the analyzed request and emotional state. The input used here is the analyzed user request and emotional state. Useful information is retrieved from databases and other sources, and the search results are provided as output.

[0577] Step 5:

[0578] The server uses a generative AI model to construct a response based on the retrieved information. This process generates an emotionally sensitive response by including emotional states as prompts. The input consists of search results and prompts, which are processed by the AI ​​model to produce a generated response as output.

[0579] Step 6:

[0580] The terminal receives the output from the response generation module and presents it to the user in audio or visual form using a presentation device. The input for this step is the response sentence constructed in step 5. The final output is the response presented in a format easily understood by the user.

[0581] 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.

[0582] 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.

[0583] 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.

[0584] [Fourth Embodiment]

[0585] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0586] 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.

[0587] 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).

[0588] 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.

[0589] 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.

[0590] 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).

[0591] 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.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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".

[0598] This invention is a system that enables users to easily obtain information through information terminals such as smartphones. This system provides comprehensive support to users by coordinating an input device, a conversion means, an analysis means, a search means, a generation means, and an output device.

[0599] First, the user can input a request for information retrieval into the terminal using voice or text. In the case of voice input, the terminal sends the data to the server, where a conversion device converts the voice into text data.

[0600] The server analyzes this text data using parsing tools to understand the user's intent. Based on this understood intent, search tools collect necessary information using the network and internal databases.

[0601] Based on the collected information, the server generates a user-appropriate response through a generation mechanism. This response can be personalized based on the user's attributes and requests.

[0602] The terminal presents the final response in either voice or text. Voice output utilizes speech synthesis, while text output is displayed on the screen. This process allows elderly users and those unfamiliar with technology to intuitively obtain the necessary information.

[0603] For example, if a user voice-inputs "I want to know tomorrow's weather," the terminal sends this voice to the server, and a conversion means converts it into text. Then, an analysis means interprets the user's request as "getting a weather forecast," and a search means retrieves weather information. A generation means creates a response based on that information, such as "It's going to be sunny tomorrow," and the terminal conveys it to the user by voice. This allows the user to receive the information in an easy-to-understand way.

[0604] The following describes the processing flow.

[0605] Step 1:

[0606] The user enters their information request via voice or text. In the case of voice input, the device acquires voice data through the microphone. In the case of text input, it receives character data from the keyboard.

[0607] Step 2:

[0608] The device sends the acquired audio data to the server. The server uses a speech recognition engine to convert the audio data into corresponding text data.

[0609] Step 3:

[0610] The server analyzes the converted text data and inputs it into a generative AI model to understand the user's intent. The model recognizes the user's request and generates a specific information retrieval query.

[0611] Step 4:

[0612] Based on the recognized query, the server searches for the necessary information from the internet or internal databases. Relevant information is collected through the search method.

[0613] Step 5:

[0614] Based on the information collected by the server, a response is generated for the user. The generative AI model creates a response in natural language, and in some cases, it may be personalized according to the user's attributes.

[0615] Step 6:

[0616] The server sends the generated response to the terminal. The terminal receives this data and presents the response to the user using methods such as speech synthesis or text display. In the case of audio output, the audio is played through the speaker.

[0617] Step 7:

[0618] If the user requests further information or wishes to perform a different action, they can return to Step 1 and begin the next input. This process is repeated until the user obtains the information they need.

[0619] (Example 1)

[0620] 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".

[0621] The challenge is to enable users to efficiently acquire information through voice or text input and receive appropriate responses tailored to their individual needs. In particular, it is necessary to provide a system that allows even users unfamiliar with information technology to intuitively acquire information.

[0622] 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.

[0623] In this invention, the server includes data collection means, voice processing means, analysis means, information acquisition means, response generation means, and result output means. This makes it possible to retrieve necessary information from requests entered by the user in voice or text, and to provide responses in voice or visual form that are tailored to the individual characteristics based on the results.

[0624] "Data collection means" refers to a device or function for receiving requests from users in voice or text.

[0625] "Speech processing means" refers to technologies and programs for converting collected speech data into text data.

[0626] "Analysis means" refers to functions and processes for analyzing text data to determine the user's intentions and requests.

[0627] "Information acquisition means" refers to the process of searching for and acquiring necessary information from networks and databases based on the analysis results.

[0628] A "response generation means" refers to a program or function that constructs an appropriate response to the user based on the acquired information.

[0629] "Result output means" refers to a device or technology that presents the generated response to the user in audio or visual form.

[0630] In implementing this invention, a user can first request information acquisition using a terminal such as a smartphone. The user can input the request by voice or text, and in the case of voice input, the terminal sends the voice data to the server. The server converts the voice into text data using voice processing software. In this process, it is conceivable that speech recognition technology such as Google Cloud Speech-to-Text would be used.

[0631] The converted text data is analyzed by server-side analysis tools to understand the user's intent. Natural language processing techniques are used for this analysis, sometimes including models like Google BERT. This analysis helps to grasp the user's request and prepares the system for obtaining the necessary information in the next step.

[0632] To obtain information, the server collects the necessary data from the network and databases through information acquisition means. Search engines and APIs (e.g., weather forecast APIs) are used to collect relevant information based on user requests.

[0633] Based on the collected information, the server generates an appropriate response to the user using a response generation mechanism. OpenAI GPT-3, for example, may be used as the generation AI model for this response generation. Because the response is adjusted based on the user's attributes and characteristics, personalized information provision becomes possible.

[0634] Finally, the response sent from the server is presented to the user via the terminal's result output mechanism. If an audio response is required, speech synthesis software, such as Amazon Polly, is used, and the terminal screen is used for visual presentation.

[0635] For example, if a user inputs "I want to know tomorrow's weather" via voice, the prompt might be "Predict what information the user will request next and generate a response." Following this prompt, the server generates a specific response such as "It is expected to be sunny tomorrow" and provides that information to the user via the terminal. This system allows the user to smoothly obtain the information they need.

[0636] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0637] Step 1:

[0638] The user inputs information requests to a device such as a smartphone via voice or text. For example, the input might be a voice message saying, "I want to know tomorrow's weather." The input data is temporarily stored on the device.

[0639] Step 2:

[0640] When using voice input, the terminal sends the voice data to the server. The server uses voice processing software to convert this voice into text data. Specifically, it uses speech recognition technology to convert "I want to know tomorrow's weather" into the text "I want to know tomorrow's weather". This process converts the voice data into a parseable text format.

[0641] Step 3:

[0642] The server processes the converted text data using an analysis tool. This analysis tool utilizes natural language processing technology to understand the user's intent from the text. Based on the input text data, it extracts a specific request, such as "obtain weather forecast." This process includes keyword extraction and contextual analysis.

[0643] Step 4:

[0644] Based on the analyzed user intent, the server searches for the necessary information using information retrieval methods. In this step, it accesses networks and databases to obtain the required data, such as tomorrow's weather information from a weather forecast API. This collects the specific data needed to satisfy the user's request.

[0645] Step 5:

[0646] The server generates a response to the user using a response generation mechanism based on the collected information. This process uses a generative AI model and may use a prompt such as, "Predict what information the user will ask for next and generate a response." The response generated here would be a specific and natural sentence, such as, "It is expected to be sunny tomorrow."

[0647] Step 6:

[0648] The terminal presents the server-generated response to the user through a result output mechanism. If voice output is specified, speech synthesis software is used to produce a speech response, for example, "It is expected to be sunny tomorrow," which is then played for the user. If text output is specified, it is displayed as text on the terminal's screen. Ultimately, the user can receive a response to their request through either sight or sound.

[0649] (Application Example 1)

[0650] 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".

[0651] In modern cities, residents and tourists need to be able to quickly and appropriately access information about daily life and tourism. However, conventional systems struggle to personalize information based on users' geographical location and individual attributes. Furthermore, there is a need for enhanced systems that allow users to intuitively access information using voice interfaces. This is expected to significantly improve the user experience in cities.

[0652] 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.

[0653] In this invention, the server includes an input unit that receives voice or text input from a user, a conversion unit that converts the input voice into text data, an analysis unit that analyzes the text data to recognize the user's request, a search unit that searches for information based on the request, a generation unit that generates a response based on the information obtained by the search unit, a location information unit that obtains the user's geographical location information, and an output unit that presents the response generated based on the location information to the user. This enables the provision of fast and personalized information to the user based on location information.

[0654] An "input unit" is a device for receiving information acquisition requests from users in the form of voice or text.

[0655] A "conversion unit" is a device that converts audio data into text data.

[0656] An "analysis unit" is a device that analyzes text data and recognizes user requests.

[0657] A "search unit" is a device that searches for information based on the user's request.

[0658] A "generation unit" is a device that generates a response based on information acquired by the exploration unit.

[0659] A "location information unit" is a device used to acquire a user's geographical location information.

[0660] An "output unit" is a device that presents the generated response either audibly or visually.

[0661] The system for carrying out this invention is centered around a terminal device equipped with a user interface that accepts voice or text input. When the server receives voice input, it first uses speech recognition software (for example, Google Cloud Speech-to-Text) to convert the voice data into text data.

[0662] Next, the server parses this text data using a natural language processing API (e.g., Dialogflow) to identify the user's request. In this process, the server utilizes a location unit to obtain the user's geographical location. This location information is used to determine where the user is currently located and whether the requested information is relevant to that location.

[0663] After the analysis is complete, the server searches for information. Specifically, it uses a search unit to collect the requested information from the internet and local databases. Based on the information obtained from this search, a generation unit creates an appropriate response. This response is further personalized based on the user's attributes and location information.

[0664] Finally, the terminal uses an output unit to present a response. The response may be synthesized as speech or displayed as visual text on a screen. For example, if a user asks, "Are there any restaurants nearby?", the system will determine the user's current location and either respond verbally or display a list of nearby restaurants on the screen.

[0665] For example, if a user asks, "What events are currently taking place in a nearby park?", the server can determine the user's location via a location information unit, search for relevant event information, and generate a response such as, "There is currently a music festival taking place in a nearby park."

[0666] Example prompt: "Please provide the most relevant event information based on the user's current location and time of day."

[0667] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0668] Step 1:

[0669] The terminal accepts voice or text input from the user. Voice input is treated as audio data and immediately sent to the next processing step. Text input is passed directly as text data to the next step.

[0670] Step 2:

[0671] When the server receives voice input, it uses speech recognition software to convert the voice data into text data. Specifically, it forwards the voice input to the Google Cloud Speech-to-Text API and retrieves the corresponding string. The input for this step is voice data, and the output is text data.

[0672] Step 3:

[0673] The server analyzes the generated text data using a natural language processing API to identify the user's request. Dialogflow is used for natural language processing. When analyzing the text data, the user's intent is clarified, and requests based on that intent are sent to the next step.

[0674] Step 4:

[0675] The server uses a location unit to obtain the user's geographical location. This location information is crucial data for determining which region the requested information relates to. In this step, location information is the input, and specific information about the user's current location is the output.

[0676] Step 5:

[0677] Based on the analyzed request and acquired location information, the server uses a search unit to collect necessary information from internet sources and databases. The collected information is specifically related to the user's request and is formatted as search results.

[0678] Step 6:

[0679] The server generates a response based on the search results. The generation unit uses Dialogflow or a similar system to assemble the most suitable response for the user. This response is personalized based on the user's requests, location, and attributes.

[0680] Step 7:

[0681] The terminal receives the generated response and uses an output unit to present the response to the user as audio or text data. Specifically, it generates audio using a speech synthesis API and outputs it through the speaker or displays it as text on the screen. The output in this step presents information in a format that is easy for the user to understand.

[0682] 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.

[0683] The present invention is a system that takes user emotions into consideration, receiving user input, recognizing emotions using an emotion engine, and providing personalized responses to achieve more intuitive and human-like interaction. This system includes an input device that accepts voice or text input, a conversion means for converting voice data, an analysis means for analyzing data, a search means for retrieving information, a generation means for generating responses, an output device for presenting responses, and an emotion engine for recognizing emotions.

[0684] When a user inputs information via voice or text into a device such as a smartphone, the device records the input and, in the case of voice input, converts it into text data using a conversion device. The server analyzes this text data using an analysis device to recognize the user's request.

[0685] Furthermore, an emotion engine extracts emotions from the user's input. This emotion engine recognizes emotions such as joy, sadness, and anger that the user is feeling by analyzing voice tone, speed, and linguistic indicators.

[0686] Based on the user's request obtained by the analysis means and the emotion recognized by the emotion engine, the server uses the search means to collect appropriate information. The generation means considers this information and the emotion to construct an appropriate response that matches the user's mood.

[0687] Finally, the constructed response is presented to the user by the device either as voice or text. For example, if the user asks in a sad voice, "What's the weather like today?", the system generates a caring message such as, "It looks like it's going to be sunny today, so cheer up!" and delivers it aloud. This allows the user to feel reassured and comforted. In this way, the present invention can provide users with more human-like interaction and emotionally responsive support.

[0688] The following describes the processing flow.

[0689] Step 1:

[0690] The user enters an information request into the terminal via voice or text. In the case of voice input, the terminal captures the voice data through the microphone. In the case of text input, it receives the string data from the keyboard.

[0691] Step 2:

[0692] The device sends the captured audio data to the server. The server uses a speech recognition engine to convert the audio into text data. This process transforms the audio into usable text information.

[0693] Step 3:

[0694] The server analyzes the converted character data using an analysis tool to recognize the user's request. The analysis tool uses a generative AI model to determine what the user's request is.

[0695] Step 4:

[0696] While the server is analyzing the data, it uses an emotion engine to detect the user's emotions. The emotion engine analyzes the user's input, including their tone of voice, speed, and word choice, to estimate their emotional state.

[0697] Step 5:

[0698] Based on the requests obtained by the analysis tools and the emotional information detected by the emotion engine, the server uses search tools to retrieve relevant information from the web and databases. This ensures that information aligned with the user's requests is gathered.

[0699] Step 6:

[0700] The server considers the information it collects and the user's emotions, and constructs an appropriate response using a generation method. The generation AI model customizes the response using a tone and expression that is appropriate for the user's emotions.

[0701] Step 7:

[0702] The server sends the generated response to the terminal. The terminal converts the received response into speech using speech synthesis technology and either plays it to the user through the speaker or displays it as text on the screen.

[0703] Step 8:

[0704] The user receives a response from the system and asks further questions if necessary. The system continues this process, responding to the user's information requests.

[0705] (Example 2)

[0706] 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".

[0707] Conventional interface systems have a problem in that their responses to user input are simplistic and lack human-like qualities that take emotions into consideration, resulting in users perceiving them as mechanical. In particular, it has been difficult to provide responses that are sensitive to the user's emotions.

[0708] 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.

[0709] In this invention, the server includes emotion recognition means for extracting emotions from user input, search means for retrieving information based on the user's requests and emotions, and response generation means for generating a response that takes the retrieved information and emotions into consideration. This makes it possible to construct and provide to the user a more humane and approachable response that reflects the user's emotions.

[0710] An "input device" is a device for receiving voice or text input from a user.

[0711] A "conversion device" is a device that converts input audio into text data.

[0712] An "analysis device" is a device that analyzes received text data to recognize the user's requests.

[0713] An "emotion recognition device" is a device that extracts emotions from user input.

[0714] A "search device" is a device used to retrieve necessary information based on analyzed requests and extracted emotions.

[0715] A "response generation device" is a device that generates a response to present to the user, taking into account the information and emotions obtained.

[0716] An "output device" is a device that presents the generated response to the user.

[0717] This invention is a system that generates responses while considering the user's emotions, and achieves more intuitive and human-like interaction based on user input. The system can be implemented using the following hardware and software.

[0718] When users input information via voice or text, they use devices such as smartphones or personal computers. These devices function as input devices, and in the case of voice input, they use a voice recognition cloud service (for example, a common voice recognition API) as a conversion device to convert voice data into text data.

[0719] Subsequently, the server uses a natural language processing library (e.g., an open-source natural language processing toolkit) as an analysis device to analyze the text data and extract the user's request. At the same time, it uses an emotion analysis service (a general language analysis API) as an emotion recognition device to identify the user's emotions from their voice tone and input content.

[0720] Based on the information obtained by the analysis device and the emotion recognition device, the server uses a database search engine (e.g., a distributed search engine) as a search device to collect appropriate information. This activates a response generation device that generates a response based on the requested information and emotion. The generation device uses a generation AI model (e.g., a general-purpose AI model) to construct an emotion-appropriate response.

[0721] Finally, the terminal acts as an output device, presenting the generated response in voice or text using a speech synthesis service (e.g., a common speech synthesis API). This process allows the user to receive a friendly, rather than mechanical, response.

[0722] For example, if a user asks "What's the weather like today?" in a sad voice, the system can generate and deliver a comforting message such as "It looks like it's going to be sunny today, so cheer up!" An example of a prompt might be "Give a cheering response when the user asks about the weather in a sad voice."

[0723] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0724] Step 1:

[0725] The user inputs information via voice or text into a device such as a smartphone. The device, acting as an input device, receives this input. The input here is voice data or text data spoken by the user, such as "Tell me the weather tomorrow." The voice data is then converted into text data using a speech recognition API. The output is the converted text data.

[0726] Step 2:

[0727] The server receives the converted character data and performs analysis using a natural language processing library as its parsing device. This analysis identifies the user's request from the character data. By using the converted character data as input and identifying the request, the server can obtain a specific request, such as "weather information inquiry," as output.

[0728] Step 3:

[0729] The server, acting as an emotion recognition device, simultaneously uses an emotion analysis API to analyze the user's emotions from the input data. The input includes voice tone and text, and based on this, it identifies emotions (joy, sadness, anger, etc.) as output. In this example, the output indicates that the user is sad.

[0730] Step 4:

[0731] The server uses a database search engine as its search mechanism to retrieve the necessary information based on the collected requests and sentiment information. The input is the aforementioned request content and sentiment information, and the output is the search results based on this. In this case, the information collected is "Tomorrow's weather will be sunny."

[0732] Step 5:

[0733] The server utilizes a generative AI model as a response generator to produce responses that take into account the information and emotions collected by the search device. The inputs used are search results and emotion information. For example, considering both "sunny" and "the user is sad," it might generate the text response, "It looks like it will be sunny tomorrow, so cheer up!" This is the output of this step.

[0734] Step 6:

[0735] The terminal uses an output device to either play the generated response as audio using a speech synthesis API or display it as text on the screen. The input is the generated response text, which is delivered to the user either as audio output in a soft tone or as text output on the screen. This output is the terminal's final response to the user.

[0736] (Application Example 2)

[0737] 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".

[0738] When users interact with systems, they sometimes respond coldly and mechanically without adequately considering the user's emotions. This problem is particularly important in consumer devices such as home robots, where providing a more user-friendly and enriching experience is crucial. Conventional systems struggle to construct appropriate responses that reflect the user's emotions, often resulting in user dissatisfaction.

[0739] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0740] In this invention, the server includes a reception module that receives information from the user, a data conversion device that converts the input voice into text data, and a data analysis device that analyzes the text data to interpret the user's request. This makes it possible to provide a more human-like interaction that takes the user's emotions into consideration.

[0741] A "reception module for receiving user information" is a component that is responsible for receiving voice and text data input from users.

[0742] A "data conversion device" is a device that performs the process of converting input audio data into text data.

[0743] A "data analysis device" is a device that interprets converted text data and performs processing to understand user requests.

[0744] A "data retrieval tool" is a means of searching for necessary information and knowledge from databases, etc., based on user requests.

[0745] A "response generation module" is a module that has the function of composing a response to the user based on the information that has been searched.

[0746] A "sentiment analysis engine" is an engine that detects emotions from a user's voice or text and evaluates their emotional state, such as joy or sadness.

[0747] A "presentation device" is a device that outputs the generated response to the user as audio or visual information.

[0748] The program for implementing this system is designed to run on a home robot. The user provides input directly to the robot via voice or text. The terminal transmits this input, and in the case of voice input, a data conversion device converts it into text data. The converted text data is sent to a data analysis device, where the user's request is interpreted.

[0749] Next, an emotion analysis engine is implemented to detect emotions from user input. Specifically, it grasps emotional states through voice tone and speed, and the linguistic elements used. This allows it to recognize emotions such as joy, sadness, and anger.

[0750] Subsequently, a data retrieval tool searches for appropriate knowledge based on the analyzed requests and emotional states. During this process, a generative AI model constructs the information necessary to generate a response. Finally, a response generation module organizes this information and shapes a personalized response that takes the user's emotions into consideration. The created response is then conveyed to the user as audio or visual information through a presentation device.

[0751] As a concrete example, consider a case where a user, in a tired voice, types, "Can you recommend a song that will cheer me up?" In this case, the system would determine that the user is fatigued, select and play positive music, and provide an encouraging message such as, "Let's relax together." The system might use prompts like the following:

[0752] User request: "Can you suggest some uplifting music?"

[0753] Emotion detection: Fatigue

[0754] Prompt: Consider the user's fatigue and suggest an uplifting music playlist, providing cheerful music to lift their spirits.

[0755] In this way, the system can provide users with a user-friendly and emotionally resonant experience.

[0756] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0757] Step 1:

[0758] The terminal receives voice or text input from the user. In the case of voice input, the terminal sends this voice data to a data conversion device, which converts it into text data. The output of this step is the converted text data.

[0759] Step 2:

[0760] The server uses a data analysis device to analyze the received text data and interpret the user's request. The input is text data, and natural language processing techniques are used to extract meaning. The output is the analyzed user request.

[0761] Step 3:

[0762] The server uses an emotion analysis engine to analyze the emotions contained in the text data. The input is the text data converted in step 1. It analyzes voice tone and linguistic indicators to extract the user's emotions. The output of this step is the identification result of the emotional state.

[0763] Step 4:

[0764] The server uses data retrieval tools to search for relevant information corresponding to the analyzed request and emotional state. The input used here is the analyzed user request and emotional state. Useful information is retrieved from databases and other sources, and the search results are provided as output.

[0765] Step 5:

[0766] The server uses a generative AI model to construct a response based on the retrieved information. This process generates an emotionally sensitive response by including emotional states as prompts. The input consists of search results and prompts, which are processed by the AI ​​model to produce a generated response as output.

[0767] Step 6:

[0768] The terminal receives the output from the response generation module and presents it to the user in audio or visual form using a presentation device. The input for this step is the response sentence constructed in step 5. The final output is the response presented in a format easily understood by the user.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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."

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0790] The following is further disclosed regarding the embodiments described above.

[0791] (Claim 1)

[0792] An input device that receives voice or text input from the user,

[0793] A conversion means for converting input audio into text data,

[0794] An analysis means for analyzing the aforementioned character data and recognizing the user's request,

[0795] A search means for retrieving information based on the aforementioned request,

[0796] A generation means that generates a response based on the information obtained by the search means,

[0797] An output device that presents the generated response to the user,

[0798] A system that includes this.

[0799] (Claim 2)

[0800] The system according to claim 1, wherein the analysis means generates a personalized response that takes into account information corresponding to the user's attributes.

[0801] (Claim 3)

[0802] The system according to claim 1, wherein the output device presents the generated response audibly or visually.

[0803] "Example 1"

[0804] (Claim 1)

[0805] A data collection means for receiving voice or text requests from users,

[0806] A speech processing means for converting speech data into text data,

[0807] An analytical means that processes text data to determine the user's intent,

[0808] Information acquisition means that acquires information based on the analysis results,

[0809] A response generation means that generates a response based on data acquired by an information acquisition means,

[0810] A result output means that presents the generated response to the user,

[0811] A system that includes this.

[0812] (Claim 2)

[0813] The system according to claim 1, wherein the analysis means adjusts the response based on the user's characteristics.

[0814] (Claim 3)

[0815] The system according to claim 1, wherein the result output means communicates the generated response to the user audibly or visually.

[0816] "Application Example 1"

[0817] (Claim 1)

[0818] An input unit that receives voice or text input from the user,

[0819] A conversion unit that converts input audio into text data,

[0820] An analysis unit that analyzes the aforementioned character data to recognize the user's request,

[0821] A search unit that searches for information based on the aforementioned request,

[0822] A generation unit that generates a response based on the information obtained by the aforementioned search unit,

[0823] A location information unit that acquires the user's geographical location information,

[0824] An output unit that presents a response generated based on the aforementioned location information to the user,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1, wherein the analysis unit generates a personalized response that takes into account information corresponding to the user's characteristics.

[0828] (Claim 3)

[0829] The system according to claim 1, wherein the output unit presents the generated response audibly or visually, and presents appropriate information based on the user's geographical location.

[0830] "Example 2 of combining an emotion engine"

[0831] (Claim 1)

[0832] An input device that receives voice or text input from the user,

[0833] A conversion device that converts input audio into text data,

[0834] An analysis device that analyzes the aforementioned character data to recognize the user's request,

[0835] An emotion recognition device that extracts emotions from user input,

[0836] A search device that retrieves information based on the aforementioned requests and emotions,

[0837] A response generation device that generates a response considering the information and emotions acquired by the aforementioned search device,

[0838] An output device that presents the generated response to the user,

[0839] A system that includes this.

[0840] (Claim 2)

[0841] The system according to claim 1, wherein the analysis device generates a personalized response taking into account the user's attributes and emotions.

[0842] (Claim 3)

[0843] The system according to claim 1, wherein the output device presents the generated response audibly or visually.

[0844] "Application example 2 when combining with an emotional engine"

[0845] (Claim 1)

[0846] A reception module that receives information from users,

[0847] A data conversion device that converts input audio into text data,

[0848] A data analysis device that analyzes the aforementioned text data and interprets the user's request,

[0849] A data retrieval means for retrieving knowledge based on the aforementioned requirements,

[0850] A response generation module that constructs a response based on the knowledge obtained by the data retrieval means,

[0851] A sentiment analysis engine that detects the user's emotions,

[0852] A presentation device that presents a response generated based on the aforementioned emotion analysis engine,

[0853] A system that includes this.

[0854] (Claim 2)

[0855] The system according to claim 1, wherein the data analysis device generates an individualized response based on the user's emotional state and attributes.

[0856] (Claim 3)

[0857] The system according to claim 1, wherein the presentation device outputs the generated response in audio or visual form. [Explanation of symbols]

[0858] 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. An input device that receives voice or text input from the user, A conversion means for converting input audio into text data, An analysis means for analyzing the aforementioned character data and recognizing the user's request, A search means for retrieving information based on the aforementioned request, A generation means that generates a response based on the information obtained by the search means, An output device that presents the generated response to the user, A system that includes this.

2. The system according to claim 1, wherein the analysis means generates a personalized response that takes into account information corresponding to the user's attributes.

3. The system according to claim 1, wherein the output device presents the generated response audibly or visually.

Images