System

Abstract

An object of a system according to an embodiment is to quickly and appropriately respond to a question or a request from an end user.SOLUTION: A system includes a question reception unit, an analysis unit, a response generation unit, and a response transmission unit. The question receiver receives a question or request from an end user. The analysis unit analyzes the question or the request received by the question reception unit. The response generation unit generates a response on the basis of the content analyzed by the analysis unit. The response transmission unit transmits the response generated by the response generation unit to the end user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies have had the problem of making it difficult to respond quickly and appropriately to questions and requests from end users.

[0005] The system according to the embodiment aims to provide a prompt and appropriate response to questions and requests from end users. [Means for solving the problem]

[0006] The system according to the embodiment includes a question receiving unit, an analysis unit, a response generation unit, and a response sending unit. The question receiving unit receives a question or request from an end user. The analysis unit analyzes the question or request received by the question receiving unit. The response generating unit generates a response based on the content analyzed by the analysis unit. The response sending unit sends the response generated by the response generating unit to the end user. [Effects of the Invention]

[0007] The system according to the embodiment can respond quickly and appropriately to questions and requests from end users. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The generation AI service system according to an embodiment of the present invention receives questions and requests from end users via SMS, generates a response from the generation AI, and sends it back to the end user via SMS. This allows the generation AI service system to generate revenue from upstream SMS communication charges from end users, allowing end users to easily use the generation AI service.

[0029] A generative AI service system according to an embodiment includes a question receiving unit, an analysis unit, a response generation unit, and a response sending unit. The question receiving unit receives a question or request from an end user. For example, an end user can send a question such as "What's the weather like today?" or "Can you tell me where a nearby restaurant is?" via SMS. The analysis unit analyzes the question or request received by the question receiving unit. For example, the generative AI analyzes the intent of the question using natural language processing technology. The response generation unit generates a response based on the content analyzed by the analysis unit. For example, the generative AI generates a response such as "Today's weather is sunny. The maximum temperature will be 25 degrees." The response sending unit sends the response generated by the response generation unit to the end user. For example, the generative AI sends the response to the end user via SMS. This allows the generative AI service system according to an embodiment to generate and send an appropriate response to a question or request from an end user.

[0030] The question receiving unit can automatically obtain the end user's location information and generate a response based on that location. For example, when the end user asks, "Tell me about restaurants nearby," the question receiving unit generates a response such as, "There's a restaurant called XX within 500 meters of your current location. The address is △△." Also, when the end user asks, "Tell me about cafes nearby," the question receiving unit generates a response such as, "There's a cafe called XX within 200 meters of your current location. The address is △△." This makes it possible to generate a response based on the end user's location information.

[0031] The question receiving unit can receive a question or request from an end user through speech and convert it into text using speech recognition technology. For example, if an end user verbally asks, "Tell me about a nearby restaurant," the generation AI uses speech recognition technology to convert the speech into text and generates a response based on that text. For example, a response such as, "There's a XX restaurant nearby. Its address is △△." is provided. Also, if an end user verbally asks, "What's the weather like today?" the question receiving unit can convert the speech into text using speech recognition technology and generate a response based on that text. For example, a response such as, "It's sunny today. The maximum temperature is 25 degrees." is provided. Also, if an end user verbally asks, "Tell me about a nearby cafe," the generation AI can convert the speech into text using speech recognition technology and generate a response based on that text. For example, a response such as, "There's a XX cafe nearby. Its address is △△." is provided. This allows the end user's verbal questions and requests to be converted into text.

[0032] The analysis unit can refer to the end user's past purchase history or behavioral history and provide related information. For example, when an end user asks, "Tell me about a nearby restaurant," the generation AI refers to the end user's past purchase history and provides information about their favorite restaurants. For example, it generates a response such as, "There's a restaurant called XX that I visited before nearby. Its address is △△." Similarly, when an end user asks, "What's the weather like today?" the analysis unit refers to the end user's past behavioral history and provides a response that emphasizes weather factors that the end user is particularly concerned about. For example, it generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Similarly, when an end user asks, "Tell me about a nearby cafe," the analysis unit refers to the end user's past purchase history and provides information about their favorite cafe. For example, it generates a response such as, "There's a cafe called XX that I visited before nearby. Its address is △△." This makes it possible to provide information based on the end user's past purchase history and behavioral history.

[0033] The response generation unit can refer to a related external database to provide more detailed information. For example, when an end user asks, "Tell me about a nearby restaurant," the generation AI refers to a related external database to provide the latest restaurant information. For example, it generates a response such as, "There's a XX restaurant nearby. Its address is △△. It has received high ratings in the latest reviews." Also, when an end user asks, "What's the weather like today?" the response generation unit refers to a weather database to provide the latest weather information. For example, it generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Also, when an end user asks, "Tell me about a nearby cafe," the response generation unit refers to a cafe database to provide the latest cafe information. For example, it generates a response such as, "There's a XX cafe nearby. It's address is △△. It has received high ratings in the latest reviews." This allows the response generation unit to refer to a related external database to provide more detailed information.

[0034] The response generation unit can understand the context of questions and requests and generate a response based on the context. For example, if an end user asks, "Tell me about a nearby restaurant," the generation AI understands the context and generates a response based on the type of restaurant and atmosphere the user is looking for. For example, it provides a response such as, "The nearby XX restaurant has a quiet and relaxing atmosphere. Its address is △△." Similarly, if an end user asks, "What's the weather like today?" the response generation unit understands the context and provides a response that highlights the weather factors the user is particularly concerned about. For example, it generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Similarly, if an end user asks, "Tell me about a nearby cafe," the response generation unit understands the context and generates a response based on the type of cafe and atmosphere the user is looking for. For example, it provides a response such as, "The nearby XX cafe has a bright and lively atmosphere. Its address is △△." This allows the AI ​​to understand the context of questions and requests and generate responses based on the context.

[0035] The response generation unit can analyze images or videos and generate responses containing visual information. For example, when an end user asks, "Tell me about restaurants nearby," the response generation unit generates a response containing visual information by analyzing related images and videos. For example, it provides a response such as, "There's a XX restaurant nearby. Please see the image below." When an end user asks, "What's the weather like today?", the response generation unit analyzes images and videos retrieved from a weather database to provide visual weather information. For example, it generates a response such as, "Today's weather is sunny. Please see the weather map below." When an end user asks, "Tell me about cafes nearby," the response generation unit analyzes images and videos retrieved from a cafe database to provide visual cafe information. For example, it generates a response such as, "There's a XX cafe nearby. Please see the image below." This makes it possible to analyze images and videos and generate responses containing visual information.

[0036] The response generation unit can analyze questions and requests in different languages ​​and generate responses in multiple languages. For example, if an end user asks in different languages, "Tell me about restaurants nearby," the response generation unit analyzes the language and generates a response in multiple languages. For example, it provides a response such as, "There's a XX restaurant nearby. Its address is △△." Also, if an end user asks in different languages, "What's the weather like today?" the response generation unit analyzes the language and provides weather information in multiple languages. For example, it generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees." Also, if an end user asks in different languages, "Tell me about cafes nearby," the response generation unit analyzes the language and provides cafe information in multiple languages. For example, it generates a response such as, "There's a XX cafe nearby. Its address is △△." This makes it possible to analyze questions and requests in different languages ​​and generate responses in multiple languages.

[0037] The response sending unit can refer to the end user's past response history and provide consistent responses. For example, when an end user asks, "Tell me about nearby restaurants," the generation AI refers to the past response history and provides consistent restaurant information. For example, it generates a response such as, "There's a XX restaurant nearby that I've visited before. Its address is △△." Also, when an end user asks, "What's the weather like today?" the response sending unit refers to the past response history and provides consistent weather information. For example, it generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Also, when an end user asks, "Tell me about nearby cafes," the generation AI refers to the past response history and provides consistent cafe information. For example, it generates a response such as, "There's a XX cafe nearby that I've visited before. Its address is △△." This allows the generation AI to refer to the end user's past response history and provide consistent responses.

[0038] The response sending unit can provide a response based on the end user's current situation. For example, if an end user asks, "Tell me about a nearby restaurant," the generation AI provides restaurant information based on the end user's current time zone and location. For example, the response sending unit generates a response such as, "There is a certain restaurant within 500 meters of my current location. The address is △△." Also, if an end user asks, "What's the weather like today?" the response sending unit generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Also, if an end user asks, "Tell me about a nearby cafe," the response sending unit generates a response such as, "There is a certain cafe within 200 meters of my current location. The address is △△." This makes it possible to provide a response based on the end user's current situation.

[0039] The response sending unit can provide a response including media according to the end user's preferences. For example, when an end user asks, "Tell me about a nearby restaurant," the generation AI provides a response including an image according to the end user's preferences. For example, the response sending unit generates a response such as, "There's a XX restaurant nearby. Please see the image below." Also, when an end user asks, "What's the weather like today?" the response sending unit generates a response including audio according to the end user's preferences. For example, the response sending unit generates an audio response such as, "Today's weather is sunny. The maximum temperature is 25 degrees." Also, when an end user asks, "Tell me about a nearby cafe," the response sending unit generates a response including an image according to the end user's preferences. For example, the response sending unit generates a response such as, "There's a XX cafe nearby. Please see the image below." This makes it possible to provide a response including media according to the end user's preferences.

[0040] The response sending unit can provide a response in a format optimized for the end user's device. For example, when an end user asks, "Tell me about nearby restaurants," the generation AI provides a response in a format optimized for the end user's device. For example, in the case of a smartphone, the response sending unit generates a response including short text and images. Also, when an end user asks, "What's the weather like today?" the response sending unit provides a response in a format optimized for the end user's device. For example, in the case of a smartwatch, the response sending unit generates a response including short text and audio. Also, when an end user asks, "Tell me about nearby cafes," the response sending unit provides a response in a format optimized for the end user's device. For example, in the case of a tablet, the response sending unit generates a response including detailed text and images. This makes it possible to provide a response in a format optimized for the end user's device.

[0041] The system provides additional premium services when end users submit specific questions or requests, generating additional revenue from the additional fees. For example, when an end user asks, "Tell me about nearby restaurants," the system generates a response such as, "There's a nearby restaurant called XX. Its address is △△. Premium members can also view information about special offers." Similarly, when an end user asks, "What's the weather like today?" the system generates a response such as, "It's sunny today. The maximum temperature is 25 degrees. Premium members can also view information about weather warnings." Similarly, when an end user asks, "Tell me about nearby cafes," the system generates a response such as, "There's a nearby cafe called XX. Its address is △△. Premium members can also view information about special offers." This allows the system to provide additional premium services for specific questions or requests, generating additional revenue from the additional fees.

[0042] The system increases frequency of use by providing discounts and special offers when end users submit questions or requests a certain number of times. For example, if an end user submits questions or requests a certain number of times, the generation AI provides discount coupons and special offers. For example, a special offer may be offered such as, "If you submit 10 questions, your next question will be free." Furthermore, if an end user submits questions or requests a certain number of times, the generation AI provides special offer information to increase frequency of use. For example, a special offer may be offered such as, "If you submit 20 questions, you will be upgraded to a premium membership for free." Furthermore, if an end user submits questions or requests a certain number of times, the generation AI provides special offer information to increase frequency of use. For example, a special offer may be offered such as, "If you submit 30 questions, you will receive a special discount coupon." This allows for discounts and special offers to be offered for questions or requests a certain number of times, thereby increasing frequency of use.

[0043] The system generates revenue from advertising and sponsorship in addition to upstream SMS communication fees. For example, when an end user sends a question or request, the generation AI displays a relevant advertisement along with the response, thereby earning advertising revenue. For example, it provides a response such as, "There's a nearby restaurant called XX. Its address is △△. Please see the advertisement below." Also, when an end user sends a question or request, the generation AI displays sponsorship information along with the response, thereby earning sponsorship revenue. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. Please see the sponsor information below." Also, when an end user sends a question or request, the generation AI displays a relevant advertisement along with the response, thereby earning advertising revenue. For example, it provides a response such as, "There's a nearby cafe called XX. Its address is △△. Please see the advertisement below." This allows the system to generate revenue from advertising and sponsorship in addition to upstream SMS communication fees.

[0044] The system generates revenue from referral fees when end users refer other users. For example, when an end user refers another user, the generation AI generates revenue from the referral fees. For example, the system provides a benefit such as, "If you refer a friend, your next question will be free." Also, when an end user refers another user, the generation AI generates revenue from the referral fees. For example, the system provides a benefit such as, "If you refer a friend, you will receive a special discount coupon." Also, when an end user refers another user, the generation AI generates revenue from the referral fees. For example, the system provides a benefit such as, "If you refer a friend, you will be upgraded to a premium membership for free." In this way, referral fees can be generated as a revenue source by referring other users.

[0045] The system proposes new services based on the end user's interests and diversifies services. For example, when an end user asks, "Tell me about restaurants nearby," the generating AI proposes new services based on the end user's interests and diversifies services. For example, when an end user asks, "What's the weather like today?" ...What's the weather like today?" the generating AI proposes new services based on the end user's interests and diversifies services. For example, when an end user asks, "What's the weather like today?" the generating AI proposes new services based on the end user's interests and diversifies services. For example, when an end user asks, "What's the weather like today?" the generating AI proposes new services based on the end user's interests and diversifies services.

[0046] The system collects end user feedback and improves services based on that feedback. For example, when an end user asks, "Tell me about a nearby restaurant," the system's generating AI collects end user feedback and improves services based on that feedback. For example, it provides a response such as, "There's a XX restaurant nearby. Its address is △△. What do you think?". Also, when an end user asks, "What's the weather like today?" the system's generating AI collects end user feedback and improves services based on that feedback. For example, it provides a response such as, "It's sunny today. The maximum temperature is 25 degrees. What do you think?". Also, when an end user asks, "Tell me about a nearby cafe," the system's generating AI collects end user feedback and improves services based on that feedback. For example, it provides a response such as, "There's a XX cafe nearby. Its address is △△. What do you think?". This makes it possible to improve services based on end user feedback.

[0047] The system integrates services from different industries and fields to provide crossover services. For example, when an end user asks, "Tell me about restaurants nearby," the generation AI integrates services from different industries and fields to provide a crossover service. For example, it provides a response such as, "There's a XX restaurant nearby. Its address is △△. You can also view information about nearby tourist attractions." Similarly, when an end user asks, "What's the weather like today?" the generation AI integrates services from different industries and fields to provide a crossover service. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. You can also view information about weekend events." Similarly, when an end user asks, "Tell me about cafes nearby," the generation AI integrates services from different industries and fields to provide a crossover service. For example, it provides a response such as, "There's a XX cafe nearby. Its address is △△. You can also view information about nearby shopping." This allows the system to integrate services from different industries and fields to provide a crossover service.

[0048] The system provides personalized services tailored to the end user's lifestyle. For example, when an end user asks, "Tell me about a nearby restaurant," the generation AI provides personalized services tailored to the end user's lifestyle. For example, it provides a response such as, "There's a nearby restaurant called XX. Its address is △△. You can also view menu information tailored to your preferences." Similarly, when an end user asks, "What's the weather like today?" the generation AI provides personalized services tailored to the end user's lifestyle. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. You can also view clothing advice tailored to your activities." Similarly, when an end user asks, "Tell me about a nearby cafe," the generation AI provides personalized services tailored to the end user's lifestyle. For example, it provides a response such as, "There's a nearby cafe called XX. Its address is △△. You can also view drink information tailored to your preferences." This makes it possible to provide personalized services tailored to the end user's lifestyle.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The question receiving unit can receive a voice question or request from an end user and convert it into text using speech recognition technology. For example, if an end user speaks, "Tell me about a nearby restaurant," the generation AI converts the voice into text using speech recognition technology and generates a response based on that text. For example, it can provide a response such as, "There's a XX restaurant nearby. Its address is △△." Furthermore, if an end user speaks, "What's the weather like today?" the question receiving unit can convert the voice into text using speech recognition technology and generate a response based on that text. For example, it can provide a response such as, "It's sunny today. The maximum temperature is 25 degrees." Furthermore, if an end user speaks, "Tell me about a nearby cafe," the question receiving unit can convert the voice into text using speech recognition technology and generate a response based on that text. For example, it can provide a response such as, "There's a XX cafe nearby. Its address is △△." This allows the generation AI to convert voice questions and requests from end users into text.

[0051] The analysis unit can refer to the end user's past purchase history or behavioral history to provide relevant information. For example, if an end user asks, "Tell me about a nearby restaurant," the generation AI can refer to the end user's past purchase history and provide information about their favorite restaurants. For example, it can generate a response such as, "There's a restaurant called XX that I visited before nearby. Its address is △△." Similarly, if an end user asks, "What's the weather like today?" the analysis unit can refer to the end user's past behavioral history and provide a response that emphasizes weather factors that the end user is particularly concerned about. For example, it can generate a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Similarly, if an end user asks, "Tell me about a nearby cafe," the generation AI can refer to the end user's past purchase history and provide information about their favorite cafe. For example, it can generate a response such as, "There's a cafe called XX that I visited before nearby. Its address is △△." This makes it possible to provide information based on the end user's past purchase history and behavioral history.

[0052] The response generation unit can refer to a related external database to provide more detailed information. For example, if an end user asks, "Tell me about a nearby restaurant," the generation AI can refer to a related external database to provide the latest restaurant information. For example, it can generate a response such as, "There's a XX restaurant nearby. Its address is △△. It has received high ratings in the latest reviews." Also, if an end user asks, "What's the weather like today?" the response generation unit can refer to a weather database to provide the latest weather information. For example, it can generate a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Also, if an end user asks, "Tell me about a nearby cafe," the response generation unit can refer to a cafe database to provide the latest cafe information. For example, it can generate a response such as, "There's a XX cafe nearby. It's address is △△. It has received high ratings in the latest reviews." This allows the response generation unit to refer to a related external database to provide more detailed information.

[0053] The response generation unit can understand the context of questions and requests and generate responses based on the context. For example, if an end user asks, "Tell me about a nearby restaurant," the generation AI understands the context and generates a response based on the type of restaurant and atmosphere the user is looking for. For example, it might provide a response such as, "The nearby XX restaurant has a quiet and relaxing atmosphere. Its address is △△." Similarly, if an end user asks, "What's the weather like today?" the response generation unit understands the context and provides a response that emphasizes the weather factors the user is particularly concerned about. For example, it might generate a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Similarly, if an end user asks, "Tell me about a nearby cafe," the response generation unit understands the context and generates a response based on the type of cafe and atmosphere the user is looking for. For example, it might provide a response such as, "The nearby XX cafe has a bright and lively atmosphere. Its address is △△." This allows the AI ​​to understand the context of questions and requests and generate responses based on the context.

[0054] The response generation unit can analyze images or videos and generate responses containing visual information. For example, if an end user asks, "Tell me about restaurants nearby," the generation AI analyzes related images and videos and generates a response containing visual information. For example, it provides a response such as, "There's a XX restaurant nearby. Please see the image below." Also, if an end user asks, "What's the weather like today?" the response generation unit analyzes images and videos retrieved from a weather database and provides visual weather information. For example, it generates a response such as, "It's sunny today. Please see the weather map below." Also, if an end user asks, "Tell me about cafes nearby," the response generation unit analyzes images and videos retrieved from a cafe database and provides visual cafe information. For example, it generates a response such as, "There's a XX cafe nearby. Please see the image below." This makes it possible to analyze images and videos and generate responses containing visual information.

[0055] The response generation unit can analyze questions and requests in different languages ​​and generate responses in multiple languages. For example, if an end user asks in different languages, such as "Tell me about restaurants nearby," the generation AI analyzes the language and generates responses in multiple languages. For example, it provides a response such as, "There's a XX restaurant nearby. Its address is △△." Also, if an end user asks in different languages, such as "What's the weather like today?", the response generation unit analyzes the language and provides weather information in multiple languages. For example, it generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees." Also, if an end user asks in different languages, such as "Tell me about cafes nearby," the response generation unit analyzes the language and provides cafe information in multiple languages. For example, it generates a response such as, "There's a XX cafe nearby. Its address is △△." This makes it possible to analyze questions and requests in different languages ​​and generate responses in multiple languages.

[0056] The response sending unit can refer to the end user's past response history and provide consistent responses. For example, if the end user asks, "Tell me about nearby restaurants," the generation AI can refer to the past response history and provide consistent restaurant information. For example, it can generate a response such as, "There's a XX restaurant nearby that I've visited before. Its address is △△." Also, if the end user asks, "What's the weather like today?" the response sending unit can refer to the past response history and provide consistent weather information. For example, it can generate a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Also, if the end user asks, "Tell me about nearby cafes," the response sending unit can refer to the past response history and provide consistent cafe information. For example, it can generate a response such as, "There's a XX cafe nearby that I've visited before. Its address is △△." This allows the generation AI to refer to the end user's past response history and provide consistent responses.

[0057] The response sending unit can provide a response based on the end user's current situation. For example, if an end user asks, "Tell me about nearby restaurants," the generation AI provides restaurant information based on the end user's current time zone and location. For example, it generates a response such as, "There is a certain restaurant within 500 meters of my current location. The address is △△." Also, if an end user asks, "What's the weather like today?" the response sending unit provides weather information based on the end user's current time zone. For example, it generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Also, if an end user asks, "Tell me about nearby cafes," the response sending unit provides cafe information based on the end user's current time zone and location. For example, it generates a response such as, "There is a certain cafe within 200 meters of my current location. The address is △△." This makes it possible to provide a response based on the end user's current situation.

[0058] The response sending unit can provide a response including media according to the end user's preferences. For example, if the end user asks, "Tell me about restaurants nearby," the generation AI provides a response including images according to the end user's preferences. For example, it generates a response such as, "There's a XX restaurant nearby. Please see the image below." Also, if the end user asks, "What's the weather like today?" the response sending unit can provide a response including audio according to the end user's preferences. For example, it generates an audio response such as, "Today's weather is sunny. The maximum temperature is 25 degrees." Also, if the end user asks, "Tell me about cafes nearby," the response sending unit can provide a response including images according to the end user's preferences. For example, it generates a response such as, "There's a XX cafe nearby. Please see the image below." This makes it possible to provide a response including media according to the end user's preferences.

[0059] The response sending unit can provide a response in a format optimized for the end user's device. For example, if the end user asks, "Tell me about nearby restaurants," the generation AI provides a response in a format optimized for the end user's device. For example, in the case of a smartphone, the generation AI generates a response including short text and images. Also, if the end user asks, "What's the weather like today?" the response sending unit can provide a response in a format optimized for the end user's device. For example, in the case of a smart watch, the generation AI generates a response including short text and audio. Also, if the end user asks, "Tell me about nearby cafes," the generation AI can provide a response in a format optimized for the end user's device. For example, in the case of a tablet, the generation AI generates a response including detailed text and images. This makes it possible to provide a response in a format optimized for the end user's device.

[0060] The system provides additional premium services when end users submit specific questions or requests, generating revenue from the additional fees. For example, if an end user asks, "Tell me about nearby restaurants," the AI ​​generator can provide detailed restaurant reviews and special offer information as a premium service, generating revenue from the additional fees. For example, it generates a response such as, "There's a nearby restaurant called XX. Its address is △△. Premium members can also view special offer information." Similarly, if an end user asks, "What's the weather like today?" the AI ​​generator can provide detailed weather forecasts and weather warning information as a premium service, generating revenue from the additional fees. For example, it generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. Premium members can also view weather warning information." Similarly, if an end user asks, "Tell me about nearby cafes," the AI ​​generator can provide detailed cafe reviews and special offer information as a premium service, generating revenue from the additional fees. For example, it generates a response such as, "There's a nearby cafe called XX. Its address is △△. Premium members can also view special offer information." This allows the system to provide additional premium services for specific questions or requests, generating revenue from the additional fees.

[0061] The system provides discounts and special offers when end users submit questions or requests a certain number of times, thereby increasing frequency of use. For example, if an end user submits questions or requests a certain number of times, the generation AI provides discount coupons and special offers. For example, a special offer may be offered such as, "If you submit 10 questions, your next question will be free." Furthermore, if an end user submits questions or requests a certain number of times, the generation AI provides special offer information to increase frequency of use. For example, a special offer may be offered such as, "If you submit 20 questions, you will be upgraded to a premium membership for free." Furthermore, if an end user submits questions or requests a certain number of times, the generation AI provides special offer information to increase frequency of use. For example, a special offer may be offered such as, "If you submit 30 questions, you will receive a special discount coupon." This allows for discounts and special offers to be offered for questions or requests a certain number of times, thereby increasing frequency of use.

[0062] The system generates revenue from advertising and sponsorship in addition to upstream SMS communication fees. For example, when an end user sends a question or request, the generation AI displays a relevant advertisement along with the response, earning advertising revenue. For example, it provides a response such as, "There's a nearby restaurant called XX. Its address is △△. Please see the advertisement below." Also, when an end user sends a question or request, the generation AI displays sponsorship information along with the response, earning sponsorship revenue. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. Please see the sponsor information below." Also, when an end user sends a question or request, the generation AI displays a relevant advertisement along with the response, earning advertising revenue. For example, it provides a response such as, "There's a nearby cafe called XX. Its address is △△. Please see the advertisement below." This allows the system to generate revenue from advertising and sponsorship in addition to upstream SMS communication fees.

[0063] The system earns revenue from referral fees when end users refer other users. For example, when an end user refers another user, the generation AI earns revenue from the referral fees. For example, the system may provide a perk such as, "If you refer a friend, your next question will be free." Also, when an end user refers another user, the system earns revenue from the referral fees. For example, the system may provide a perk such as, "If you refer a friend, you will receive a special discount coupon." Also, when an end user refers another user, the system earns revenue from the referral fees. For example, the system may provide a perk such as, "If you refer a friend, you will be upgraded to a premium membership for free." This allows the system to earn revenue from referral fees when an end user refers other users.

[0064] The system proposes new services based on the end user's interests and diversifies services. For example, if an end user asks, "Tell me about restaurants nearby," the generation AI proposes new services based on the end user's interests and diversifies services. For example, if an end user asks, "What's the weather like today?" ...What's the weather like today?" the generation AI proposes new services based on the end user's interests and diversifies services. For example, if an end user asks, "What's the weather like today?" the generation AI proposes new services based on the end user's interests and diversifies services. For example, if an end user asks, "What's the weather like today?" the generation AI proposes new services based on the end user's interests and diversifies services.

[0065] The system collects end user feedback and improves services based on that feedback. For example, if an end user asks, "Tell me about a nearby restaurant," the generation AI collects end user feedback and improves services based on that feedback. For example, it provides a response such as, "There's a XX restaurant nearby. Its address is △△. What do you think?". Also, if an end user asks, "What's the weather like today?" the generation AI collects end user feedback and improves services based on that feedback. For example, it provides a response such as, "It's sunny today. The maximum temperature is 25 degrees. What do you think?". Also, if an end user asks, "Tell me about a nearby cafe," the generation AI collects end user feedback and improves services based on that feedback. For example, it provides a response such as, "There's a XX cafe nearby. Its address is △△. What do you think?". This makes it possible to improve services based on end user feedback.

[0066] The system integrates services from different industries and fields to provide crossover services. For example, when an end user asks, "Tell me about restaurants nearby," the generation AI integrates services from different industries and fields to provide a crossover service. For example, it provides a response such as, "There's a XX restaurant nearby. Its address is △△. You can also view information about nearby tourist attractions." Similarly, when an end user asks, "What's the weather like today?" the generation AI integrates services from different industries and fields to provide a crossover service. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. You can also view information about weekend events." Similarly, when an end user asks, "Tell me about cafes nearby," the generation AI integrates services from different industries and fields to provide a crossover service. For example, it provides a response such as, "There's a XX cafe nearby. Its address is △△. You can also view information about nearby shopping." This allows the system to integrate services from different industries and fields to provide a crossover service.

[0067] The system provides personalized services tailored to the end user's lifestyle. For example, if an end user asks, "Tell me about restaurants nearby," the generation AI provides personalized services tailored to the end user's lifestyle. For example, it provides a response such as, "There's a certain restaurant nearby. Its address is △△. You can also view menu information tailored to your preferences." Similarly, if an end user asks, "What's the weather like today?" the generation AI provides personalized services tailored to the end user's lifestyle. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. You can also view clothing advice tailored to your activities." Similarly, if an end user asks, "Tell me about cafes nearby," the generation AI provides personalized services tailored to the end user's lifestyle. For example, it provides a response such as, "There's a certain cafe nearby. Its address is △△. You can also view drink information tailored to your preferences." This makes it possible to provide personalized services tailored to the end user's lifestyle.

[0068] The processing flow of the first embodiment will be briefly explained below.

[0069] Step 1: The question receiver receives a question or request from an end user. For example, an end user can send a question such as "What's the weather like today?" or "Can you tell me where the nearest restaurant is?" via SMS. Step 2: The analysis unit analyzes the question or request received by the question receiving unit. For example, the generation AI analyzes the intent of the question using natural language processing technology. Step 3: The response generation unit generates a response based on the content analyzed by the analysis unit. For example, the generation AI generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees." Step 4: The response sending unit sends the response generated by the response generating unit to the end user. For example, the generating AI sends the response to the end user via SMS.

[0070] (Example 2) The generation AI service system according to an embodiment of the present invention receives questions and requests from end users via SMS, generates a response from the generation AI, and sends it back to the end user via SMS. This allows the generation AI service system to generate revenue from upstream SMS communication charges from end users, allowing end users to easily use the generation AI service.

[0071] A generative AI service system according to an embodiment includes a question receiving unit, an analysis unit, a response generation unit, and a response sending unit. The question receiving unit receives a question or request from an end user. For example, an end user can send a question such as "What's the weather like today?" or "Can you tell me where a nearby restaurant is?" via SMS. The analysis unit analyzes the question or request received by the question receiving unit. For example, the generative AI analyzes the intent of the question using natural language processing technology. The response generation unit generates a response based on the content analyzed by the analysis unit. For example, the generative AI generates a response such as "Today's weather is sunny. The maximum temperature will be 25 degrees." The response sending unit sends the response generated by the response generation unit to the end user. For example, the generative AI sends the response to the end user via SMS. This allows the generative AI service system according to an embodiment to generate and send an appropriate response to a question or request from an end user.

[0072] The question receiving unit can automatically obtain the end user's location information and generate a response based on that location. For example, when the end user asks, "Tell me about restaurants nearby," the question receiving unit generates a response such as, "There's a restaurant called XX within 500 meters of your current location. The address is △△." Also, when the end user asks, "Tell me about cafes nearby," the question receiving unit generates a response such as, "There's a cafe called XX within 200 meters of your current location. The address is △△." This makes it possible to generate a response based on the end user's location information.

[0073] The analysis unit can estimate the end user's emotional state and generate a response based on that emotion. For example, if an end user asks, "What's the weather like today?", the generation AI uses the emotion estimation function to estimate the end user's emotional state and generate a response that elicits positive emotions. For example, it provides a response such as, "The weather is sunny today. The maximum temperature is 25 degrees. It looks like it's going to be a great day." If an end user asks, "Tell me about a nearby restaurant," the analysis unit uses the emotion estimation function to estimate the end user's emotional state and provide information about relaxing restaurants. For example, it generates a response such as, "The nearby XX restaurant has a quiet and relaxing atmosphere. Its address is △△." If an end user asks, "Tell me about a nearby cafe," the analysis unit uses the emotion estimation function to estimate the end user's emotional state and provide information about cafes that will lift their spirits. For example, it generates a response such as, "The nearby XX cafe has a bright and lively atmosphere. Its address is △△." This allows the generation of responses based on the end user's emotional state.

[0074] The question receiving unit can receive a question or request from an end user through speech and convert it into text using speech recognition technology. For example, if an end user verbally asks, "Tell me about a nearby restaurant," the generation AI uses speech recognition technology to convert the speech into text and generates a response based on that text. For example, a response such as, "There's a XX restaurant nearby. Its address is △△." is provided. Also, if an end user verbally asks, "What's the weather like today?" the question receiving unit can convert the speech into text using speech recognition technology and generate a response based on that text. For example, a response such as, "It's sunny today. The maximum temperature is 25 degrees." is provided. Also, if an end user verbally asks, "Tell me about a nearby cafe," the generation AI can convert the speech into text using speech recognition technology and generate a response based on that text. For example, a response such as, "There's a XX cafe nearby. Its address is △△." is provided. This allows the end user's verbal questions and requests to be converted into text.

[0075] The analysis unit can refer to the end user's past purchase history or behavioral history and provide related information. For example, when an end user asks, "Tell me about a nearby restaurant," the generation AI refers to the end user's past purchase history and provides information about their favorite restaurants. For example, it generates a response such as, "There's a restaurant called XX that I visited before nearby. Its address is △△." Similarly, when an end user asks, "What's the weather like today?" the analysis unit refers to the end user's past behavioral history and provides a response that emphasizes weather factors that the end user is particularly concerned about. For example, it generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Similarly, when an end user asks, "Tell me about a nearby cafe," the analysis unit refers to the end user's past purchase history and provides information about their favorite cafe. For example, it generates a response such as, "There's a cafe called XX that I visited before nearby. Its address is △△." This makes it possible to provide information based on the end user's past purchase history and behavioral history.

[0076] The analysis unit can estimate the end user's emotions in real time and make suggestions that will elicit positive emotions. For example, when an end user asks, "What's the weather like today?", the generation AI uses its emotion estimation function to estimate the end user's emotions in real time and make suggestions that will elicit positive emotions. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. It looks like it's going to be a great day." Similarly, when an end user asks, "Tell me about a nearby restaurant," the generation AI uses its emotion estimation function to estimate the end user's emotions in real time and provide information about relaxing restaurants. For example, it generates a response such as, "The nearby XX restaurant has a quiet and relaxing atmosphere. Its address is △△." Similarly, when an end user asks, "Tell me about a nearby cafe," the generation AI uses its emotion estimation function to estimate the end user's emotions in real time and provide information about cafes that will lift their spirits. For example, it generates a response such as, "The nearby XX cafe has a bright and lively atmosphere. Its address is △△." This allows the generation AI to estimate the end user's emotions in real time and make suggestions that will elicit positive emotions.

[0077] The response generation unit can refer to a related external database to provide more detailed information. For example, when an end user asks, "Tell me about a nearby restaurant," the generation AI refers to a related external database to provide the latest restaurant information. For example, it generates a response such as, "There's a XX restaurant nearby. Its address is △△. It has received high ratings in the latest reviews." Also, when an end user asks, "What's the weather like today?" the response generation unit refers to a weather database to provide the latest weather information. For example, it generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Also, when an end user asks, "Tell me about a nearby cafe," the response generation unit refers to a cafe database to provide the latest cafe information. For example, it generates a response such as, "There's a XX cafe nearby. It's address is △△. It has received high ratings in the latest reviews." This allows the response generation unit to refer to a related external database to provide more detailed information.

[0078] The response generation unit can understand the context of questions and requests and generate a response based on the context. For example, if an end user asks, "Tell me about a nearby restaurant," the generation AI understands the context and generates a response based on the type of restaurant and atmosphere the user is looking for. For example, it provides a response such as, "The nearby XX restaurant has a quiet and relaxing atmosphere. Its address is △△." Similarly, if an end user asks, "What's the weather like today?" the response generation unit understands the context and provides a response that highlights the weather factors the user is particularly concerned about. For example, it generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Similarly, if an end user asks, "Tell me about a nearby cafe," the response generation unit understands the context and generates a response based on the type of cafe and atmosphere the user is looking for. For example, it provides a response such as, "The nearby XX cafe has a bright and lively atmosphere. Its address is △△." This allows the AI ​​to understand the context of questions and requests and generate responses based on the context.

[0079] The response generation unit uses the emotion estimation function to generate a response that corresponds to the end user's emotions, thereby gaining emotional empathy. For example, when an end user asks, "What's the weather like today?", the generation AI uses the emotion estimation function to estimate the end user's emotions and generate a response that elicits positive emotions. For example, it provides a response such as, "The weather is sunny today. The maximum temperature is 25 degrees. It looks like it's going to be a great day." Furthermore, when an end user asks, "Tell me about a nearby restaurant," the response generation unit uses the emotion estimation function to estimate the end user's emotions and provide information about relaxing restaurants. For example, it generates a response such as, "The nearby XX restaurant has a quiet and relaxing atmosphere. Its address is △△." Furthermore, when an end user asks, "Tell me about a nearby cafe," the response generation unit uses the emotion estimation function to estimate the end user's emotions and provide information about cafes that will lift their spirits. For example, it generates a response such as, "The nearby XX cafe has a bright and lively atmosphere. Its address is △△." This allows the generation of a response that corresponds to the end user's emotions and gaining emotional empathy.

[0080] The response generation unit can analyze images or videos and generate responses containing visual information. For example, when an end user asks, "Tell me about restaurants nearby," the response generation unit generates a response containing visual information by analyzing related images and videos. For example, it provides a response such as, "There's a XX restaurant nearby. Please see the image below." When an end user asks, "What's the weather like today?", the response generation unit analyzes images and videos retrieved from a weather database to provide visual weather information. For example, it generates a response such as, "Today's weather is sunny. Please see the weather map below." When an end user asks, "Tell me about cafes nearby," the response generation unit analyzes images and videos retrieved from a cafe database to provide visual cafe information. For example, it generates a response such as, "There's a XX cafe nearby. Please see the image below." This makes it possible to analyze images and videos and generate responses containing visual information.

[0081] The response generation unit can analyze questions and requests in different languages ​​and generate responses in multiple languages. For example, if an end user asks in different languages, "Tell me about restaurants nearby," the response generation unit analyzes the language and generates a response in multiple languages. For example, it provides a response such as, "There's a XX restaurant nearby. Its address is △△." Also, if an end user asks in different languages, "What's the weather like today?" the response generation unit analyzes the language and provides weather information in multiple languages. For example, it generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees." Also, if an end user asks in different languages, "Tell me about cafes nearby," the response generation unit analyzes the language and provides cafe information in multiple languages. For example, it generates a response such as, "There's a XX cafe nearby. Its address is △△." This makes it possible to analyze questions and requests in different languages ​​and generate responses in multiple languages.

[0082] The response generation unit can use the emotion estimation function to adjust the tone and style of the response based on the end user's emotion. For example, when an end user asks, "What's the weather like today?", the generation AI uses the emotion estimation function to estimate the end user's emotion and generates a response in a tone and style based on that emotion. For example, it provides a response such as, "The weather is sunny today. The maximum temperature is 25 degrees. It looks like it's going to be a great day." Also, when an end user asks, "Can you tell me about a nearby restaurant?", the response generation unit can use the emotion estimation function to estimate the end user's emotion and generate a response in a tone and style based on that emotion. For example, it can provide a response such as, "The nearby XX restaurant has a quiet and relaxing atmosphere. Its address is △△." Also, when an end user asks, "Can you tell me about a nearby cafe?", the response generation unit can use the emotion estimation function to estimate the end user's emotion and generate a response in a tone and style based on that emotion. For example, it can provide a response such as, "The nearby XX cafe has a bright and lively atmosphere. Its address is △△." This allows the generation AI to adjust the tone and style of the response based on the end user's emotion.

[0083] The response sending unit can refer to the end user's past response history and provide consistent responses. For example, when an end user asks, "Tell me about nearby restaurants," the generation AI refers to the past response history and provides consistent restaurant information. For example, it generates a response such as, "There's a XX restaurant nearby that I've visited before. Its address is △△." Also, when an end user asks, "What's the weather like today?" the response sending unit refers to the past response history and provides consistent weather information. For example, it generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Also, when an end user asks, "Tell me about nearby cafes," the generation AI refers to the past response history and provides consistent cafe information. For example, it generates a response such as, "There's a XX cafe nearby that I've visited before. Its address is △△." This allows the generation AI to refer to the end user's past response history and provide consistent responses.

[0084] The response sending unit can provide a response based on the end user's current situation. For example, if an end user asks, "Tell me about a nearby restaurant," the generation AI provides restaurant information based on the end user's current time zone and location. For example, the response sending unit generates a response such as, "There is a certain restaurant within 500 meters of my current location. The address is △△." Also, if an end user asks, "What's the weather like today?" the response sending unit generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Also, if an end user asks, "Tell me about a nearby cafe," the response sending unit generates a response such as, "There is a certain cafe within 200 meters of my current location. The address is △△." This makes it possible to provide a response based on the end user's current situation.

[0085] The response sending unit can use the emotion estimation function to adjust the timing and frequency of responses according to the end user's emotions. For example, when an end user asks, "What's the weather like today?", the generation AI uses the emotion estimation function to estimate the end user's emotions and sends a response at a timing appropriate to the emotions. For example, to elicit positive emotions, the response sending unit may send a response immediately. Also, when an end user asks, "Tell me about nearby restaurants," the response sending unit can use the emotion estimation function to estimate the end user's emotions and send a response at a frequency appropriate to the emotions. For example, to provide a relaxing atmosphere, the response sending unit may send a response with a slight delay. Also, when an end user asks, "Tell me about nearby cafes," the response sending unit can use the emotion estimation function to estimate the end user's emotions and send a response at a timing appropriate to the emotions. For example, to lift the mood, the response may be sent immediately. This makes it possible to adjust the timing and frequency of responses according to the end user's emotions.

[0086] The response sending unit can provide a response including media according to the end user's preferences. For example, when an end user asks, "Tell me about a nearby restaurant," the generation AI provides a response including an image according to the end user's preferences. For example, the response sending unit generates a response such as, "There's a XX restaurant nearby. Please see the image below." Also, when an end user asks, "What's the weather like today?" the response sending unit generates a response including audio according to the end user's preferences. For example, the response sending unit generates an audio response such as, "Today's weather is sunny. The maximum temperature is 25 degrees." Also, when an end user asks, "Tell me about a nearby cafe," the response sending unit generates a response including an image according to the end user's preferences. For example, the response sending unit generates a response such as, "There's a XX cafe nearby. Please see the image below." This makes it possible to provide a response including media according to the end user's preferences.

[0087] The response sending unit can provide a response in a format optimized for the end user's device. For example, when an end user asks, "Tell me about nearby restaurants," the generation AI provides a response in a format optimized for the end user's device. For example, in the case of a smartphone, the response sending unit generates a response including short text and images. Also, when an end user asks, "What's the weather like today?" the response sending unit provides a response in a format optimized for the end user's device. For example, in the case of a smartwatch, the response sending unit generates a response including short text and audio. Also, when an end user asks, "Tell me about nearby cafes," the response sending unit provides a response in a format optimized for the end user's device. For example, in the case of a tablet, the response sending unit generates a response including detailed text and images. This makes it possible to provide a response in a format optimized for the end user's device.

[0088] The response sending unit can use the emotion estimation function to adjust the format and content of the response based on the end user's emotion. For example, when an end user asks, "What's the weather today?", the response sending unit uses the emotion estimation function to estimate the end user's emotion and provides a response with a format and content based on that emotion. For example, to elicit positive emotions, the response sending unit generates a response including text and images in a bright tone. Also, when an end user asks, "Tell me about nearby restaurants," the response sending unit uses the emotion estimation function to estimate the end user's emotion and provides a response with a format and content based on that emotion. For example, to provide a relaxing atmosphere, the response sending unit generates a response including text and images in a calm tone. Also, when an end user asks, "Tell me about nearby cafes," the response sending unit uses the emotion estimation function to estimate the end user's emotion and provides a response with a format and content based on that emotion. For example, to lift the mood, the response sending unit generates a response including text and images in a bright tone. This makes it possible to adjust the format and content of the response based on the end user's emotion.

[0089] The system provides additional premium services when end users submit specific questions or requests, generating additional revenue from the additional fees. For example, when an end user asks, "Tell me about nearby restaurants," the system generates a response such as, "There's a nearby restaurant called XX. Its address is △△. Premium members can also view information about special offers." Similarly, when an end user asks, "What's the weather like today?" the system generates a response such as, "It's sunny today. The maximum temperature is 25 degrees. Premium members can also view information about weather warnings." Similarly, when an end user asks, "Tell me about nearby cafes," the system generates a response such as, "There's a nearby cafe called XX. Its address is △△. Premium members can also view information about special offers." This allows the system to provide additional premium services for specific questions or requests, generating additional revenue from the additional fees.

[0090] The system increases frequency of use by providing discounts and special offers when end users submit questions or requests a certain number of times. For example, if an end user submits questions or requests a certain number of times, the generation AI provides discount coupons and special offers. For example, a special offer may be offered such as, "If you submit 10 questions, your next question will be free." Furthermore, if an end user submits questions or requests a certain number of times, the generation AI provides special offer information to increase frequency of use. For example, a special offer may be offered such as, "If you submit 20 questions, you will be upgraded to a premium membership for free." Furthermore, if an end user submits questions or requests a certain number of times, the generation AI provides special offer information to increase frequency of use. For example, a special offer may be offered such as, "If you submit 30 questions, you will receive a special discount coupon." This allows for discounts and special offers to be offered for questions or requests a certain number of times, thereby increasing frequency of use.

[0091] The system uses the emotion estimation function to provide perks and discounts that correspond to the end user's emotions, thereby encouraging usage. For example, when an end user submits a question or request, the generation AI uses the emotion estimation function to estimate the end user's emotions and provide perks and discounts that elicit positive emotions. For example, a perk such as, "To make you feel even better, your next question will be free." is provided. Also, when an end user submits a question or request, the generation AI uses the emotion estimation function to estimate the end user's emotions and provide perks and discounts that elicit positive emotions. For example, a perk such as, "To make you feel even better, you will be upgraded to a premium membership for free." is provided. In this way, perks and discounts that correspond to the end user's emotions can be provided, encouraging usage.

[0092] The system generates revenue from advertising and sponsorship in addition to upstream SMS communication fees. For example, when an end user sends a question or request, the generation AI displays a relevant advertisement along with the response, thereby earning advertising revenue. For example, it provides a response such as, "There's a nearby restaurant called XX. Its address is △△. Please see the advertisement below." Also, when an end user sends a question or request, the generation AI displays sponsorship information along with the response, thereby earning sponsorship revenue. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. Please see the sponsor information below." Also, when an end user sends a question or request, the generation AI displays a relevant advertisement along with the response, thereby earning advertising revenue. For example, it provides a response such as, "There's a nearby cafe called XX. Its address is △△. Please see the advertisement below." This allows the system to generate revenue from advertising and sponsorship in addition to upstream SMS communication fees.

[0093] The system generates revenue from referral fees when end users refer other users. For example, when an end user refers another user, the generation AI generates revenue from the referral fees. For example, the system provides a benefit such as, "If you refer a friend, your next question will be free." Also, when an end user refers another user, the generation AI generates revenue from the referral fees. For example, the system provides a benefit such as, "If you refer a friend, you will receive a special discount coupon." Also, when an end user refers another user, the generation AI generates revenue from the referral fees. For example, the system provides a benefit such as, "If you refer a friend, you will be upgraded to a premium membership for free." In this way, referral fees can be generated as a revenue source by referring other users.

[0094] The system uses the emotion estimation function to provide advertisements and promotions based on the end user's emotions, thereby increasing revenue. For example, when an end user submits a question or request, the generation AI uses the emotion estimation function to estimate the end user's emotions and provide advertisements based on those emotions. For example, the system provides a response such as, "To make you feel even better, please take a look at the advertisement below." Also, when an end user submits a question or request, the generation AI uses the emotion estimation function to estimate the end user's emotions and provide promotions based on those emotions. For example, the system provides a response such as, "To make you feel even better, please take a look at the sponsor information below." Also, when an end user submits a question or request, the generation AI uses the emotion estimation function to estimate the end user's emotions and provide advertisements based on those emotions. For example, the system provides a response such as, "To make you feel even better, please take a look at the sponsor information below." This allows the system to provide advertisements and promotions based on the end user's emotions, thereby increasing revenue.

[0095] The system proposes new services based on the end user's interests and diversifies services. For example, when an end user asks, "Tell me about restaurants nearby," the generating AI proposes new services based on the end user's interests and diversifies services. For example, when an end user asks, "What's the weather like today?" ...What's the weather like today?" the generating AI proposes new services based on the end user's interests and diversifies services. For example, when an end user asks, "What's the weather like today?" the generating AI proposes new services based on the end user's interests and diversifies services. For example, when an end user asks, "What's the weather like today?" the generating AI proposes new services based on the end user's interests and diversifies services.

[0096] The system collects end user feedback and improves services based on that feedback. For example, when an end user asks, "Tell me about a nearby restaurant," the system's generating AI collects end user feedback and improves services based on that feedback. For example, it provides a response such as, "There's a XX restaurant nearby. Its address is △△. What do you think?". Also, when an end user asks, "What's the weather like today?" the system's generating AI collects end user feedback and improves services based on that feedback. For example, it provides a response such as, "It's sunny today. The maximum temperature is 25 degrees. What do you think?". Also, when an end user asks, "Tell me about a nearby cafe," the system's generating AI collects end user feedback and improves services based on that feedback. For example, it provides a response such as, "There's a XX cafe nearby. Its address is △△. What do you think?". This makes it possible to improve services based on end user feedback.

[0097] The system uses the emotion estimation function to develop and provide new services based on the end user's emotions. For example, when an end user asks, "Tell me about a nearby restaurant," the generation AI uses the emotion estimation function to infer the end user's emotions and develops and provides a new service based on that emotion. For example, it provides a response such as, "There's a nearby XX restaurant. Its address is △△. You can also view information about cafes where you can relax." Similarly, when an end user asks, "What's the weather like today?" the generation AI uses the emotion estimation function to infer the end user's emotions and develops and provides a new service based on that emotion. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. You can also view the weekend weather forecast." Similarly, when an end user asks, "Tell me about a nearby cafe," the generation AI uses the emotion estimation function to infer the end user's emotions and develops and provides a new service based on that emotion. For example, it provides a response such as, "There's a nearby XX cafe. Its address is △△. You can also view information about restaurants that will lift your spirits." This allows the system to develop and provide new services based on the end user's emotions.

[0098] The system integrates services from different industries and fields to provide crossover services. For example, when an end user asks, "Tell me about restaurants nearby," the generation AI integrates services from different industries and fields to provide a crossover service. For example, it provides a response such as, "There's a XX restaurant nearby. Its address is △△. You can also view information about nearby tourist attractions." Similarly, when an end user asks, "What's the weather like today?" the generation AI integrates services from different industries and fields to provide a crossover service. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. You can also view information about weekend events." Similarly, when an end user asks, "Tell me about cafes nearby," the generation AI integrates services from different industries and fields to provide a crossover service. For example, it provides a response such as, "There's a XX cafe nearby. Its address is △△. You can also view information about nearby shopping." This allows the system to integrate services from different industries and fields to provide a crossover service.

[0099] The system provides personalized services tailored to the end user's lifestyle. For example, when an end user asks, "Tell me about a nearby restaurant," the generation AI provides personalized services tailored to the end user's lifestyle. For example, it provides a response such as, "There's a nearby restaurant called XX. Its address is △△. You can also view menu information tailored to your preferences." Similarly, when an end user asks, "What's the weather like today?" the generation AI provides personalized services tailored to the end user's lifestyle. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. You can also view clothing advice tailored to your activities." Similarly, when an end user asks, "Tell me about a nearby cafe," the generation AI provides personalized services tailored to the end user's lifestyle. For example, it provides a response such as, "There's a nearby cafe called XX. Its address is △△. You can also view drink information tailored to your preferences." This makes it possible to provide personalized services tailored to the end user's lifestyle.

[0100] The system uses the emotion estimation function to customize services based on the end user's emotions, improving satisfaction. For example, when an end user asks, "Tell me about nearby restaurants," the generation AI uses the emotion estimation function to estimate the end user's emotions and provide customized restaurant information based on that emotion. For example, it provides a response such as, "There's a nearby XX restaurant. Its address is △△. You can also view information about restaurants with a relaxing atmosphere." Similarly, when an end user asks, "What's the weather like today?" the generation AI uses the emotion estimation function to estimate the end user's emotions and provide customized weather information based on that emotion. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. You can also view information about activities to lift your spirits." Similarly, when an end user asks, "Tell me about nearby cafes," the generation AI uses the emotion estimation function to estimate the end user's emotions and provide customized cafe information based on that emotion. For example, it provides a response such as, "There's a nearby XX cafe. It's address is △△. You can also view information about drinks to refresh your mood." This allows the system to customize services based on the end user's emotions and improve satisfaction.

[0101] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0102] The question receiving unit can receive a voice question or request from an end user and convert it into text using speech recognition technology. For example, if an end user speaks, "Tell me about a nearby restaurant," the generation AI converts the voice into text using speech recognition technology and generates a response based on that text. For example, it can provide a response such as, "There's a XX restaurant nearby. Its address is △△." Furthermore, if an end user speaks, "What's the weather like today?" the question receiving unit can convert the voice into text using speech recognition technology and generate a response based on that text. For example, it can provide a response such as, "It's sunny today. The maximum temperature is 25 degrees." Furthermore, if an end user speaks, "Tell me about a nearby cafe," the question receiving unit can convert the voice into text using speech recognition technology and generate a response based on that text. For example, it can provide a response such as, "There's a XX cafe nearby. Its address is △△." This allows the generation AI to convert voice questions and requests from end users into text.

[0103] The analysis unit can refer to the end user's past purchase history or behavioral history to provide relevant information. For example, if an end user asks, "Tell me about a nearby restaurant," the generation AI can refer to the end user's past purchase history and provide information about their favorite restaurants. For example, it can generate a response such as, "There's a restaurant called XX that I visited before nearby. Its address is △△." Similarly, if an end user asks, "What's the weather like today?" the analysis unit can refer to the end user's past behavioral history and provide a response that emphasizes weather factors that the end user is particularly concerned about. For example, it can generate a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Similarly, if an end user asks, "Tell me about a nearby cafe," the generation AI can refer to the end user's past purchase history and provide information about their favorite cafe. For example, it can generate a response such as, "There's a cafe called XX that I visited before nearby. Its address is △△." This makes it possible to provide information based on the end user's past purchase history and behavioral history.

[0104] The analysis unit can estimate the end user's emotional state and generate a response based on that emotion. For example, if an end user asks, "What's the weather like today?", the generation AI uses its emotion estimation function to estimate the end user's emotional state and generate a response that elicits positive emotions. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. It looks like it's going to be a great day." Similarly, if an end user asks, "Tell me about a nearby restaurant," the generation AI uses its emotion estimation function to estimate the end user's emotional state and provide information about relaxing restaurants. For example, it generates a response such as, "The nearby XX restaurant has a quiet and relaxing atmosphere. Its address is △△." Similarly, if an end user asks, "Tell me about a nearby cafe," the generation AI uses its emotion estimation function to estimate the end user's emotional state and provide information about cafes that will lift their spirits. For example, it generates a response such as, "The nearby XX cafe has a bright and lively atmosphere. Its address is △△." This allows the generation of responses based on the end user's emotional state.

[0105] The response generation unit can refer to a related external database to provide more detailed information. For example, if an end user asks, "Tell me about a nearby restaurant," the generation AI can refer to a related external database to provide the latest restaurant information. For example, it can generate a response such as, "There's a XX restaurant nearby. Its address is △△. It has received high ratings in the latest reviews." Also, if an end user asks, "What's the weather like today?" the response generation unit can refer to a weather database to provide the latest weather information. For example, it can generate a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Also, if an end user asks, "Tell me about a nearby cafe," the response generation unit can refer to a cafe database to provide the latest cafe information. For example, it can generate a response such as, "There's a XX cafe nearby. It's address is △△. It has received high ratings in the latest reviews." This allows the response generation unit to refer to a related external database to provide more detailed information.

[0106] The response generation unit can understand the context of questions and requests and generate responses based on the context. For example, if an end user asks, "Tell me about a nearby restaurant," the generation AI understands the context and generates a response based on the type of restaurant and atmosphere the user is looking for. For example, it might provide a response such as, "The nearby XX restaurant has a quiet and relaxing atmosphere. Its address is △△." Similarly, if an end user asks, "What's the weather like today?" the response generation unit understands the context and provides a response that emphasizes the weather factors the user is particularly concerned about. For example, it might generate a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Similarly, if an end user asks, "Tell me about a nearby cafe," the response generation unit understands the context and generates a response based on the type of cafe and atmosphere the user is looking for. For example, it might provide a response such as, "The nearby XX cafe has a bright and lively atmosphere. Its address is △△." This allows the AI ​​to understand the context of questions and requests and generate responses based on the context.

[0107] The response generation unit uses the emotion estimation function to generate a response that corresponds to the end user's emotions, thereby gaining emotional empathy. For example, if an end user asks, "What's the weather like today?", the generation AI uses the emotion estimation function to estimate the end user's emotions and generate a response that elicits positive emotions. For example, it provides a response such as, "The weather is sunny today. The maximum temperature is 25 degrees. It looks like it's going to be a great day." Furthermore, if an end user asks, "Tell me about a nearby restaurant," the response generation unit uses the emotion estimation function to estimate the end user's emotions and provide information about relaxing restaurants. For example, it generates a response such as, "The nearby XX restaurant has a quiet and relaxing atmosphere. Its address is △△." Furthermore, if an end user asks, "Tell me about a nearby cafe," the response generation unit uses the emotion estimation function to estimate the end user's emotions and provide information about cafes that will lift their spirits. For example, it generates a response such as, "The nearby XX cafe has a bright and lively atmosphere. Its address is △△." This allows the generation of a response that corresponds to the end user's emotions and gaining emotional empathy.

[0108] The response generation unit can analyze images or videos and generate responses containing visual information. For example, if an end user asks, "Tell me about restaurants nearby," the generation AI analyzes related images and videos and generates a response containing visual information. For example, it provides a response such as, "There's a XX restaurant nearby. Please see the image below." Also, if an end user asks, "What's the weather like today?" the response generation unit analyzes images and videos retrieved from a weather database and provides visual weather information. For example, it generates a response such as, "It's sunny today. Please see the weather map below." Also, if an end user asks, "Tell me about cafes nearby," the response generation unit analyzes images and videos retrieved from a cafe database and provides visual cafe information. For example, it generates a response such as, "There's a XX cafe nearby. Please see the image below." This makes it possible to analyze images and videos and generate responses containing visual information.

[0109] The response generation unit can analyze questions and requests in different languages ​​and generate responses in multiple languages. For example, if an end user asks in different languages, such as "Tell me about restaurants nearby," the generation AI analyzes the language and generates responses in multiple languages. For example, it provides a response such as, "There's a XX restaurant nearby. Its address is △△." Also, if an end user asks in different languages, such as "What's the weather like today?", the response generation unit analyzes the language and provides weather information in multiple languages. For example, it generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees." Also, if an end user asks in different languages, such as "Tell me about cafes nearby," the response generation unit analyzes the language and provides cafe information in multiple languages. For example, it generates a response such as, "There's a XX cafe nearby. Its address is △△." This makes it possible to analyze questions and requests in different languages ​​and generate responses in multiple languages.

[0110] The response generation unit can use the emotion estimation function to adjust the tone and style of the response based on the end user's emotion. For example, if an end user asks, "What's the weather like today?", the generation AI uses the emotion estimation function to estimate the end user's emotion and generates a response in a tone and style based on that emotion. For example, it provides a response such as, "The weather is sunny today. The maximum temperature is 25 degrees. It looks like it's going to be a great day." Also, if an end user asks, "Tell me about a nearby restaurant," the response generation unit can use the emotion estimation function to estimate the end user's emotion and generate a response in a tone and style based on that emotion. For example, it provides a response such as, "The nearby XX restaurant has a quiet and relaxing atmosphere. Its address is △△." Also, if an end user asks, "Tell me about a nearby cafe," the response generation unit can use the emotion estimation function to estimate the end user's emotion and generate a response in a tone and style based on that emotion. For example, it provides a response such as, "The nearby XX cafe has a bright and lively atmosphere. Its address is △△." This allows the generation AI to adjust the tone and style of the response based on the end user's emotion.

[0111] The response sending unit can refer to the end user's past response history and provide consistent responses. For example, if the end user asks, "Tell me about nearby restaurants," the generation AI can refer to the past response history and provide consistent restaurant information. For example, it can generate a response such as, "There's a XX restaurant nearby that I've visited before. Its address is △△." Also, if the end user asks, "What's the weather like today?" the response sending unit can refer to the past response history and provide consistent weather information. For example, it can generate a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Also, if the end user asks, "Tell me about nearby cafes," the response sending unit can refer to the past response history and provide consistent cafe information. For example, it can generate a response such as, "There's a XX cafe nearby that I've visited before. Its address is △△." This allows the generation AI to refer to the end user's past response history and provide consistent responses.

[0112] The response sending unit can provide a response based on the end user's current situation. For example, if an end user asks, "Tell me about nearby restaurants," the generation AI provides restaurant information based on the end user's current time zone and location. For example, it generates a response such as, "There is a certain restaurant within 500 meters of my current location. The address is △△." Also, if an end user asks, "What's the weather like today?" the response sending unit provides weather information based on the end user's current time zone. For example, it generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees, and the chance of precipitation is 0%." Also, if an end user asks, "Tell me about nearby cafes," the response sending unit provides cafe information based on the end user's current time zone and location. For example, it generates a response such as, "There is a certain cafe within 200 meters of my current location. The address is △△." This makes it possible to provide a response based on the end user's current situation.

[0113] The response sending unit can use the emotion estimation function to adjust the timing and frequency of responses according to the end user's emotions. For example, when an end user asks, "What's the weather like today?", the generation AI uses the emotion estimation function to estimate the end user's emotions and sends a response at a timing appropriate to that emotion. For example, to elicit positive emotions, the response may be sent immediately. Also, when an end user asks, "Tell me about a nearby restaurant," the response sending unit can use the emotion estimation function to estimate the end user's emotions and send a response at a frequency appropriate to that emotion. For example, to provide a relaxing atmosphere, the response may be sent with a slight delay. Also, when an end user asks, "Tell me about a nearby cafe," the response sending unit can use the emotion estimation function to estimate the end user's emotions and send a response at a timing appropriate to that emotion. For example, to lift the user's spirits, the response may be sent immediately. This makes it possible to adjust the timing and frequency of responses according to the end user's emotions.

[0114] The response sending unit can provide a response including media according to the end user's preferences. For example, if the end user asks, "Tell me about restaurants nearby," the generation AI provides a response including images according to the end user's preferences. For example, it generates a response such as, "There's a XX restaurant nearby. Please see the image below." Also, if the end user asks, "What's the weather like today?" the response sending unit can provide a response including audio according to the end user's preferences. For example, it generates an audio response such as, "Today's weather is sunny. The maximum temperature is 25 degrees." Also, if the end user asks, "Tell me about cafes nearby," the response sending unit can provide a response including images according to the end user's preferences. For example, it generates a response such as, "There's a XX cafe nearby. Please see the image below." This makes it possible to provide a response including media according to the end user's preferences.

[0115] The response sending unit can provide a response in a format optimized for the end user's device. For example, if the end user asks, "Tell me about nearby restaurants," the generation AI provides a response in a format optimized for the end user's device. For example, in the case of a smartphone, the generation AI generates a response including short text and images. Also, if the end user asks, "What's the weather like today?" the response sending unit can provide a response in a format optimized for the end user's device. For example, in the case of a smart watch, the generation AI generates a response including short text and audio. Also, if the end user asks, "Tell me about nearby cafes," the generation AI can provide a response in a format optimized for the end user's device. For example, in the case of a tablet, the generation AI generates a response including detailed text and images. This makes it possible to provide a response in a format optimized for the end user's device.

[0116] The response sending unit can use the emotion estimation function to adjust the format and content of the response based on the end user's emotion. For example, when an end user asks, "What's the weather like today?", the generation AI uses the emotion estimation function to estimate the end user's emotion and provides a response with a format and content based on that emotion. For example, to elicit positive emotions, the generation AI generates a response including text and images in a bright tone. When an end user asks, "Tell me about nearby restaurants," the response sending unit can use the emotion estimation function to estimate the end user's emotion and provide a response with a format and content based on that emotion. For example, to provide a relaxing atmosphere, the generation AI generates a response including text and images in a calm tone. When an end user asks, "Tell me about nearby cafes," the response sending unit can use the emotion estimation function to estimate the end user's emotion and provide a response with a format and content based on that emotion. For example, to lift the mood, the generation AI generates a response including text and images in a bright tone. This makes it possible to adjust the format and content of the response based on the end user's emotion.

[0117] The system provides additional premium services when end users submit specific questions or requests, generating revenue from the additional fees. For example, if an end user asks, "Tell me about nearby restaurants," the AI ​​generator can provide detailed restaurant reviews and special offer information as a premium service, generating revenue from the additional fees. For example, it generates a response such as, "There's a nearby restaurant called XX. Its address is △△. Premium members can also view special offer information." Similarly, if an end user asks, "What's the weather like today?" the AI ​​generator can provide detailed weather forecasts and weather warning information as a premium service, generating revenue from the additional fees. For example, it generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. Premium members can also view weather warning information." Similarly, if an end user asks, "Tell me about nearby cafes," the AI ​​generator can provide detailed cafe reviews and special offer information as a premium service, generating revenue from the additional fees. For example, it generates a response such as, "There's a nearby cafe called XX. Its address is △△. Premium members can also view special offer information." This allows the system to provide additional premium services for specific questions or requests, generating revenue from the additional fees.

[0118] The system provides discounts and special offers when end users submit questions or requests a certain number of times, thereby increasing frequency of use. For example, if an end user submits questions or requests a certain number of times, the generation AI provides discount coupons and special offers. For example, a special offer may be offered such as, "If you submit 10 questions, your next question will be free." Furthermore, if an end user submits questions or requests a certain number of times, the generation AI provides special offer information to increase frequency of use. For example, a special offer may be offered such as, "If you submit 20 questions, you will be upgraded to a premium membership for free." Furthermore, if an end user submits questions or requests a certain number of times, the generation AI provides special offer information to increase frequency of use. For example, a special offer may be offered such as, "If you submit 30 questions, you will receive a special discount coupon." This allows for discounts and special offers to be offered for questions or requests a certain number of times, thereby increasing frequency of use.

[0119] The system uses the emotion estimation function to provide perks and discounts that correspond to the end user's emotions, encouraging usage. For example, when an end user submits a question or request, the generation AI uses the emotion estimation function to estimate the end user's emotions and provide perks and discounts that elicit positive emotions. For example, a perk such as, "To make you feel even better, your next question will be free." is provided. Also, when an end user submits a question or request, the system uses the emotion estimation function to estimate the end user's emotions and provide perks and discounts that elicit positive emotions. For example, a perk such as, "To make you feel even better, you will be upgraded to a premium membership for free." is provided. In this way, perks and discounts that correspond to the end user's emotions can be provided, encouraging usage.

[0120] The system generates revenue from advertising and sponsorship in addition to upstream SMS communication fees. For example, when an end user sends a question or request, the generation AI displays a relevant advertisement along with the response, earning advertising revenue. For example, it provides a response such as, "There's a nearby restaurant called XX. Its address is △△. Please see the advertisement below." Also, when an end user sends a question or request, the generation AI displays sponsorship information along with the response, earning sponsorship revenue. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. Please see the sponsor information below." Also, when an end user sends a question or request, the generation AI displays a relevant advertisement along with the response, earning advertising revenue. For example, it provides a response such as, "There's a nearby cafe called XX. Its address is △△. Please see the advertisement below." This allows the system to generate revenue from advertising and sponsorship in addition to upstream SMS communication fees.

[0121] The system earns revenue from referral fees when end users refer other users. For example, when an end user refers another user, the generation AI earns revenue from the referral fees. For example, the system may provide a perk such as, "If you refer a friend, your next question will be free." Also, when an end user refers another user, the system earns revenue from the referral fees. For example, the system may provide a perk such as, "If you refer a friend, you will receive a special discount coupon." Also, when an end user refers another user, the system earns revenue from the referral fees. For example, the system may provide a perk such as, "If you refer a friend, you will be upgraded to a premium membership for free." This allows the system to earn revenue from referral fees when an end user refers other users.

[0122] The system uses the emotion estimation function to provide advertisements and promotions based on the end user's emotions, thereby increasing revenue. For example, when an end user submits a question or request, the generation AI uses the emotion estimation function to estimate the end user's emotions and provide advertisements based on those emotions. For example, it provides a response such as, "To make you feel even better, please take a look at the advertisement below." Also, when an end user submits a question or request, the system uses the emotion estimation function to estimate the end user's emotions and provide promotions based on those emotions. For example, it provides a response such as, "To make you feel even better, please take a look at the sponsor information below." Also, when an end user submits a question or request, the system uses the emotion estimation function to estimate the end user's emotions and provide advertisements based on those emotions. For example, it provides a response such as, "To make you feel even better, please take a look at the sponsor information below." This allows the system to provide advertisements and promotions based on the end user's emotions, thereby increasing revenue.

[0123] The system proposes new services based on the end user's interests and diversifies services. For example, if an end user asks, "Tell me about restaurants nearby," the generation AI proposes new services based on the end user's interests and diversifies services. For example, if an end user asks, "What's the weather like today?" ...What's the weather like today?" the generation AI proposes new services based on the end user's interests and diversifies services. For example, if an end user asks, "What's the weather like today?" the generation AI proposes new services based on the end user's interests and diversifies services. For example, if an end user asks, "What's the weather like today?" the generation AI proposes new services based on the end user's interests and diversifies services.

[0124] The system collects end user feedback and improves services based on that feedback. For example, if an end user asks, "Tell me about a nearby restaurant," the generation AI collects end user feedback and improves services based on that feedback. For example, it provides a response such as, "There's a XX restaurant nearby. Its address is △△. What do you think?". Also, if an end user asks, "What's the weather like today?" the generation AI collects end user feedback and improves services based on that feedback. For example, it provides a response such as, "It's sunny today. The maximum temperature is 25 degrees. What do you think?". Also, if an end user asks, "Tell me about a nearby cafe," the generation AI collects end user feedback and improves services based on that feedback. For example, it provides a response such as, "There's a XX cafe nearby. Its address is △△. What do you think?". This makes it possible to improve services based on end user feedback.

[0125] The system uses the emotion estimation function to develop and provide new services based on the end user's emotions. For example, if an end user asks, "Tell me about a nearby restaurant," the generation AI uses the emotion estimation function to infer the end user's emotions and develops and provides a new service based on that emotion. For example, it provides a response such as, "There's a nearby XX restaurant. Its address is △△. You can also view information about cafes where you can relax." Similarly, if an end user asks, "What's the weather like today?" the system uses the emotion estimation function to infer the end user's emotions and develops and provides a new service based on that emotion. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. You can also view the weekend weather forecast." Similarly, if an end user asks, "Tell me about a nearby cafe," the generation AI uses the emotion estimation function to infer the end user's emotions and develops and provides a new service based on that emotion. For example, it provides a response such as, "There's a nearby XX cafe. Its address is △△. You can also view information about restaurants that will lift your spirits." This allows the system to develop and provide new services based on the end user's emotions.

[0126] The system integrates services from different industries and fields to provide crossover services. For example, when an end user asks, "Tell me about restaurants nearby," the generation AI integrates services from different industries and fields to provide a crossover service. For example, it provides a response such as, "There's a XX restaurant nearby. Its address is △△. You can also view information about nearby tourist attractions." Similarly, when an end user asks, "What's the weather like today?" the generation AI integrates services from different industries and fields to provide a crossover service. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. You can also view information about weekend events." Similarly, when an end user asks, "Tell me about cafes nearby," the generation AI integrates services from different industries and fields to provide a crossover service. For example, it provides a response such as, "There's a XX cafe nearby. Its address is △△. You can also view information about nearby shopping." This allows the system to integrate services from different industries and fields to provide a crossover service.

[0127] The system provides personalized services tailored to the end user's lifestyle. For example, if an end user asks, "Tell me about restaurants nearby," the generation AI provides personalized services tailored to the end user's lifestyle. For example, it provides a response such as, "There's a certain restaurant nearby. Its address is △△. You can also view menu information tailored to your preferences." Similarly, if an end user asks, "What's the weather like today?" the generation AI provides personalized services tailored to the end user's lifestyle. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. You can also view clothing advice tailored to your activities." Similarly, if an end user asks, "Tell me about cafes nearby," the generation AI provides personalized services tailored to the end user's lifestyle. For example, it provides a response such as, "There's a certain cafe nearby. Its address is △△. You can also view drink information tailored to your preferences." This makes it possible to provide personalized services tailored to the end user's lifestyle.

[0128] The system uses the emotion estimation function to customize services based on the end user's emotions, improving satisfaction. For example, if an end user asks, "Tell me about nearby restaurants," the generation AI uses the emotion estimation function to infer the end user's emotions and provides customized restaurant information based on that emotion. For example, it provides a response such as, "There's a nearby XX restaurant. Its address is △△. You can also view information about restaurants with a relaxing atmosphere." Similarly, if an end user asks, "What's the weather like today?" the system uses the emotion estimation function to infer the end user's emotions and provides customized weather information based on that emotion. For example, it provides a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees. You can also view information about activities to lift your spirits." Similarly, if an end user asks, "Tell me about nearby cafes," the generation AI uses the emotion estimation function to infer the end user's emotions and provides customized cafe information based on that emotion. For example, it provides a response such as, "There's a nearby XX cafe. It's address is △△. You can also view information about drinks to refresh your mood." This allows the system to customize services based on the end user's emotions and improve satisfaction.

[0129] The processing flow of the second embodiment will be briefly explained below.

[0130] Step 1: The question receiver receives a question or request from an end user. For example, an end user can send a question such as "What's the weather like today?" or "Can you tell me where the nearest restaurant is?" via SMS. Step 2: The analysis unit analyzes the question or request received by the question receiving unit. For example, the generation AI analyzes the intent of the question using natural language processing technology. Step 3: The response generation unit generates a response based on the content analyzed by the analysis unit. For example, the generation AI generates a response such as, "Today's weather is sunny. The maximum temperature is 25 degrees." Step 4: The response sending unit sends the response generated by the response generating unit to the end user. For example, the generating AI sends the response to the end user via SMS.

[0131] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0132] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0133] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0134] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0135] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0136] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0137] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0138] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0140] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0141] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0142] 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.

[0143] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0144] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0145] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0146] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0147] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0148] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0149] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0150] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

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

[0152] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

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

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0155] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0156] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0157] 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.

[0158] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0159] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0160] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0161] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0162] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0163] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0164] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0165] 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.

[0166] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0167] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0168] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0169] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0170] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0171] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0172] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0173] 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.

[0174] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0175] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0176] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0177] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0178] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0179] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0180] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0181] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0182] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0183] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0184] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0185] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0186] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0187] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0188] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0189] 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.

[0190] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0191] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0192] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0193] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0194] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0195] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0196] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0197] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0198] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a question receiving unit for receiving a question or request from an end user; an analysis unit that analyzes the question or request received by the question receiving unit; a response generation unit that generates a response based on the content analyzed by the analysis unit; a response sending unit that sends the response generated by the response generating unit to an end user. A system characterized by:

2. The question receiving unit Automatically obtain location information for the end user and generate a response based on that location.

2. The system of claim 1.

3. The analysis unit Inferring the end user's emotional state and generating a response according to that emotion 2. The system of claim 1.

4. The question receiving unit receiving the end user's spoken question or request and converting it to text using speech recognition technology; 2. The system of claim 1.

5. The analysis unit Refer to the end user's past purchase history or behavioral history and provide related information 2. The system of claim 1.

6. The analysis unit Estimate the end user's emotions in real time and make suggestions that elicit positive emotions 2. The system of claim 1.

Images