system

Abstract

We provide the system. [Solution] A means for receiving voice input and converting the input voice into text information, A means for analyzing the aforementioned textual information and identifying the content of the voice request, A means of arranging transportation or food delivery services from an external service provider based on identified voice requests, A means of tracking the progress of the arrangement and notifying the user of the progress information, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Since the elderly are not familiar with smartphone and Internet technologies, there is a problem that it is difficult for them to use modern services such as ride-sharing and food delivery services. In addition, there are problems with the complexity of the interface and operability when the elderly use such services. Furthermore, it is necessary to provide an environment where the progress of the service can be grasped in real time and the service can be used with confidence.

Means for Solving the Problems

[0005] This invention provides a system that allows elderly people to easily use services via telephone. When a user makes a request by voice, it is converted into text information in real time using speech recognition technology, and the user's intent is accurately understood by an analysis means. Based on the analysis results, ride-sharing and food delivery services are arranged in cooperation with external providers, and their progress is tracked. Furthermore, progress information is notified in real time using speech synthesis technology, providing an environment in which elderly people can use services with peace of mind.

[0006] "Voice input" is the process of acquiring voice information spoken by a user through a receiving device such as a microphone.

[0007] "Textual information" refers to data that represents the content of speech converted by speech recognition technology in text format.

[0008] "Analysis" is the process of analyzing input text information and identifying the user's requests and intentions from its content.

[0009] A "voice request" refers to the specific requests or instructions that a user sends to the system via voice.

[0010] "Transportation" refers to services provided to support users' mobility, such as ride-sharing and taxi services.

[0011] A "food delivery service" refers to a service that delivers food ordered by restaurants and other eateries to a designated location.

[0012] An "external service provider" refers to an entity that exists outside the system and provides services such as transportation or food delivery.

[0013] "Arrangement" refers to the process of making necessary requests to external service providers based on user requests and confirming the service.

[0014] "Progress status" refers to information indicating at what stage or in what state the arranged service currently is.

[0015] "Notification" refers to the act of the system transmitting information to the user in forms such as voice or text.

[0016] "Voice synthesis technology" refers to the technology that generates natural voice based on character information and provides it in an easy-to-hear form for the user.

Brief Explanation of Drawings

[0017] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12]It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0021] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] As shown in Figure 2, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0037] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0038] This invention relates to a system that allows elderly people to easily use ride-sharing and food delivery services via telephone. This system is built by integrating speech recognition technology, natural language processing technology, and speech synthesis technology.

[0039] The user makes a voice request via telephone, telling the system something like, "I'd like a car arranged to take me to the station." The terminal receives this voice and converts it into text in real time. This text is sent to a server, which uses natural language processing technology to analyze the user's intent. As a result of the analysis, the server identifies the service the user is requesting as a rideshare.

[0040] Based on the analyzed information, the server accesses external ride-sharing service providers via APIs. For example, it might request the nearest vehicle to be dispatched based on the user's current location and take them to their destination. If the dispatch is successful, the response from the provider is returned to the server, which then checks the progress of the dispatch.

[0041] Based on this progress information, the server sends a notification to the user using speech synthesis technology. The terminal plays the notification as audio, reporting to the user, for example, "The car will arrive in 10 minutes." The user can then wait with peace of mind based on this information and make further inquiries if necessary.

[0042] For example, the same process applies when a user requests food delivery. If the user says, "I want to order a pizza," the system searches for the nearest partner restaurant, checks the menu, and arranges for the specified food item. The server confirms the order details and delivery time and notifies the user via the terminal.

[0043] Thus, the system of the present invention facilitates access to technology and improves the convenience of daily life by supporting elderly people in intuitively using ride-sharing and food delivery services through voice commands.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The user makes a phone call and makes a voice request. The device receives and records this voice message.

[0047] Step 2:

[0048] The device sends the received audio data to the speech recognition engine, which converts the audio into text.

[0049] Step 3:

[0050] The terminal sends the obtained text data to the server. The server then prepares this text for analysis.

[0051] Step 4:

[0052] The server uses natural language processing technology to analyze the user's request and identify its content. For example, it might determine that a rideshare arrangement is being requested.

[0053] Step 5:

[0054] Based on the analysis results, the server arranges rideshare or food delivery through an external service provider's API. It sends the necessary information as an API request.

[0055] Step 6:

[0056] The server receives a response from the external service provider and confirms that the arrangement is complete. It also retrieves information such as the service progress and estimated arrival time.

[0057] Step 7:

[0058] The server generates a message to report to the user based on the acquired progress information. It uses speech synthesis technology to convert text information into speech.

[0059] Step 8:

[0060] The terminal plays the converted audio data to the user and reports the service status. This allows the user to understand the progress of the service in real time.

[0061] Step 9:

[0062] Users can call again for further inquiries or problems. The server will respond to additional requests and provide the necessary information and guidance.

[0063] (Example 1)

[0064] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0065] There is a need for systems that allow elderly and technologically unfamiliar users to intuitively and easily access transportation and grocery delivery services through voice commands. Conventional systems require many operations and complex procedures, which is a burden on users.

[0066] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0067] In this invention, the server includes means for receiving voice input and converting the input voice into digital information, technology for analyzing the digital information and identifying the intent of the voice request, and technology for arranging transportation means or food delivery services with external suppliers based on the identified voice request. This makes it possible for users to easily request services using their voice.

[0068] "Voice input" is a method of transmitting instructions and requests that users make verbally to a system.

[0069] "Digital information" refers to data obtained by converting voice input into a format that can be processed electronically.

[0070] "Analysis" is the process of extracting meaning and intent contained in digital information.

[0071] "The intent behind a voice request" refers to the content of the wishes or instructions that the user intends to convey through voice.

[0072] "Transportation" refers to services that support travel from a designated departure point to a destination specified by the user.

[0073] A "grocery delivery service" is a service that delivers groceries requested by the user to a specified location.

[0074] An "external supplier" is a third-party organization or company that provides transportation and food delivery services in conjunction with the system.

[0075] "Sound synthesis technology" is a technology that generates text information as speech.

[0076] "Progress information" refers to status information such as the arrangement status and estimated arrival time of services related to the user's request.

[0077] "Instant updates" means that users will be notified quickly when new information becomes available.

[0078] This invention provides a system that allows users to easily access transportation and food delivery services through voice commands. This system is built by integrating voice input technology, natural language processing, and sound synthesis technology.

[0079] Users make voice requests using their phones. For example, they can make a voice request such as, "Please arrange a car to take me to the station." The device converts this voice into text information using the Google® Cloud Speech-to-Text API.

[0080] This converted text information is sent to a server, which uses a generative AI model to perform natural language processing and analyze the intent of the voice request. For example, it might identify that the request is for a rideshare arrangement. Based on the identified request, the server uses APIs to access external providers of transportation or grocery delivery services. Here, the server arranges the appropriate service based on the user's current location and destination.

[0081] Once the arrangement is complete, the server receives a response from the external supplier and checks the progress of the service. This progress information is generated as audio using sound synthesis technology. The terminal plays this audio to the user, notifying them in a format such as, "The car will arrive in 10 minutes." This allows the user to confidently check the progress of the service.

[0082] As a concrete example of its use, if a user says, "I want to order a pizza," the terminal converts the voice into text, and the server analyzes the request using a generated AI model. The server then accesses the nearest restaurant and arranges for the specified food item. Once the delivery time is confirmed, the server informs the user of this information via voice notification.

[0083] Examples of prompts include, "How can elderly people easily use ride-sharing services by phone?" and "Please explain what a voice-based pizza ordering system is."

[0084] In this way, the entire system is designed so that users can intuitively request services using voice and easily obtain the results. The goal is to ensure that even elderly users and users unfamiliar with technology can use these services with peace of mind.

[0085] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0086] Step 1:

[0087] The user makes a voice request via telephone. The device receives the voice data as input. The device processes this voice data using the Google Cloud Speech-to-Text API and outputs it as text. This conversion transforms the voice into digital text data.

[0088] Step 2:

[0089] The terminal sends the data, converted into text information, to the server. The server uses the received text information as input and performs analysis using a generative AI model. Specifically, it uses natural language processing technology to extract the user's intent from the text data. Through this analysis, it identifies an intent such as "arrange a car to the station," and obtains the result as output data.

[0090] Step 3:

[0091] Based on the analysis results, the server initiates access to external suppliers. It uses identified service requests and user location information as input. Using an API, it sends data to the external supplier's system and arranges the requested service (e.g., rideshare arrangement). This process allows the server to receive the service arrangement results and obtain response data from the supplier as output.

[0092] Step 4:

[0093] The server uses response data received from external suppliers as input to check progress information. Based on this check, it generates a voice message using sound synthesis technology. As output, it creates voice data containing progress information and makes it available for notification to the user.

[0094] Step 5:

[0095] The terminal receives audio data sent from the server as input. The terminal plays this data as audio and notifies the user directly. This allows the user to check the situation by voice, such as "The car will arrive in 10 minutes."

[0096] (Application Example 1)

[0097] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0098] This invention aims to solve the problem that elderly people find it difficult to intuitively use the latest technologies and to provide an environment in which more people can use transportation and food delivery services with peace of mind. Specifically, the objective is to enable elderly people to arrange transportation and food delivery using only simple voice commands and to monitor the progress in real time.

[0099] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0100] In this invention, the server includes means for receiving voice input and converting the input voice into text information; means for analyzing the text information and identifying the content of the voice request; means for arranging transportation or food delivery services with an external service provider based on the identified voice request; means for tracking the progress of the arrangement and notifying the user of the progress information; means for obtaining the user's current location and arranging the nearest resources when arranging with an external service provider; means for generating the progress information using speech synthesis technology and providing it to the user; means for voice input and notification using a smartphone or smart glasses; and means for obtaining data required by the user in real time based on the notification information generated using the speech synthesis technology and notifying the user as quickly as possible. This makes it possible for elderly people to easily use daily living services by voice and smoothly grasp the information.

[0101] "Voice input" is the process of capturing the voice spoken by the user as a digital signal into the system.

[0102] "Textual information" refers to text data converted from voice input, and it forms the basis for analysis and processing.

[0103] A "voice request" refers to a user's wishes or instructions communicated to the system via voice, and is subject to specific service arrangements and information provision.

[0104] An "external service provider" is a service provider that the system connects to in response to user requests and provides services such as transportation and food delivery.

[0105] "Progress status" refers to the current stage of a service that has been arranged, and is part of the information provided to the user.

[0106] "Speech synthesis technology" is a technology that converts text information into audio data and provides it to users as audio.

[0107] "Current location" refers to the user's physical location and is information used to identify the nearest resource when arranging a service.

[0108] A "smartphone" is a type of portable information terminal that functions as part of a system by incorporating features such as voice input and notification capabilities.

[0109] "Smart glasses" are a type of wearable device that, when worn on the eyes, enables information display and voice input.

[0110] "Notification information" refers to information provided by the system to inform users about the progress and results of service arrangements.

[0111] The system that implements this application example includes a series of processes that integrate voice input, natural language processing, external service arrangement, progress management, and notifications.

[0112] The server receives instructions from the user using voice input and uses speech recognition software to convert the voice into text. Next, it analyzes the acquired text information using natural language processing techniques to identify the user's intended request. In this process, a generative AI model is utilized to gain a more precise understanding of the request.

[0113] After understanding the user's textual request, the server accesses appropriate external service providers via APIs and arranges the nearest resources based on the user's current location. For example, if the user instructs "I want to eat udon," the server finds the nearest food and beverage provider and automates the ordering process. To do this, the server uses location services and HTTPS communication.

[0114] The progress of the arrangement is updated in real time based on feedback from external service providers. The server converts this progress information into speech using speech synthesis technology and provides feedback to the user. This notification is performed using a smartphone or smart glasses.

[0115] These voice notifications allow users to quickly and intuitively check the progress of their order on the spot. For example, they might receive a message like, "Your udon order is complete. It will be delivered within 30 minutes."

[0116] A concrete example would be when a user says, "I want to order a pizza," and the nearest delivery service accepts the order and notifies the user via voice, "It will be delivered in 24 minutes."

[0117] An example of a prompt message might be: "Based on this audio data, please tell me how to interpret the user's intent and arrange a delivery service suitable for an elderly person."

[0118] Based on the above, this system is designed to be intuitively usable by elderly people themselves and to improve the convenience of their daily lives.

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] The terminal receives voice input from the user. The voice data is converted into digital format using the microphone subsystem and then passed to the speech recognition module, which converts the voice to text. In this process, the input is voice data, and the output is text information. The terminal then sends this text data to the server.

[0122] Step 2:

[0123] The server passes the received text information to the natural language processing engine. Here, a generative AI model is used to analyze the text data and interpret the user's intent. In this process, the input is text data, and the output is a specific request from the user (e.g., ordering a specific food item). Based on the analysis results, the server moves on to the next processing step.

[0124] Step 3:

[0125] The server sends an API request to an external service provider in response to the user's request. This request obtains the user's current location and performs calculations to arrange the nearest resource. The inputs are the user's request and current location information, and the output is the result of the arranged service (e.g., confirmed order information). The server then passes this information to the next step.

[0126] Step 4:

[0127] The server uses a speech synthesis engine to convert the progress information into speech based on the order results obtained. The input is the order result information, and the output is speech data. The server sends this speech data to the terminal.

[0128] Step 5:

[0129] The terminal plays the audio data received from the server and notifies the user. By listening to the notified audio information, the user can understand the service availability and estimated time. In this step, the input is audio data, and the output is an audio presentation to the user. The user can make further voice inputs as needed to convey additional requests to the terminal.

[0130] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0131] This invention relates to a system that provides an advanced user experience when users utilize ride-sharing or food delivery services via telephone by combining it with an emotion engine. This system is built by integrating an emotion engine with speech recognition technology, natural language processing technology, and speech synthesis technology.

[0132] When a user makes a voice request via phone, the device receives and records the audio. Using speech recognition technology, the recorded audio is converted to text, while an emotion engine analyzes the audio data to recognize the user's emotional state. For example, if the user is feeling anxious when making the request, that emotion is identified.

[0133] The server receives textual and sentiment data, uses natural language processing techniques to analyze the user's specific request, and identifies what the request is asking for. For example, it might determine that the user needs to arrange a rideshare.

[0134] Next, based on the analyzed information, the server accesses external ride-sharing service providers via API to arrange the necessary services. If the arrangement is successful, a response is returned from the external provider, and the server checks the progress of the arrangement. At this time, notification information is generated based on the results of the emotion engine. If the user is feeling anxious, the message is adjusted to include prompt action or a warning.

[0135] Notification information is converted into speech using speech synthesis technology, and the device plays that information back to the user as audio. For example, if a user urgently requests, "I need a car immediately," the device might report, "The car will arrive in 5 minutes. Don't worry."

[0136] Furthermore, if the emotion engine detects an abnormal emotional state, such as extreme stress or frustration, the server can also notify customer support to provide additional assistance. Thus, the present invention, which combines the emotion engine, aims to help users obtain a more appropriate and personalized service experience.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The user contacts the system by phone and requests service via voice. The terminal receives this voice and records it through the microphone.

[0140] Step 2:

[0141] The device inputs the received audio data into its speech recognition engine and converts the data into text. Simultaneously, it uses an emotion engine to identify the user's emotional state from the audio data.

[0142] Step 3:

[0143] The terminal sends the generated text information and sentiment data to the server. The server uses natural language processing technology to analyze the text information and identify the user's request.

[0144] Step 4:

[0145] Based on the analyzed information, the server accesses the APIs of external service providers to arrange the transportation or food delivery service requested by the user.

[0146] Step 5:

[0147] The server receives the information returned from the external service provider and confirms that the service arrangement is complete. It also retrieves the arrangement details and prepares a notification.

[0148] Step 6:

[0149] The server customizes notification information based on emotional data obtained from the emotion engine. If the user is feeling anxious, notifications are adjusted to be sent more quickly. Reassuring messages are also included as needed.

[0150] Step 7:

[0151] The server converts notification messages into speech using speech synthesis technology. This information is then played back to the user by their device. The user can then check the service progress in real time.

[0152] Step 8:

[0153] If the emotion engine detects an abnormal emotional state, the server can determine that additional support is needed and send an alert to customer support.

[0154] Step 9:

[0155] The user can make further inquiries as needed, and the server will provide additional information and assistance in response to those requests.

[0156] (Example 2)

[0157] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0158] Conventional voice request analysis systems failed to adequately provide personalized notifications that took into account the user's emotional state, nor to respond appropriately to abnormal emotional states. As a result, users sometimes received notifications at inappropriate times or in inappropriate ways, and it was difficult to respond quickly to stress or frustration. This made it difficult to provide a better user experience.

[0159] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0160] In this invention, the server includes means for receiving voice input and converting the input voice into text information, emotion recognition means for analyzing the user's emotional state, and means for arranging transportation or food supply services with external service providers based on identified voice requests. This enables flexible notifications and quick responses that respond to the user's emotions.

[0161] "Voice input" refers to instructions or requests that users give to a system using their voice.

[0162] "Textual information" refers to data that has been converted from voice input into a machine-recognizable string of characters.

[0163] "Voice requests" refer to the specific content and actions that users request from the system, extracted by analyzing voice input.

[0164] "External service providers" refer to external service providers whose work is requested through integration with the system.

[0165] "Emotion recognition means" refers to methods or devices that analyze and identify an emotional state from a user's voice or other inputs.

[0166] "Notification information" refers to information used to communicate the content and progress of what the system provides to users.

[0167] "Alarming measures" refer to functions or devices that detect abnormal emotional states, alert the user to a problem, and indicate that additional action is required.

[0168] "Speech synthesis technology" refers to a technology that generates text information as speech and conveys information to users aurally.

[0169] This invention relates to a system that provides personalized services to users based on voice input. This system achieves an advanced user experience by integrating voice recognition technology, natural language processing technology, and emotion recognition technology. Specific embodiments are described below.

[0170] The device first receives voice input from the user via telephone. This voice is recorded and converted into text using speech recognition software. For example, open-source speech recognition libraries and cloud-based speech recognition services are commonly available as speech recognition software.

[0171] Next, the server receives the text information sent from the terminal and analyzes the user's voice request using natural language processing technology. Based on the analyzed request, the necessary transportation and food supply services are identified and arranged through the API of external service providers. At this time, emotion recognition is also used to analyze the user's emotional state from the voice input. Emotion recognition is often performed by analyzing features such as intonation, tempo, and volume of the voice.

[0172] For example, if a user makes an urgent request such as "I need a ride arranged immediately," the emotion recognition system identifies that emotion and prompts the server to take immediate action. When the arrangement is successful, the server generates progress information and notifies the terminal using speech synthesis technology. The speech synthesis technology uses, for example, a cloud-based speech synthesis engine to output text information as speech.

[0173] As a concrete example, here is an example of a prompt message for a generative AI model: "If the user is feeling anxious, generate a message that will respond appropriately and reassure them." Through this prompt, the AI ​​model can generate the most appropriate message based on the user's emotions.

[0174] Thus, the present invention enables the provision of a more personalized service experience to users by considering emotions in notifications and enhancing responsiveness.

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] The device receives voice input from the user via telephone. This voice data is recorded and saved in a digital format. The input is the user's raw voice, and the output is a recorded digital audio file.

[0178] Step 2:

[0179] The device inputs the recorded audio data into a speech recognition system and converts it into text. Speech recognition technology is used, for example, by utilizing a cloud-based speech recognition service. In this process, the audio data is converted into text data. The output is the user's request in text format.

[0180] Step 3:

[0181] The server receives text data from the terminal and inputs it into the emotion recognition engine. The engine processes not only text but also emotional information extracted from speech to analyze the user's emotional state. The data processing performed here is emotion identification based on text and speech signal processing. The output is emotion data indicating the user's emotional state.

[0182] Step 4:

[0183] The server uses natural language processing technology to analyze text data and identify the specific content of the user's request. This involves analyzing the text structure and extracting keywords. The output is the analyzed request information.

[0184] Step 5:

[0185] Based on the analysis results, the server accesses the API of the external service provider for the identified service (e.g., ridesharing) to make the necessary arrangements. This process involves API communication and receiving responses from the external service provider. The output is status information based on the success or failure of the arrangement.

[0186] Step 6:

[0187] The server considers emotional data to generate an appropriate notification message for the user. Using speech synthesis technology, the generated text message is converted to speech and sent to the terminal. The data processing in this step is text-to-speech conversion. The output is a notification message in audio format.

[0188] Step 7:

[0189] The terminal plays the voice notification message received from the server and presents it to the user. Based on the response from the server, the user can obtain the necessary information. The output is the voice information received by the user.

[0190] (Application Example 2)

[0191] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0192] In modern voice-based services, it's common to provide information without considering the user's emotions. This leads to challenges such as a lack of personalized responses tailored to the user's situation, resulting in decreased convenience and satisfaction. This is especially true for services requiring immediacy, such as food delivery, where communication that responds to the user's emotions is crucial.

[0193] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0194] In this invention, the server includes means for receiving voice input and converting the input voice into text information, means for analyzing the text information and identifying the content of the voice request, and means for determining the user's emotional state from the voice input using emotion analysis technology and adjusting notification information based on the emotion. This makes it possible to provide personalized notifications that correspond to the user's emotional state.

[0195] "Voice input" refers to information or commands provided by the user verbally.

[0196] "Means of converting into text information" refers to technologies that analyze voice input and convert it into corresponding text data.

[0197] "Means for identifying the content of voice requests" refers to the process of analyzing the converted text information to clarify what the user is requesting.

[0198] "Transportation or meal delivery service" refers to an external service that arranges vehicles or meals according to the user's request.

[0199] An "external service provider" is a third-party organization that actually provides the transportation or meal delivery requested by the user.

[0200] "Means of notifying users of progress information" refers to technologies that inform users of the stage in which their request is being processed.

[0201] "Emotional analysis technology" is a method for visualizing and understanding a user's emotional state from their voice.

[0202] A "means for adjusting notification information" refers to a mechanism that optimizes the information and message content provided according to the user's emotional state.

[0203] The system that implements this invention primarily involves a server and a terminal. The server is equipped with speech recognition technology, natural language processing technology, sentiment analysis technology, and speech synthesis technology. Specifically, it uses the Google Speech-to-Text API to convert speech input into text data and the Python NLTK library to analyze the content of this text. The user's emotional state is analyzed using IBM Watson® Tone Analyzer, and notification information is adjusted based on the results. This adjusted notification information is then converted into speech using Amazon Polly and provided to the user via the terminal.

[0204] The device, such as a smartphone or computer, provides a user interface for users to request services by voice. The device plays voice feedback from the server, providing a personalized experience tailored to the user's emotions.

[0205] For example, if a user requests "I want my pizza delivered quickly" using their smartphone, the server recognizes the user's impatience and calmly provides feedback in a voice that the pizza is expected to be delivered within 20 minutes.

[0206] An example of a prompt for a generative AI model is: "If a user is hungry and irritable, how can you generate a reassuring voice message? Please provide an answer based on a specific scenario." This prompt provides guidance for generating more appropriate user responses.

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] The user provides voice input to the device. This voice input is captured through the smartphone's microphone and sent to the server. This primarily contains basic voice data indicating the user's desired service.

[0210] Step 2:

[0211] The server uses the Google Speech-to-Text API to convert received speech input into text. Speech data is the input, and corresponding text data is generated as the output. This text data forms the basis for subsequent processing steps.

[0212] Step 3:

[0213] The server parses the converted character information using the Python NLTK library. The input here is text data, and the output is an identification of the specific content of the user's voice request. This allows the server to understand what the user is asking for.

[0214] Step 4:

[0215] The server uses IBM Watson Tone Analyzer to perform sentiment analysis based on text data. The input is the analyzed text information, and based on that, the user's emotional state is output. For example, information such as whether the user is anxious or relaxed.

[0216] Step 5:

[0217] The server uses Amazon Polly to generate customized notification information as voice based on the results of sentiment analysis. Here, the input is sentiment state and user request information, and the output is a personalized voice message.

[0218] Step 6:

[0219] The terminal plays an audio message provided by the server to the user. Here, the direct input is audio data, and the output is auditory feedback to the user. At this stage, the user checks the progress of the service and responses through the audio message.

[0220] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0221] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0222] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0226] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0227] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0228] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0229] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0230] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0231] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0232] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0233] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0234] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0235] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0236] This invention relates to a system that allows elderly people to easily use ride-sharing and food delivery services via telephone. This system is built by integrating speech recognition technology, natural language processing technology, and speech synthesis technology.

[0237] The user makes a voice request via telephone, telling the system something like, "I'd like a car arranged to take me to the station." The terminal receives this voice and converts it into text in real time. This text is sent to a server, which uses natural language processing technology to analyze the user's intent. As a result of the analysis, the server identifies the service the user is requesting as a rideshare.

[0238] Based on the analyzed information, the server accesses external ride-sharing service providers via APIs. For example, it might request the nearest vehicle to be dispatched based on the user's current location and take them to their destination. If the dispatch is successful, the response from the provider is returned to the server, which then checks the progress of the dispatch.

[0239] Based on this progress information, the server sends a notification to the user using speech synthesis technology. The terminal plays the notification as audio, reporting to the user, for example, "The car will arrive in 10 minutes." The user can then wait with peace of mind based on this information and make further inquiries if necessary.

[0240] For example, the same process applies when a user requests food delivery. If the user says, "I want to order a pizza," the system searches for the nearest partner restaurant, checks the menu, and arranges for the specified food item. The server confirms the order details and delivery time and notifies the user via the terminal.

[0241] Thus, the system of the present invention facilitates access to technology and improves the convenience of daily life by supporting elderly people in intuitively using ride-sharing and food delivery services through voice commands.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The user makes a phone call and makes a voice request. The device receives and records this voice message.

[0245] Step 2:

[0246] The device sends the received audio data to the speech recognition engine, which converts the audio into text.

[0247] Step 3:

[0248] The terminal sends the obtained text data to the server. The server then prepares this text for analysis.

[0249] Step 4:

[0250] The server uses natural language processing technology to analyze the user's request and identify its content. For example, it might determine that a rideshare arrangement is being requested.

[0251] Step 5:

[0252] Based on the analysis results, the server arranges rideshare or food delivery through an external service provider's API. It sends the necessary information as an API request.

[0253] Step 6:

[0254] The server receives a response from the external service provider and confirms that the arrangement is complete. It also retrieves information such as the service progress and estimated arrival time.

[0255] Step 7:

[0256] The server generates a message to report to the user based on the acquired progress information. It uses speech synthesis technology to convert text information into speech.

[0257] Step 8:

[0258] The terminal plays the converted audio data to the user and reports the service status. This allows the user to understand the progress of the service in real time.

[0259] Step 9:

[0260] Users can call again for further inquiries or problems. The server will respond to additional requests and provide the necessary information and guidance.

[0261] (Example 1)

[0262] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0263] There is a need for systems that allow elderly and technologically unfamiliar users to intuitively and easily access transportation and grocery delivery services through voice commands. Conventional systems require many operations and complex procedures, which is a burden on users.

[0264] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0265] In this invention, the server includes means for receiving voice input and converting the input voice into digital information, technology for analyzing the digital information and identifying the intent of the voice request, and technology for arranging transportation means or food delivery services with external suppliers based on the identified voice request. This makes it possible for users to easily request services using their voice.

[0266] "Voice input" is a method of transmitting instructions and requests that users make verbally to a system.

[0267] "Digital information" refers to data obtained by converting voice input into a format that can be processed electronically.

[0268] "Analysis" is the process of extracting meaning and intent contained in digital information.

[0269] "The intent behind a voice request" refers to the content of the wishes or instructions that the user intends to convey through voice.

[0270] "Transportation" refers to services that support travel from a designated departure point to a destination specified by the user.

[0271] A "grocery delivery service" is a service that delivers groceries requested by the user to a specified location.

[0272] An "external supplier" is a third-party organization or company that provides transportation and food delivery services in conjunction with the system.

[0273] "Sound synthesis technology" is a technology that generates text information as speech.

[0274] "Progress information" refers to status information such as the arrangement status and estimated arrival time of services related to the user's request.

[0275] "Instant updates" means that users will be notified quickly when new information becomes available.

[0276] This invention provides a system that allows users to easily access transportation and food delivery services through voice commands. This system is built by integrating voice input technology, natural language processing, and sound synthesis technology.

[0277] Users make voice requests using their phones. For example, they can make a voice request such as, "Please arrange a car to take me to the station." The device then converts this voice into text using the Google Cloud Speech-to-Text API.

[0278] This converted text information is sent to a server, which uses a generative AI model to perform natural language processing and analyze the intent of the voice request. For example, it might identify that the request is for a rideshare arrangement. Based on the identified request, the server uses APIs to access external providers of transportation or grocery delivery services. Here, the server arranges the appropriate service based on the user's current location and destination.

[0279] When the arrangement is completed, the server receives a response from an external provider and checks the progress of the service. This progress information is generated as voice using speech synthesis technology. The terminal plays this voice to the user and notifies in the form of "The vehicle will arrive in 10 minutes." Thus, the user can confirm the progress of the service with confidence.

[0280] As a specific usage example, when the user conveys "I want to order pizza", the terminal converts the voice into character information, and the server analyzes the request using the generated AI model. Then, the server accesses the nearest restaurant and arranges the specified food. When the delivery time is confirmed, the server conveys that information to the user as a voice notification.

[0281] Examples of prompt sentences include "Please teach me how an elderly person can easily use ride-sharing by phone" and "Please explain what a system for ordering pizza by voice is."

[0282] In this way, the entire system is designed so that the user can intuitively use voice to request a service and easily obtain the result. The aim is that even elderly people and users unfamiliar with technology can use these services with confidence.

[0283] The flow of the specific process in Example 1 will be described using FIG. 11.

[0284] Step 1:

[0285] The user makes a voice request over the phone. As input, voice data is received by the terminal. The terminal processes the voice data using the Google Cloud Speech-to-Text API and outputs it as character information. By this conversion, the voice becomes digital-form text data.

[0286] Step 2:

[0287] The terminal sends the data, converted into text information, to the server. The server uses the received text information as input and performs analysis using a generative AI model. Specifically, it uses natural language processing technology to extract the user's intent from the text data. Through this analysis, it identifies an intent such as "arrange a car to the station," and obtains the result as output data.

[0288] Step 3:

[0289] Based on the analysis results, the server initiates access to external suppliers. It uses identified service requests and user location information as input. Using an API, it sends data to the external supplier's system and arranges the requested service (e.g., rideshare arrangement). This process allows the server to receive the service arrangement results and obtain response data from the supplier as output.

[0290] Step 4:

[0291] The server uses response data received from external suppliers as input to check progress information. Based on this check, it generates a voice message using sound synthesis technology. As output, it creates voice data containing progress information and makes it available for notification to the user.

[0292] Step 5:

[0293] The terminal receives audio data sent from the server as input. The terminal plays this data as audio and notifies the user directly. This allows the user to check the situation by voice, such as "The car will arrive in 10 minutes."

[0294] (Application Example 1)

[0295] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0296] This invention aims to solve the problem that elderly people find it difficult to intuitively use the latest technologies and to provide an environment in which more people can use transportation and food delivery services with peace of mind. Specifically, the objective is to enable elderly people to arrange transportation and food delivery using only simple voice commands and to monitor the progress in real time.

[0297] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0298] In this invention, the server includes means for receiving voice input and converting the input voice into text information; means for analyzing the text information and identifying the content of the voice request; means for arranging transportation or food delivery services with an external service provider based on the identified voice request; means for tracking the progress of the arrangement and notifying the user of the progress information; means for obtaining the user's current location and arranging the nearest resources when arranging with an external service provider; means for generating the progress information using speech synthesis technology and providing it to the user; means for voice input and notification using a smartphone or smart glasses; and means for obtaining data required by the user in real time based on the notification information generated using the speech synthesis technology and notifying the user as quickly as possible. This makes it possible for elderly people to easily use daily living services by voice and smoothly grasp the information.

[0299] "Voice input" is the process of capturing the voice spoken by the user as a digital signal into the system.

[0300] "Textual information" refers to text data converted from voice input, and it forms the basis for analysis and processing.

[0301] A "voice request" refers to a user's wishes or instructions communicated to the system via voice, and is subject to specific service arrangements and information provision.

[0302] "External service provider" refers to a service provider that the system connects to in response to the user's request and provides services such as transportation means and food delivery.

[0303] "Progress status" refers to the stage at which the arranged service is currently at and is part of the information provided to the user.

[0304] "Voice synthesis technology" is a technology that converts text information into voice data and provides it to the user as voice.

[0305] "Current location" refers to the physical location of the user and is information used to identify the nearest resources when arranging services.

[0306] "Smartphone" is a type of mobile information terminal and is a device that operates as part of the system by having voice input and notification functions.

[0307] "Smart glasses" are a type of wearable device that enables information display and voice input when worn on the eyes.

[0308] "Notification information" is information provided by the system to convey to the user about the progress and results of service arrangement.

[0309] The system that realizes this application example includes a series of processes that integrate voice input, natural language processing, external service arrangement, progress management, and notification.

[0310] [[ID=3I]] The server receives instructions from the user using voice input and uses speech recognition software to convert the voice into text. Next, the acquired character information is analyzed using natural language processing technology to identify the user's intended request. In this process, a generative AI model is utilized to understand the request content more precisely.

[0311] After understanding the user's textual request, the server accesses appropriate external service providers via APIs and arranges the nearest resources based on the user's current location. For example, if the user instructs "I want to eat udon," the server finds the nearest food and beverage provider and automates the ordering process. To do this, the server uses location services and HTTPS communication.

[0312] The progress of the arrangement is updated in real time based on feedback from external service providers. The server converts this progress information into speech using speech synthesis technology and provides feedback to the user. This notification is performed using a smartphone or smart glasses.

[0313] These voice notifications allow users to quickly and intuitively check the progress of their order on the spot. For example, they might receive a message like, "Your udon order is complete. It will be delivered within 30 minutes."

[0314] A concrete example would be when a user says, "I want to order a pizza," and the nearest delivery service accepts the order and notifies the user via voice, "It will be delivered in 24 minutes."

[0315] An example of a prompt message might be: "Based on this audio data, please tell me how to interpret the user's intent and arrange a delivery service suitable for an elderly person."

[0316] Based on the above, this system is designed to be intuitively usable by elderly people themselves and to improve the convenience of their daily lives.

[0317] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0318] Step 1:

[0319] The terminal receives voice input from the user. The voice data is converted into digital format using the microphone subsystem and then passed to the speech recognition module, which converts the voice to text. In this process, the input is voice data, and the output is text information. The terminal then sends this text data to the server.

[0320] Step 2:

[0321] The server passes the received text information to the natural language processing engine. Here, a generative AI model is used to analyze the text data and interpret the user's intent. In this process, the input is text data, and the output is a specific request from the user (e.g., ordering a specific food item). Based on the analysis results, the server moves on to the next processing step.

[0322] Step 3:

[0323] The server sends an API request to an external service provider in response to the user's request. This request obtains the user's current location and performs calculations to arrange the nearest resource. The inputs are the user's request and current location information, and the output is the result of the arranged service (e.g., confirmed order information). The server then passes this information to the next step.

[0324] Step 4:

[0325] The server uses a speech synthesis engine to convert the progress information into speech based on the order results obtained. The input is the order result information, and the output is speech data. The server sends this speech data to the terminal.

[0326] Step 5:

[0327] The terminal plays the audio data received from the server and notifies the user. By listening to the notified audio information, the user can understand the service availability and estimated time. In this step, the input is audio data, and the output is an audio presentation to the user. The user can make further voice inputs as needed to convey additional requests to the terminal.

[0328] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0329] This invention relates to a system that provides an advanced user experience when users utilize ride-sharing or food delivery services via telephone by combining it with an emotion engine. This system is built by integrating an emotion engine with speech recognition technology, natural language processing technology, and speech synthesis technology.

[0330] When a user makes a voice request via phone, the device receives and records the audio. Using speech recognition technology, the recorded audio is converted to text, while an emotion engine analyzes the audio data to recognize the user's emotional state. For example, if the user is feeling anxious when making the request, that emotion is identified.

[0331] The server receives textual and sentiment data, uses natural language processing techniques to analyze the user's specific request, and identifies what the request is asking for. For example, it might determine that the user needs to arrange a rideshare.

[0332] Next, based on the analyzed information, the server accesses external ride-sharing service providers via API to arrange the necessary services. If the arrangement is successful, a response is returned from the external provider, and the server checks the progress of the arrangement. At this time, notification information is generated based on the results of the emotion engine. If the user is feeling anxious, the message is adjusted to include prompt action or a warning.

[0333] Notification information is converted into speech using speech synthesis technology, and the device plays that information back to the user as audio. For example, if a user urgently requests, "I need a car immediately," the device might report, "The car will arrive in 5 minutes. Don't worry."

[0334] Furthermore, if the emotion engine detects an abnormal emotional state, such as extreme stress or frustration, the server can also notify customer support to provide additional assistance. Thus, the present invention, which combines the emotion engine, aims to help users obtain a more appropriate and personalized service experience.

[0335] The following describes the processing flow.

[0336] Step 1:

[0337] The user contacts the system by phone and requests service via voice. The terminal receives this voice and records it through the microphone.

[0338] Step 2:

[0339] The device inputs the received audio data into its speech recognition engine and converts the data into text. Simultaneously, it uses an emotion engine to identify the user's emotional state from the audio data.

[0340] Step 3:

[0341] The terminal sends the generated text information and sentiment data to the server. The server uses natural language processing technology to analyze the text information and identify the user's request.

[0342] Step 4:

[0343] Based on the analyzed information, the server accesses the APIs of external service providers to arrange the transportation or food delivery service requested by the user.

[0344] Step 5:

[0345] The server receives the information returned from the external service provider and confirms that the service arrangement is complete. It also retrieves the arrangement details and prepares a notification.

[0346] Step 6:

[0347] The server customizes notification information based on emotional data obtained from the emotion engine. If the user is feeling anxious, notifications are adjusted to be sent more quickly. Reassuring messages are also included as needed.

[0348] Step 7:

[0349] The server converts notification messages into speech using speech synthesis technology. This information is then played back to the user by their device. The user can then check the service progress in real time.

[0350] Step 8:

[0351] If the emotion engine detects an abnormal emotional state, the server can determine that additional support is needed and send an alert to customer support.

[0352] Step 9:

[0353] The user can make further inquiries as needed, and the server will provide additional information and assistance in response to those requests.

[0354] (Example 2)

[0355] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0356] Conventional voice request analysis systems failed to adequately provide personalized notifications that took into account the user's emotional state, nor to respond appropriately to abnormal emotional states. As a result, users sometimes received notifications at inappropriate times or in inappropriate ways, and it was difficult to respond quickly to stress or frustration. This made it difficult to provide a better user experience.

[0357] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0358] In this invention, the server includes means for receiving voice input and converting the input voice into text information, emotion recognition means for analyzing the user's emotional state, and means for arranging transportation or food supply services with external service providers based on identified voice requests. This enables flexible notifications and quick responses that respond to the user's emotions.

[0359] "Voice input" refers to instructions or requests that users give to a system using their voice.

[0360] "Textual information" refers to data that has been converted from voice input into a machine-recognizable string of characters.

[0361] "Voice requests" refer to the specific content and actions that users request from the system, extracted by analyzing voice input.

[0362] "External service providers" refer to external service providers whose work is requested through integration with the system.

[0363] "Emotion recognition means" refers to methods or devices that analyze and identify an emotional state from a user's voice or other inputs.

[0364] "Notification information" refers to information used to communicate the content and progress of what the system provides to users.

[0365] "Alarming measures" refer to functions or devices that detect abnormal emotional states, alert the user to a problem, and indicate that additional action is required.

[0366] "Speech synthesis technology" refers to a technology that generates text information as speech and conveys information to users aurally.

[0367] This invention relates to a system that provides personalized services to users based on voice input. This system achieves an advanced user experience by integrating voice recognition technology, natural language processing technology, and emotion recognition technology. Specific embodiments are described below.

[0368] The device first receives voice input from the user via telephone. This voice is recorded and converted into text using speech recognition software. For example, open-source speech recognition libraries and cloud-based speech recognition services are commonly available as speech recognition software.

[0369] Next, the server receives the text information sent from the terminal and analyzes the user's voice request using natural language processing technology. Based on the analyzed request, the necessary transportation and food supply services are identified and arranged through the API of external service providers. At this time, emotion recognition is also used to analyze the user's emotional state from the voice input. Emotion recognition is often performed by analyzing features such as intonation, tempo, and volume of the voice.

[0370] For example, if a user makes an urgent request such as "I need a ride arranged immediately," the emotion recognition system identifies that emotion and prompts the server to take immediate action. When the arrangement is successful, the server generates progress information and notifies the terminal using speech synthesis technology. The speech synthesis technology uses, for example, a cloud-based speech synthesis engine to output text information as speech.

[0371] As a concrete example, here is an example of a prompt message for a generative AI model: "If the user is feeling anxious, generate a message that will respond appropriately and reassure them." Through this prompt, the AI ​​model can generate the most appropriate message based on the user's emotions.

[0372] Thus, the present invention enables the provision of a more personalized service experience to users by considering emotions in notifications and enhancing responsiveness.

[0373] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0374] Step 1:

[0375] The device receives voice input from the user via telephone. This voice data is recorded and saved in a digital format. The input is the user's raw voice, and the output is a recorded digital audio file.

[0376] Step 2:

[0377] The device inputs the recorded audio data into a speech recognition system and converts it into text. Speech recognition technology is used, for example, by utilizing a cloud-based speech recognition service. In this process, the audio data is converted into text data. The output is the user's request in text format.

[0378] Step 3:

[0379] The server receives text data from the terminal and inputs it into the emotion recognition engine. The engine processes not only text but also emotional information extracted from speech to analyze the user's emotional state. The data processing performed here is emotion identification based on text and speech signal processing. The output is emotion data indicating the user's emotional state.

[0380] Step 4:

[0381] The server uses natural language processing technology to analyze text data and identify the specific content of the user's request. This involves analyzing the text structure and extracting keywords. The output is the analyzed request information.

[0382] Step 5:

[0383] Based on the analysis results, the server accesses the API of the external service provider for the identified service (e.g., ridesharing) to make the necessary arrangements. This process involves API communication and receiving responses from the external service provider. The output is status information based on the success or failure of the arrangement.

[0384] Step 6:

[0385] The server considers emotional data to generate an appropriate notification message for the user. Using speech synthesis technology, the generated text message is converted to speech and sent to the terminal. The data processing in this step is text-to-speech conversion. The output is a notification message in audio format.

[0386] Step 7:

[0387] The terminal plays the voice notification message received from the server and presents it to the user. Based on the response from the server, the user can obtain the necessary information. The output is the voice information received by the user.

[0388] (Application Example 2)

[0389] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0390] In modern voice-based services, it's common to provide information without considering the user's emotions. This leads to challenges such as a lack of personalized responses tailored to the user's situation, resulting in decreased convenience and satisfaction. This is especially true for services requiring immediacy, such as food delivery, where communication that responds to the user's emotions is crucial.

[0391] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0392] In this invention, the server includes means for receiving voice input and converting the input voice into text information, means for analyzing the text information and identifying the content of the voice request, and means for determining the user's emotional state from the voice input using emotion analysis technology and adjusting notification information based on the emotion. This makes it possible to provide personalized notifications that correspond to the user's emotional state.

[0393] "Voice input" refers to information or commands provided by the user verbally.

[0394] "Means of converting into text information" refers to technologies that analyze voice input and convert it into corresponding text data.

[0395] "Means for identifying the content of voice requests" refers to the process of analyzing the converted text information to clarify what the user is requesting.

[0396] "Transportation or meal delivery service" refers to an external service that arranges vehicles or meals according to the user's request.

[0397] An "external service provider" is a third-party organization that actually provides the transportation or meal delivery requested by the user.

[0398] "Means of notifying users of progress information" refers to technologies that inform users of the stage in which their request is being processed.

[0399] "Emotional analysis technology" is a method for visualizing and understanding a user's emotional state from their voice.

[0400] A "means for adjusting notification information" refers to a mechanism that optimizes the information and message content provided according to the user's emotional state.

[0401] The system that implements this invention primarily involves a server and a terminal. The server is equipped with speech recognition technology, natural language processing technology, sentiment analysis technology, and speech synthesis technology. Specifically, it uses the Google Speech-to-Text API to convert speech input into text data and the Python NLTK library to analyze the content of this text. The user's emotional state is analyzed using IBM Watson Tone Analyzer, and notification information is adjusted based on the results. This adjusted notification information is then converted into speech using Amazon Polly and delivered to the user via the terminal.

[0402] The device, such as a smartphone or computer, provides a user interface for users to request services by voice. The device plays voice feedback from the server, providing a personalized experience tailored to the user's emotions.

[0403] For example, if a user requests "I want my pizza delivered quickly" using their smartphone, the server recognizes the user's impatience and calmly provides feedback in a voice that the pizza is expected to be delivered within 20 minutes.

[0404] An example of a prompt for a generative AI model is: "If a user is hungry and irritable, how can you generate a reassuring voice message? Please provide an answer based on a specific scenario." This prompt provides guidance for generating more appropriate user responses.

[0405] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0406] Step 1:

[0407] The user provides voice input to the device. This voice input is captured through the smartphone's microphone and sent to the server. This primarily contains basic voice data indicating the user's desired service.

[0408] Step 2:

[0409] The server uses the Google Speech-to-Text API to convert received speech input into text. Speech data is the input, and corresponding text data is generated as the output. This text data forms the basis for subsequent processing steps.

[0410] Step 3:

[0411] The server parses the converted character information using the Python NLTK library. The input here is text data, and the output is an identification of the specific content of the user's voice request. This allows the server to understand what the user is asking for.

[0412] Step 4:

[0413] The server uses IBM Watson Tone Analyzer to perform sentiment analysis based on text data. The input is the analyzed text information, and based on that, the user's emotional state is output. For example, information such as whether the user is anxious or relaxed.

[0414] Step 5:

[0415] The server uses Amazon Polly to generate customized notification information as voice based on the results of sentiment analysis. Here, the input is sentiment state and user request information, and the output is a personalized voice message.

[0416] Step 6:

[0417] The terminal plays an audio message provided by the server to the user. Here, the direct input is audio data, and the output is auditory feedback to the user. At this stage, the user checks the progress of the service and responses through the audio message.

[0418] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0419] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0420] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0421] [Third Embodiment]

[0422] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0423] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0424] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0425] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0426] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0427] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0428] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0429] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0430] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0431] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0432] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0433] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0434] This invention relates to a system that allows elderly people to easily use ride-sharing and food delivery services via telephone. This system is built by integrating speech recognition technology, natural language processing technology, and speech synthesis technology.

[0435] The user makes a voice request via telephone, telling the system something like, "I'd like a car arranged to take me to the station." The terminal receives this voice and converts it into text in real time. This text is sent to a server, which uses natural language processing technology to analyze the user's intent. As a result of the analysis, the server identifies the service the user is requesting as a rideshare.

[0436] Based on the analyzed information, the server accesses external ride-sharing service providers via APIs. For example, it might request the nearest vehicle to be dispatched based on the user's current location and take them to their destination. If the dispatch is successful, the response from the provider is returned to the server, which then checks the progress of the dispatch.

[0437] Based on this progress information, the server sends a notification to the user using speech synthesis technology. The terminal plays the notification as audio, reporting to the user, for example, "The car will arrive in 10 minutes." The user can then wait with peace of mind based on this information and make further inquiries if necessary.

[0438] For example, the same process applies when a user requests food delivery. If the user says, "I want to order a pizza," the system searches for the nearest partner restaurant, checks the menu, and arranges for the specified food item. The server confirms the order details and delivery time and notifies the user via the terminal.

[0439] Thus, the system of the present invention facilitates access to technology and improves the convenience of daily life by supporting elderly people in intuitively using ride-sharing and food delivery services through voice commands.

[0440] The following describes the processing flow.

[0441] Step 1:

[0442] The user makes a phone call and makes a voice request. The device receives and records this voice message.

[0443] Step 2:

[0444] The device sends the received audio data to the speech recognition engine, which converts the audio into text.

[0445] Step 3:

[0446] The terminal sends the obtained text data to the server. The server then prepares this text for analysis.

[0447] Step 4:

[0448] The server uses natural language processing technology to analyze the user's request and identify its content. For example, it might determine that a rideshare arrangement is being requested.

[0449] Step 5:

[0450] Based on the analysis results, the server arranges rideshare or food delivery through an external service provider's API. It sends the necessary information as an API request.

[0451] Step 6:

[0452] The server receives a response from the external service provider and confirms that the arrangement is complete. It also retrieves information such as the service progress and estimated arrival time.

[0453] Step 7:

[0454] The server generates a message to report to the user based on the acquired progress information. It uses speech synthesis technology to convert text information into speech.

[0455] Step 8:

[0456] The terminal plays the converted audio data to the user and reports the service status. This allows the user to understand the progress of the service in real time.

[0457] Step 9:

[0458] Users can call again for further inquiries or problems. The server will respond to additional requests and provide the necessary information and guidance.

[0459] (Example 1)

[0460] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0461] There is a need for systems that allow elderly and technologically unfamiliar users to intuitively and easily access transportation and grocery delivery services through voice commands. Conventional systems require many operations and complex procedures, which is a burden on users.

[0462] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0463] In this invention, the server includes means for receiving voice input and converting the input voice into digital information, technology for analyzing the digital information and identifying the intent of the voice request, and technology for arranging transportation means or food delivery services with external suppliers based on the identified voice request. This makes it possible for users to easily request services using their voice.

[0464] "Voice input" is a method of transmitting instructions and requests that users make verbally to a system.

[0465] "Digital information" refers to data obtained by converting voice input into a format that can be processed electronically.

[0466] "Analysis" is the process of extracting meaning and intent contained in digital information.

[0467] "The intent behind a voice request" refers to the content of the wishes or instructions that the user intends to convey through voice.

[0468] "Transportation" refers to services that support travel from a designated departure point to a destination specified by the user.

[0469] A "grocery delivery service" is a service that delivers groceries requested by the user to a specified location.

[0470] An "external supplier" is a third-party organization or company that provides transportation and food delivery services in conjunction with the system.

[0471] "Sound synthesis technology" is a technology that generates text information as speech.

[0472] "Progress information" refers to status information such as the arrangement status and estimated arrival time of services related to the user's request.

[0473] "Instant updates" means that users will be notified quickly when new information becomes available.

[0474] This invention provides a system that allows users to easily access transportation and food delivery services through voice commands. This system is built by integrating voice input technology, natural language processing, and sound synthesis technology.

[0475] Users make voice requests using their phones. For example, they can make a voice request such as, "Please arrange a car to take me to the station." The device then converts this voice into text using the Google Cloud Speech-to-Text API.

[0476] This converted text information is sent to a server, which uses a generative AI model to perform natural language processing and analyze the intent of the voice request. For example, it might identify that the request is for a rideshare arrangement. Based on the identified request, the server uses APIs to access external providers of transportation or grocery delivery services. Here, the server arranges the appropriate service based on the user's current location and destination.

[0477] Once the arrangement is complete, the server receives a response from the external supplier and checks the progress of the service. This progress information is generated as audio using sound synthesis technology. The terminal plays this audio to the user, notifying them in a format such as, "The car will arrive in 10 minutes." This allows the user to confidently check the progress of the service.

[0478] As a concrete example of its use, if a user says, "I want to order a pizza," the terminal converts the voice into text, and the server analyzes the request using a generated AI model. The server then accesses the nearest restaurant and arranges for the specified food item. Once the delivery time is confirmed, the server informs the user of this information via voice notification.

[0479] Examples of prompts include, "How can elderly people easily use ride-sharing services by phone?" and "Please explain what a voice-based pizza ordering system is."

[0480] In this way, the entire system is designed so that users can intuitively request services using voice and easily obtain the results. The goal is to ensure that even elderly users and users unfamiliar with technology can use these services with peace of mind.

[0481] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0482] Step 1:

[0483] The user makes a voice request via telephone. The device receives the voice data as input. The device processes this voice data using the Google Cloud Speech-to-Text API and outputs it as text. This conversion transforms the voice into digital text data.

[0484] Step 2:

[0485] The terminal sends the data, converted into text information, to the server. The server uses the received text information as input and performs analysis using a generative AI model. Specifically, it uses natural language processing technology to extract the user's intent from the text data. Through this analysis, it identifies an intent such as "arrange a car to the station," and obtains the result as output data.

[0486] Step 3:

[0487] Based on the analysis results, the server initiates access to external suppliers. It uses identified service requests and user location information as input. Using an API, it sends data to the external supplier's system and arranges the requested service (e.g., rideshare arrangement). This process allows the server to receive the service arrangement results and obtain response data from the supplier as output.

[0488] Step 4:

[0489] The server uses response data received from external suppliers as input to check progress information. Based on this check, it generates a voice message using sound synthesis technology. As output, it creates voice data containing progress information and makes it available for notification to the user.

[0490] Step 5:

[0491] The terminal receives audio data sent from the server as input. The terminal plays this data as audio and notifies the user directly. This allows the user to check the situation by voice, such as "The car will arrive in 10 minutes."

[0492] (Application Example 1)

[0493] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0494] This invention aims to solve the problem that elderly people find it difficult to intuitively use the latest technologies and to provide an environment in which more people can use transportation and food delivery services with peace of mind. Specifically, the objective is to enable elderly people to arrange transportation and food delivery using only simple voice commands and to monitor the progress in real time.

[0495] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0496] In this invention, the server includes means for receiving voice input and converting the input voice into text information; means for analyzing the text information and identifying the content of the voice request; means for arranging transportation or food delivery services with an external service provider based on the identified voice request; means for tracking the progress of the arrangement and notifying the user of the progress information; means for obtaining the user's current location and arranging the nearest resources when arranging with an external service provider; means for generating the progress information using speech synthesis technology and providing it to the user; means for voice input and notification using a smartphone or smart glasses; and means for obtaining data required by the user in real time based on the notification information generated using the speech synthesis technology and notifying the user as quickly as possible. This makes it possible for elderly people to easily use daily living services by voice and smoothly grasp the information.

[0497] "Voice input" is the process of capturing the voice spoken by the user as a digital signal into the system.

[0498] "Textual information" refers to text data converted from voice input, and it forms the basis for analysis and processing.

[0499] A "voice request" refers to a user's wishes or instructions communicated to the system via voice, and is subject to specific service arrangements and information provision.

[0500] An "external service provider" is a service provider that the system connects to in response to user requests and provides services such as transportation and food delivery.

[0501] "Progress status" refers to the current stage of a service that has been arranged, and is part of the information provided to the user.

[0502] "Speech synthesis technology" is a technology that converts text information into audio data and provides it to users as audio.

[0503] "Current location" refers to the user's physical location and is information used to identify the nearest resource when arranging a service.

[0504] A "smartphone" is a type of portable information terminal that functions as part of a system by incorporating features such as voice input and notification capabilities.

[0505] "Smart glasses" are a type of wearable device that, when worn on the eyes, enables information display and voice input.

[0506] "Notification information" refers to information provided by the system to inform users about the progress and results of service arrangements.

[0507] The system that implements this application example includes a series of processes that integrate voice input, natural language processing, external service arrangement, progress management, and notifications.

[0508] The server receives instructions from the user using voice input and uses speech recognition software to convert the voice into text. Next, it analyzes the acquired text information using natural language processing techniques to identify the user's intended request. In this process, a generative AI model is utilized to gain a more precise understanding of the request.

[0509] After understanding the user's textual request, the server accesses appropriate external service providers via APIs and arranges the nearest resources based on the user's current location. For example, if the user instructs "I want to eat udon," the server finds the nearest food and beverage provider and automates the ordering process. To do this, the server uses location services and HTTPS communication.

[0510] The progress of the arrangement is updated in real time based on feedback from external service providers. The server converts this progress information into speech using speech synthesis technology and provides feedback to the user. This notification is performed using a smartphone or smart glasses.

[0511] These voice notifications allow users to quickly and intuitively check the progress of their order on the spot. For example, they might receive a message like, "Your udon order is complete. It will be delivered within 30 minutes."

[0512] A concrete example would be when a user says, "I want to order a pizza," and the nearest delivery service accepts the order and notifies the user via voice, "It will be delivered in 24 minutes."

[0513] An example of a prompt message might be: "Based on this audio data, please tell me how to interpret the user's intent and arrange a delivery service suitable for an elderly person."

[0514] Based on the above, this system is designed to be intuitively usable by elderly people themselves and to improve the convenience of their daily lives.

[0515] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0516] Step 1:

[0517] The terminal receives voice input from the user. The voice data is converted into digital format using the microphone subsystem and then passed to the speech recognition module, which converts the voice to text. In this process, the input is voice data, and the output is text information. The terminal then sends this text data to the server.

[0518] Step 2:

[0519] The server passes the received text information to the natural language processing engine. Here, a generative AI model is used to analyze the text data and interpret the user's intent. In this process, the input is text data, and the output is a specific request from the user (e.g., ordering a specific food item). Based on the analysis results, the server moves on to the next processing step.

[0520] Step 3:

[0521] The server sends an API request to an external service provider in response to the user's request. This request obtains the user's current location and performs calculations to arrange the nearest resource. The inputs are the user's request and current location information, and the output is the result of the arranged service (e.g., confirmed order information). The server then passes this information to the next step.

[0522] Step 4:

[0523] The server uses a speech synthesis engine to convert the progress information into speech based on the order results obtained. The input is the order result information, and the output is speech data. The server sends this speech data to the terminal.

[0524] Step 5:

[0525] The terminal plays the audio data received from the server and notifies the user. By listening to the notified audio information, the user can understand the service availability and estimated time. In this step, the input is audio data, and the output is an audio presentation to the user. The user can make further voice inputs as needed to convey additional requests to the terminal.

[0526] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0527] This invention relates to a system that provides an advanced user experience when users utilize ride-sharing or food delivery services via telephone by combining it with an emotion engine. This system is built by integrating an emotion engine with speech recognition technology, natural language processing technology, and speech synthesis technology.

[0528] When a user makes a voice request via phone, the device receives and records the audio. Using speech recognition technology, the recorded audio is converted to text, while an emotion engine analyzes the audio data to recognize the user's emotional state. For example, if the user is feeling anxious when making the request, that emotion is identified.

[0529] The server receives textual and sentiment data, uses natural language processing techniques to analyze the user's specific request, and identifies what the request is asking for. For example, it might determine that the user needs to arrange a rideshare.

[0530] Next, based on the analyzed information, the server accesses external ride-sharing service providers via API to arrange the necessary services. If the arrangement is successful, a response is returned from the external provider, and the server checks the progress of the arrangement. At this time, notification information is generated based on the results of the emotion engine. If the user is feeling anxious, the message is adjusted to include prompt action or a warning.

[0531] Notification information is converted into speech using speech synthesis technology, and the device plays that information back to the user as audio. For example, if a user urgently requests, "I need a car immediately," the device might report, "The car will arrive in 5 minutes. Don't worry."

[0532] Furthermore, if the emotion engine detects an abnormal emotional state, such as extreme stress or frustration, the server can also notify customer support to provide additional assistance. Thus, the present invention, which combines the emotion engine, aims to help users obtain a more appropriate and personalized service experience.

[0533] The following describes the processing flow.

[0534] Step 1:

[0535] The user contacts the system by phone and requests service via voice. The terminal receives this voice and records it through the microphone.

[0536] Step 2:

[0537] The device inputs the received audio data into its speech recognition engine and converts the data into text. Simultaneously, it uses an emotion engine to identify the user's emotional state from the audio data.

[0538] Step 3:

[0539] The terminal sends the generated text information and sentiment data to the server. The server uses natural language processing technology to analyze the text information and identify the user's request.

[0540] Step 4:

[0541] Based on the analyzed information, the server accesses the APIs of external service providers to arrange the transportation or food delivery service requested by the user.

[0542] Step 5:

[0543] The server receives the information returned from the external service provider and confirms that the service arrangement is complete. It also retrieves the arrangement details and prepares a notification.

[0544] Step 6:

[0545] The server customizes notification information based on emotional data obtained from the emotion engine. If the user is feeling anxious, notifications are adjusted to be sent more quickly. Reassuring messages are also included as needed.

[0546] Step 7:

[0547] The server converts notification messages into speech using speech synthesis technology. This information is then played back to the user by their device. The user can then check the service progress in real time.

[0548] Step 8:

[0549] If the emotion engine detects an abnormal emotional state, the server can determine that additional support is needed and send an alert to customer support.

[0550] Step 9:

[0551] The user can make further inquiries as needed, and the server will provide additional information and assistance in response to those requests.

[0552] (Example 2)

[0553] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0554] Conventional voice request analysis systems failed to adequately provide personalized notifications that took into account the user's emotional state, nor to respond appropriately to abnormal emotional states. As a result, users sometimes received notifications at inappropriate times or in inappropriate ways, and it was difficult to respond quickly to stress or frustration. This made it difficult to provide a better user experience.

[0555] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0556] In this invention, the server includes means for receiving voice input and converting the input voice into text information, emotion recognition means for analyzing the user's emotional state, and means for arranging transportation or food supply services with external service providers based on identified voice requests. This enables flexible notifications and quick responses that respond to the user's emotions.

[0557] "Voice input" refers to instructions or requests that users give to a system using their voice.

[0558] "Textual information" refers to data that has been converted from voice input into a machine-recognizable string of characters.

[0559] "Voice requests" refer to the specific content and actions that users request from the system, extracted by analyzing voice input.

[0560] "External service providers" refer to external service providers whose work is requested through integration with the system.

[0561] "Emotion recognition means" refers to methods or devices that analyze and identify an emotional state from a user's voice or other inputs.

[0562] "Notification information" refers to information used to communicate the content and progress of what the system provides to users.

[0563] "Alarming measures" refer to functions or devices that detect abnormal emotional states, alert the user to a problem, and indicate that additional action is required.

[0564] "Speech synthesis technology" refers to a technology that generates text information as speech and conveys information to users aurally.

[0565] This invention relates to a system that provides personalized services to users based on voice input. This system achieves an advanced user experience by integrating voice recognition technology, natural language processing technology, and emotion recognition technology. Specific embodiments are described below.

[0566] The device first receives voice input from the user via telephone. This voice is recorded and converted into text using speech recognition software. For example, open-source speech recognition libraries and cloud-based speech recognition services are commonly available as speech recognition software.

[0567] Next, the server receives the text information sent from the terminal and analyzes the user's voice request using natural language processing technology. Based on the analyzed request, the necessary transportation and food supply services are identified and arranged through the API of external service providers. At this time, emotion recognition is also used to analyze the user's emotional state from the voice input. Emotion recognition is often performed by analyzing features such as intonation, tempo, and volume of the voice.

[0568] For example, if a user makes an urgent request such as "I need a ride arranged immediately," the emotion recognition system identifies that emotion and prompts the server to take immediate action. When the arrangement is successful, the server generates progress information and notifies the terminal using speech synthesis technology. The speech synthesis technology uses, for example, a cloud-based speech synthesis engine to output text information as speech.

[0569] As a concrete example, here is an example of a prompt message for a generative AI model: "If the user is feeling anxious, generate a message that will respond appropriately and reassure them." Through this prompt, the AI ​​model can generate the most appropriate message based on the user's emotions.

[0570] Thus, the present invention enables the provision of a more personalized service experience to users by considering emotions in notifications and enhancing responsiveness.

[0571] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0572] Step 1:

[0573] The device receives voice input from the user via telephone. This voice data is recorded and saved in a digital format. The input is the user's raw voice, and the output is a recorded digital audio file.

[0574] Step 2:

[0575] The device inputs the recorded audio data into a speech recognition system and converts it into text. Speech recognition technology is used, for example, by utilizing a cloud-based speech recognition service. In this process, the audio data is converted into text data. The output is the user's request in text format.

[0576] Step 3:

[0577] The server receives text data from the terminal and inputs it into the emotion recognition engine. The engine processes not only text but also emotional information extracted from speech to analyze the user's emotional state. The data processing performed here is emotion identification based on text and speech signal processing. The output is emotion data indicating the user's emotional state.

[0578] Step 4:

[0579] The server uses natural language processing technology to analyze text data and identify the specific content of the user's request. This involves analyzing the text structure and extracting keywords. The output is the analyzed request information.

[0580] Step 5:

[0581] Based on the analysis results, the server accesses the API of the external service provider for the identified service (e.g., ridesharing) to make the necessary arrangements. This process involves API communication and receiving responses from the external service provider. The output is status information based on the success or failure of the arrangement.

[0582] Step 6:

[0583] The server considers emotional data to generate an appropriate notification message for the user. Using speech synthesis technology, the generated text message is converted to speech and sent to the terminal. The data processing in this step is text-to-speech conversion. The output is a notification message in audio format.

[0584] Step 7:

[0585] The terminal plays the voice notification message received from the server and presents it to the user. Based on the response from the server, the user can obtain the necessary information. The output is the voice information received by the user.

[0586] (Application Example 2)

[0587] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0588] In modern voice-based services, it's common to provide information without considering the user's emotions. This leads to challenges such as a lack of personalized responses tailored to the user's situation, resulting in decreased convenience and satisfaction. This is especially true for services requiring immediacy, such as food delivery, where communication that responds to the user's emotions is crucial.

[0589] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0590] In this invention, the server includes means for receiving voice input and converting the input voice into text information, means for analyzing the text information and identifying the content of the voice request, and means for determining the user's emotional state from the voice input using emotion analysis technology and adjusting notification information based on the emotion. This makes it possible to provide personalized notifications that correspond to the user's emotional state.

[0591] "Voice input" refers to information or commands provided by the user verbally.

[0592] "Means of converting into text information" refers to technologies that analyze voice input and convert it into corresponding text data.

[0593] "Means for identifying the content of voice requests" refers to the process of analyzing the converted text information to clarify what the user is requesting.

[0594] "Transportation or meal delivery service" refers to an external service that arranges vehicles or meals according to the user's request.

[0595] An "external service provider" is a third-party organization that actually provides the transportation or meal delivery requested by the user.

[0596] "Means of notifying users of progress information" refers to technologies that inform users of the stage in which their request is being processed.

[0597] "Emotional analysis technology" is a method for visualizing and understanding a user's emotional state from their voice.

[0598] A "means for adjusting notification information" refers to a mechanism that optimizes the information and message content provided according to the user's emotional state.

[0599] The system that implements this invention primarily involves a server and a terminal. The server is equipped with speech recognition technology, natural language processing technology, sentiment analysis technology, and speech synthesis technology. Specifically, it uses the Google Speech-to-Text API to convert speech input into text data and the Python NLTK library to analyze the content of this text. The user's emotional state is analyzed using IBM Watson Tone Analyzer, and notification information is adjusted based on the results. This adjusted notification information is then converted into speech using Amazon Polly and delivered to the user via the terminal.

[0600] The device, such as a smartphone or computer, provides a user interface for users to request services by voice. The device plays voice feedback from the server, providing a personalized experience tailored to the user's emotions.

[0601] For example, if a user requests "I want my pizza delivered quickly" using their smartphone, the server recognizes the user's impatience and calmly provides feedback in a voice that the pizza is expected to be delivered within 20 minutes.

[0602] An example of a prompt for a generative AI model is: "If a user is hungry and irritable, how can you generate a reassuring voice message? Please provide an answer based on a specific scenario." This prompt provides guidance for generating more appropriate user responses.

[0603] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0604] Step 1:

[0605] The user provides voice input to the device. This voice input is captured through the smartphone's microphone and sent to the server. This primarily contains basic voice data indicating the user's desired service.

[0606] Step 2:

[0607] The server uses the Google Speech-to-Text API to convert received speech input into text. Speech data is the input, and corresponding text data is generated as the output. This text data forms the basis for subsequent processing steps.

[0608] Step 3:

[0609] The server parses the converted character information using the Python NLTK library. The input here is text data, and the output is an identification of the specific content of the user's voice request. This allows the server to understand what the user is asking for.

[0610] Step 4:

[0611] The server uses IBM Watson Tone Analyzer to perform sentiment analysis based on text data. The input is the analyzed text information, and based on that, the user's emotional state is output. For example, information such as whether the user is anxious or relaxed.

[0612] Step 5:

[0613] The server uses Amazon Polly to generate customized notification information as voice based on the results of sentiment analysis. Here, the input is sentiment state and user request information, and the output is a personalized voice message.

[0614] Step 6:

[0615] The terminal plays an audio message provided by the server to the user. Here, the direct input is audio data, and the output is auditory feedback to the user. At this stage, the user checks the progress of the service and responses through the audio message.

[0616] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0617] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0618] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0619] [Fourth Embodiment]

[0620] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0621] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0622] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0623] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0624] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0625] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0626] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0627] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0628] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0629] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0630] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0631] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0632] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0633] This invention relates to a system that allows elderly people to easily use ride-sharing and food delivery services via telephone. This system is built by integrating speech recognition technology, natural language processing technology, and speech synthesis technology.

[0634] The user makes a voice request via telephone, telling the system something like, "I'd like a car arranged to take me to the station." The terminal receives this voice and converts it into text in real time. This text is sent to a server, which uses natural language processing technology to analyze the user's intent. As a result of the analysis, the server identifies the service the user is requesting as a rideshare.

[0635] Based on the analyzed information, the server accesses external ride-sharing service providers via APIs. For example, it might request the nearest vehicle to be dispatched based on the user's current location and take them to their destination. If the dispatch is successful, the response from the provider is returned to the server, which then checks the progress of the dispatch.

[0636] Based on this progress information, the server sends a notification to the user using speech synthesis technology. The terminal plays the notification as audio, reporting to the user, for example, "The car will arrive in 10 minutes." The user can then wait with peace of mind based on this information and make further inquiries if necessary.

[0637] For example, the same process applies when a user requests food delivery. If the user says, "I want to order a pizza," the system searches for the nearest partner restaurant, checks the menu, and arranges for the specified food item. The server confirms the order details and delivery time and notifies the user via the terminal.

[0638] Thus, the system of the present invention facilitates access to technology and improves the convenience of daily life by supporting elderly people in intuitively using ride-sharing and food delivery services through voice commands.

[0639] The following describes the processing flow.

[0640] Step 1:

[0641] The user makes a phone call and makes a voice request. The device receives and records this voice message.

[0642] Step 2:

[0643] The device sends the received audio data to the speech recognition engine, which converts the audio into text.

[0644] Step 3:

[0645] The terminal sends the obtained text data to the server. The server then prepares this text for analysis.

[0646] Step 4:

[0647] The server uses natural language processing technology to analyze the user's request and identify its content. For example, it might determine that a rideshare arrangement is being requested.

[0648] Step 5:

[0649] Based on the analysis results, the server arranges rideshare or food delivery through an external service provider's API. It sends the necessary information as an API request.

[0650] Step 6:

[0651] The server receives a response from the external service provider and confirms that the arrangement is complete. It also retrieves information such as the service progress and estimated arrival time.

[0652] Step 7:

[0653] The server generates a message to report to the user based on the acquired progress information. It uses speech synthesis technology to convert text information into speech.

[0654] Step 8:

[0655] The terminal plays the converted audio data to the user and reports the service status. This allows the user to understand the progress of the service in real time.

[0656] Step 9:

[0657] Users can call again for further inquiries or problems. The server will respond to additional requests and provide the necessary information and guidance.

[0658] (Example 1)

[0659] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0660] There is a need for systems that allow elderly and technologically unfamiliar users to intuitively and easily access transportation and grocery delivery services through voice commands. Conventional systems require many operations and complex procedures, which is a burden on users.

[0661] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0662] In this invention, the server includes means for receiving voice input and converting the input voice into digital information, technology for analyzing the digital information and identifying the intent of the voice request, and technology for arranging transportation means or food delivery services with external suppliers based on the identified voice request. This makes it possible for users to easily request services using their voice.

[0663] "Voice input" is a method of transmitting instructions and requests that users make verbally to a system.

[0664] "Digital information" refers to data obtained by converting voice input into a format that can be processed electronically.

[0665] "Analysis" is the process of extracting meaning and intent contained in digital information.

[0666] "The intent behind a voice request" refers to the content of the wishes or instructions that the user intends to convey through voice.

[0667] "Transportation" refers to services that support travel from a designated departure point to a destination specified by the user.

[0668] A "grocery delivery service" is a service that delivers groceries requested by the user to a specified location.

[0669] An "external supplier" is a third-party organization or company that provides transportation and food delivery services in conjunction with the system.

[0670] "Sound synthesis technology" is a technology that generates text information as speech.

[0671] "Progress information" refers to status information such as the arrangement status and estimated arrival time of services related to the user's request.

[0672] "Instant updates" means that users will be notified quickly when new information becomes available.

[0673] This invention provides a system that allows users to easily access transportation and food delivery services through voice commands. This system is built by integrating voice input technology, natural language processing, and sound synthesis technology.

[0674] Users make voice requests using their phones. For example, they can make a voice request such as, "Please arrange a car to take me to the station." The device then converts this voice into text using the Google Cloud Speech-to-Text API.

[0675] This converted text information is sent to a server, which uses a generative AI model to perform natural language processing and analyze the intent of the voice request. For example, it might identify that the request is for a rideshare arrangement. Based on the identified request, the server uses APIs to access external providers of transportation or grocery delivery services. Here, the server arranges the appropriate service based on the user's current location and destination.

[0676] Once the arrangement is complete, the server receives a response from the external supplier and checks the progress of the service. This progress information is generated as audio using sound synthesis technology. The terminal plays this audio to the user, notifying them in a format such as, "The car will arrive in 10 minutes." This allows the user to confidently check the progress of the service.

[0677] As a concrete example of its use, if a user says, "I want to order a pizza," the terminal converts the voice into text, and the server analyzes the request using a generated AI model. The server then accesses the nearest restaurant and arranges for the specified food item. Once the delivery time is confirmed, the server informs the user of this information via voice notification.

[0678] Examples of prompts include, "How can elderly people easily use ride-sharing services by phone?" and "Please explain what a voice-based pizza ordering system is."

[0679] In this way, the entire system is designed so that users can intuitively request services using voice and easily obtain the results. The goal is to ensure that even elderly users and users unfamiliar with technology can use these services with peace of mind.

[0680] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0681] Step 1:

[0682] The user makes a voice request via telephone. The device receives the voice data as input. The device processes this voice data using the Google Cloud Speech-to-Text API and outputs it as text. This conversion transforms the voice into digital text data.

[0683] Step 2:

[0684] The terminal sends the data, converted into text information, to the server. The server uses the received text information as input and performs analysis using a generative AI model. Specifically, it uses natural language processing technology to extract the user's intent from the text data. Through this analysis, it identifies an intent such as "arrange a car to the station," and obtains the result as output data.

[0685] Step 3:

[0686] Based on the analysis results, the server initiates access to external suppliers. It uses identified service requests and user location information as input. Using an API, it sends data to the external supplier's system and arranges the requested service (e.g., rideshare arrangement). This process allows the server to receive the service arrangement results and obtain response data from the supplier as output.

[0687] Step 4:

[0688] The server uses response data received from external suppliers as input to check progress information. Based on this check, it generates a voice message using sound synthesis technology. As output, it creates voice data containing progress information and makes it available for notification to the user.

[0689] Step 5:

[0690] The terminal receives audio data sent from the server as input. The terminal plays this data as audio and notifies the user directly. This allows the user to check the situation by voice, such as "The car will arrive in 10 minutes."

[0691] (Application Example 1)

[0692] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0693] This invention aims to solve the problem that elderly people find it difficult to intuitively use the latest technologies and to provide an environment in which more people can use transportation and food delivery services with peace of mind. Specifically, the objective is to enable elderly people to arrange transportation and food delivery using only simple voice commands and to monitor the progress in real time.

[0694] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0695] In this invention, the server includes means for receiving voice input and converting the input voice into text information; means for analyzing the text information and identifying the content of the voice request; means for arranging transportation or food delivery services with an external service provider based on the identified voice request; means for tracking the progress of the arrangement and notifying the user of the progress information; means for obtaining the user's current location and arranging the nearest resources when arranging with an external service provider; means for generating the progress information using speech synthesis technology and providing it to the user; means for voice input and notification using a smartphone or smart glasses; and means for obtaining data required by the user in real time based on the notification information generated using the speech synthesis technology and notifying the user as quickly as possible. This makes it possible for elderly people to easily use daily living services by voice and smoothly grasp the information.

[0696] "Voice input" is the process of capturing the voice spoken by the user as a digital signal into the system.

[0697] "Textual information" refers to text data converted from voice input, and it forms the basis for analysis and processing.

[0698] A "voice request" refers to a user's wishes or instructions communicated to the system via voice, and is subject to specific service arrangements and information provision.

[0699] An "external service provider" is a service provider that the system connects to in response to user requests and provides services such as transportation and food delivery.

[0700] "Progress status" refers to the current stage of a service that has been arranged, and is part of the information provided to the user.

[0701] "Speech synthesis technology" is a technology that converts text information into audio data and provides it to users as audio.

[0702] "Current location" refers to the user's physical location and is information used to identify the nearest resource when arranging a service.

[0703] A "smartphone" is a type of portable information terminal that functions as part of a system by incorporating features such as voice input and notification capabilities.

[0704] "Smart glasses" are a type of wearable device that, when worn on the eyes, enables information display and voice input.

[0705] "Notification information" refers to information provided by the system to inform users about the progress and results of service arrangements.

[0706] The system that implements this application example includes a series of processes that integrate voice input, natural language processing, external service arrangement, progress management, and notifications.

[0707] The server receives instructions from the user using voice input and uses speech recognition software to convert the voice into text. Next, it analyzes the acquired text information using natural language processing techniques to identify the user's intended request. In this process, a generative AI model is utilized to gain a more precise understanding of the request.

[0708] After understanding the user's textual request, the server accesses appropriate external service providers via APIs and arranges the nearest resources based on the user's current location. For example, if the user instructs "I want to eat udon," the server finds the nearest food and beverage provider and automates the ordering process. To do this, the server uses location services and HTTPS communication.

[0709] The progress of the arrangement is updated in real time based on feedback from external service providers. The server converts this progress information into speech using speech synthesis technology and provides feedback to the user. This notification is performed using a smartphone or smart glasses.

[0710] These voice notifications allow users to quickly and intuitively check the progress of their order on the spot. For example, they might receive a message like, "Your udon order is complete. It will be delivered within 30 minutes."

[0711] A concrete example would be when a user says, "I want to order a pizza," and the nearest delivery service accepts the order and notifies the user via voice, "It will be delivered in 24 minutes."

[0712] An example of a prompt message might be: "Based on this audio data, please tell me how to interpret the user's intent and arrange a delivery service suitable for an elderly person."

[0713] Based on the above, this system is designed to be intuitively usable by elderly people themselves and to improve the convenience of their daily lives.

[0714] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0715] Step 1:

[0716] The terminal receives voice input from the user. The voice data is converted into digital format using the microphone subsystem and then passed to the speech recognition module, which converts the voice to text. In this process, the input is voice data, and the output is text information. The terminal then sends this text data to the server.

[0717] Step 2:

[0718] The server passes the received text information to the natural language processing engine. Here, a generative AI model is used to analyze the text data and interpret the user's intent. In this process, the input is text data, and the output is a specific request from the user (e.g., ordering a specific food item). Based on the analysis results, the server moves on to the next processing step.

[0719] Step 3:

[0720] The server sends an API request to an external service provider in response to the user's request. This request obtains the user's current location and performs calculations to arrange the nearest resource. The inputs are the user's request and current location information, and the output is the result of the arranged service (e.g., confirmed order information). The server then passes this information to the next step.

[0721] Step 4:

[0722] The server uses a speech synthesis engine to convert the progress information into speech based on the order results obtained. The input is the order result information, and the output is speech data. The server sends this speech data to the terminal.

[0723] Step 5:

[0724] The terminal plays the audio data received from the server and notifies the user. By listening to the notified audio information, the user can understand the service availability and estimated time. In this step, the input is audio data, and the output is an audio presentation to the user. The user can make further voice inputs as needed to convey additional requests to the terminal.

[0725] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0726] This invention relates to a system that provides an advanced user experience when users utilize ride-sharing or food delivery services via telephone by combining it with an emotion engine. This system is built by integrating an emotion engine with speech recognition technology, natural language processing technology, and speech synthesis technology.

[0727] When a user makes a voice request via phone, the device receives and records the audio. Using speech recognition technology, the recorded audio is converted to text, while an emotion engine analyzes the audio data to recognize the user's emotional state. For example, if the user is feeling anxious when making the request, that emotion is identified.

[0728] The server receives textual and sentiment data, uses natural language processing techniques to analyze the user's specific request, and identifies what the request is asking for. For example, it might determine that the user needs to arrange a rideshare.

[0729] Next, based on the analyzed information, the server accesses external ride-sharing service providers via API to arrange the necessary services. If the arrangement is successful, a response is returned from the external provider, and the server checks the progress of the arrangement. At this time, notification information is generated based on the results of the emotion engine. If the user is feeling anxious, the message is adjusted to include prompt action or a warning.

[0730] Notification information is converted into speech using speech synthesis technology, and the device plays that information back to the user as audio. For example, if a user urgently requests, "I need a car immediately," the device might report, "The car will arrive in 5 minutes. Don't worry."

[0731] Furthermore, if the emotion engine detects an abnormal emotional state, such as extreme stress or frustration, the server can also notify customer support to provide additional assistance. Thus, the present invention, which combines the emotion engine, aims to help users obtain a more appropriate and personalized service experience.

[0732] The following describes the processing flow.

[0733] Step 1:

[0734] The user contacts the system by phone and requests service via voice. The terminal receives this voice and records it through the microphone.

[0735] Step 2:

[0736] The device inputs the received audio data into its speech recognition engine and converts the data into text. Simultaneously, it uses an emotion engine to identify the user's emotional state from the audio data.

[0737] Step 3:

[0738] The terminal sends the generated text information and sentiment data to the server. The server uses natural language processing technology to analyze the text information and identify the user's request.

[0739] Step 4:

[0740] Based on the analyzed information, the server accesses the APIs of external service providers to arrange the transportation or food delivery service requested by the user.

[0741] Step 5:

[0742] The server receives the information returned from the external service provider and confirms that the service arrangement is complete. It also retrieves the arrangement details and prepares a notification.

[0743] Step 6:

[0744] The server customizes notification information based on emotional data obtained from the emotion engine. If the user is feeling anxious, notifications are adjusted to be sent more quickly. Reassuring messages are also included as needed.

[0745] Step 7:

[0746] The server converts notification messages into speech using speech synthesis technology. This information is then played back to the user by their device. The user can then check the service progress in real time.

[0747] Step 8:

[0748] If the emotion engine detects an abnormal emotional state, the server can determine that additional support is needed and send an alert to customer support.

[0749] Step 9:

[0750] The user can make further inquiries as needed, and the server will provide additional information and assistance in response to those requests.

[0751] (Example 2)

[0752] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0753] Conventional voice request analysis systems failed to adequately provide personalized notifications that took into account the user's emotional state, nor to respond appropriately to abnormal emotional states. As a result, users sometimes received notifications at inappropriate times or in inappropriate ways, and it was difficult to respond quickly to stress or frustration. This made it difficult to provide a better user experience.

[0754] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0755] In this invention, the server includes means for receiving voice input and converting the input voice into text information, emotion recognition means for analyzing the user's emotional state, and means for arranging transportation or food supply services with external service providers based on identified voice requests. This enables flexible notifications and quick responses that respond to the user's emotions.

[0756] "Voice input" refers to instructions or requests that users give to a system using their voice.

[0757] "Textual information" refers to data that has been converted from voice input into a machine-recognizable string of characters.

[0758] "Voice requests" refer to the specific content and actions that users request from the system, extracted by analyzing voice input.

[0759] "External service providers" refer to external service providers whose work is requested through integration with the system.

[0760] "Emotion recognition means" refers to methods or devices that analyze and identify an emotional state from a user's voice or other inputs.

[0761] "Notification information" refers to information used to communicate the content and progress of what the system provides to users.

[0762] "Alarming measures" refer to functions or devices that detect abnormal emotional states, alert the user to a problem, and indicate that additional action is required.

[0763] "Speech synthesis technology" refers to a technology that generates text information as speech and conveys information to users aurally.

[0764] This invention relates to a system that provides personalized services to users based on voice input. This system achieves an advanced user experience by integrating voice recognition technology, natural language processing technology, and emotion recognition technology. Specific embodiments are described below.

[0765] The device first receives voice input from the user via telephone. This voice is recorded and converted into text using speech recognition software. For example, open-source speech recognition libraries and cloud-based speech recognition services are commonly available as speech recognition software.

[0766] Next, the server receives the text information sent from the terminal and analyzes the user's voice request using natural language processing technology. Based on the analyzed request, the necessary transportation and food supply services are identified and arranged through the API of external service providers. At this time, emotion recognition is also used to analyze the user's emotional state from the voice input. Emotion recognition is often performed by analyzing features such as intonation, tempo, and volume of the voice.

[0767] For example, if a user makes an urgent request such as "I need a ride arranged immediately," the emotion recognition system identifies that emotion and prompts the server to take immediate action. When the arrangement is successful, the server generates progress information and notifies the terminal using speech synthesis technology. The speech synthesis technology uses, for example, a cloud-based speech synthesis engine to output text information as speech.

[0768] As a concrete example, here is an example of a prompt message for a generative AI model: "If the user is feeling anxious, generate a message that will respond appropriately and reassure them." Through this prompt, the AI ​​model can generate the most appropriate message based on the user's emotions.

[0769] Thus, the present invention enables the provision of a more personalized service experience to users by considering emotions in notifications and enhancing responsiveness.

[0770] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0771] Step 1:

[0772] The device receives voice input from the user via telephone. This voice data is recorded and saved in a digital format. The input is the user's raw voice, and the output is a recorded digital audio file.

[0773] Step 2:

[0774] The device inputs the recorded audio data into a speech recognition system and converts it into text. Speech recognition technology is used, for example, by utilizing a cloud-based speech recognition service. In this process, the audio data is converted into text data. The output is the user's request in text format.

[0775] Step 3:

[0776] The server receives text data from the terminal and inputs it into the emotion recognition engine. The engine processes not only text but also emotional information extracted from speech to analyze the user's emotional state. The data processing performed here is emotion identification based on text and speech signal processing. The output is emotion data indicating the user's emotional state.

[0777] Step 4:

[0778] The server uses natural language processing technology to analyze text data and identify the specific content of the user's request. This involves analyzing the text structure and extracting keywords. The output is the analyzed request information.

[0779] Step 5:

[0780] Based on the analysis results, the server accesses the API of the external service provider for the identified service (e.g., ridesharing) to make the necessary arrangements. This process involves API communication and receiving responses from the external service provider. The output is status information based on the success or failure of the arrangement.

[0781] Step 6:

[0782] The server considers emotional data to generate an appropriate notification message for the user. Using speech synthesis technology, the generated text message is converted to speech and sent to the terminal. The data processing in this step is text-to-speech conversion. The output is a notification message in audio format.

[0783] Step 7:

[0784] The terminal plays the voice notification message received from the server and presents it to the user. Based on the response from the server, the user can obtain the necessary information. The output is the voice information received by the user.

[0785] (Application Example 2)

[0786] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0787] In modern voice-based services, it's common to provide information without considering the user's emotions. This leads to challenges such as a lack of personalized responses tailored to the user's situation, resulting in decreased convenience and satisfaction. This is especially true for services requiring immediacy, such as food delivery, where communication that responds to the user's emotions is crucial.

[0788] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0789] In this invention, the server includes means for receiving voice input and converting the input voice into text information, means for analyzing the text information and identifying the content of the voice request, and means for determining the user's emotional state from the voice input using emotion analysis technology and adjusting notification information based on the emotion. This makes it possible to provide personalized notifications that correspond to the user's emotional state.

[0790] "Voice input" refers to information or commands provided by the user verbally.

[0791] "Means of converting into text information" refers to technologies that analyze voice input and convert it into corresponding text data.

[0792] "Means for identifying the content of voice requests" refers to the process of analyzing the converted text information to clarify what the user is requesting.

[0793] "Transportation or meal delivery service" refers to an external service that arranges vehicles or meals according to the user's request.

[0794] An "external service provider" is a third-party organization that actually provides the transportation or meal delivery requested by the user.

[0795] "Means of notifying users of progress information" refers to technologies that inform users of the stage in which their request is being processed.

[0796] "Emotional analysis technology" is a method for visualizing and understanding a user's emotional state from their voice.

[0797] A "means for adjusting notification information" refers to a mechanism that optimizes the information and message content provided according to the user's emotional state.

[0798] The system that implements this invention primarily involves a server and a terminal. The server is equipped with speech recognition technology, natural language processing technology, sentiment analysis technology, and speech synthesis technology. Specifically, it uses the Google Speech-to-Text API to convert speech input into text data and the Python NLTK library to analyze the content of this text. The user's emotional state is analyzed using IBM Watson Tone Analyzer, and notification information is adjusted based on the results. This adjusted notification information is then converted into speech using Amazon Polly and delivered to the user via the terminal.

[0799] The device, such as a smartphone or computer, provides a user interface for users to request services by voice. The device plays voice feedback from the server, providing a personalized experience tailored to the user's emotions.

[0800] For example, if a user requests "I want my pizza delivered quickly" using their smartphone, the server recognizes the user's impatience and calmly provides feedback in a voice that the pizza is expected to be delivered within 20 minutes.

[0801] An example of a prompt for a generative AI model is: "If a user is hungry and irritable, how can you generate a reassuring voice message? Please provide an answer based on a specific scenario." This prompt provides guidance for generating more appropriate user responses.

[0802] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0803] Step 1:

[0804] The user provides voice input to the device. This voice input is captured through the smartphone's microphone and sent to the server. This primarily contains basic voice data indicating the user's desired service.

[0805] Step 2:

[0806] The server uses the Google Speech-to-Text API to convert received speech input into text. Speech data is the input, and corresponding text data is generated as the output. This text data forms the basis for subsequent processing steps.

[0807] Step 3:

[0808] The server parses the converted character information using the Python NLTK library. The input here is text data, and the output is an identification of the specific content of the user's voice request. This allows the server to understand what the user is asking for.

[0809] Step 4:

[0810] The server uses IBM Watson Tone Analyzer to perform sentiment analysis based on text data. The input is the analyzed text information, and based on that, the user's emotional state is output. For example, information such as whether the user is anxious or relaxed.

[0811] Step 5:

[0812] The server uses Amazon Polly to generate customized notification information as voice based on the results of sentiment analysis. Here, the input is sentiment state and user request information, and the output is a personalized voice message.

[0813] Step 6:

[0814] The terminal plays an audio message provided by the server to the user. Here, the direct input is audio data, and the output is auditory feedback to the user. At this stage, the user checks the progress of the service and responses through the audio message.

[0815] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0816] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0817] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0818] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0819] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0820] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0821] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0822] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0823] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0824] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0825] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0826] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0827] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0828] 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.

[0829] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0830] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0831] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0832] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0833] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0834] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0835] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0836] The following is further disclosed regarding the embodiments described above.

[0837] (Claim 1)

[0838] A means for receiving voice input and converting the input voice into text information,

[0839] A means for analyzing the aforementioned textual information and identifying the content of the voice request,

[0840] A means of arranging transportation or food delivery services from an external service provider based on identified voice requests,

[0841] A means of tracking the progress of the arrangement and notifying the user of the progress information,

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1, further comprising means for generating notification information as voice using speech synthesis technology and providing it to the user.

[0845] (Claim 3)

[0846] The system according to claim 1, further comprising means for updating and providing to the user in real time notification information relating to the arrangement of the external service provider.

[0847] "Example 1"

[0848] (Claim 1)

[0849] A means for receiving voice input and converting the input voice into digital information,

[0850] A technology for analyzing the aforementioned digital information and identifying the intent of a voice request,

[0851] Technology for arranging transportation or food delivery services from external suppliers based on identified voice requests,

[0852] Technology to monitor the progress of arrangements and notify users of the progress information,

[0853] A system that includes this.

[0854] (Claim 2)

[0855] The system according to claim 1, further comprising a technology for generating notification information as voice using sound synthesis technology and providing it to the user.

[0856] (Claim 3)

[0857] The system according to claim 1, further comprising technology for immediately updating and providing to users notification information related to the arrangement of the aforementioned external supplier.

[0858] "Application Example 1"

[0859] (Claim 1)

[0860] A means for receiving voice input and converting the input voice into text information,

[0861] A means for analyzing the aforementioned textual information and identifying the content of the voice request,

[0862] A means of arranging transportation or food delivery services from an external service provider based on identified voice requests,

[0863] A means of tracking the progress of the arrangement and notifying the user of the progress information,

[0864] When arranging with an external service provider, the means of obtaining the user's current location and arranging the nearest resource,

[0865] A means for generating the aforementioned progress information using speech synthesis technology and providing it to the user,

[0866] A system that includes this.

[0867] (Claim 2)

[0868] The system according to claim 1, further comprising means for voice input and notification using a smartphone or smart glasses.

[0869] (Claim 3)

[0870] The system according to claim 1, further comprising means for obtaining data required by the user in real time based on notification information generated using the aforementioned speech synthesis technology and notifying the user as quickly as possible.

[0871] "Example 2 of combining an emotion engine"

[0872] (Claim 1)

[0873] A means for receiving voice input and converting the input voice into text information,

[0874] A means for analyzing the aforementioned textual information and identifying the content of the voice request,

[0875] A means of arranging transportation or food delivery services from external service providers based on identified voice requests,

[0876] A means of tracking the progress of arrangements and notifying users of the progress information,

[0877] A means of recognizing emotions for analyzing the emotional state of users,

[0878] A means of adjusting notification information based on emotion recognition results,

[0879] An alarm system to provide additional support when an abnormal emotional state is detected,

[0880] A system that includes this.

[0881] (Claim 2)

[0882] The system according to claim 1, further comprising means for generating notification information as voice using speech synthesis technology and providing it to the user.

[0883] (Claim 3)

[0884] The system according to claim 1, further comprising means for immediately updating and providing to users notification information related to the arrangement of the aforementioned external service provider.

[0885] "Application example 2 when combining with an emotional engine"

[0886] (Claim 1)

[0887] A means for receiving voice input and converting the input voice into text information,

[0888] A means for analyzing the aforementioned textual information and identifying the content of the voice request,

[0889] A means of arranging transportation or meal delivery services from an external service provider based on an identified voice request,

[0890] A means of tracking the progress of arrangements and notifying users of the progress information,

[0891] A means of using emotion analysis technology to determine the user's emotional state from voice input and adjusting notification information based on that emotion,

[0892] A system that includes this.

[0893] (Claim 2)

[0894] The system according to claim 1, further comprising means for generating and providing to a user customized notification information as voice, according to emotions, using speech synthesis technology.

[0895] (Claim 3)

[0896] The system according to claim 1, further comprising means for updating and providing to users in real time notification information related to arrangements with external service providers. [Explanation of Symbols]

[0897] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving voice input and converting the input voice into text information, A means for analyzing the aforementioned textual information and identifying the content of the voice request, A means of arranging transportation or food delivery services from an external service provider based on identified voice requests, A means of tracking the progress of the arrangement and notifying the user of the progress information, A system that includes this.

2. The system according to claim 1, further comprising means for generating notification information as voice using speech synthesis technology and providing it to the user.

3. The system according to claim 1, further comprising means for updating and providing to the user in real time notification information related to the arrangement of the external service provider.

Images