System

Abstract

A system is provided.SOLUTION: The system includes a means for receiving information related to the pet by voice input, a means for converting the received voice information into text, a natural language processing means for analyzing the converted text information, a means for storing the analyzed information in a database, a means for generating advice for health management and life support of the pet based on the stored information, and a means for notifying the user of the generated advice.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Today's pet owners face the challenge of managing their pets' health and necessary vaccinations and medications in their busy daily lives. It also takes a lot of time to select the right products to suit their pets' preferences. There is a need for an efficient system that can solve these challenges and improve the health and quality of life of pets. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means: a system including means for receiving information about a pet through voice input, means for converting the received voice information into text, natural language processing means for analyzing the converted text information, means for storing the analyzed information in a database, means for generating advice on health management and lifestyle support for the pet based on the stored information, and means for notifying the user of the generated advice. This system makes it possible to constantly monitor the health condition of a pet and provide appropriate advice in a timely manner.

[0006] "Voice input" refers to the act of a user providing voice information to a system through an input device such as a microphone.

[0007] "Convert to text" is a process of converting audio information into character data.

[0008] "Natural language processing" is a technology that allows computers to understand the natural language used by humans, and involves analyzing and classifying text data.

[0009] A "database" is a software system that stores information in an organized manner and references and updates it as needed.

[0010] "Advice" is advice about pet health management and lifestyle support generated based on the analysis results.

[0011] "Notifying the user" refers to the act of providing the generated advice to the user in the form of voice or text.

[0012] A "vaccine schedule" refers to managing the vaccination schedule that your pet should receive.

[0013] "Routine medication management" means properly managing the medication schedule for your pet. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

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

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

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

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

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

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

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

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0035] The present invention is a system for efficiently managing the health of pets and supporting their daily lives, and in particular, it establishes a series of processes for collecting, analyzing, saving, and notifying information using voice input. This system allows a user to provide information about their pet through voice input, converts that information into text, analyzes it, and generates advice based on the analysis results. The system is realized in a format in which the generated advice is then notified to the user. An embodiment of this system is described in detail below.

[0036] When a user speaks to the device about their pet's health or daily changes, the device's microphone picks up the voice and the voice data is converted into text using recognition software. For example, suppose a user says, "My dog ​​has gained 3 kilograms." This voice input is automatically converted into text, and the device's screen displays, "My dog ​​has gained 3 kilograms."

[0037] The text data is then sent from the device to a server, which receives the data and uses a natural language processing (NLP) engine to analyze the meaning of what the user has entered. This process involves extracting keywords from the text data and identifying associated health information or signs of abnormalities.

[0038] The analyzed information is stored in a database on the server. This database stores your pet's past health data and history, and when combined with newly added data, it serves as the basis for generating more accurate advice. This stored data can be referenced later, allowing for centralized management of your pet's health.

[0039] The server then generates pet health care advice based on the stored data. The advice generation engine formulates specific advice based on the analyzed information. For example, it might provide advice such as, "Your pet is gaining weight, so we recommend a low-calorie diet." Because such advice is automatically generated based on expert knowledge, users can receive reliable information.

[0040] The generated advice is sent from the server to the device. The device then notifies the user of the advice. This notification is provided as a voice message or text message. The advice is not only displayed on the device screen, but also provided as a voice guide if necessary, making it easy for the user to receive the advice.

[0041] As a concrete example, consider the case where a user voice-inputs, "My cat's appetite has decreased recently." This voice input is converted into text and sent to the server. The server analyzes this data and attempts to identify, for example, the "cause of the loss of appetite." As a result, advice is generated, such as, "It's possible that your cat's new type of food doesn't suit your taste," and is notified to the user. Based on this advice, the user can take measures such as changing the food.

[0042] As described above, the system of the present invention can collect, analyze, and notify pet health information through voice input, enabling users to easily manage their pet's health. This system has the effect of making pet health monitoring more efficient and reducing the burden on users.

[0043] The processing flow will be explained below.

[0044] Step 1:

[0045] The user speaks into the device to input information about their pet. The user provides information by speaking details about the health and behavior of their pet at home.

[0046] Step 2:

[0047] The device captures the user's voice through a microphone, and this voice data is sent in real time to speech recognition software.

[0048] Step 3:

[0049] Speech recognition software converts the audio data into text. For example, "My dog ​​has gained 3 kilos" becomes "My dog ​​has gained 3 kilos."

[0050] Step 4:

[0051] The device sends the text data to the server, where it is transferred using a secure communication protocol.

[0052] Step 5:

[0053] The server receives the text data and analyzes it using a natural language processing (NLP) engine. During the analysis, the server performs tasks such as understanding the meaning of the text, extracting keywords, and analyzing context to extract important information about the pet's health.

[0054] Step 6:

[0055] The server then stores the information in a database based on the analysis results, and the data is stored along with the pet's past health history for future reference and comparison.

[0056] Step 7:

[0057] The server uses the stored information to generate advice for pet health management and lifestyle support. This advice generation engine automatically creates specific advice such as, "Your pet is gaining weight, so we recommend a low-calorie diet."

[0058] Step 8:

[0059] The server sends the generated advice to the terminal, which is designed to reach the user quickly and accurately.

[0060] Step 9:

[0061] The device notifies the user of the received advice, and the user can confirm the advice by text displayed on the device screen or by voice output, allowing the user to take specific actions based on the advice provided.

[0062] Example 1

[0063] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0064] In the field of pet health management and lifestyle support, it is important to enable users to easily input information and receive specific advice based on that information. Conventional systems require users to manually input information, which is time-consuming and often requires specialized knowledge, making it difficult to respond quickly to pet conditions.

[0065] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0066] In this invention, the server includes means for receiving information about the pet through voice input, speech recognition means for converting the received speech information into text, means for transmitting the converted text information to the server, natural language processing means for analyzing the transmitted text information, means for storing the analyzed information in a database, advice generation means for generating advice on health management and lifestyle support for the pet based on the stored information, and means for notifying the user of the generated advice. This enables the user to easily and quickly provide information about the pet to the system through voice input and receive specific and reliable advice based on the resulting analysis.

[0067] "Voice input" is a means by which the user provides information about the pet to the system in the form of voice.

[0068] A "voice recognition means" is software or hardware for converting user-provided voice information into text format.

[0069] "Text information" is data in a sentence format converted from voice data by a voice recognition means.

[0070] A "server" is a central computing unit that receives, analyzes, stores, and generates advice about text information.

[0071] "Natural language processing means" refers to technology or software for analyzing text data and understanding its content.

[0072] A "database" is a data storage system for storing analyzed information in an organized manner.

[0073] The "advice generation means" is an engine or software for automatically generating specific advice for pet health management and lifestyle support based on the stored information.

[0074] A "notification means" is a method, medium, or technique for notifying a user of generated advice.

[0075] This invention is a system for efficiently managing the health and lifestyle of pets. In particular, it utilizes voice input to build a series of processes for collecting, analyzing, saving, and notifying information. This system allows the user to provide information about their pet through voice input, converts that information into text, analyzes it, and generates advice based on the analysis results. The system is realized in a way that the generated advice is then notified to the user.

[0076] The user inputs information about their pet's health condition and daily changes into the device by voice. For example, they might say, "My cat's appetite has decreased recently." The device's microphone receives this voice, and the voice data is converted into text using recognition software (e.g., Google® Speech-to-Text API). This voice input is converted into text format as "My cat's appetite has decreased recently," and the message "My cat's appetite has decreased recently" is displayed on the device's screen.

[0077] The text data is then sent from the device to a server. The server receives this text data and analyzes it using a natural language processing (NLP) engine (e.g., Amazon Comprehend). Specifically, it extracts keywords (e.g., "cat," "appetite," and "decreased") from the text data and understands its content. Based on this analysis, it can determine information about the pet's health and any signs of abnormalities.

[0078] The analyzed information is stored in a database on the server. This database stores your pet's past health data and history, and when combined with newly added data, it serves as the basis for generating more accurate advice. This stored data can be referenced later, allowing for centralized management of your pet's health.

[0079] The server then generates advice on pet health management based on the stored data. This advice generation engine (e.g., Microsoft® Azure® Machine Learning) uses the analyzed information to create specific advice. For example, it might suggest, "Your new type of food may not suit your cat's taste. Try a different food." Because such advice is automatically generated based on expert knowledge, users can be confident that they receive reliable information.

[0080] The generated advice is sent from the server to the device. The device then notifies the user of the advice. This notification is provided as a voice message or text message. The advice is not only displayed on the device screen, but also provides voice guidance as needed, making it easy for users to receive the advice.

[0081] As a concrete example, consider the case where a user voice-inputs "My dog ​​has gained weight." This voice input is converted into text "My dog ​​has gained weight" and sent to the server. The server analyzes this data and identifies the keyword "weight gain." The server compares it with past health data and generates advice to "introduce a low-calorie diet." This advice is sent to the device, and the user is notified that "Your dog has gained weight, so we recommend a low-calorie diet."

[0082] An example prompt is, "Convert the most recent voice input about your pet's condition to text and generate health advice based on the analysis of that text. For example, if your dog reports that it has gained weight, provide advice on appropriate diet and exercise."

[0083] This system will make pet health monitoring more efficient and reduce the burden on users.

[0084] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0085] Step 1:

[0086] The user inputs information about their pet's health condition and daily changes into the device by voice. For example, they might say, "My cat's appetite has decreased recently." This input is captured by the device's microphone, and the voice data is generated. Voice data is given as input, and the same voice data is obtained as output.

[0087] Step 2:

[0088] The device converts the received voice data into text format using voice recognition software (e.g., Google Speech-to-Text API). This voice is recognized as "My cat's appetite has decreased recently" and converted into text data. Voice data is given as input, and text data is output as the processing result. Specifically, phonemic and contextual analysis is performed on the voice data, and the corresponding text is generated.

[0089] Step 3:

[0090] The text data is sent from the terminal to the server. The terminal encodes the conversion result as packet data and sends it to the server via the network. Text data is given as input, and network packets arrive at the server as output. Specifically, the terminal sends an HTTP request, and the server receives it at the corresponding endpoint.

[0091] Step 4:

[0092] The server uses a natural language processing (NLP) engine (e.g., Amazon Comprehend) to analyze the received text data. The server extracts keywords (e.g., "cat," "appetite," and "dropped") from the text data and analyzes their meaning. The text data is given as input, and keywords and analysis results are output. Specifically, morphological and semantic analysis is performed on the text data, and the results are extracted.

[0093] Step 5:

[0094] The parsed information is stored in a database on the server. The server inserts the parsed results into the database as structured data. The parsed results are given as input, and the information stored in the database is output. Specifically, an INSERT statement is executed into the database, and the information is permanently saved.

[0095] Step 6:

[0096] The server generates advice on pet health care based on the stored data. This advice generation engine (e.g., Microsoft Azure Machine Learning) uses the analysis results to form specific advice. The stored data is given as input, and the generated advice is obtained as output. Specifically, a machine learning model analyzes the data and generates advice statements.

[0097] Step 7:

[0098] The generated advice is sent from the server to the terminal. The server encodes the advice in text format and sends it to the terminal via the network. The generated advice is given as input, and a network packet arrives at the terminal as output. Specifically, an HTTP response is generated and received by the terminal.

[0099] Step 8:

[0100] The terminal notifies the user of the received advice. The advice is displayed on the terminal screen and, if necessary, is also provided as a voice message. The advice from the server is given as input, and the advice displayed to the user is output. Specifically, the terminal's GUI is updated, and text is displayed and voice is played.

[0101] (Application example 1)

[0102] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0103] Modern homes and offices require efficient and reliable security management. Conventional security systems that rely on cameras and sensors are prone to false alarms and false positives, making it difficult to respond quickly. Another issue facing security management is the lack of specific advice that allows users to take appropriate measures immediately.

[0104] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0105] In this invention, the server includes means for receiving security-related information by voice input, means for converting the received voice information into text, natural language processing means for analyzing the converted text information, means for storing the analyzed information in a database, means for generating advice on security management and life support based on the stored information, and means for notifying the generated advice to the user. This enables the user to easily report security information by voice input and quickly receive specific advice based on the information.

[0106] "Voice input" is a technology that recognizes voice and processes it as digital information.

[0107] "Security information" is data that indicates the security status of a home or office, including unauthorized intrusions, abnormal activity, and the status of equipment.

[0108] "Means for converting to text" refers to technology that converts voice data into text information.

[0109] "Natural language processing means" refers to technology that analyzes human language, understands its meaning, and processes it.

[0110] "Means of storing in a database" refers to the technology used to manage and store analyzed information within the system.

[0111] "Means for generating advice" refers to technology that automatically creates appropriate instructions or suggestions for the user based on the stored information.

[0112] "Means for notifying" refers to a communication technique for conveying the generated advice to the user.

[0113] "Server" refers to a computer system that centrally processes and manages data.

[0114] "Security management" refers to activities aimed at protecting a home or office and preventing unauthorized access.

[0115] "Lifestyle support" refers to providing instructions and advice to users in their daily lives.

[0116] This invention is a security management system that uses voice input, and provides a mechanism for users to report the security status of their home or office by voice and receive appropriate advice based on the content of the report. This system includes a series of processes such as voice input, text conversion, information analysis, data storage, advice generation, and notification.

[0117] Hardware Configuration

[0118] The system uses the following hardware:

[0119] 1. Smartphones and smart speakers: Used for voice input and receiving notifications.

[0120] 2. Microphone and speaker: Used for recording and playing audio.

[0121] Software Configuration

[0122] The system uses the following software:

[0123] 1. Speech recognition engine (e.g. Google Cloud Speech-to-Text): Converts speech into text.

[0124] 2. Natural language processing engine (e.g., Dialogflow, Amazon Comprehend): Analyzes the input text and understands its meaning.

[0125] 3. Cloud database (e.g., AWS® DynamoDB, GOOGLE FI® restore): Stores the analyzed information.

[0126] 4. Notification system (e.g., Firebase Cloud Messaging, Twilio): Notifies the user of the generated advice.

[0127] System Operation

[0128] 1. Voice input:

[0129] The user reports the security situation by voice to a smartphone or smart speaker, for example, saying, "The office window is open."

[0130] 2. Text conversion:

[0131] The device will record your voice and convert it to text using Google Cloud Speech-to-Text, which will say "The office window is open."

[0132] 3. Information analysis:

[0133] The text information is sent to a natural language processing engine for semantic analysis. Dialogflow and Amazon Comprehend are used to understand the content of the text and assess security risks. For example, an "open window" can be recognized as a risk and assessed accordingly.

[0134] 4. Data Retention:

[0135] The analyzed information is stored in a cloud database, including risk assessment and situation details.

[0136] 5. Advice Generation:

[0137] Based on the stored data, a generative AI model (e.g., GPT-3 (registered trademark)) is used to generate specific countermeasures. For example, advice such as "Check and close windows immediately" is generated.

[0138] 6. Notice:

[0139] Firebase Cloud Messaging and Twilio are used to notify users of the generated advice, which is delivered via voice or text to smartphones or smart speakers.

[0140] Specific examples

[0141] Example prompts if the user says "My office windows are open":

[0142] The user has spoken "The office window is open." Use this information to identify security risks and notify the user of countermeasures.

[0143] Based on this prompt, the generative AI model generates advice such as, "It appears that a window in your office is open. Please check immediately and close the window if necessary."

[0144] As described above, the system of the present invention allows a user to easily report security information through voice input and quickly receive specific advice based on that information.

[0145] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0146] Step 1: Voice Input

[0147] The user reports the security situation by voice to a smartphone or smart speaker. The voice input is information such as "The office window is open." The device's microphone records the voice and the data is sent to the device.

[0148] Step 2: Text conversion

[0149] The device sends the recorded voice data to a speech recognition engine (e.g., Google Cloud Speech-to-Text). The speech recognition engine analyzes the voice data and converts it into text information. The input is voice data, and the output is text data such as "The office window is open."

[0150] Step 3: Information analysis

[0151] Text data is sent to a natural language processing engine (e.g., Dialogflow, Amazon Comprehend). The natural language processing engine analyzes the text and understands its meaning. The input is text data, and the output is a security risk assessment and detailed information as the analysis results. For example, risk information such as "the window is open" is evaluated.

[0152] Step 4: Save Data

[0153] The analysis results are stored in a cloud database (e.g., AWS DynamoDB, Google Firestore). The input is the analyzed information, and the output is the risk assessment and situation details stored in the database. This accumulates data that can be used for future reference.

[0154] Step 5: Advice Generation

[0155] The server uses a generative AI model (e.g., GPT-3) based on the stored information to generate specific countermeasures. The input is the database information and a prompt, and the output is specific advice. For example, the generated advice might be, "Check and close the windows immediately."

[0156] Step 6: Notification

[0157] The generated advice is sent to the user via a notification system (e.g., Firebase Cloud Messaging, Twilio). The input is the generated advice, and the output is a notification that is displayed on the user's smartphone or smart speaker or played aloud.

[0158] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0159] The present invention combines a system for managing the health and lifestyle of pets using voice input with an emotion engine that recognizes the emotions of the user. This system includes a voice input function in which the user provides information about the pet, a function for converting the voice information into text, a function for analyzing the text data using a natural language processing (NLP) engine, a function for saving the analysis results in a database, a function for generating advice based on the saved data, a function for notifying the user of the advice, and a function for recognizing emotions using the emotion engine. Specific embodiments of the system are described below.

[0160] The user speaks into the device to input information about their pet's health and behavior. For example, if the user types, "My dog ​​has gained 3 kilos," the device's microphone captures this voice. This voice data is sent to speech recognition software in real time and converted into text. The resulting text is, "My dog ​​has gained 3 kilos."

[0161] The text data is then sent from the device to a server. The server receives the text data and analyzes it using a natural language processing engine. During the analysis process, the server performs tasks such as understanding the intent of the text, extracting keywords, and analyzing context to extract important information about the pet's health. The results of this analysis are stored in a database on the server. The pet's past health data is also stored, and together with newly added data, it serves as the basis for generating more accurate advice.

[0162] The server generates advice for pet health management and lifestyle support based on the stored information. For example, it may provide advice such as, "Your pet is gaining weight, so we recommend a low-calorie diet." This advice generation engine automatically generates specific advice based on expert knowledge, ensuring that users receive reliable information.

[0163] One of the features of the present invention is the incorporation of an emotion engine. The emotion engine has the function of analyzing the user's emotions during voice input and recognizing emotional states such as anxiety, anger, and joy. For example, if the user is feeling stressed, the emotion engine will classify that emotion as "worry." This emotion data is stored in a database and will be referenced the next time advice is generated.

[0164] The user's emotions recognized by the emotion engine can influence the advice that is generated. For example, if a user says, "I'm worried because my cat's appetite has decreased recently," the emotion engine will detect the emotion "worry." Based on this information, the server will generate advice that takes the emotion into consideration. Specifically, it will provide advice that is sensitive to the user's emotions, such as, "Your cat's appetite has decreased, but it might be a good idea to try a new type of food. Don't worry, just wait and see."

[0165] The generated advice is sent from the server to the device. The device notifies the user of this advice by voice or text. The user can check the advice on the device screen or listen to the guide message by voice. This notification allows the user to take appropriate measures for managing their pet's health.

[0166] As a concrete example, consider the case where a user voice-inputs, "My dog ​​has gained 3 kg, and I'm very worried." This voice is converted into text and sent to the server. The server analyzes the text and emotional information to detect the user's concern. As a result, it generates emotionally sensitive advice such as, "Your dog has gained weight, but as long as it's not a big increase, it's not a problem. I recommend you increase moderate exercise and switch to a low-calorie diet. Don't worry too much." and sends it to the device. The device notifies the user, who can then take appropriate action based on the advice.

[0167] This invention allows users to easily understand their pet's health condition through voice input and receive appropriate support tailored to their individual needs and emotions. This system has the effect of streamlining pet health monitoring and significantly reducing the burden on users.

[0168] The processing flow will be explained below.

[0169] Step 1:

[0170] The user speaks information about their pet into the device, for example, saying, "My dog ​​has gained 3 kilograms."

[0171] Step 2:

[0172] The device captures the user's voice through a microphone, and the captured voice data is sent directly to voice recognition software.

[0173] Step 3:

[0174] The speech recognition software converts the received speech data into text, resulting in the text "My dog ​​has gained 3 kilos."

[0175] Step 4:

[0176] The device then transmits the converted data to the server, where it is securely transferred using a security protocol.

[0177] Step 5:

[0178] The server receives the text data and analyzes it using a natural language processing (NLP) engine, which performs semantic analysis of the text, keyword extraction, context understanding, and more.

[0179] Step 6:

[0180] The server stores the analyzed data in a database, which also contains the pet's health history and past information, and centrally records the analysis results.

[0181] Step 7:

[0182] The server generates advice on pet health management and lifestyle support based on the stored information, such as "Your pet is gaining weight, so we recommend a low-calorie diet."

[0183] Step 8:

[0184] The server uses an emotion engine to analyze the user's emotions when generating advice. It recognizes the user's emotional state (e.g., worry, joy, anger) from their voice data and formulates advice that takes their emotions into consideration.

[0185] Step 9:

[0186] The server then sends advice based on the generated emotions to the device, again using a security protocol to transfer data.

[0187] Step 10:

[0188] The device then notifies the user of the advice it receives, which is displayed as a voice message or text message, such as "A low-calorie diet is recommended to prevent weight gain. Don't worry too much."

[0189] Step 11:

[0190] Users can check the provided advice and take action to manage their pet's health (e.g., changing its diet or increasing its exercise) based on it, thus enabling them to effectively manage their pet's health.

[0191] Example 2

[0192] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0193] While conventional pet health management systems can obtain information about pets through voice input, they face the challenge of efficiently analyzing that information and providing appropriate advice that takes the user's feelings into consideration. Furthermore, advice provided without considering the user's anxieties and worries may not be satisfactory to the user. Furthermore, there is a lack of systems that centrally manage pet health information and provide effective notifications.

[0194] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0195] In this invention, the server includes means for receiving information about the pet through voice input, means for converting the received voice information into text, natural language processing means for analyzing the converted text information, means for storing the analyzed information in a database, means for generating advice on pet health management and lifestyle support based on the stored information, means for notifying the user of the generated advice, emotion recognition means for analyzing the user's emotions, and means for adjusting the advice based on the emotion recognition results. This makes it possible to easily collect pet health information through voice input and provide highly accurate advice that takes the user's emotions into consideration.

[0196] "Voice input" is the means by which a user's spoken voice data is received and interpreted by the system.

[0197] "Voice information" means information about a pet provided by a user through voice input.

[0198] "Means for converting to text" refers to a technique for converting voice information into character string data.

[0199] "Natural language processing means" is a technology for analyzing text data and understanding its content.

[0200] "Means of storing in a database" refers to technology that centrally manages analyzed information and makes it available for future reference.

[0201] The "means for generating advice" is a technique for creating specific instructions or suggestions for the user based on the stored information.

[0202] The "means for notifying advice" is a technique for conveying the generated advice to the user.

[0203] "Emotion recognition means" is a technology for analyzing and recognizing a user's emotional state through voice input.

[0204] "Means for adjusting advice" refers to technology that changes or customizes the content of advice based on emotion recognition results.

[0205] The present invention is a system that utilizes voice input to manage the health and lifestyle of pets, and combines it with an emotion engine that recognizes the user's emotions. This system is composed of a combination of multiple hardware and software components.

[0206] Specific hardware and software configurations

[0207] Device: Use a smartphone or tablet with a microphone, which allows the user to input voice.

[0208] Server: A cloud-based server is used, which analyzes and manages the voice data.

[0209] Speech Recognition Software: We use the Google Speech-to-Text API to convert voice data into text.

[0210] Natural language processing engine: spaCy is used to analyze text data and extract important information.

[0211] Database: A MySQL® database is used to store the analyzed data.

[0212] Emotion Engine: Uses IBM Watson® Tone Analyzer to analyze the user's emotions.

[0213] Specific examples of implementation

[0214] The user speaks to the device to provide information about their pet's health and behavior. For example, if they say, "My dog ​​has gained 3 kilograms," the device's microphone captures this voice. This voice data is sent in real time to the Google Speech-to-Text API and converted into text. The resulting text is, "My dog ​​has gained 3 kilograms."

[0215] The converted data is then sent from the device to a server. The server receives this text data and analyzes it using a natural language processing engine (spaCy). During the analysis process, the intent of the text is understood, keywords are extracted, and context is analyzed to extract important information about the pet's health. The analysis results are stored in a MySQL database on the server.

[0216] The server generates advice for pet health management and lifestyle support based on the stored information. For example, the server may generate advice such as, "Your pet is gaining weight, so we recommend a low-calorie diet." The generated advice is sent from the server to the device, which then notifies the user of the advice by text or voice.

[0217] Furthermore, the emotion engine (IBM Watson Tone Analyzer) analyzes the user's emotions during voice input and recognizes emotions such as anxiety, anger, and joy. For example, if a user says, "I'm very worried," the emotion engine will detect the emotion "worry." This emotion data is stored in a database and will be referenced the next time advice is generated.

[0218] The user's emotions recognized by the emotion engine can influence the content of the advice generated. For example, if a user says, "My cat's appetite has decreased recently, and I'm worried," the emotion engine detects the emotion "worry." Based on this information, the server generates advice that takes emotions into consideration. Specifically, it provides advice that is sensitive to the user's emotions, such as, "Your cat's appetite has decreased, but it might be a good idea to try a new type of food. Don't worry, just wait and see."

[0219] An example of a prompt sentence is, "My pet has recently gained weight. What should I do? I'm worried." This system allows users to easily understand their pet's health status through voice input and receive appropriate support tailored to their individual needs and emotions. This has the effect of streamlining pet health monitoring and significantly reducing the burden on users.

[0220] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0221] Step 1:

[0222] The user speaks information about the pet into the terminal.

[0223] Input: User speech (e.g., "My dog ​​has gained 3 kilos").

[0224] What it does: The user opens a recording app on their smartphone and dictates their pet's health status. The device's microphone captures the audio.

[0225] Output: The captured audio data.

[0226] Step 2:

[0227] The device sends the captured voice data to speech recognition software (Google Speech-to-Text API) in real time, which converts the voice data into text.

[0228] Input: Captured speech data (e.g., "My dog ​​has gained 3 kilos").

[0229] What it does: It sends audio data to the Google Speech-to-Text API, which then recognizes the speech and converts it into text.

[0230] Output: Text data (e.g., "My dog ​​has gained 3 kg").

[0231] Step 3:

[0232] The terminal transmits the converted text data to the server.

[0233] Input: Text data (e.g., "My dog ​​has gained 3 kg").

[0234] Specific behavior: Sends text data to the server as an HTTP POST request.

[0235] Output: The text data sent to the server.

[0236] Step 4:

[0237] The server analyzes the text data it receives using a natural language processing engine (spaCy) to extract important information about the pet's health.

[0238] Input: Text data sent to the server (e.g., "My dog ​​has gained 3 kilos").

[0239] Specific operation: The server passes the text data to spaCy, which performs intent understanding, keyword extraction, context analysis, etc.

[0240] Output: Analysis results (e.g. keywords such as "dog", "weight", "gained 3kg").

[0241] Step 5:

[0242] The server stores the analysis results in a database (MySQL).

[0243] Input: Analysis results (e.g. keywords such as "dog", "weight", "gained 3kg").

[0244] Specific operation: The parsed results are sent to the MySQL database as an INSERT query and saved.

[0245] Output: Analysis results stored in a database.

[0246] Step 6:

[0247] The server generates advice on health management and lifestyle support for pets based on the stored information.

[0248] Input: Analysis results stored in the database (e.g. "dog", "weight", "gained 3 kg", etc.).

[0249] Specific operation: The server runs the advice generation engine based on the stored data and generates health management advice.

[0250] Output: The generated advice (e.g., "Your pet is gaining weight, so we recommend a low-calorie diet").

[0251] Step 7:

[0252] The server analyzes the user's emotions during voice input using an emotion recognition engine (IBM Watson Tone Analyzer).

[0253] Input: Text data sent to the server (e.g., "My dog ​​has gained 3 kilos").

[0254] How it works: The server passes the text data to IBM Watson Tone Analyzer, which analyzes emotions such as anxiety, anger, and joy.

[0255] Output: Emotion recognition result (e.g., "worried").

[0256] Step 8:

[0257] The server adjusts the advice generated based on the emotion recognition results.

[0258] Input: Emotion recognition result (e.g., "worried") and generated advice (e.g., "your pet is gaining weight, so we recommend a low-calorie diet").

[0259] Specific behavior: The server takes into account the emotion recognition results and adjusts the advice. Specifically, it adjusts the advice to say, "It might be a good idea to try a new type of food. Don't worry, let's see how it goes."

[0260] Output: Tailored advice (e.g., "Maybe you should try a new type of food. Don't worry, let's see how it goes.").

[0261] Step 9:

[0262] The server sends the advice to the terminal, which then notifies the user.

[0263] Input: Tailored advice (e.g., "Maybe you should try a new type of food. Don't worry, let's see how it goes.").

[0264] Specific behavior: The advice is sent to the device via an HTTP response, and the device app notifies the user.

[0265] Output: Advice given to the user (e.g. "Maybe you should try a new type of food. Don't worry, just wait and see").

[0266] (Application example 2)

[0267] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0268] Conventional pet health management systems often require users to manually enter data, which is time-consuming and inaccurate. Furthermore, since the advice provided does not take into account the user's feelings, it is difficult to provide suggestions in a way that is easy for the user to accept. Furthermore, data storage and management are cumbersome, which can delay appropriate responses in situations where a prompt response is required.

[0269] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0270] In this invention, the server includes means for receiving information about a pet through voice input, means for converting the received voice information into text, natural language processing means for analyzing the converted text information, means for saving the analyzed information in a database, means for generating advice on health management and lifestyle support for the pet based on the saved information, means for notifying the user of the generated advice, and means for analyzing the user's emotions, saving the information, and reflecting it in subsequent advice. This allows the user to easily manage the health condition of their pet through voice input, and by receiving advice that takes emotions into consideration, more effective pet care is possible.

[0271] "Voice input" is a method in which a user communicates information about a pet to the system through a voice capture device such as a microphone.

[0272] A "means for converting to text" is a device or software that includes speech recognition technology for analyzing speech information and converting it into a corresponding string of characters.

[0273] "Natural language processing means" is a technology that uses computers to analyze human language and understand intent and meaning, and analyzes text data.

[0274] A "means for storing in a database" is a process or device that organizes the analyzed information and stores it in a storage device in a format that can be accessed later.

[0275] A "means for generating pet health care and lifestyle support advice" is a process or device that automatically generates recommendations related to a pet's health and lifestyle based on stored data.

[0276] The "means for notifying the user" refers to a method or device for distributing the generated advice or information in a form that the user can check.

[0277] The "means for analyzing user emotions" is a technology for analyzing and recognizing emotions expressed by a user during voice input.

[0278] The "means for reflecting in future advice" is a process or device for storing the analyzed emotional state of the user in a database and taking that emotional information into account when generating future advice.

[0279] The "Pet Care Advisor" system for implementing this invention is mainly composed of a voice input function, a text conversion function, a natural language processing (NLP) engine, a database storage function, an advice generation engine, a notification function, and a sentiment analysis engine. Each function will be described in detail below.

[0280] Speech to text conversion

[0281] Users use a smartphone or other voice input device to voice-record information about their pet's health and behavior. This voice data is converted into text in real time using speech recognition software (e.g., Google Cloud Speech-to-Text API). In this process, speech such as "My dog ​​has gained 3 kilograms and I'm worried" can be converted into text.

[0282] Natural Language Processing (NLP) Engine

[0283] The text data is sent to a server and analyzed by a natural language processing engine (for example, Google Cloud Natural Language API). This engine understands the intent of the text, extracts keywords, and analyzes the context to extract important information about the pet's health. For example, information such as "weight gain" or "worries" may be extracted.

[0284] Database storage function

[0285] The analyzed data is stored in a database on the server, which also stores the pet's past health data and, together with the newly added data, serves as the basis for generating advice.

[0286] Sentiment Analysis Engine

[0287] An emotion analysis engine (for example, IBM Watson Tone Analyzer) analyzes the user's emotions during voice input and recognizes emotional states such as anxiety, anger, and joy. This emotional data is also stored in a database and is referenced the next time advice is generated. For example, the emotion "worry" may be detected from the input voice.

[0288] Advice Generation Engine

[0289] The server generates advice on pet health management and lifestyle support based on the stored information. For example, it might say, "Your pet is gaining weight, so we recommend a low-calorie diet. Don't worry too much, but increase your pet's moderate exercise." The engine generates reliable information based on past data and expert knowledge.

[0290] Notification function

[0291] The generated advice is sent from the server to the user's device. The user can check the advice on the device screen or listen to the guide message via audio. The device then assists the user in taking appropriate measures.

[0292] Specific examples

[0293] For example, if a user says, "My dog ​​has gained 3 kilograms and I'm worried," this speech is converted into text and sent to the server. The server analyzes the text and emotional information to detect the user's concern. As a result, advice such as "Your dog has gained weight, but as long as it's not a big increase, it's not a problem. I recommend you increase moderate exercise and switch to a low-calorie diet. Don't worry too much" is generated and sent to the device.

[0294] Prompt Sentence Examples

[0295] The user's voice input is converted to text and then that text is used as the prompt.

[0296] example:

[0297] Prompt: The user says, "My dog ​​has gained 3 kg and I'm worried." Text: "My dog ​​has gained 3 kg and I'm worried." Use this information and the user's emotion of "worry" to generate specific advice related to pet health care.

[0298] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0299] Step 1:

[0300] The user uses a voice input device such as a smartphone to input information about the health and behavior of their pet. Specifically, the user speaks into the device's microphone, saying, "My dog ​​has gained 3 kilograms, and I'm worried." This input voice becomes the initial data for the system. The input in Step 1 is the user's voice. The output is voice data.

[0301] Step 2:

[0302] The voice data received by the device is sent in real time to voice recognition software, which converts it into text. This process uses voice recognition technology such as the Google Cloud Speech-to-Text API. The input in step 2 is voice data, and the output is text data. Specifically, the text generated is, "My dog ​​has gained 3 kilograms and I'm worried."

[0303] Step 3:

[0304] The converted data is sent from the terminal to the server. The server receives this text data and prepares it for the next analysis step. The input of step 3 is the converted text data, and the output is the status of completion of transmission to the server.

[0305] Step 4:

[0306] The text data received by the server is analyzed using a natural language processing engine (for example, Google Cloud Natural Language API). Here, the intent of the text is understood, keywords are extracted, and context is analyzed to extract important information about the pet's health condition. The input for step 4 is the text data, and the output is the analyzed key data. Specifically, keywords such as "weight gain" and "worry" are extracted.

[0307] Step 5:

[0308] The analyzed data is saved in a database. This database also stores the pet's past health data, and together with the newly added data, it serves as the basis for generating advice. The input of Step 5 is the analyzed key data, and the output is the data saving completion status.

[0309] Step 6:

[0310] The server analyzes the user's emotions during voice input using an emotion analysis engine (e.g., IBM Watson Tone Analyzer). Here, emotional states such as anxiety, anger, and joy are recognized. The input in step 6 is speech-to-text data, and the output is emotional information. For example, the emotion "worry" is detected.

[0311] Step 7:

[0312] The emotional data is saved in the database. The user's emotional information obtained through emotion analysis will also be referenced the next time advice is generated. The input of step 7 is the emotional information, and the output is the data saving completion status.

[0313] Step 8:

[0314] The server generates advice for pet health management and lifestyle support based on the stored information. This advice generation engine uses a machine learning model to provide optimal advice based on the stored health data and emotional data. The input to step 8 is analysis data and emotional data, and the output is specific advice text. For example, advice such as "Your pet has gained weight, but as long as it's not a significant increase, it's not a problem. We recommend increasing moderate exercise and switching to a low-calorie diet. Don't worry too much" may be generated.

[0315] Step 9:

[0316] The generated advice is sent to the user's device. The user can check the advice through the device and take any necessary measures. The input of step 9 is the advice text, and the output is the notification completion status to the user. Specifically, a message is displayed on the smartphone screen saying, "You've gained weight, but as long as it's not a significant increase, it's not a problem. We recommend that you increase moderate exercise and switch to a low-calorie diet. Don't worry too much."

[0317] Example prompt sentence:

[0318] A user says, "My dog ​​has gained 3 kg and I'm worried." Text: "My dog ​​has gained 3 kg and I'm worried." Use this information and the user's emotion, "worried," to generate specific advice related to pet health care.

[0319] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0320] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0321] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0322] [Second embodiment]

[0323] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0324] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0325] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0326] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0327] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0328] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0329] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0330] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0331] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0332] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0333] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0334] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0335] The present invention is a system for efficiently managing the health of pets and supporting their daily lives, and in particular, it establishes a series of processes for collecting, analyzing, saving, and notifying information using voice input. This system allows a user to provide information about their pet through voice input, converts that information into text, analyzes it, and generates advice based on the analysis results. The system is realized in a format in which the generated advice is then notified to the user. An embodiment of this system is described in detail below.

[0336] When a user speaks to the device about their pet's health or daily changes, the device's microphone picks up the voice and the voice data is converted into text using recognition software. For example, suppose a user says, "My dog ​​has gained 3 kilograms." This voice input is automatically converted into text, and the device's screen displays, "My dog ​​has gained 3 kilograms."

[0337] The text data is then sent from the device to a server, which receives the data and uses a natural language processing (NLP) engine to analyze the meaning of what the user has entered. This process involves extracting keywords from the text data and identifying associated health information or signs of abnormalities.

[0338] The analyzed information is stored in a database on the server. This database stores your pet's past health data and history, and when combined with newly added data, it serves as the basis for generating more accurate advice. This stored data can be referenced later, allowing for centralized management of your pet's health.

[0339] The server then generates pet health care advice based on the stored data. The advice generation engine formulates specific advice based on the analyzed information. For example, it might provide advice such as, "Your pet is gaining weight, so we recommend a low-calorie diet." Because such advice is automatically generated based on expert knowledge, users can receive reliable information.

[0340] The generated advice is sent from the server to the device. The device then notifies the user of the advice. This notification is provided as a voice message or text message. The advice is not only displayed on the device screen, but also provided as a voice guide if necessary, making it easy for the user to receive the advice.

[0341] As a concrete example, consider the case where a user voice-inputs, "My cat's appetite has decreased recently." This voice input is converted into text and sent to the server. The server analyzes this data and attempts to identify, for example, the "cause of the loss of appetite." As a result, advice is generated, such as, "It's possible that your cat's new type of food doesn't suit your taste," and is notified to the user. Based on this advice, the user can take measures such as changing the food.

[0342] As described above, the system of the present invention can collect, analyze, and notify pet health information through voice input, enabling users to easily manage their pet's health. This system has the effect of making pet health monitoring more efficient and reducing the burden on users.

[0343] The processing flow will be explained below.

[0344] Step 1:

[0345] The user speaks into the device to input information about their pet. The user provides information by speaking details about the health and behavior of their pet at home.

[0346] Step 2:

[0347] The device captures the user's voice through a microphone, and this voice data is sent in real time to speech recognition software.

[0348] Step 3:

[0349] Speech recognition software converts the audio data into text. For example, "My dog ​​has gained 3 kilos" becomes "My dog ​​has gained 3 kilos."

[0350] Step 4:

[0351] The device sends the text data to the server, where it is transferred using a secure communication protocol.

[0352] Step 5:

[0353] The server receives the text data and analyzes it using a natural language processing (NLP) engine. During the analysis, the server performs tasks such as understanding the meaning of the text, extracting keywords, and analyzing context to extract important information about the pet's health.

[0354] Step 6:

[0355] The server then stores the information in a database based on the analysis results, and the data is stored along with the pet's past health history for future reference and comparison.

[0356] Step 7:

[0357] The server uses the stored information to generate advice for pet health management and lifestyle support. This advice generation engine automatically creates specific advice such as, "Your pet is gaining weight, so we recommend a low-calorie diet."

[0358] Step 8:

[0359] The server sends the generated advice to the terminal, which is designed to reach the user quickly and accurately.

[0360] Step 9:

[0361] The device notifies the user of the received advice, and the user can confirm the advice by text displayed on the device screen or by voice output, allowing the user to take specific actions based on the advice provided.

[0362] Example 1

[0363] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0364] In the field of pet health management and lifestyle support, it is important to enable users to easily input information and receive specific advice based on that information. Conventional systems require users to manually input information, which is time-consuming and often requires specialized knowledge, making it difficult to respond quickly to pet conditions.

[0365] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0366] In this invention, the server includes means for receiving information about the pet through voice input, speech recognition means for converting the received speech information into text, means for transmitting the converted text information to the server, natural language processing means for analyzing the transmitted text information, means for storing the analyzed information in a database, advice generation means for generating advice on health management and lifestyle support for the pet based on the stored information, and means for notifying the user of the generated advice. This enables the user to easily and quickly provide information about the pet to the system through voice input and receive specific and reliable advice based on the resulting analysis.

[0367] "Voice input" is a means by which the user provides information about the pet to the system in the form of voice.

[0368] A "voice recognition means" is software or hardware for converting user-provided voice information into text format.

[0369] "Text information" is data in a sentence format converted from voice data by a voice recognition means.

[0370] A "server" is a central computing unit that receives, analyzes, stores, and generates advice about text information.

[0371] "Natural language processing means" refers to technology or software for analyzing text data and understanding its content.

[0372] A "database" is a data storage system for storing analyzed information in an organized manner.

[0373] The "advice generation means" is an engine or software for automatically generating specific advice for pet health management and lifestyle support based on the stored information.

[0374] A "notification means" is a method, medium, or technique for notifying a user of generated advice.

[0375] This invention is a system for efficiently managing the health and lifestyle of pets. In particular, it utilizes voice input to build a series of processes for collecting, analyzing, saving, and notifying information. This system allows the user to provide information about their pet through voice input, converts that information into text, analyzes it, and generates advice based on the analysis results. The system is realized in a way that the generated advice is then notified to the user.

[0376] The user inputs information about their pet's health condition and daily changes into the device by voice. For example, they might say, "My cat's appetite has decreased recently." The device's microphone receives this voice, and the voice data is converted into text using recognition software (e.g., Google Speech-to-Text API). This voice input is converted into text format as "My cat's appetite has decreased recently," and the message "My cat's appetite has decreased recently" is displayed on the device's screen.

[0377] The text data is then sent from the device to a server. The server receives this text data and analyzes it using a natural language processing (NLP) engine (e.g., Amazon Comprehend). Specifically, it extracts keywords (e.g., "cat," "appetite," and "decreased") from the text data and understands its content. Based on this analysis, it can determine information about the pet's health and any signs of abnormalities.

[0378] The analyzed information is stored in a database on the server. This database stores your pet's past health data and history, and when combined with newly added data, it serves as the basis for generating more accurate advice. This stored data can be referenced later, allowing for centralized management of your pet's health.

[0379] The server then generates advice on pet health management based on the stored data. This advice generation engine (e.g., Microsoft Azure Machine Learning) uses the analyzed information to form specific advice. For example, it might provide advice such as, "Your cat's new type of food may not be to its liking, so try a different food." Because such advice is automatically generated based on expert knowledge, users can be assured of reliable information.

[0380] The generated advice is sent from the server to the device. The device then notifies the user of the advice. This notification is provided as a voice message or text message. The advice is not only displayed on the device screen, but also provides voice guidance as needed, making it easy for users to receive the advice.

[0381] As a concrete example, consider the case where a user voice-inputs "My dog ​​has gained weight." This voice input is converted into text "My dog ​​has gained weight" and sent to the server. The server analyzes this data and identifies the keyword "weight gain." The server compares it with past health data and generates advice to "introduce a low-calorie diet." This advice is sent to the device, and the user is notified that "Your dog has gained weight, so we recommend a low-calorie diet."

[0382] An example prompt is, "Convert the most recent voice input about your pet's condition to text and generate health advice based on the analysis of that text. For example, if your dog reports that it has gained weight, provide advice on appropriate diet and exercise."

[0383] This system will make pet health monitoring more efficient and reduce the burden on users.

[0384] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0385] Step 1:

[0386] The user inputs information about their pet's health condition and daily changes into the device by voice. For example, they might say, "My cat's appetite has decreased recently." This input is captured by the device's microphone, and the voice data is generated. Voice data is given as input, and the same voice data is obtained as output.

[0387] Step 2:

[0388] The device converts the received voice data into text format using voice recognition software (e.g., Google Speech-to-Text API). This voice is recognized as "My cat's appetite has decreased recently" and converted into text data. Voice data is given as input, and text data is output as the processing result. Specifically, phonemic and contextual analysis is performed on the voice data, and the corresponding text is generated.

[0389] Step 3:

[0390] The text data is sent from the terminal to the server. The terminal encodes the conversion result as packet data and sends it to the server via the network. Text data is given as input, and network packets arrive at the server as output. Specifically, the terminal sends an HTTP request, and the server receives it at the corresponding endpoint.

[0391] Step 4:

[0392] The server uses a natural language processing (NLP) engine (e.g., Amazon Comprehend) to analyze the received text data. The server extracts keywords (e.g., "cat," "appetite," and "dropped") from the text data and analyzes their meaning. The text data is given as input, and keywords and analysis results are output. Specifically, morphological and semantic analysis is performed on the text data, and the results are extracted.

[0393] Step 5:

[0394] The parsed information is stored in a database on the server. The server inserts the parsed results into the database as structured data. The parsed results are given as input, and the information stored in the database is output. Specifically, an INSERT statement is executed into the database, and the information is permanently saved.

[0395] Step 6:

[0396] The server generates advice on pet health care based on the stored data. This advice generation engine (e.g., Microsoft Azure Machine Learning) uses the analysis results to form specific advice. The stored data is given as input, and the generated advice is obtained as output. Specifically, a machine learning model analyzes the data and generates advice statements.

[0397] Step 7:

[0398] The generated advice is sent from the server to the terminal. The server encodes the advice in text format and sends it to the terminal via the network. The generated advice is given as input, and a network packet arrives at the terminal as output. Specifically, an HTTP response is generated and received by the terminal.

[0399] Step 8:

[0400] The terminal notifies the user of the received advice. The advice is displayed on the terminal screen and, if necessary, is also provided as a voice message. The advice from the server is given as input, and the advice displayed to the user is output. Specifically, the terminal's GUI is updated, and text is displayed and voice is played.

[0401] (Application example 1)

[0402] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0403] Modern homes and offices require efficient and reliable security management. Conventional security systems that rely on cameras and sensors are prone to false alarms and false positives, making it difficult to respond quickly. Another issue facing security management is the lack of specific advice that allows users to take appropriate measures immediately.

[0404] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0405] In this invention, the server includes means for receiving security-related information by voice input, means for converting the received voice information into text, natural language processing means for analyzing the converted text information, means for storing the analyzed information in a database, means for generating advice on security management and life support based on the stored information, and means for notifying the generated advice to the user. This enables the user to easily report security information by voice input and quickly receive specific advice based on the information.

[0406] "Voice input" is a technology that recognizes voice and processes it as digital information.

[0407] "Security information" is data that indicates the security status of a home or office, including unauthorized intrusions, abnormal activity, and the status of equipment.

[0408] "Means for converting to text" refers to technology that converts voice data into text information.

[0409] "Natural language processing means" refers to technology that analyzes human language, understands its meaning, and processes it.

[0410] "Means of storing in a database" refers to the technology used to manage and store analyzed information within the system.

[0411] "Means for generating advice" refers to technology that automatically creates appropriate instructions or suggestions for the user based on the stored information.

[0412] "Means for notifying" refers to a communication technique for conveying the generated advice to the user.

[0413] "Server" refers to a computer system that centrally processes and manages data.

[0414] "Security management" refers to activities aimed at protecting a home or office and preventing unauthorized access.

[0415] "Lifestyle support" refers to providing instructions and advice to users in their daily lives.

[0416] This invention is a security management system that uses voice input, and provides a mechanism for users to report the security status of their home or office by voice and receive appropriate advice based on the content of the report. This system includes a series of processes such as voice input, text conversion, information analysis, data storage, advice generation, and notification.

[0417] Hardware Configuration

[0418] The system uses the following hardware:

[0419] 1. Smartphones and smart speakers: Used for voice input and receiving notifications.

[0420] 2. Microphone and speaker: Used for recording and playing audio.

[0421] Software Configuration

[0422] The system uses the following software:

[0423] 1. Speech recognition engine (e.g. Google Cloud Speech-to-Text): Converts speech into text.

[0424] 2. Natural language processing engine (e.g., Dialogflow, Amazon Comprehend): Analyzes the input text and understands its meaning.

[0425] 3. Cloud database (e.g. AWS DynamoDB, Google Firestore): Stores the analyzed information.

[0426] 4. Notification system (e.g., Firebase Cloud Messaging, Twilio): Notifies the user of the generated advice.

[0427] System Operation

[0428] 1. Voice input:

[0429] The user reports the security situation by voice to a smartphone or smart speaker, for example, saying, "The office window is open."

[0430] 2. Text conversion:

[0431] The device will record your voice and convert it to text using Google Cloud Speech-to-Text, which will say "The office window is open."

[0432] 3. Information analysis:

[0433] The text information is sent to a natural language processing engine for semantic analysis. Dialogflow and Amazon Comprehend are used to understand the content of the text and assess security risks. For example, an "open window" can be recognized as a risk and assessed accordingly.

[0434] 4. Data Retention:

[0435] The analyzed information is stored in a cloud database, including risk assessment and situation details.

[0436] 5. Advice Generation:

[0437] Based on the stored data, a generative AI model (e.g., GPT-3) is used to generate specific countermeasures, such as advice like "Check and close windows immediately."

[0438] 6. Notice:

[0439] Firebase Cloud Messaging and Twilio are used to notify users of the generated advice, which is delivered via voice or text to smartphones or smart speakers.

[0440] Specific examples

[0441] Example prompts if the user says "My office windows are open":

[0442] The user has spoken "The office window is open." Use this information to identify security risks and notify the user of countermeasures.

[0443] Based on this prompt, the generative AI model generates advice such as, "It appears that a window in your office is open. Please check immediately and close the window if necessary."

[0444] As described above, the system of the present invention allows a user to easily report security information through voice input and quickly receive specific advice based on that information.

[0445] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0446] Step 1: Voice Input

[0447] The user reports the security situation by voice to a smartphone or smart speaker. The voice input is information such as "The office window is open." The device's microphone records the voice and the data is sent to the device.

[0448] Step 2: Text conversion

[0449] The device sends the recorded voice data to a speech recognition engine (e.g., Google Cloud Speech-to-Text). The speech recognition engine analyzes the voice data and converts it into text information. The input is voice data, and the output is text data such as "The office window is open."

[0450] Step 3: Information analysis

[0451] Text data is sent to a natural language processing engine (e.g., Dialogflow, Amazon Comprehend). The natural language processing engine analyzes the text and understands its meaning. The input is text data, and the output is a security risk assessment and detailed information as the analysis results. For example, risk information such as "the window is open" is evaluated.

[0452] Step 4: Save Data

[0453] The analysis results are stored in a cloud database (e.g., AWS DynamoDB, Google Firestore). The input is the analyzed information, and the output is the risk assessment and situation details stored in the database. This accumulates data that can be used for future reference.

[0454] Step 5: Advice Generation

[0455] The server uses a generative AI model (e.g., GPT-3) based on the stored information to generate specific countermeasures. The input is the database information and a prompt, and the output is specific advice. For example, the generated advice might be, "Check and close the windows immediately."

[0456] Step 6: Notification

[0457] The generated advice is sent to the user via a notification system (e.g., Firebase Cloud Messaging, Twilio). The input is the generated advice, and the output is a notification that is displayed on the user's smartphone or smart speaker or played aloud.

[0458] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0459] The present invention combines a system for managing the health and lifestyle of pets using voice input with an emotion engine that recognizes the emotions of the user. This system includes a voice input function in which the user provides information about the pet, a function for converting the voice information into text, a function for analyzing the text data using a natural language processing (NLP) engine, a function for saving the analysis results in a database, a function for generating advice based on the saved data, a function for notifying the user of the advice, and a function for recognizing emotions using the emotion engine. Specific embodiments of the system are described below.

[0460] The user speaks into the device to input information about their pet's health and behavior. For example, if the user types, "My dog ​​has gained 3 kilos," the device's microphone captures this voice. This voice data is sent to speech recognition software in real time and converted into text. The resulting text is, "My dog ​​has gained 3 kilos."

[0461] The text data is then sent from the device to a server. The server receives the text data and analyzes it using a natural language processing engine. During the analysis process, the server performs tasks such as understanding the intent of the text, extracting keywords, and analyzing context to extract important information about the pet's health. The results of this analysis are stored in a database on the server. The pet's past health data is also stored, and together with newly added data, it serves as the basis for generating more accurate advice.

[0462] The server generates advice for pet health management and lifestyle support based on the stored information. For example, it may provide advice such as, "Your pet is gaining weight, so we recommend a low-calorie diet." This advice generation engine automatically generates specific advice based on expert knowledge, ensuring that users receive reliable information.

[0463] One of the features of the present invention is the incorporation of an emotion engine. The emotion engine has the function of analyzing the user's emotions during voice input and recognizing emotional states such as anxiety, anger, and joy. For example, if the user is feeling stressed, the emotion engine will classify that emotion as "worry." This emotion data is stored in a database and will be referenced the next time advice is generated.

[0464] The user's emotions recognized by the emotion engine can influence the advice that is generated. For example, if a user says, "I'm worried because my cat's appetite has decreased recently," the emotion engine will detect the emotion "worry." Based on this information, the server will generate advice that takes the emotion into consideration. Specifically, it will provide advice that is sensitive to the user's emotions, such as, "Your cat's appetite has decreased, but it might be a good idea to try a new type of food. Don't worry, just wait and see."

[0465] The generated advice is sent from the server to the device. The device notifies the user of this advice by voice or text. The user can check the advice on the device screen or listen to the guide message by voice. This notification allows the user to take appropriate measures for managing their pet's health.

[0466] As a concrete example, consider the case where a user voice-inputs, "My dog ​​has gained 3 kg, and I'm very worried." This voice is converted into text and sent to the server. The server analyzes the text and emotional information to detect the user's concern. As a result, it generates emotionally sensitive advice such as, "Your dog has gained weight, but as long as it's not a big increase, it's not a problem. I recommend you increase moderate exercise and switch to a low-calorie diet. Don't worry too much." and sends it to the device. The device notifies the user, who can then take appropriate action based on the advice.

[0467] This invention allows users to easily understand their pet's health condition through voice input and receive appropriate support tailored to their individual needs and emotions. This system has the effect of streamlining pet health monitoring and significantly reducing the burden on users.

[0468] The processing flow will be explained below.

[0469] Step 1:

[0470] The user speaks information about their pet into the device, for example, saying, "My dog ​​has gained 3 kilograms."

[0471] Step 2:

[0472] The device captures the user's voice through a microphone, and the captured voice data is sent directly to voice recognition software.

[0473] Step 3:

[0474] The speech recognition software converts the received speech data into text, resulting in the text "My dog ​​has gained 3 kilos."

[0475] Step 4:

[0476] The device then transmits the converted data to the server, where it is securely transferred using a security protocol.

[0477] Step 5:

[0478] The server receives the text data and analyzes it using a natural language processing (NLP) engine, which performs semantic analysis of the text, keyword extraction, context understanding, and more.

[0479] Step 6:

[0480] The server stores the analyzed data in a database, which also contains the pet's health history and past information, and centrally records the analysis results.

[0481] Step 7:

[0482] The server generates advice on pet health management and lifestyle support based on the stored information, such as "Your pet is gaining weight, so we recommend a low-calorie diet."

[0483] Step 8:

[0484] The server uses an emotion engine to analyze the user's emotions when generating advice. It recognizes the user's emotional state (e.g., worry, joy, anger) from their voice data and formulates advice that takes their emotions into consideration.

[0485] Step 9:

[0486] The server then sends advice based on the generated emotions to the device, again using a security protocol to transfer data.

[0487] Step 10:

[0488] The device then notifies the user of the advice it receives, which is displayed as a voice message or text message, such as "A low-calorie diet is recommended to prevent weight gain. Don't worry too much."

[0489] Step 11:

[0490] Users can check the provided advice and take action to manage their pet's health (e.g., changing its diet or increasing its exercise) based on it, thus enabling them to effectively manage their pet's health.

[0491] Example 2

[0492] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0493] While conventional pet health management systems can obtain information about pets through voice input, they face the challenge of efficiently analyzing that information and providing appropriate advice that takes the user's feelings into consideration. Furthermore, advice provided without considering the user's anxieties and worries may not be satisfactory to the user. Furthermore, there is a lack of systems that centrally manage pet health information and provide effective notifications.

[0494] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0495] In this invention, the server includes means for receiving information about the pet through voice input, means for converting the received voice information into text, natural language processing means for analyzing the converted text information, means for storing the analyzed information in a database, means for generating advice on pet health management and lifestyle support based on the stored information, means for notifying the user of the generated advice, emotion recognition means for analyzing the user's emotions, and means for adjusting the advice based on the emotion recognition results. This makes it possible to easily collect pet health information through voice input and provide highly accurate advice that takes the user's emotions into consideration.

[0496] "Voice input" is the means by which a user's spoken voice data is received and interpreted by the system.

[0497] "Voice information" means information about a pet provided by a user through voice input.

[0498] "Means for converting to text" refers to a technique for converting voice information into character string data.

[0499] "Natural language processing means" is a technology for analyzing text data and understanding its content.

[0500] "Means of storing in a database" refers to technology that centrally manages analyzed information and makes it available for future reference.

[0501] The "means for generating advice" is a technique for creating specific instructions or suggestions for the user based on the stored information.

[0502] The "means for notifying advice" is a technique for conveying the generated advice to the user.

[0503] "Emotion recognition means" is a technology for analyzing and recognizing a user's emotional state through voice input.

[0504] "Means for adjusting advice" refers to technology that changes or customizes the content of advice based on emotion recognition results.

[0505] The present invention is a system that utilizes voice input to manage the health and lifestyle of pets, and combines it with an emotion engine that recognizes the user's emotions. This system is composed of a combination of multiple hardware and software components.

[0506] Specific hardware and software configurations

[0507] Device: Use a smartphone or tablet with a microphone, which allows the user to input voice.

[0508] Server: A cloud-based server is used, which analyzes and manages the voice data.

[0509] Speech Recognition Software: We use the Google Speech-to-Text API to convert voice data into text.

[0510] Natural language processing engine: spaCy is used to analyze text data and extract important information.

[0511] Database: A MySQL database is used to store the analyzed data.

[0512] Emotion Engine: Uses IBM Watson Tone Analyzer to analyze user emotions.

[0513] Specific examples of implementation

[0514] The user speaks to the device to provide information about their pet's health and behavior. For example, if they say, "My dog ​​has gained 3 kilograms," the device's microphone captures this voice. This voice data is sent in real time to the Google Speech-to-Text API and converted into text. The resulting text is, "My dog ​​has gained 3 kilograms."

[0515] The converted data is then sent from the device to a server. The server receives this text data and analyzes it using a natural language processing engine (spaCy). During the analysis process, the intent of the text is understood, keywords are extracted, and context is analyzed to extract important information about the pet's health. The analysis results are stored in a MySQL database on the server.

[0516] The server generates advice for pet health management and lifestyle support based on the stored information. For example, the server may generate advice such as, "Your pet is gaining weight, so we recommend a low-calorie diet." The generated advice is sent from the server to the device, which then notifies the user of the advice by text or voice.

[0517] Furthermore, the emotion engine (IBM Watson Tone Analyzer) analyzes the user's emotions during voice input and recognizes emotions such as anxiety, anger, and joy. For example, if a user says, "I'm very worried," the emotion engine will detect the emotion "worry." This emotion data is stored in a database and will be referenced the next time advice is generated.

[0518] The user's emotions recognized by the emotion engine can influence the content of the advice generated. For example, if a user says, "My cat's appetite has decreased recently, and I'm worried," the emotion engine detects the emotion "worry." Based on this information, the server generates advice that takes emotions into consideration. Specifically, it provides advice that is sensitive to the user's emotions, such as, "Your cat's appetite has decreased, but it might be a good idea to try a new type of food. Don't worry, just wait and see."

[0519] An example of a prompt sentence is, "My pet has recently gained weight. What should I do? I'm worried." This system allows users to easily understand their pet's health status through voice input and receive appropriate support tailored to their individual needs and emotions. This has the effect of streamlining pet health monitoring and significantly reducing the burden on users.

[0520] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0521] Step 1:

[0522] The user speaks information about the pet into the terminal.

[0523] Input: User speech (e.g., "My dog ​​has gained 3 kilos").

[0524] What it does: The user opens a recording app on their smartphone and dictates their pet's health status. The device's microphone captures the audio.

[0525] Output: The captured audio data.

[0526] Step 2:

[0527] The device sends the captured voice data to speech recognition software (Google Speech-to-Text API) in real time, which converts the voice data into text.

[0528] Input: Captured speech data (e.g., "My dog ​​has gained 3 kilos").

[0529] What it does: It sends audio data to the Google Speech-to-Text API, which then recognizes the speech and converts it into text.

[0530] Output: Text data (e.g., "My dog ​​has gained 3 kg").

[0531] Step 3:

[0532] The terminal transmits the converted text data to the server.

[0533] Input: Text data (e.g., "My dog ​​has gained 3 kg").

[0534] Specific behavior: Sends text data to the server as an HTTP POST request.

[0535] Output: The text data sent to the server.

[0536] Step 4:

[0537] The server analyzes the text data it receives using a natural language processing engine (spaCy) to extract important information about the pet's health.

[0538] Input: Text data sent to the server (e.g., "My dog ​​has gained 3 kilos").

[0539] Specific operation: The server passes the text data to spaCy, which performs intent understanding, keyword extraction, context analysis, etc.

[0540] Output: Analysis results (e.g. keywords such as "dog", "weight", "gained 3kg").

[0541] Step 5:

[0542] The server stores the analysis results in a database (MySQL).

[0543] Input: Analysis results (e.g. keywords such as "dog", "weight", "gained 3kg").

[0544] Specific operation: The parsed results are sent to the MySQL database as an INSERT query and saved.

[0545] Output: Analysis results stored in a database.

[0546] Step 6:

[0547] The server generates advice on health management and lifestyle support for pets based on the stored information.

[0548] Input: Analysis results stored in the database (e.g. "dog", "weight", "gained 3 kg", etc.).

[0549] Specific operation: The server runs the advice generation engine based on the stored data and generates health management advice.

[0550] Output: The generated advice (e.g., "Your pet is gaining weight, so we recommend a low-calorie diet").

[0551] Step 7:

[0552] The server analyzes the user's emotions during voice input using an emotion recognition engine (IBM Watson Tone Analyzer).

[0553] Input: Text data sent to the server (e.g., "My dog ​​has gained 3 kilos").

[0554] How it works: The server passes the text data to IBM Watson Tone Analyzer, which analyzes emotions such as anxiety, anger, and joy.

[0555] Output: Emotion recognition result (e.g., "worried").

[0556] Step 8:

[0557] The server adjusts the advice generated based on the emotion recognition results.

[0558] Input: Emotion recognition result (e.g., "worried") and generated advice (e.g., "your pet is gaining weight, so we recommend a low-calorie diet").

[0559] Specific behavior: The server takes into account the emotion recognition results and adjusts the advice. Specifically, it adjusts the advice to say, "It might be a good idea to try a new type of food. Don't worry, let's see how it goes."

[0560] Output: Tailored advice (e.g., "Maybe you should try a new type of food. Don't worry, let's see how it goes.").

[0561] Step 9:

[0562] The server sends the advice to the terminal, which then notifies the user.

[0563] Input: Tailored advice (e.g., "Maybe you should try a new type of food. Don't worry, let's see how it goes.").

[0564] Specific behavior: The advice is sent to the device via an HTTP response, and the device app notifies the user.

[0565] Output: Advice given to the user (e.g. "Maybe you should try a new type of food. Don't worry, just wait and see").

[0566] (Application example 2)

[0567] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0568] Conventional pet health management systems often require users to manually enter data, which is time-consuming and inaccurate. Furthermore, since the advice provided does not take into account the user's feelings, it is difficult to provide suggestions in a way that is easy for the user to accept. Furthermore, data storage and management are cumbersome, which can delay appropriate responses in situations where a prompt response is required.

[0569] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0570] In this invention, the server includes means for receiving information about a pet through voice input, means for converting the received voice information into text, natural language processing means for analyzing the converted text information, means for saving the analyzed information in a database, means for generating advice on health management and lifestyle support for the pet based on the saved information, means for notifying the user of the generated advice, and means for analyzing the user's emotions, saving the information, and reflecting it in subsequent advice. This allows the user to easily manage the health condition of their pet through voice input, and by receiving advice that takes emotions into consideration, more effective pet care is possible.

[0571] "Voice input" is a method in which a user communicates information about a pet to the system through a voice capture device such as a microphone.

[0572] A "means for converting to text" is a device or software that includes speech recognition technology for analyzing speech information and converting it into a corresponding string of characters.

[0573] "Natural language processing means" is a technology that uses computers to analyze human language and understand intent and meaning, and analyzes text data.

[0574] A "means for storing in a database" is a process or device that organizes the analyzed information and stores it in a storage device in a format that can be accessed later.

[0575] A "means for generating pet health care and lifestyle support advice" is a process or device that automatically generates recommendations related to a pet's health and lifestyle based on stored data.

[0576] The "means for notifying the user" refers to a method or device for distributing the generated advice or information in a form that the user can check.

[0577] The "means for analyzing user emotions" is a technology for analyzing and recognizing emotions expressed by a user during voice input.

[0578] The "means for reflecting in future advice" is a process or device for storing the analyzed emotional state of the user in a database and taking that emotional information into account when generating future advice.

[0579] The "Pet Care Advisor" system for implementing this invention is mainly composed of a voice input function, a text conversion function, a natural language processing (NLP) engine, a database storage function, an advice generation engine, a notification function, and a sentiment analysis engine. Each function will be described in detail below.

[0580] Speech to text conversion

[0581] Users use a smartphone or other voice input device to voice-record information about their pet's health and behavior. This voice data is converted into text in real time using speech recognition software (e.g., Google Cloud Speech-to-Text API). In this process, speech such as "My dog ​​has gained 3 kilograms and I'm worried" can be converted into text.

[0582] Natural Language Processing (NLP) Engine

[0583] The text data is sent to a server and analyzed by a natural language processing engine (for example, Google Cloud Natural Language API). This engine understands the intent of the text, extracts keywords, and analyzes the context to extract important information about the pet's health. For example, information such as "weight gain" or "worries" may be extracted.

[0584] Database storage function

[0585] The analyzed data is stored in a database on the server, which also stores the pet's past health data and, together with the newly added data, serves as the basis for generating advice.

[0586] Sentiment Analysis Engine

[0587] An emotion analysis engine (for example, IBM Watson Tone Analyzer) analyzes the user's emotions during voice input and recognizes emotional states such as anxiety, anger, and joy. This emotional data is also stored in a database and is referenced the next time advice is generated. For example, the emotion "worry" may be detected from the input voice.

[0588] Advice Generation Engine

[0589] The server generates advice on pet health management and lifestyle support based on the stored information. For example, it might say, "Your pet is gaining weight, so we recommend a low-calorie diet. Don't worry too much, but increase your pet's moderate exercise." The engine generates reliable information based on past data and expert knowledge.

[0590] Notification function

[0591] The generated advice is sent from the server to the user's device. The user can check the advice on the device screen or listen to the guide message via audio. The device then assists the user in taking appropriate measures.

[0592] Specific examples

[0593] For example, if a user says, "My dog ​​has gained 3 kilograms and I'm worried," this speech is converted into text and sent to the server. The server analyzes the text and emotional information to detect the user's concern. As a result, advice such as "Your dog has gained weight, but as long as it's not a big increase, it's not a problem. I recommend you increase moderate exercise and switch to a low-calorie diet. Don't worry too much" is generated and sent to the device.

[0594] Prompt Sentence Examples

[0595] The user's voice input is converted to text and then that text is used as the prompt.

[0596] example:

[0597] Prompt: The user says, "My dog ​​has gained 3 kg and I'm worried." Text: "My dog ​​has gained 3 kg and I'm worried." Use this information and the user's emotion of "worry" to generate specific advice related to pet health care.

[0598] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0599] Step 1:

[0600] The user uses a voice input device such as a smartphone to input information about the health and behavior of their pet. Specifically, the user speaks into the device's microphone, saying, "My dog ​​has gained 3 kilograms, and I'm worried." This input voice becomes the initial data for the system. The input in Step 1 is the user's voice. The output is voice data.

[0601] Step 2:

[0602] The voice data received by the device is sent in real time to voice recognition software, which converts it into text. This process uses voice recognition technology such as the Google Cloud Speech-to-Text API. The input in step 2 is voice data, and the output is text data. Specifically, the text generated is, "My dog ​​has gained 3 kilograms and I'm worried."

[0603] Step 3:

[0604] The converted data is sent from the terminal to the server. The server receives this text data and prepares it for the next analysis step. The input of step 3 is the converted text data, and the output is the status of completion of transmission to the server.

[0605] Step 4:

[0606] The text data received by the server is analyzed using a natural language processing engine (for example, Google Cloud Natural Language API). Here, the intent of the text is understood, keywords are extracted, and context is analyzed to extract important information about the pet's health condition. The input for step 4 is the text data, and the output is the analyzed key data. Specifically, keywords such as "weight gain" and "worry" are extracted.

[0607] Step 5:

[0608] The analyzed data is saved in a database. This database also stores the pet's past health data, and together with the newly added data, it serves as the basis for generating advice. The input of Step 5 is the analyzed key data, and the output is the data saving completion status.

[0609] Step 6:

[0610] The server analyzes the user's emotions during voice input using an emotion analysis engine (e.g., IBM Watson Tone Analyzer). Here, emotional states such as anxiety, anger, and joy are recognized. The input in step 6 is speech-to-text data, and the output is emotional information. For example, the emotion "worry" is detected.

[0611] Step 7:

[0612] The emotional data is saved in the database. The user's emotional information obtained through emotion analysis will also be referenced the next time advice is generated. The input of step 7 is the emotional information, and the output is the data saving completion status.

[0613] Step 8:

[0614] The server generates advice for pet health management and lifestyle support based on the stored information. This advice generation engine uses a machine learning model to provide optimal advice based on the stored health data and emotional data. The input to step 8 is analysis data and emotional data, and the output is specific advice text. For example, advice such as "Your pet has gained weight, but as long as it's not a significant increase, it's not a problem. We recommend increasing moderate exercise and switching to a low-calorie diet. Don't worry too much" may be generated.

[0615] Step 9:

[0616] The generated advice is sent to the user's device. The user can check the advice through the device and take any necessary measures. The input of step 9 is the advice text, and the output is the notification completion status to the user. Specifically, a message is displayed on the smartphone screen saying, "You've gained weight, but as long as it's not a significant increase, it's not a problem. We recommend that you increase moderate exercise and switch to a low-calorie diet. Don't worry too much."

[0617] Example prompt sentence:

[0618] A user says, "My dog ​​has gained 3 kg and I'm worried." Text: "My dog ​​has gained 3 kg and I'm worried." Use this information and the user's emotion, "worried," to generate specific advice related to pet health care.

[0619] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0620] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0621] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0622] [Third embodiment]

[0623] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0624] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0625] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0626] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0627] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0628] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0629] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0630] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0631] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0632] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0633] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0634] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0635] The present invention is a system for efficiently managing the health of pets and supporting their daily lives, and in particular, it establishes a series of processes for collecting, analyzing, saving, and notifying information using voice input. This system allows a user to provide information about their pet through voice input, converts that information into text, analyzes it, and generates advice based on the analysis results. The system is realized in a format in which the generated advice is then notified to the user. An embodiment of this system is described in detail below.

[0636] When a user speaks to the device about their pet's health or daily changes, the device's microphone picks up the voice and the voice data is converted into text using recognition software. For example, suppose a user says, "My dog ​​has gained 3 kilograms." This voice input is automatically converted into text, and the device's screen displays, "My dog ​​has gained 3 kilograms."

[0637] The text data is then sent from the device to a server, which receives the data and uses a natural language processing (NLP) engine to analyze the meaning of what the user has entered. This process involves extracting keywords from the text data and identifying associated health information or signs of abnormalities.

[0638] The analyzed information is stored in a database on the server. This database stores your pet's past health data and history, and when combined with newly added data, it serves as the basis for generating more accurate advice. This stored data can be referenced later, allowing for centralized management of your pet's health.

[0639] The server then generates pet health care advice based on the stored data. The advice generation engine formulates specific advice based on the analyzed information. For example, it might provide advice such as, "Your pet is gaining weight, so we recommend a low-calorie diet." Because such advice is automatically generated based on expert knowledge, users can receive reliable information.

[0640] The generated advice is sent from the server to the device. The device then notifies the user of the advice. This notification is provided as a voice message or text message. The advice is not only displayed on the device screen, but also provided as a voice guide if necessary, making it easy for the user to receive the advice.

[0641] As a concrete example, consider the case where a user voice-inputs, "My cat's appetite has decreased recently." This voice input is converted into text and sent to the server. The server analyzes this data and attempts to identify, for example, the "cause of the loss of appetite." As a result, advice is generated, such as, "It's possible that your cat's new type of food doesn't suit your taste," and is notified to the user. Based on this advice, the user can take measures such as changing the food.

[0642] As described above, the system of the present invention can collect, analyze, and notify pet health information through voice input, enabling users to easily manage their pet's health. This system has the effect of making pet health monitoring more efficient and reducing the burden on users.

[0643] The processing flow will be explained below.

[0644] Step 1:

[0645] The user speaks into the device to input information about their pet. The user provides information by speaking details about the health and behavior of their pet at home.

[0646] Step 2:

[0647] The device captures the user's voice through a microphone, and this voice data is sent in real time to speech recognition software.

[0648] Step 3:

[0649] Speech recognition software converts the audio data into text. For example, "My dog ​​has gained 3 kilos" becomes "My dog ​​has gained 3 kilos."

[0650] Step 4:

[0651] The device sends the text data to the server, where it is transferred using a secure communication protocol.

[0652] Step 5:

[0653] The server receives the text data and analyzes it using a natural language processing (NLP) engine. During the analysis, the server performs tasks such as understanding the meaning of the text, extracting keywords, and analyzing context to extract important information about the pet's health.

[0654] Step 6:

[0655] The server then stores the information in a database based on the analysis results, and the data is stored along with the pet's past health history for future reference and comparison.

[0656] Step 7:

[0657] The server uses the stored information to generate advice for pet health management and lifestyle support. This advice generation engine automatically creates specific advice such as, "Your pet is gaining weight, so we recommend a low-calorie diet."

[0658] Step 8:

[0659] The server sends the generated advice to the terminal, which is designed to reach the user quickly and accurately.

[0660] Step 9:

[0661] The device notifies the user of the received advice, and the user can confirm the advice by text displayed on the device screen or by voice output, allowing the user to take specific actions based on the advice provided.

[0662] Example 1

[0663] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0664] In the field of pet health management and lifestyle support, it is important to enable users to easily input information and receive specific advice based on that information. Conventional systems require users to manually input information, which is time-consuming and often requires specialized knowledge, making it difficult to respond quickly to pet conditions.

[0665] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0666] In this invention, the server includes means for receiving information about the pet through voice input, speech recognition means for converting the received speech information into text, means for transmitting the converted text information to the server, natural language processing means for analyzing the transmitted text information, means for storing the analyzed information in a database, advice generation means for generating advice on health management and lifestyle support for the pet based on the stored information, and means for notifying the user of the generated advice. This enables the user to easily and quickly provide information about the pet to the system through voice input and receive specific and reliable advice based on the resulting analysis.

[0667] "Voice input" is a means by which the user provides information about the pet to the system in the form of voice.

[0668] A "voice recognition means" is software or hardware for converting user-provided voice information into text format.

[0669] "Text information" is data in a sentence format converted from voice data by a voice recognition means.

[0670] A "server" is a central computing unit that receives, analyzes, stores, and generates advice about text information.

[0671] "Natural language processing means" refers to technology or software for analyzing text data and understanding its content.

[0672] A "database" is a data storage system for storing analyzed information in an organized manner.

[0673] The "advice generation means" is an engine or software for automatically generating specific advice for pet health management and lifestyle support based on the stored information.

[0674] A "notification means" is a method, medium, or technique for notifying a user of generated advice.

[0675] This invention is a system for efficiently managing the health and lifestyle of pets. In particular, it utilizes voice input to build a series of processes for collecting, analyzing, saving, and notifying information. This system allows the user to provide information about their pet through voice input, converts that information into text, analyzes it, and generates advice based on the analysis results. The system is realized in a way that the generated advice is then notified to the user.

[0676] The user inputs information about their pet's health condition and daily changes into the device by voice. For example, they might say, "My cat's appetite has decreased recently." The device's microphone receives this voice, and the voice data is converted into text using recognition software (e.g., Google Speech-to-Text API). This voice input is converted into text format as "My cat's appetite has decreased recently," and the message "My cat's appetite has decreased recently" is displayed on the device's screen.

[0677] The text data is then sent from the device to a server. The server receives this text data and analyzes it using a natural language processing (NLP) engine (e.g., Amazon Comprehend). Specifically, it extracts keywords (e.g., "cat," "appetite," and "decreased") from the text data and understands its content. Based on this analysis, it can determine information about the pet's health and any signs of abnormalities.

[0678] The analyzed information is stored in a database on the server. This database stores your pet's past health data and history, and when combined with newly added data, it serves as the basis for generating more accurate advice. This stored data can be referenced later, allowing for centralized management of your pet's health.

[0679] The server then generates advice on pet health management based on the stored data. This advice generation engine (e.g., Microsoft Azure Machine Learning) uses the analyzed information to form specific advice. For example, it might provide advice such as, "Your cat's new type of food may not be to its liking, so try a different food." Because such advice is automatically generated based on expert knowledge, users can be assured of reliable information.

[0680] The generated advice is sent from the server to the device. The device then notifies the user of the advice. This notification is provided as a voice message or text message. The advice is not only displayed on the device screen, but also provides voice guidance as needed, making it easy for users to receive the advice.

[0681] As a concrete example, consider the case where a user voice-inputs "My dog ​​has gained weight." This voice input is converted into text "My dog ​​has gained weight" and sent to the server. The server analyzes this data and identifies the keyword "weight gain." The server compares it with past health data and generates advice to "introduce a low-calorie diet." This advice is sent to the device, and the user is notified that "Your dog has gained weight, so we recommend a low-calorie diet."

[0682] An example prompt is, "Convert the most recent voice input about your pet's condition to text and generate health advice based on the analysis of that text. For example, if your dog reports that it has gained weight, provide advice on appropriate diet and exercise."

[0683] This system will make pet health monitoring more efficient and reduce the burden on users.

[0684] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0685] Step 1:

[0686] The user inputs information about their pet's health condition and daily changes into the device by voice. For example, they might say, "My cat's appetite has decreased recently." This input is captured by the device's microphone, and the voice data is generated. Voice data is given as input, and the same voice data is obtained as output.

[0687] Step 2:

[0688] The device converts the received voice data into text format using voice recognition software (e.g., Google Speech-to-Text API). This voice is recognized as "My cat's appetite has decreased recently" and converted into text data. Voice data is given as input, and text data is output as the processing result. Specifically, phonemic and contextual analysis is performed on the voice data, and the corresponding text is generated.

[0689] Step 3:

[0690] The text data is sent from the terminal to the server. The terminal encodes the conversion result as packet data and sends it to the server via the network. Text data is given as input, and network packets arrive at the server as output. Specifically, the terminal sends an HTTP request, and the server receives it at the corresponding endpoint.

[0691] Step 4:

[0692] The server uses a natural language processing (NLP) engine (e.g., Amazon Comprehend) to analyze the received text data. The server extracts keywords (e.g., "cat," "appetite," and "dropped") from the text data and analyzes their meaning. The text data is given as input, and keywords and analysis results are output. Specifically, morphological and semantic analysis is performed on the text data, and the results are extracted.

[0693] Step 5:

[0694] The parsed information is stored in a database on the server. The server inserts the parsed results into the database as structured data. The parsed results are given as input, and the information stored in the database is output. Specifically, an INSERT statement is executed into the database, and the information is permanently saved.

[0695] Step 6:

[0696] The server generates advice on pet health care based on the stored data. This advice generation engine (e.g., Microsoft Azure Machine Learning) uses the analysis results to form specific advice. The stored data is given as input, and the generated advice is obtained as output. Specifically, a machine learning model analyzes the data and generates advice statements.

[0697] Step 7:

[0698] The generated advice is sent from the server to the terminal. The server encodes the advice in text format and sends it to the terminal via the network. The generated advice is given as input, and a network packet arrives at the terminal as output. Specifically, an HTTP response is generated and received by the terminal.

[0699] Step 8:

[0700] The terminal notifies the user of the received advice. The advice is displayed on the terminal screen and, if necessary, is also provided as a voice message. The advice from the server is given as input, and the advice displayed to the user is output. Specifically, the terminal's GUI is updated, and text is displayed and voice is played.

[0701] (Application example 1)

[0702] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0703] Modern homes and offices require efficient and reliable security management. Conventional security systems that rely on cameras and sensors are prone to false alarms and false positives, making it difficult to respond quickly. Another issue facing security management is the lack of specific advice that allows users to take appropriate measures immediately.

[0704] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0705] In this invention, the server includes means for receiving security-related information by voice input, means for converting the received voice information into text, natural language processing means for analyzing the converted text information, means for storing the analyzed information in a database, means for generating advice on security management and life support based on the stored information, and means for notifying the generated advice to the user. This enables the user to easily report security information by voice input and quickly receive specific advice based on the information.

[0706] "Voice input" is a technology that recognizes voice and processes it as digital information.

[0707] "Security information" is data that indicates the security status of a home or office, including unauthorized intrusions, abnormal activity, and the status of equipment.

[0708] "Means for converting to text" refers to technology that converts voice data into text information.

[0709] "Natural language processing means" refers to technology that analyzes human language, understands its meaning, and processes it.

[0710] "Means of storing in a database" refers to the technology used to manage and store analyzed information within the system.

[0711] "Means for generating advice" refers to technology that automatically creates appropriate instructions or suggestions for the user based on the stored information.

[0712] "Means for notifying" refers to a communication technique for conveying the generated advice to the user.

[0713] "Server" refers to a computer system that centrally processes and manages data.

[0714] "Security management" refers to activities aimed at protecting a home or office and preventing unauthorized access.

[0715] "Lifestyle support" refers to providing instructions and advice to users in their daily lives.

[0716] This invention is a security management system that uses voice input, and provides a mechanism for users to report the security status of their home or office by voice and receive appropriate advice based on the content of the report. This system includes a series of processes such as voice input, text conversion, information analysis, data storage, advice generation, and notification.

[0717] Hardware Configuration

[0718] The system uses the following hardware:

[0719] 1. Smartphones and smart speakers: Used for voice input and receiving notifications.

[0720] 2. Microphone and speaker: Used for recording and playing audio.

[0721] Software Configuration

[0722] The system uses the following software:

[0723] 1. Speech recognition engine (e.g. Google Cloud Speech-to-Text): Converts speech into text.

[0724] 2. Natural language processing engine (e.g., Dialogflow, Amazon Comprehend): Analyzes the input text and understands its meaning.

[0725] 3. Cloud database (e.g. AWS DynamoDB, Google Firestore): Stores the analyzed information.

[0726] 4. Notification system (e.g., Firebase Cloud Messaging, Twilio): Notifies the user of the generated advice.

[0727] System Operation

[0728] 1. Voice input:

[0729] The user reports the security situation by voice to a smartphone or smart speaker, for example, saying, "The office window is open."

[0730] 2. Text conversion:

[0731] The device will record your voice and convert it to text using Google Cloud Speech-to-Text, which will say "The office window is open."

[0732] 3. Information analysis:

[0733] The text information is sent to a natural language processing engine for semantic analysis. Dialogflow and Amazon Comprehend are used to understand the content of the text and assess security risks. For example, an "open window" can be recognized as a risk and assessed accordingly.

[0734] 4. Data Retention:

[0735] The analyzed information is stored in a cloud database, including risk assessment and situation details.

[0736] 5. Advice Generation:

[0737] Based on the stored data, a generative AI model (e.g., GPT-3) is used to generate specific countermeasures, such as advice like "Check and close windows immediately."

[0738] 6. Notice:

[0739] Firebase Cloud Messaging and Twilio are used to notify users of the generated advice, which is delivered via voice or text to smartphones or smart speakers.

[0740] Specific examples

[0741] Example prompts if the user says "My office windows are open":

[0742] The user has spoken "The office window is open." Use this information to identify security risks and notify the user of countermeasures.

[0743] Based on this prompt, the generative AI model generates advice such as, "It appears that a window in your office is open. Please check immediately and close the window if necessary."

[0744] As described above, the system of the present invention allows a user to easily report security information through voice input and quickly receive specific advice based on that information.

[0745] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0746] Step 1: Voice Input

[0747] The user reports the security situation by voice to a smartphone or smart speaker. The voice input is information such as "The office window is open." The device's microphone records the voice and the data is sent to the device.

[0748] Step 2: Text conversion

[0749] The device sends the recorded voice data to a speech recognition engine (e.g., Google Cloud Speech-to-Text). The speech recognition engine analyzes the voice data and converts it into text information. The input is voice data, and the output is text data such as "The office window is open."

[0750] Step 3: Information analysis

[0751] Text data is sent to a natural language processing engine (e.g., Dialogflow, Amazon Comprehend). The natural language processing engine analyzes the text and understands its meaning. The input is text data, and the output is a security risk assessment and detailed information as the analysis results. For example, risk information such as "the window is open" is evaluated.

[0752] Step 4: Save Data

[0753] The analysis results are stored in a cloud database (e.g., AWS DynamoDB, Google Firestore). The input is the analyzed information, and the output is the risk assessment and situation details stored in the database. This accumulates data that can be used for future reference.

[0754] Step 5: Advice Generation

[0755] The server uses a generative AI model (e.g., GPT-3) based on the stored information to generate specific countermeasures. The input is the database information and a prompt, and the output is specific advice. For example, the generated advice might be, "Check and close the windows immediately."

[0756] Step 6: Notification

[0757] The generated advice is sent to the user via a notification system (e.g., Firebase Cloud Messaging, Twilio). The input is the generated advice, and the output is a notification that is displayed on the user's smartphone or smart speaker or played aloud.

[0758] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0759] The present invention combines a system for managing the health and lifestyle of pets using voice input with an emotion engine that recognizes the emotions of the user. This system includes a voice input function in which the user provides information about the pet, a function for converting the voice information into text, a function for analyzing the text data using a natural language processing (NLP) engine, a function for saving the analysis results in a database, a function for generating advice based on the saved data, a function for notifying the user of the advice, and a function for recognizing emotions using the emotion engine. Specific embodiments of the system are described below.

[0760] The user speaks into the device to input information about their pet's health and behavior. For example, if the user types, "My dog ​​has gained 3 kilos," the device's microphone captures this voice. This voice data is sent to speech recognition software in real time and converted into text. The resulting text is, "My dog ​​has gained 3 kilos."

[0761] The text data is then sent from the device to a server. The server receives the text data and analyzes it using a natural language processing engine. During the analysis process, the server performs tasks such as understanding the intent of the text, extracting keywords, and analyzing context to extract important information about the pet's health. The results of this analysis are stored in a database on the server. The pet's past health data is also stored, and together with newly added data, it serves as the basis for generating more accurate advice.

[0762] The server generates advice for pet health management and lifestyle support based on the stored information. For example, it may provide advice such as, "Your pet is gaining weight, so we recommend a low-calorie diet." This advice generation engine automatically generates specific advice based on expert knowledge, ensuring that users receive reliable information.

[0763] One of the features of the present invention is the incorporation of an emotion engine. The emotion engine has the function of analyzing the user's emotions during voice input and recognizing emotional states such as anxiety, anger, and joy. For example, if the user is feeling stressed, the emotion engine will classify that emotion as "worry." This emotion data is stored in a database and will be referenced the next time advice is generated.

[0764] The user's emotions recognized by the emotion engine can influence the advice that is generated. For example, if a user says, "I'm worried because my cat's appetite has decreased recently," the emotion engine will detect the emotion "worry." Based on this information, the server will generate advice that takes the emotion into consideration. Specifically, it will provide advice that is sensitive to the user's emotions, such as, "Your cat's appetite has decreased, but it might be a good idea to try a new type of food. Don't worry, just wait and see."

[0765] The generated advice is sent from the server to the device. The device notifies the user of this advice by voice or text. The user can check the advice on the device screen or listen to the guide message by voice. This notification allows the user to take appropriate measures for managing their pet's health.

[0766] As a concrete example, consider the case where a user voice-inputs, "My dog ​​has gained 3 kg, and I'm very worried." This voice is converted into text and sent to the server. The server analyzes the text and emotional information to detect the user's concern. As a result, it generates emotionally sensitive advice such as, "Your dog has gained weight, but as long as it's not a big increase, it's not a problem. I recommend you increase moderate exercise and switch to a low-calorie diet. Don't worry too much." and sends it to the device. The device notifies the user, who can then take appropriate action based on the advice.

[0767] This invention allows users to easily understand their pet's health condition through voice input and receive appropriate support tailored to their individual needs and emotions. This system has the effect of streamlining pet health monitoring and significantly reducing the burden on users.

[0768] The processing flow will be explained below.

[0769] Step 1:

[0770] The user speaks information about their pet into the device, for example, saying, "My dog ​​has gained 3 kilograms."

[0771] Step 2:

[0772] The device captures the user's voice through a microphone, and the captured voice data is sent directly to voice recognition software.

[0773] Step 3:

[0774] The speech recognition software converts the received speech data into text, resulting in the text "My dog ​​has gained 3 kilos."

[0775] Step 4:

[0776] The device then transmits the converted data to the server, where it is securely transferred using a security protocol.

[0777] Step 5:

[0778] The server receives the text data and analyzes it using a natural language processing (NLP) engine, which performs semantic analysis of the text, keyword extraction, context understanding, and more.

[0779] Step 6:

[0780] The server stores the analyzed data in a database, which also contains the pet's health history and past information, and centrally records the analysis results.

[0781] Step 7:

[0782] The server generates advice on pet health management and lifestyle support based on the stored information, such as "Your pet is gaining weight, so we recommend a low-calorie diet."

[0783] Step 8:

[0784] The server uses an emotion engine to analyze the user's emotions when generating advice. It recognizes the user's emotional state (e.g., worry, joy, anger) from their voice data and formulates advice that takes their emotions into consideration.

[0785] Step 9:

[0786] The server then sends advice based on the generated emotions to the device, again using a security protocol to transfer data.

[0787] Step 10:

[0788] The device then notifies the user of the advice it receives, which is displayed as a voice message or text message, such as "A low-calorie diet is recommended to prevent weight gain. Don't worry too much."

[0789] Step 11:

[0790] Users can check the provided advice and take action to manage their pet's health (e.g., changing its diet or increasing its exercise) based on it, thus enabling them to effectively manage their pet's health.

[0791] Example 2

[0792] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0793] While conventional pet health management systems can obtain information about pets through voice input, they face the challenge of efficiently analyzing that information and providing appropriate advice that takes the user's feelings into consideration. Furthermore, advice provided without considering the user's anxieties and worries may not be satisfactory to the user. Furthermore, there is a lack of systems that centrally manage pet health information and provide effective notifications.

[0794] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0795] In this invention, the server includes means for receiving information about the pet through voice input, means for converting the received voice information into text, natural language processing means for analyzing the converted text information, means for storing the analyzed information in a database, means for generating advice on pet health management and lifestyle support based on the stored information, means for notifying the user of the generated advice, emotion recognition means for analyzing the user's emotions, and means for adjusting the advice based on the emotion recognition results. This makes it possible to easily collect pet health information through voice input and provide highly accurate advice that takes the user's emotions into consideration.

[0796] "Voice input" is the means by which a user's spoken voice data is received and interpreted by the system.

[0797] "Voice information" means information about a pet provided by a user through voice input.

[0798] "Means for converting to text" refers to a technique for converting voice information into character string data.

[0799] "Natural language processing means" is a technology for analyzing text data and understanding its content.

[0800] "Means of storing in a database" refers to technology that centrally manages analyzed information and makes it available for future reference.

[0801] The "means for generating advice" is a technique for creating specific instructions or suggestions for the user based on the stored information.

[0802] The "means for notifying advice" is a technique for conveying the generated advice to the user.

[0803] "Emotion recognition means" is a technology for analyzing and recognizing a user's emotional state through voice input.

[0804] "Means for adjusting advice" refers to technology that changes or customizes the content of advice based on emotion recognition results.

[0805] The present invention is a system that utilizes voice input to manage the health and lifestyle of pets, and combines it with an emotion engine that recognizes the user's emotions. This system is composed of a combination of multiple hardware and software components.

[0806] Specific hardware and software configurations

[0807] Device: Use a smartphone or tablet with a microphone, which allows the user to input voice.

[0808] Server: A cloud-based server is used, which analyzes and manages the voice data.

[0809] Speech Recognition Software: We use the Google Speech-to-Text API to convert voice data into text.

[0810] Natural language processing engine: spaCy is used to analyze text data and extract important information.

[0811] Database: A MySQL database is used to store the analyzed data.

[0812] Emotion Engine: Uses IBM Watson Tone Analyzer to analyze user emotions.

[0813] Specific examples of implementation

[0814] The user speaks to the device to provide information about their pet's health and behavior. For example, if they say, "My dog ​​has gained 3 kilograms," the device's microphone captures this voice. This voice data is sent in real time to the Google Speech-to-Text API and converted into text. The resulting text is, "My dog ​​has gained 3 kilograms."

[0815] The converted data is then sent from the device to a server. The server receives this text data and analyzes it using a natural language processing engine (spaCy). During the analysis process, the intent of the text is understood, keywords are extracted, and context is analyzed to extract important information about the pet's health. The analysis results are stored in a MySQL database on the server.

[0816] The server generates advice for pet health management and lifestyle support based on the stored information. For example, the server may generate advice such as, "Your pet is gaining weight, so we recommend a low-calorie diet." The generated advice is sent from the server to the device, which then notifies the user of the advice by text or voice.

[0817] Furthermore, the emotion engine (IBM Watson Tone Analyzer) analyzes the user's emotions during voice input and recognizes emotions such as anxiety, anger, and joy. For example, if a user says, "I'm very worried," the emotion engine will detect the emotion "worry." This emotion data is stored in a database and will be referenced the next time advice is generated.

[0818] The user's emotions recognized by the emotion engine can influence the content of the advice generated. For example, if a user says, "My cat's appetite has decreased recently, and I'm worried," the emotion engine detects the emotion "worry." Based on this information, the server generates advice that takes emotions into consideration. Specifically, it provides advice that is sensitive to the user's emotions, such as, "Your cat's appetite has decreased, but it might be a good idea to try a new type of food. Don't worry, just wait and see."

[0819] An example of a prompt sentence is, "My pet has recently gained weight. What should I do? I'm worried." This system allows users to easily understand their pet's health status through voice input and receive appropriate support tailored to their individual needs and emotions. This has the effect of streamlining pet health monitoring and significantly reducing the burden on users.

[0820] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0821] Step 1:

[0822] The user speaks information about the pet into the terminal.

[0823] Input: User speech (e.g., "My dog ​​has gained 3 kilos").

[0824] What it does: The user opens a recording app on their smartphone and dictates their pet's health status. The device's microphone captures the audio.

[0825] Output: The captured audio data.

[0826] Step 2:

[0827] The device sends the captured voice data to speech recognition software (Google Speech-to-Text API) in real time, which converts the voice data into text.

[0828] Input: Captured speech data (e.g., "My dog ​​has gained 3 kilos").

[0829] What it does: It sends audio data to the Google Speech-to-Text API, which then recognizes the speech and converts it into text.

[0830] Output: Text data (e.g., "My dog ​​has gained 3 kg").

[0831] Step 3:

[0832] The terminal transmits the converted text data to the server.

[0833] Input: Text data (e.g., "My dog ​​has gained 3 kg").

[0834] Specific behavior: Sends text data to the server as an HTTP POST request.

[0835] Output: The text data sent to the server.

[0836] Step 4:

[0837] The server analyzes the text data it receives using a natural language processing engine (spaCy) to extract important information about the pet's health.

[0838] Input: Text data sent to the server (e.g., "My dog ​​has gained 3 kilos").

[0839] Specific operation: The server passes the text data to spaCy, which performs intent understanding, keyword extraction, context analysis, etc.

[0840] Output: Analysis results (e.g. keywords such as "dog", "weight", "gained 3kg").

[0841] Step 5:

[0842] The server stores the analysis results in a database (MySQL).

[0843] Input: Analysis results (e.g. keywords such as "dog", "weight", "gained 3kg").

[0844] Specific operation: The parsed results are sent to the MySQL database as an INSERT query and saved.

[0845] Output: Analysis results stored in a database.

[0846] Step 6:

[0847] The server generates advice on health management and lifestyle support for pets based on the stored information.

[0848] Input: Analysis results stored in the database (e.g. "dog", "weight", "gained 3 kg", etc.).

[0849] Specific operation: The server runs the advice generation engine based on the stored data and generates health management advice.

[0850] Output: The generated advice (e.g., "Your pet is gaining weight, so we recommend a low-calorie diet").

[0851] Step 7:

[0852] The server analyzes the user's emotions during voice input using an emotion recognition engine (IBM Watson Tone Analyzer).

[0853] Input: Text data sent to the server (e.g., "My dog ​​has gained 3 kilos").

[0854] How it works: The server passes the text data to IBM Watson Tone Analyzer, which analyzes emotions such as anxiety, anger, and joy.

[0855] Output: Emotion recognition result (e.g., "worried").

[0856] Step 8:

[0857] The server adjusts the advice generated based on the emotion recognition results.

[0858] Input: Emotion recognition result (e.g., "worried") and generated advice (e.g., "your pet is gaining weight, so we recommend a low-calorie diet").

[0859] Specific behavior: The server takes into account the emotion recognition results and adjusts the advice. Specifically, it adjusts the advice to say, "It might be a good idea to try a new type of food. Don't worry, let's see how it goes."

[0860] Output: Tailored advice (e.g., "Maybe you should try a new type of food. Don't worry, let's see how it goes.").

[0861] Step 9:

[0862] The server sends the advice to the terminal, which then notifies the user.

[0863] Input: Tailored advice (e.g., "Maybe you should try a new type of food. Don't worry, let's see how it goes.").

[0864] Specific behavior: The advice is sent to the device via an HTTP response, and the device app notifies the user.

[0865] Output: Advice given to the user (e.g. "Maybe you should try a new type of food. Don't worry, just wait and see").

[0866] (Application example 2)

[0867] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0868] Conventional pet health management systems often require users to manually enter data, which is time-consuming and inaccurate. Furthermore, since the advice provided does not take into account the user's feelings, it is difficult to provide suggestions in a way that is easy for the user to accept. Furthermore, data storage and management are cumbersome, which can delay appropriate responses in situations where a prompt response is required.

[0869] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0870] In this invention, the server includes means for receiving information about a pet through voice input, means for converting the received voice information into text, natural language processing means for analyzing the converted text information, means for saving the analyzed information in a database, means for generating advice on health management and lifestyle support for the pet based on the saved information, means for notifying the user of the generated advice, and means for analyzing the user's emotions, saving the information, and reflecting it in subsequent advice. This allows the user to easily manage the health condition of their pet through voice input, and by receiving advice that takes emotions into consideration, more effective pet care is possible.

[0871] "Voice input" is a method in which a user communicates information about a pet to the system through a voice capture device such as a microphone.

[0872] A "means for converting to text" is a device or software that includes speech recognition technology for analyzing speech information and converting it into a corresponding string of characters.

[0873] "Natural language processing means" is a technology that uses computers to analyze human language and understand intent and meaning, and analyzes text data.

[0874] A "means for storing in a database" is a process or device that organizes the analyzed information and stores it in a storage device in a format that can be accessed later.

[0875] A "means for generating pet health care and lifestyle support advice" is a process or device that automatically generates recommendations related to a pet's health and lifestyle based on stored data.

[0876] The "means for notifying the user" refers to a method or device for distributing the generated advice or information in a form that the user can check.

[0877] The "means for analyzing user emotions" is a technology for analyzing and recognizing emotions expressed by a user during voice input.

[0878] The "means for reflecting in future advice" is a process or device for storing the analyzed emotional state of the user in a database and taking that emotional information into account when generating future advice.

[0879] The "Pet Care Advisor" system for implementing this invention is mainly composed of a voice input function, a text conversion function, a natural language processing (NLP) engine, a database storage function, an advice generation engine, a notification function, and a sentiment analysis engine. Each function will be described in detail below.

[0880] Speech to text conversion

[0881] Users use a smartphone or other voice input device to voice-record information about their pet's health and behavior. This voice data is converted into text in real time using speech recognition software (e.g., Google Cloud Speech-to-Text API). In this process, speech such as "My dog ​​has gained 3 kilograms and I'm worried" can be converted into text.

[0882] Natural Language Processing (NLP) Engine

[0883] The text data is sent to a server and analyzed by a natural language processing engine (for example, Google Cloud Natural Language API). This engine understands the intent of the text, extracts keywords, and analyzes the context to extract important information about the pet's health. For example, information such as "weight gain" or "worries" may be extracted.

[0884] Database storage function

[0885] The analyzed data is stored in a database on the server, which also stores the pet's past health data and, together with the newly added data, serves as the basis for generating advice.

[0886] Sentiment Analysis Engine

[0887] An emotion analysis engine (for example, IBM Watson Tone Analyzer) analyzes the user's emotions during voice input and recognizes emotional states such as anxiety, anger, and joy. This emotional data is also stored in a database and is referenced the next time advice is generated. For example, the emotion "worry" may be detected from the input voice.

[0888] Advice Generation Engine

[0889] The server generates advice on pet health management and lifestyle support based on the stored information. For example, it might say, "Your pet is gaining weight, so we recommend a low-calorie diet. Don't worry too much, but increase your pet's moderate exercise." The engine generates reliable information based on past data and expert knowledge.

[0890] Notification function

[0891] The generated advice is sent from the server to the user's device. The user can check the advice on the device screen or listen to the guide message via audio. The device then assists the user in taking appropriate measures.

[0892] Specific examples

[0893] For example, if a user says, "My dog ​​has gained 3 kilograms and I'm worried," this speech is converted into text and sent to the server. The server analyzes the text and emotional information to detect the user's concern. As a result, advice such as "Your dog has gained weight, but as long as it's not a big increase, it's not a problem. I recommend you increase moderate exercise and switch to a low-calorie diet. Don't worry too much" is generated and sent to the device.

[0894] Prompt Sentence Examples

[0895] The user's voice input is converted to text and then that text is used as the prompt.

[0896] example:

[0897] Prompt: The user says, "My dog ​​has gained 3 kg and I'm worried." Text: "My dog ​​has gained 3 kg and I'm worried." Use this information and the user's emotion of "worry" to generate specific advice related to pet health care.

[0898] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0899] Step 1:

[0900] The user uses a voice input device such as a smartphone to input information about the health and behavior of their pet. Specifically, the user speaks into the device's microphone, saying, "My dog ​​has gained 3 kilograms, and I'm worried." This input voice becomes the initial data for the system. The input in Step 1 is the user's voice. The output is voice data.

[0901] Step 2:

[0902] The voice data received by the device is sent in real time to voice recognition software, which converts it into text. This process uses voice recognition technology such as the Google Cloud Speech-to-Text API. The input in step 2 is voice data, and the output is text data. Specifically, the text generated is, "My dog ​​has gained 3 kilograms and I'm worried."

[0903] Step 3:

[0904] The converted data is sent from the terminal to the server. The server receives this text data and prepares it for the next analysis step. The input of step 3 is the converted text data, and the output is the status of completion of transmission to the server.

[0905] Step 4:

[0906] The text data received by the server is analyzed using a natural language processing engine (for example, Google Cloud Natural Language API). Here, the intent of the text is understood, keywords are extracted, and context is analyzed to extract important information about the pet's health condition. The input for step 4 is the text data, and the output is the analyzed key data. Specifically, keywords such as "weight gain" and "worry" are extracted.

[0907] Step 5:

[0908] The analyzed data is saved in a database. This database also stores the pet's past health data, and together with the newly added data, it serves as the basis for generating advice. The input of Step 5 is the analyzed key data, and the output is the data saving completion status.

[0909] Step 6:

[0910] The server analyzes the user's emotions during voice input using an emotion analysis engine (e.g., IBM Watson Tone Analyzer). Here, emotional states such as anxiety, anger, and joy are recognized. The input in step 6 is speech-to-text data, and the output is emotional information. For example, the emotion "worry" is detected.

[0911] Step 7:

[0912] The emotional data is saved in the database. The user's emotional information obtained through emotion analysis will also be referenced the next time advice is generated. The input of step 7 is the emotional information, and the output is the data saving completion status.

[0913] Step 8:

[0914] The server generates advice for pet health management and lifestyle support based on the stored information. This advice generation engine uses a machine learning model to provide optimal advice based on the stored health data and emotional data. The input to step 8 is analysis data and emotional data, and the output is specific advice text. For example, advice such as "Your pet has gained weight, but as long as it's not a significant increase, it's not a problem. We recommend increasing moderate exercise and switching to a low-calorie diet. Don't worry too much" may be generated.

[0915] Step 9:

[0916] The generated advice is sent to the user's device. The user can check the advice through the device and take any necessary measures. The input of step 9 is the advice text, and the output is the notification completion status to the user. Specifically, a message is displayed on the smartphone screen saying, "You've gained weight, but as long as it's not a significant increase, it's not a problem. We recommend that you increase moderate exercise and switch to a low-calorie diet. Don't worry too much."

[0917] Example prompt sentence:

[0918] A user says, "My dog ​​has gained 3 kg and I'm worried." Text: "My dog ​​has gained 3 kg and I'm worried." Use this information and the user's emotion, "worried," to generate specific advice related to pet health care.

[0919] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0920] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0921] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0922] [Fourth embodiment]

[0923] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0924] 7, a 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.

[0925] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0926] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0927] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0928] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0929] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0930] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0931] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0932] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0933] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0934] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0935] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0936] The present invention is a system for efficiently managing the health of pets and supporting their daily lives, and in particular, it establishes a series of processes for collecting, analyzing, saving, and notifying information using voice input. This system allows a user to provide information about their pet through voice input, converts that information into text, analyzes it, and generates advice based on the analysis results. The system is realized in a format in which the generated advice is then notified to the user. An embodiment of this system is described in detail below.

[0937] When a user speaks to the device about their pet's health or daily changes, the device's microphone picks up the voice and the voice data is converted into text using recognition software. For example, suppose a user says, "My dog ​​has gained 3 kilograms." This voice input is automatically converted into text, and the device's screen displays, "My dog ​​has gained 3 kilograms."

[0938] The text data is then sent from the device to a server, which receives the data and uses a natural language processing (NLP) engine to analyze the meaning of what the user has entered. This process involves extracting keywords from the text data and identifying associated health information or signs of abnormalities.

[0939] The analyzed information is stored in a database on the server. This database stores your pet's past health data and history, and when combined with newly added data, it serves as the basis for generating more accurate advice. This stored data can be referenced later, allowing for centralized management of your pet's health.

[0940] The server then generates pet health care advice based on the stored data. The advice generation engine formulates specific advice based on the analyzed information. For example, it might provide advice such as, "Your pet is gaining weight, so we recommend a low-calorie diet." Because such advice is automatically generated based on expert knowledge, users can receive reliable information.

[0941] The generated advice is sent from the server to the device. The device then notifies the user of the advice. This notification is provided as a voice message or text message. The advice is not only displayed on the device screen, but also provided as a voice guide if necessary, making it easy for the user to receive the advice.

[0942] As a concrete example, consider the case where a user voice-inputs, "My cat's appetite has decreased recently." This voice input is converted into text and sent to the server. The server analyzes this data and attempts to identify, for example, the "cause of the loss of appetite." As a result, advice is generated, such as, "It's possible that your cat's new type of food doesn't suit your taste," and is notified to the user. Based on this advice, the user can take measures such as changing the food.

[0943] As described above, the system of the present invention can collect, analyze, and notify pet health information through voice input, enabling users to easily manage their pet's health. This system has the effect of making pet health monitoring more efficient and reducing the burden on users.

[0944] The processing flow will be explained below.

[0945] Step 1:

[0946] The user speaks into the device to input information about their pet. The user provides information by speaking details about the health and behavior of their pet at home.

[0947] Step 2:

[0948] The device captures the user's voice through a microphone, and this voice data is sent in real time to speech recognition software.

[0949] Step 3:

[0950] Speech recognition software converts the audio data into text. For example, "My dog ​​has gained 3 kilos" becomes "My dog ​​has gained 3 kilos."

[0951] Step 4:

[0952] The device sends the text data to the server, where it is transferred using a secure communication protocol.

[0953] Step 5:

[0954] The server receives the text data and analyzes it using a natural language processing (NLP) engine. During the analysis, the server performs tasks such as understanding the meaning of the text, extracting keywords, and analyzing context to extract important information about the pet's health.

[0955] Step 6:

[0956] The server then stores the information in a database based on the analysis results, and the data is stored along with the pet's past health history for future reference and comparison.

[0957] Step 7:

[0958] The server uses the stored information to generate advice for pet health management and lifestyle support. This advice generation engine automatically creates specific advice such as, "Your pet is gaining weight, so we recommend a low-calorie diet."

[0959] Step 8:

[0960] The server sends the generated advice to the terminal, which is designed to reach the user quickly and accurately.

[0961] Step 9:

[0962] The device notifies the user of the received advice, and the user can confirm the advice by text displayed on the device screen or by voice output, allowing the user to take specific actions based on the advice provided.

[0963] Example 1

[0964] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0965] In the field of pet health management and lifestyle support, it is important to enable users to easily input information and receive specific advice based on that information. Conventional systems require users to manually input information, which is time-consuming and often requires specialized knowledge, making it difficult to respond quickly to pet conditions.

[0966] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0967] In this invention, the server includes means for receiving information about the pet through voice input, speech recognition means for converting the received speech information into text, means for transmitting the converted text information to the server, natural language processing means for analyzing the transmitted text information, means for storing the analyzed information in a database, advice generation means for generating advice on health management and lifestyle support for the pet based on the stored information, and means for notifying the user of the generated advice. This enables the user to easily and quickly provide information about the pet to the system through voice input and receive specific and reliable advice based on the resulting analysis.

[0968] "Voice input" is a means by which the user provides information about the pet to the system in the form of voice.

[0969] A "voice recognition means" is software or hardware for converting user-provided voice information into text format.

[0970] "Text information" is data in a sentence format converted from voice data by a voice recognition means.

[0971] A "server" is a central computing unit that receives, analyzes, stores, and generates advice about text information.

[0972] "Natural language processing means" refers to technology or software for analyzing text data and understanding its content.

[0973] A "database" is a data storage system for storing analyzed information in an organized manner.

[0974] The "advice generation means" is an engine or software for automatically generating specific advice for pet health management and lifestyle support based on the stored information.

[0975] A "notification means" is a method, medium, or technique for notifying a user of generated advice.

[0976] This invention is a system for efficiently managing the health and lifestyle of pets. In particular, it utilizes voice input to build a series of processes for collecting, analyzing, saving, and notifying information. This system allows the user to provide information about their pet through voice input, converts that information into text, analyzes it, and generates advice based on the analysis results. The system is realized in a way that the generated advice is then notified to the user.

[0977] The user inputs information about their pet's health condition and daily changes into the device by voice. For example, they might say, "My cat's appetite has decreased recently." The device's microphone receives this voice, and the voice data is converted into text using recognition software (e.g., Google Speech-to-Text API). This voice input is converted into text format as "My cat's appetite has decreased recently," and the message "My cat's appetite has decreased recently" is displayed on the device's screen.

[0978] The text data is then sent from the device to a server. The server receives this text data and analyzes it using a natural language processing (NLP) engine (e.g., Amazon Comprehend). Specifically, it extracts keywords (e.g., "cat," "appetite," and "decreased") from the text data and understands its content. Based on this analysis, it can determine information about the pet's health and any signs of abnormalities.

[0979] The analyzed information is stored in a database on the server. This database stores your pet's past health data and history, and when combined with newly added data, it serves as the basis for generating more accurate advice. This stored data can be referenced later, allowing for centralized management of your pet's health.

[0980] The server then generates advice on pet health management based on the stored data. This advice generation engine (e.g., Microsoft Azure Machine Learning) uses the analyzed information to form specific advice. For example, it might provide advice such as, "Your cat's new type of food may not be to its liking, so try a different food." Because such advice is automatically generated based on expert knowledge, users can be assured of reliable information.

[0981] The generated advice is sent from the server to the device. The device then notifies the user of the advice. This notification is provided as a voice message or text message. The advice is not only displayed on the device screen, but also provides voice guidance as needed, making it easy for users to receive the advice.

[0982] As a concrete example, consider the case where a user voice-inputs "My dog ​​has gained weight." This voice input is converted into text "My dog ​​has gained weight" and sent to the server. The server analyzes this data and identifies the keyword "weight gain." The server compares it with past health data and generates advice to "introduce a low-calorie diet." This advice is sent to the device, and the user is notified that "Your dog has gained weight, so we recommend a low-calorie diet."

[0983] An example prompt is, "Convert the most recent voice input about your pet's condition to text and generate health advice based on the analysis of that text. For example, if your dog reports that it has gained weight, provide advice on appropriate diet and exercise."

[0984] This system will make pet health monitoring more efficient and reduce the burden on users.

[0985] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0986] Step 1:

[0987] The user inputs information about their pet's health condition and daily changes into the device by voice. For example, they might say, "My cat's appetite has decreased recently." This input is captured by the device's microphone, and the voice data is generated. Voice data is given as input, and the same voice data is obtained as output.

[0988] Step 2:

[0989] The device converts the received voice data into text format using voice recognition software (e.g., Google Speech-to-Text API). This voice is recognized as "My cat's appetite has decreased recently" and converted into text data. Voice data is given as input, and text data is output as the processing result. Specifically, phonemic and contextual analysis is performed on the voice data, and the corresponding text is generated.

[0990] Step 3:

[0991] The text data is sent from the terminal to the server. The terminal encodes the conversion result as packet data and sends it to the server via the network. Text data is given as input, and network packets arrive at the server as output. Specifically, the terminal sends an HTTP request, and the server receives it at the corresponding endpoint.

[0992] Step 4:

[0993] The server uses a natural language processing (NLP) engine (e.g., Amazon Comprehend) to analyze the received text data. The server extracts keywords (e.g., "cat," "appetite," and "dropped") from the text data and analyzes their meaning. The text data is given as input, and keywords and analysis results are output. Specifically, morphological and semantic analysis is performed on the text data, and the results are extracted.

[0994] Step 5:

[0995] The parsed information is stored in a database on the server. The server inserts the parsed results into the database as structured data. The parsed results are given as input, and the information stored in the database is output. Specifically, an INSERT statement is executed into the database, and the information is permanently saved.

[0996] Step 6:

[0997] The server generates advice on pet health care based on the stored data. This advice generation engine (e.g., Microsoft Azure Machine Learning) uses the analysis results to form specific advice. The stored data is given as input, and the generated advice is obtained as output. Specifically, a machine learning model analyzes the data and generates advice statements.

[0998] Step 7:

[0999] The generated advice is sent from the server to the terminal. The server encodes the advice in text format and sends it to the terminal via the network. The generated advice is given as input, and a network packet arrives at the terminal as output. Specifically, an HTTP response is generated and received by the terminal.

[1000] Step 8:

[1001] The terminal notifies the user of the received advice. The advice is displayed on the terminal screen and, if necessary, is also provided as a voice message. The advice from the server is given as input, and the advice displayed to the user is output. Specifically, the terminal's GUI is updated, and text is displayed and voice is played.

[1002] (Application example 1)

[1003] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1004] Modern homes and offices require efficient and reliable security management. Conventional security systems that rely on cameras and sensors are prone to false alarms and false positives, making it difficult to respond quickly. Another issue facing security management is the lack of specific advice that allows users to take appropriate measures immediately.

[1005] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1006] In this invention, the server includes means for receiving security-related information by voice input, means for converting the received voice information into text, natural language processing means for analyzing the converted text information, means for storing the analyzed information in a database, means for generating advice on security management and life support based on the stored information, and means for notifying the generated advice to the user. This enables the user to easily report security information by voice input and quickly receive specific advice based on the information.

[1007] "Voice input" is a technology that recognizes voice and processes it as digital information.

[1008] "Security information" is data that indicates the security status of a home or office, including unauthorized intrusions, abnormal activity, and the status of equipment.

[1009] "Means for converting to text" refers to technology that converts voice data into text information.

[1010] "Natural language processing means" refers to technology that analyzes human language, understands its meaning, and processes it.

[1011] "Means of storing in a database" refers to the technology used to manage and store analyzed information within the system.

[1012] "Means for generating advice" refers to technology that automatically creates appropriate instructions or suggestions for the user based on the stored information.

[1013] "Means for notifying" refers to a communication technique for conveying the generated advice to the user.

[1014] "Server" refers to a computer system that centrally processes and manages data.

[1015] "Security management" refers to activities aimed at protecting a home or office and preventing unauthorized access.

[1016] "Lifestyle support" refers to providing instructions and advice to users in their daily lives.

[1017] This invention is a security management system that uses voice input, and provides a mechanism for users to report the security status of their home or office by voice and receive appropriate advice based on the content of the report. This system includes a series of processes such as voice input, text conversion, information analysis, data storage, advice generation, and notification.

[1018] Hardware Configuration

[1019] The system uses the following hardware:

[1020] 1. Smartphones and smart speakers: Used for voice input and receiving notifications.

[1021] 2. Microphone and speaker: Used for recording and playing audio.

[1022] Software Configuration

[1023] The system uses the following software:

[1024] 1. Speech recognition engine (e.g. Google Cloud Speech-to-Text): Converts speech into text.

[1025] 2. Natural language processing engine (e.g., Dialogflow, Amazon Comprehend): Analyzes the input text and understands its meaning.

[1026] 3. Cloud database (e.g. AWS DynamoDB, Google Firestore): Stores the analyzed information.

[1027] 4. Notification system (e.g., Firebase Cloud Messaging, Twilio): Notifies the user of the generated advice.

[1028] System Operation

[1029] 1. Voice input:

[1030] The user reports the security situation by voice to a smartphone or smart speaker, for example, saying, "The office window is open."

[1031] 2. Text conversion:

[1032] The device will record your voice and convert it to text using Google Cloud Speech-to-Text, which will say "The office window is open."

[1033] 3. Information analysis:

[1034] The text information is sent to a natural language processing engine for semantic analysis. Dialogflow and Amazon Comprehend are used to understand the content of the text and assess security risks. For example, an "open window" can be recognized as a risk and assessed accordingly.

[1035] 4. Data Retention:

[1036] The analyzed information is stored in a cloud database, including risk assessment and situation details.

[1037] 5. Advice Generation:

[1038] Based on the stored data, a generative AI model (e.g., GPT-3) is used to generate specific countermeasures, such as advice like "Check and close windows immediately."

[1039] 6. Notice:

[1040] Firebase Cloud Messaging and Twilio are used to notify users of the generated advice, which is delivered via voice or text to smartphones or smart speakers.

[1041] Specific examples

[1042] Example prompts if the user says "My office windows are open":

[1043] The user has spoken "The office window is open." Use this information to identify security risks and notify the user of countermeasures.

[1044] Based on this prompt, the generative AI model generates advice such as, "It appears that a window in your office is open. Please check immediately and close the window if necessary."

[1045] As described above, the system of the present invention allows a user to easily report security information through voice input and quickly receive specific advice based on that information.

[1046] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1047] Step 1: Voice Input

[1048] The user reports the security situation by voice to a smartphone or smart speaker. The voice input is information such as "The office window is open." The device's microphone records the voice and the data is sent to the device.

[1049] Step 2: Text conversion

[1050] The device sends the recorded voice data to a speech recognition engine (e.g., Google Cloud Speech-to-Text). The speech recognition engine analyzes the voice data and converts it into text information. The input is voice data, and the output is text data such as "The office window is open."

[1051] Step 3: Information analysis

[1052] Text data is sent to a natural language processing engine (e.g., Dialogflow, Amazon Comprehend). The natural language processing engine analyzes the text and understands its meaning. The input is text data, and the output is a security risk assessment and detailed information as the analysis results. For example, risk information such as "the window is open" is evaluated.

[1053] Step 4: Save Data

[1054] The analysis results are stored in a cloud database (e.g., AWS DynamoDB, Google Firestore). The input is the analyzed information, and the output is the risk assessment and situation details stored in the database. This accumulates data that can be used for future reference.

[1055] Step 5: Advice Generation

[1056] The server uses a generative AI model (e.g., GPT-3) based on the stored information to generate specific countermeasures. The input is the database information and a prompt, and the output is specific advice. For example, the generated advice might be, "Check and close the windows immediately."

[1057] Step 6: Notification

[1058] The generated advice is sent to the user via a notification system (e.g., Firebase Cloud Messaging, Twilio). The input is the generated advice, and the output is a notification that is displayed on the user's smartphone or smart speaker or played aloud.

[1059] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1060] The present invention combines a system for managing the health and lifestyle of pets using voice input with an emotion engine that recognizes the emotions of the user. This system includes a voice input function in which the user provides information about the pet, a function for converting the voice information into text, a function for analyzing the text data using a natural language processing (NLP) engine, a function for saving the analysis results in a database, a function for generating advice based on the saved data, a function for notifying the user of the advice, and a function for recognizing emotions using the emotion engine. Specific embodiments of the system are described below.

[1061] The user speaks into the device to input information about their pet's health and behavior. For example, if the user types, "My dog ​​has gained 3 kilos," the device's microphone captures this voice. This voice data is sent to speech recognition software in real time and converted into text. The resulting text is, "My dog ​​has gained 3 kilos."

[1062] The text data is then sent from the device to a server. The server receives the text data and analyzes it using a natural language processing engine. During the analysis process, the server performs tasks such as understanding the intent of the text, extracting keywords, and analyzing context to extract important information about the pet's health. The results of this analysis are stored in a database on the server. The pet's past health data is also stored, and together with newly added data, it serves as the basis for generating more accurate advice.

[1063] The server generates advice for pet health management and lifestyle support based on the stored information. For example, it may provide advice such as, "Your pet is gaining weight, so we recommend a low-calorie diet." This advice generation engine automatically generates specific advice based on expert knowledge, ensuring that users receive reliable information.

[1064] One of the features of the present invention is the incorporation of an emotion engine. The emotion engine has the function of analyzing the user's emotions during voice input and recognizing emotional states such as anxiety, anger, and joy. For example, if the user is feeling stressed, the emotion engine will classify that emotion as "worry." This emotion data is stored in a database and will be referenced the next time advice is generated.

[1065] The user's emotions recognized by the emotion engine can influence the advice that is generated. For example, if a user says, "I'm worried because my cat's appetite has decreased recently," the emotion engine will detect the emotion "worry." Based on this information, the server will generate advice that takes the emotion into consideration. Specifically, it will provide advice that is sensitive to the user's emotions, such as, "Your cat's appetite has decreased, but it might be a good idea to try a new type of food. Don't worry, just wait and see."

[1066] The generated advice is sent from the server to the device. The device notifies the user of this advice by voice or text. The user can check the advice on the device screen or listen to the guide message by voice. This notification allows the user to take appropriate measures for managing their pet's health.

[1067] As a concrete example, consider the case where a user voice-inputs, "My dog ​​has gained 3 kg, and I'm very worried." This voice is converted into text and sent to the server. The server analyzes the text and emotional information to detect the user's concern. As a result, it generates emotionally sensitive advice such as, "Your dog has gained weight, but as long as it's not a big increase, it's not a problem. I recommend you increase moderate exercise and switch to a low-calorie diet. Don't worry too much." and sends it to the device. The device notifies the user, who can then take appropriate action based on the advice.

[1068] This invention allows users to easily understand their pet's health condition through voice input and receive appropriate support tailored to their individual needs and emotions. This system has the effect of streamlining pet health monitoring and significantly reducing the burden on users.

[1069] The processing flow will be explained below.

[1070] Step 1:

[1071] The user speaks information about their pet into the device, for example, saying, "My dog ​​has gained 3 kilograms."

[1072] Step 2:

[1073] The device captures the user's voice through a microphone, and the captured voice data is sent directly to voice recognition software.

[1074] Step 3:

[1075] The speech recognition software converts the received speech data into text, resulting in the text "My dog ​​has gained 3 kilos."

[1076] Step 4:

[1077] The device then transmits the converted data to the server, where it is securely transferred using a security protocol.

[1078] Step 5:

[1079] The server receives the text data and analyzes it using a natural language processing (NLP) engine, which performs semantic analysis of the text, keyword extraction, context understanding, and more.

[1080] Step 6:

[1081] The server stores the analyzed data in a database, which also contains the pet's health history and past information, and centrally records the analysis results.

[1082] Step 7:

[1083] The server generates advice on pet health management and lifestyle support based on the stored information, such as "Your pet is gaining weight, so we recommend a low-calorie diet."

[1084] Step 8:

[1085] The server uses an emotion engine to analyze the user's emotions when generating advice. It recognizes the user's emotional state (e.g., worry, joy, anger) from their voice data and formulates advice that takes their emotions into consideration.

[1086] Step 9:

[1087] The server then sends advice based on the generated emotions to the device, again using a security protocol to transfer data.

[1088] Step 10:

[1089] The device then notifies the user of the advice it receives, which is displayed as a voice message or text message, such as "A low-calorie diet is recommended to prevent weight gain. Don't worry too much."

[1090] Step 11:

[1091] Users can check the provided advice and take action to manage their pet's health (e.g., changing its diet or increasing its exercise) based on it, thus enabling them to effectively manage their pet's health.

[1092] Example 2

[1093] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1094] While conventional pet health management systems can obtain information about pets through voice input, they face the challenge of efficiently analyzing that information and providing appropriate advice that takes the user's feelings into consideration. Furthermore, advice provided without considering the user's anxieties and worries may not be satisfactory to the user. Furthermore, there is a lack of systems that centrally manage pet health information and provide effective notifications.

[1095] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1096] In this invention, the server includes means for receiving information about the pet through voice input, means for converting the received voice information into text, natural language processing means for analyzing the converted text information, means for storing the analyzed information in a database, means for generating advice on pet health management and lifestyle support based on the stored information, means for notifying the user of the generated advice, emotion recognition means for analyzing the user's emotions, and means for adjusting the advice based on the emotion recognition results. This makes it possible to easily collect pet health information through voice input and provide highly accurate advice that takes the user's emotions into consideration.

[1097] "Voice input" is the means by which a user's spoken voice data is received and interpreted by the system.

[1098] "Voice information" means information about a pet provided by a user through voice input.

[1099] "Means for converting to text" refers to a technique for converting voice information into character string data.

[1100] "Natural language processing means" is a technology for analyzing text data and understanding its content.

[1101] "Means of storing in a database" refers to technology that centrally manages analyzed information and makes it available for future reference.

[1102] The "means for generating advice" is a technique for creating specific instructions or suggestions for the user based on the stored information.

[1103] The "means for notifying advice" is a technique for conveying the generated advice to the user.

[1104] "Emotion recognition means" is a technology for analyzing and recognizing a user's emotional state through voice input.

[1105] "Means for adjusting advice" refers to technology that changes or customizes the content of advice based on emotion recognition results.

[1106] The present invention is a system that utilizes voice input to manage the health and lifestyle of pets, and combines it with an emotion engine that recognizes the user's emotions. This system is composed of a combination of multiple hardware and software components.

[1107] Specific hardware and software configurations

[1108] Device: Use a smartphone or tablet with a microphone, which allows the user to input voice.

[1109] Server: A cloud-based server is used, which analyzes and manages the voice data.

[1110] Speech Recognition Software: We use the Google Speech-to-Text API to convert voice data into text.

[1111] Natural language processing engine: spaCy is used to analyze text data and extract important information.

[1112] Database: A MySQL database is used to store the analyzed data.

[1113] Emotion Engine: Uses IBM Watson Tone Analyzer to analyze user emotions.

[1114] Specific examples of implementation

[1115] The user speaks to the device to provide information about their pet's health and behavior. For example, if they say, "My dog ​​has gained 3 kilograms," the device's microphone captures this voice. This voice data is sent in real time to the Google Speech-to-Text API and converted into text. The resulting text is, "My dog ​​has gained 3 kilograms."

[1116] The converted data is then sent from the device to a server. The server receives this text data and analyzes it using a natural language processing engine (spaCy). During the analysis process, the intent of the text is understood, keywords are extracted, and context is analyzed to extract important information about the pet's health. The analysis results are stored in a MySQL database on the server.

[1117] The server generates advice for pet health management and lifestyle support based on the stored information. For example, the server may generate advice such as, "Your pet is gaining weight, so we recommend a low-calorie diet." The generated advice is sent from the server to the device, which then notifies the user of the advice by text or voice.

[1118] Furthermore, the emotion engine (IBM Watson Tone Analyzer) analyzes the user's emotions during voice input and recognizes emotions such as anxiety, anger, and joy. For example, if a user says, "I'm very worried," the emotion engine will detect the emotion "worry." This emotion data is stored in a database and will be referenced the next time advice is generated.

[1119] The user's emotions recognized by the emotion engine can influence the content of the advice generated. For example, if a user says, "My cat's appetite has decreased recently, and I'm worried," the emotion engine detects the emotion "worry." Based on this information, the server generates advice that takes emotions into consideration. Specifically, it provides advice that is sensitive to the user's emotions, such as, "Your cat's appetite has decreased, but it might be a good idea to try a new type of food. Don't worry, just wait and see."

[1120] An example of a prompt sentence is, "My pet has recently gained weight. What should I do? I'm worried." This system allows users to easily understand their pet's health status through voice input and receive appropriate support tailored to their individual needs and emotions. This has the effect of streamlining pet health monitoring and significantly reducing the burden on users.

[1121] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1122] Step 1:

[1123] The user speaks information about the pet into the terminal.

[1124] Input: User speech (e.g., "My dog ​​has gained 3 kilos").

[1125] What it does: The user opens a recording app on their smartphone and dictates their pet's health status. The device's microphone captures the audio.

[1126] Output: The captured audio data.

[1127] Step 2:

[1128] The device sends the captured voice data to speech recognition software (Google Speech-to-Text API) in real time, which converts the voice data into text.

[1129] Input: Captured speech data (e.g., "My dog ​​has gained 3 kilos").

[1130] What it does: It sends audio data to the Google Speech-to-Text API, which then recognizes the speech and converts it into text.

[1131] Output: Text data (e.g., "My dog ​​has gained 3 kg").

[1132] Step 3:

[1133] The terminal transmits the converted text data to the server.

[1134] Input: Text data (e.g., "My dog ​​has gained 3 kg").

[1135] Specific behavior: Sends text data to the server as an HTTP POST request.

[1136] Output: The text data sent to the server.

[1137] Step 4:

[1138] The server analyzes the text data it receives using a natural language processing engine (spaCy) to extract important information about the pet's health.

[1139] Input: Text data sent to the server (e.g., "My dog ​​has gained 3 kilos").

[1140] Specific operation: The server passes the text data to spaCy, which performs intent understanding, keyword extraction, context analysis, etc.

[1141] Output: Analysis results (e.g. keywords such as "dog", "weight", "gained 3kg").

[1142] Step 5:

[1143] The server stores the analysis results in a database (MySQL).

[1144] Input: Analysis results (e.g. keywords such as "dog", "weight", "gained 3kg").

[1145] Specific operation: The parsed results are sent to the MySQL database as an INSERT query and saved.

[1146] Output: Analysis results stored in a database.

[1147] Step 6:

[1148] The server generates advice on health management and lifestyle support for pets based on the stored information.

[1149] Input: Analysis results stored in the database (e.g. "dog", "weight", "gained 3 kg", etc.).

[1150] Specific operation: The server runs the advice generation engine based on the stored data and generates health management advice.

[1151] Output: The generated advice (e.g., "Your pet is gaining weight, so we recommend a low-calorie diet").

[1152] Step 7:

[1153] The server analyzes the user's emotions during voice input using an emotion recognition engine (IBM Watson Tone Analyzer).

[1154] Input: Text data sent to the server (e.g., "My dog ​​has gained 3 kilos").

[1155] How it works: The server passes the text data to IBM Watson Tone Analyzer, which analyzes emotions such as anxiety, anger, and joy.

[1156] Output: Emotion recognition result (e.g., "worried").

[1157] Step 8:

[1158] The server adjusts the advice generated based on the emotion recognition results.

[1159] Input: Emotion recognition result (e.g., "worried") and generated advice (e.g., "your pet is gaining weight, so we recommend a low-calorie diet").

[1160] Specific behavior: The server takes into account the emotion recognition results and adjusts the advice. Specifically, it adjusts the advice to say, "It might be a good idea to try a new type of food. Don't worry, let's see how it goes."

[1161] Output: Tailored advice (e.g., "Maybe you should try a new type of food. Don't worry, let's see how it goes.").

[1162] Step 9:

[1163] The server sends the advice to the terminal, which then notifies the user.

[1164] Input: Tailored advice (e.g., "Maybe you should try a new type of food. Don't worry, let's see how it goes.").

[1165] Specific behavior: The advice is sent to the device via an HTTP response, and the device app notifies the user.

[1166] Output: Advice given to the user (e.g. "Maybe you should try a new type of food. Don't worry, just wait and see").

[1167] (Application example 2)

[1168] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1169] Conventional pet health management systems often require users to manually enter data, which is time-consuming and inaccurate. Furthermore, since the advice provided does not take into account the user's feelings, it is difficult to provide suggestions in a way that is easy for the user to accept. Furthermore, data storage and management are cumbersome, which can delay appropriate responses in situations where a prompt response is required.

[1170] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1171] In this invention, the server includes means for receiving information about a pet through voice input, means for converting the received voice information into text, natural language processing means for analyzing the converted text information, means for saving the analyzed information in a database, means for generating advice on health management and lifestyle support for the pet based on the saved information, means for notifying the user of the generated advice, and means for analyzing the user's emotions, saving the information, and reflecting it in subsequent advice. This allows the user to easily manage the health condition of their pet through voice input, and by receiving advice that takes emotions into consideration, more effective pet care is possible.

[1172] "Voice input" is a method in which a user communicates information about a pet to the system through a voice capture device such as a microphone.

[1173] A "means for converting to text" is a device or software that includes speech recognition technology for analyzing speech information and converting it into a corresponding string of characters.

[1174] "Natural language processing means" is a technology that uses computers to analyze human language and understand intent and meaning, and analyzes text data.

[1175] A "means for storing in a database" is a process or device that organizes the analyzed information and stores it in a storage device in a format that can be accessed later.

[1176] A "means for generating pet health care and lifestyle support advice" is a process or device that automatically generates recommendations related to a pet's health and lifestyle based on stored data.

[1177] The "means for notifying the user" refers to a method or device for distributing the generated advice or information in a form that the user can check.

[1178] The "means for analyzing user emotions" is a technology for analyzing and recognizing emotions expressed by a user during voice input.

[1179] The "means for reflecting in future advice" is a process or device for storing the analyzed emotional state of the user in a database and taking that emotional information into account when generating future advice.

[1180] The "Pet Care Advisor" system for implementing this invention is mainly composed of a voice input function, a text conversion function, a natural language processing (NLP) engine, a database storage function, an advice generation engine, a notification function, and a sentiment analysis engine. Each function will be described in detail below.

[1181] Speech to text conversion

[1182] Users use a smartphone or other voice input device to voice-record information about their pet's health and behavior. This voice data is converted into text in real time using speech recognition software (e.g., Google Cloud Speech-to-Text API). In this process, speech such as "My dog ​​has gained 3 kilograms and I'm worried" can be converted into text.

[1183] Natural Language Processing (NLP) Engine

[1184] The text data is sent to a server and analyzed by a natural language processing engine (for example, Google Cloud Natural Language API). This engine understands the intent of the text, extracts keywords, and analyzes the context to extract important information about the pet's health. For example, information such as "weight gain" or "worries" may be extracted.

[1185] Database storage function

[1186] The analyzed data is stored in a database on the server, which also stores the pet's past health data and, together with the newly added data, serves as the basis for generating advice.

[1187] Sentiment Analysis Engine

[1188] An emotion analysis engine (for example, IBM Watson Tone Analyzer) analyzes the user's emotions during voice input and recognizes emotional states such as anxiety, anger, and joy. This emotional data is also stored in a database and is referenced the next time advice is generated. For example, the emotion "worry" may be detected from the input voice.

[1189] Advice Generation Engine

[1190] The server generates advice on pet health management and lifestyle support based on the stored information. For example, it might say, "Your pet is gaining weight, so we recommend a low-calorie diet. Don't worry too much, but increase your pet's moderate exercise." The engine generates reliable information based on past data and expert knowledge.

[1191] Notification function

[1192] The generated advice is sent from the server to the user's device. The user can check the advice on the device screen or listen to the guide message via audio. The device then assists the user in taking appropriate measures.

[1193] Specific examples

[1194] For example, if a user says, "My dog ​​has gained 3 kilograms and I'm worried," this speech is converted into text and sent to the server. The server analyzes the text and emotional information to detect the user's concern. As a result, advice such as "Your dog has gained weight, but as long as it's not a big increase, it's not a problem. I recommend you increase moderate exercise and switch to a low-calorie diet. Don't worry too much" is generated and sent to the device.

[1195] Prompt Sentence Examples

[1196] The user's voice input is converted to text and then that text is used as the prompt.

[1197] example:

[1198] Prompt: The user says, "My dog ​​has gained 3 kg and I'm worried." Text: "My dog ​​has gained 3 kg and I'm worried." Use this information and the user's emotion of "worry" to generate specific advice related to pet health care.

[1199] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1200] Step 1:

[1201] The user uses a voice input device such as a smartphone to input information about the health and behavior of their pet. Specifically, the user speaks into the device's microphone, saying, "My dog ​​has gained 3 kilograms, and I'm worried." This input voice becomes the initial data for the system. The input in Step 1 is the user's voice. The output is voice data.

[1202] Step 2:

[1203] The voice data received by the device is sent in real time to voice recognition software, which converts it into text. This process uses voice recognition technology such as the Google Cloud Speech-to-Text API. The input in step 2 is voice data, and the output is text data. Specifically, the text generated is, "My dog ​​has gained 3 kilograms and I'm worried."

[1204] Step 3:

[1205] The converted data is sent from the terminal to the server. The server receives this text data and prepares it for the next analysis step. The input of step 3 is the converted text data, and the output is the status of completion of transmission to the server.

[1206] Step 4:

[1207] The text data received by the server is analyzed using a natural language processing engine (for example, Google Cloud Natural Language API). Here, the intent of the text is understood, keywords are extracted, and context is analyzed to extract important information about the pet's health condition. The input for step 4 is the text data, and the output is the analyzed key data. Specifically, keywords such as "weight gain" and "worry" are extracted.

[1208] Step 5:

[1209] The analyzed data is saved in a database. This database also stores the pet's past health data, and together with the newly added data, it serves as the basis for generating advice. The input of Step 5 is the analyzed key data, and the output is the data saving completion status.

[1210] Step 6:

[1211] The server analyzes the user's emotions during voice input using an emotion analysis engine (e.g., IBM Watson Tone Analyzer). Here, emotional states such as anxiety, anger, and joy are recognized. The input in step 6 is speech-to-text data, and the output is emotional information. For example, the emotion "worry" is detected.

[1212] Step 7:

[1213] The emotional data is saved in the database. The user's emotional information obtained through emotion analysis will also be referenced the next time advice is generated. The input of step 7 is the emotional information, and the output is the data saving completion status.

[1214] Step 8:

[1215] The server generates advice for pet health management and lifestyle support based on the stored information. This advice generation engine uses a machine learning model to provide optimal advice based on the stored health data and emotional data. The input to step 8 is analysis data and emotional data, and the output is specific advice text. For example, advice such as "Your pet has gained weight, but as long as it's not a significant increase, it's not a problem. We recommend increasing moderate exercise and switching to a low-calorie diet. Don't worry too much" may be generated.

[1216] Step 9:

[1217] The generated advice is sent to the user's device. The user can check the advice through the device and take any necessary measures. The input of step 9 is the advice text, and the output is the notification completion status to the user. Specifically, a message is displayed on the smartphone screen saying, "You've gained weight, but as long as it's not a significant increase, it's not a problem. We recommend that you increase moderate exercise and switch to a low-calorie diet. Don't worry too much."

[1218] Example prompt sentence:

[1219] A user says, "My dog ​​has gained 3 kg and I'm worried." Text: "My dog ​​has gained 3 kg and I'm worried." Use this information and the user's emotion, "worried," to generate specific advice related to pet health care.

[1220] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1221] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1222] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1223] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1224] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1225] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1226] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1227] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1228] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1229] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1230] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1231] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1232] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1233] 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.

[1234] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1235] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1236] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1237] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1238] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1239] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1240] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1241] The following is further disclosed regarding the above embodiment.

[1242] (Claim 1)

[1243] means for receiving information about the pet via voice input;

[1244] means for converting the received audio information into text;

[1245] natural language processing means for analyzing the converted text information;

[1246] a means for storing the analyzed information in a database;

[1247] A means for generating advice on health management and life support for pets based on the stored information;

[1248] The system includes a means for notifying a user of the generated advice.

[1249] (Claim 2)

[1250] 10. The system of claim 1, wherein the received voice information is transmitted to a server.

[1251] (Claim 3)

[1252] The system of claim 1, which manages vaccine schedules and regular medications based on the analyzed information.

[1253] "Example 1"

[1254] (Claim 1)

[1255] means for receiving information about the pet via voice input;

[1256] a speech recognition means for converting received speech information into text;

[1257] means for transmitting the converted text information to a server;

[1258] natural language processing means for analyzing the transmitted text information;

[1259] a means for storing the analyzed information in a database;

[1260] an advice generating means for generating advice on health management and life support for a pet based on the stored information;

[1261] The system includes a means for notifying a user of the generated advice.

[1262] (Claim 2)

[1263] 10. The system of claim 1, wherein the system converts received voice information into text using voice recognition software.

[1264] (Claim 3)

[1265] The system of claim 1, wherein a machine learning model is used to generate pet health management and lifestyle support advice based on the stored information.

[1266] "Application Example 1"

[1267] (Claim 1)

[1268] a means for receiving security information by voice input;

[1269] means for converting the received audio information into text;

[1270] natural language processing means for analyzing the converted text information;

[1271] a means for storing the analyzed information in a database;

[1272] means for generating advice on security management and life support based on the stored information;

[1273] The system includes a means for notifying a user of the generated advice.

[1274] (Claim 2)

[1275] 10. The system of claim 1, wherein the received voice information is transmitted to a server.

[1276] (Claim 3)

[1277] The system according to claim 1, which evaluates security risks and manages countermeasures based on the analyzed information.

[1278] "Example 2: Combining Emotion Engines"

[1279] (Claim 1)

[1280] means for receiving information about the pet via voice input;

[1281] means for converting the received audio information into text;

[1282] natural language processing means for analyzing the converted text information;

[1283] a means for storing the analyzed information in a database;

[1284] A means for generating advice on health management and life support for pets based on the stored information;

[1285] means for notifying a user of the generated advice;

[1286] emotion recognition means for analyzing the emotion of a user;

[1287] The system includes a means for adjusting advice based on emotion recognition results.

[1288] (Claim 2)

[1289] 10. The system of claim 1, wherein the received voice information is transmitted to a server.

[1290] (Claim 3)

[1291] The system of claim 1, which manages vaccine schedules and regular medications based on the analyzed information.

[1292] "Application example 2 when combining emotion engines"

[1293] (Claim 1)

[1294] means for receiving information about the pet via voice input;

[1295] means for converting the received audio information into text;

[1296] natural language processing means for analyzing the converted text information;

[1297] a means for storing the analyzed information in a database;

[1298] A means for generating advice on health management and life support for pets based on the stored information;

[1299] means for notifying a user of the generated advice;

[1300] A system that includes a means for analyzing the user's emotions, storing that information, and reflecting it in future advice.

[1301] (Claim 2)

[1302] 10. The system of claim 1, wherein the received voice information is transmitted to a server.

[1303] (Claim 3)

[1304] The system of claim 1, which manages vaccine schedules and regular medications based on the analyzed information. [Explanation of symbols]

[1305] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving information about the pet via voice input; means for converting the received audio information into text; natural language processing means for analyzing the converted text information; a means for storing the analyzed information in a database; A means for generating advice on health management and life support for pets based on the stored information; The system includes a means for notifying a user of the generated advice.

2. 10. The system of claim 1, wherein the received voice information is transmitted to a server.

3. The system according to claim 1, wherein the system manages vaccination schedules and periodic medications based on the analyzed information.

Images