System

Abstract

An object of the system according to the embodiment is to analyze a cry or an action of a pet and accurately convert an intention or an emotion into a human language.SOLUTION: A system includes a collection unit, an analysis unit, an estimation unit, and a conversion unit. The collection unit collects a cry or an action. The analysis unit analyzes the data collected by the collection unit. The estimation unit estimates an intention or a feeling on the basis of an analysis result obtained by the analysis unit. The conversion unit converts the intention or the feeling estimated by the estimation unit into human language.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has difficulty accurately translating pet sounds and behavior, limiting the extent to which owners can understand their pets' intentions and emotions.

[0005] The system according to the embodiment aims to analyze the cries and behavior of pets and accurately convert their intentions and emotions into human language. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, an estimation unit, and a conversion unit. The collection unit collects sounds or behaviors. The analysis unit analyzes the data collected by the collection unit. The estimation unit estimates an intention or emotion based on the analysis result obtained by the analysis unit. The conversion unit converts the intention or emotion estimated by the estimation unit into human language. [Effects of the Invention]

[0007] The system according to the embodiment can analyze the cries and behavior of pets and accurately convert their intentions and emotions into human language. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A pet translation system according to an embodiment of the present invention uses a generation AI to translate the meows and behaviors of dogs and cats. The pet translation system collects the meows and behaviors of dogs and cats, analyzes them, infers their intentions and emotions, and converts them into human language. For example, the pet translation system records behaviors such as dogs barking, cats meowing, dogs wagging their tails, and cats sharpening their claws. This data is input into the generation AI. The generation AI then analyzes the collected data to infer the intentions and emotions of the dogs and cats. The generation AI analyzes the sonic patterns of the meows and behavioral characteristics and, based on the analysis, infers what the dogs and cats are thinking and doing. For example, a dog's barking sonic pattern can be used to infer that the dog or cat "wants to play," and a cat's claw sharpening behavior can be used to infer that the dog or cat "is stressed." The generation AI then converts the inferred intentions and emotions into human language. For example, if the inferred intention is "I want to play," the system translates it into "I want to play." This translation result is provided to the pet owner. This allows owners to understand what their pets are thinking and what they want to do. This deepens communication with their pets and strengthens the bond between them. Pet translation systems can deepen communication between owners and pets and build better relationships. For example, when an owner inputs their dog's bark into a translator, the generating AI analyzes the bark and provides a translation result such as "I want to play." This allows the owner to understand that their dog wants to play and play together. Similarly, when a cat sharpens its claws into a translator, the generating AI analyzes the behavior and provides a translation result such as "I'm stressed." This allows the owner to understand that their cat is stressed and take appropriate measures. In this way, pet translation systems using generating AI can be a powerful tool for deepening communication between owners and pets and building better relationships.

[0029] The pet translation system according to the embodiment includes a collection unit, an analysis unit, an estimation unit, and a conversion unit. The collection unit collects sounds and behaviors of dogs and cats. The collection unit can collect the sounds and behaviors using, for example, a microphone or a camera. The collection unit can collect, for example, the sound of a dog barking using a microphone. The collection unit can also record the behavior of a cat sharpening its claws using a camera. The collection unit can also record the behavior of a dog wagging its tail using a camera. The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the data using, for example, algorithms for sound pattern analysis and behavior pattern analysis. The analysis unit can analyze the sound of a dog barking using sound pattern analysis. The analysis unit can also analyze the behavior of a cat sharpening its claws using behavior pattern analysis. The analysis unit can also analyze the data by combining sound pattern analysis and behavior pattern analysis. The estimation unit estimates intentions and emotions based on the analysis results obtained by the analysis unit. For example, the estimation unit estimates the intention of "wanting to play" from the sound of a dog barking based on the analysis result. The estimation unit can also estimate the emotion of "feeling stressed" from the behavior of a cat sharpening its claws based on the analysis result. The estimation unit can also estimate the emotion of "happy" from the behavior of a dog wagging its tail based on the analysis result. The conversion unit converts the intention and emotion estimated by the estimation unit into human language. The conversion unit converts the intention and emotion into human language using, for example, natural language processing technology. For example, the conversion unit converts the intention of "wanting to play" into "I want to play." The conversion unit can also convert the emotion of "feeling stressed" into "I'm stressed." The conversion unit can also convert the emotion of "happy" into "I'm happy." In this way, the pet translation system according to the embodiment can deepen communication between owners and pets.

[0030] The collection unit can collect sounds or behaviors using a microphone or a camera. For example, the collection unit can collect the sound of a dog barking using a microphone. For example, the collection unit can collect sounds from a specific direction using a directional microphone. The collection unit can also record the behavior of a cat using a wide-angle camera. For example, the collection unit can record the behavior of a cat sharpening its claws using a wide-angle camera. The collection unit can also combine a microphone and a camera to simultaneously collect the sound of a dog barking and the behavior of a dog wagging its tail using a combination of a microphone and a camera. In this way, the use of a microphone or a camera improves the accuracy of collecting sounds and behaviors. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input audio data collected by a microphone to a generation AI and have the generation AI analyze the audio data.

[0031] The analysis unit can analyze data using an algorithm for sound pattern analysis or behavioral pattern analysis. For example, the analysis unit analyzes the sound of a dog barking using sound pattern analysis. For example, the analysis unit can analyze sound patterns using FFT (Fast Fourier Transform) analysis. The analysis unit can also analyze cat behavior using behavioral pattern analysis. For example, the analysis unit analyzes behavioral patterns using a machine learning algorithm. The analysis unit can also analyze data by combining sound pattern analysis and behavioral pattern analysis. For example, the analysis unit combines sound pattern analysis and behavioral pattern analysis to analyze the sound of a dog barking and its tail wagging. In this way, the accuracy of data analysis is improved by using an algorithm for sound pattern analysis or behavioral pattern analysis. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the data collected by the collection unit into a generation AI and have the generation AI analyze the data.

[0032] The estimation unit can use an algorithm that estimates intentions or emotions based on the analysis results. For example, the estimation unit estimates an intention of "wanting to play" from the sound of a dog barking based on the analysis results. The estimation unit can estimate intentions using, for example, a neural network. The estimation unit can also estimate an emotion of "feeling stressed" from a cat's behavior of sharpening its claws based on the analysis results. The estimation unit can estimate emotions using, for example, Bayesian estimation. The estimation unit can also estimate an emotion of "happy" from a dog's behavior of wagging its tail based on the analysis results. The estimation unit can also estimate intentions or emotions using, for example, a machine learning algorithm. Thus, by using an algorithm that estimates intentions or emotions based on the analysis results, the accuracy of estimation is improved. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input the analysis results obtained by the analysis unit to a generation AI and cause the generation AI to estimate intentions and emotions.

[0033] The conversion unit can convert intentions or emotions into human language using natural language processing technology. The conversion unit can convert intentions or emotions into human language using, for example, natural language processing technology. The conversion unit can convert intentions using, for example, morphological analysis. The conversion unit can also convert emotions using grammatical analysis. The conversion unit can also convert intentions or emotions using, for example, semantic analysis. For example, the conversion unit can convert the intention "I want to play" to "I want to play." The conversion unit can also convert the emotion "I'm feeling stressed" to "I'm feeling stressed." The conversion unit can also convert the emotion "happy" to "I'm happy." Thus, the use of natural language processing technology improves the accuracy of intention and emotion conversion. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the intention and emotion data obtained by the estimation unit into a generation AI and have the generation AI convert the data into human language.

[0034] The collection unit uses data on dog or cat meows or behavior as training data, which the generation AI can learn from. The collection unit, for example, uses dog bark data as training data, which the generation AI can learn from. The collection unit, for example, can also use cat behavior data as training data, which the generation AI can learn from. The collection unit, for example, can also use data on dog barks and behavior as training data, which the generation AI can learn from. In this way, the generation AI learns data on dog or cat meows and behavior, which improves the accuracy of translation. The generation AI can perform training using techniques such as GAN (generative adversarial network) and Transformer model. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the collected data into the generation AI and cause the generation AI to perform training.

[0035] The collection unit can estimate the emotion of the dog or cat and adjust the timing of collecting meows or behaviors based on the estimated emotion. For example, if the dog is excited, the collection unit can increase the frequency of meow collection to acquire detailed data. For example, if the cat is relaxed, the collection unit can reduce the frequency of behavior collection to acquire the minimum necessary data. For example, if the dog is anxious, the collection unit can simultaneously collect both meows and behaviors to acquire more diverse data. This allows for more appropriate data to be collected by adjusting the collection timing based on the emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or without AI. For example, the collection unit can estimate the emotion of the dog or cat using an emotion estimation algorithm and adjust the collection timing based on the result.

[0036] When collecting barks and behaviors, the collection unit can analyze the pet's past behavioral history and select the optimal collection method. For example, if a dog has tended to bark during a specific time period in the past, the collection unit can concentrate collection on that time period. For example, if a cat has frequently performed a specific behavior in the past, the collection unit can focus collection on that behavior. For example, if a dog has tended to bark in a specific environment in the past, the collection unit can prioritize collection in that environment. In this way, the optimal collection method can be selected by analyzing the past behavioral history. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input past behavioral history data into a generation AI and have the generation AI perform an analysis to select the optimal collection method.

[0037] When collecting meows and behaviors, the collection unit can filter them based on the pet's current health condition and environment. For example, if a dog's health condition is poor, the collection unit reduces the collection of meows. For example, if a cat is in a new environment, the collection unit can increase the collection of behaviors to obtain data on environmental adaptation. For example, if a dog is in a hospital, the collection unit can adjust the collection frequency to avoid stress. This allows appropriate data to be collected by filtering based on the pet's health condition and environment. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input health condition and environmental data into the generation AI and have the generation AI perform filtering.

[0038] When collecting meows and behaviors, the collection unit can select the optimal collection method depending on the type and age of the pet. For example, in the case of a puppy, the collection unit can collect meows using a high-sensitivity microphone. For example, in the case of an elderly cat, the collection unit can use a camera to record behavior in detail. For example, in the case of a specific dog breed, the collection unit can focus on collecting behaviors unique to that breed. This improves collection accuracy by selecting the optimal collection method depending on the type and age. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data on the type and age of the pet into the generation AI and have the generation AI perform an analysis to select the optimal collection method.

[0039] The collection unit can estimate the emotion of the dog or cat and determine the priority of data to be collected based on the estimated emotion. For example, if the dog is excited, the collection unit can prioritize collecting meow data. For example, if the cat is relaxed, the collection unit can prioritize collecting behavioral data. For example, if the dog is anxious, the collection unit can simultaneously collect both meow data and behavioral data. This allows important data to be collected preferentially by determining the priority of data based on emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or without AI. For example, the collection unit can estimate the emotion of the dog or cat using an emotion estimation algorithm and determine the priority of data to be collected based on the result.

[0040] When collecting sounds and behaviors, the collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the pet. For example, if a dog is in a park, the collection unit can prioritize collecting behavioral data related to play. For example, if a cat is indoors, the collection unit can prioritize collecting relaxed behavioral data. For example, if a dog is at a veterinary clinic, the collection unit can prioritize collecting sound data related to stress. In this way, highly relevant data can be collected preferentially by taking the geographical location information into account. Some or all of the above-described processing in the collection unit may be performed using, or without, AI. For example, the collection unit can input geographical location information data to the generation AI and cause the generation AI to perform an analysis to preferentially collect highly relevant data.

[0041] The collection unit can analyze the social media activity of the pet owner when collecting the pet's sounds and behaviors, and collect related data. For example, when the owner posts a photo of the pet on social media, the collection unit collects the pet's sounds and behaviors at that time. For example, when the owner reports the pet's health condition on social media, the collection unit can collect data at that time. For example, when the owner records the pet's behavior on social media, the collection unit can collect data related to that behavior. In this way, related data can be collected by analyzing the owner's social media activity. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the owner's social media activity data into the generation AI and cause the generation AI to perform an analysis to collect related data.

[0042] When collecting sounds and behaviors, the collection unit can customize the collection method by reflecting the pet's past feedback. For example, if the owner has placed importance on a particular sound in the past, the collection unit can focus on collecting that sound. For example, if the owner has placed importance on a particular behavior in the past, the collection unit can focus on collecting that behavior. For example, the collection unit can adjust the collection method based on feedback provided by the owner in the past. This allows the collection method to be customized by reflecting past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input past feedback data into the generation AI and cause the generation AI to perform analysis to customize the collection method.

[0043] The analysis unit can estimate the emotion of a dog or cat and adjust the analysis method of the sound wave pattern and behavior pattern based on the estimated emotion. For example, if a dog is excited, the analysis unit can focus on analyzing high-frequency sound wave patterns. For example, if a cat is relaxed, the analysis unit can focus on analyzing low-frequency sound wave patterns. For example, if a dog is anxious, the analysis unit can simultaneously analyze both the sound wave pattern and the behavior pattern. This improves analysis accuracy by adjusting the analysis method based on the emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can estimate the emotion of a dog or cat using an emotion estimation algorithm and adjust the analysis method based on the result.

[0044] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the barks and behavior. For example, if a dog's bark is very important, the analysis unit can perform a detailed sound wave analysis. For example, if a cat's behavior is very important, the analysis unit can perform a detailed behavior analysis. For example, if both a dog's bark and behavior are important, the analysis unit can perform a detailed analysis of both. This improves the accuracy of the analysis by adjusting the level of detail of the analysis based on the importance. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input importance data of the barks and behavior into the generation AI and cause the generation AI to perform an analysis to adjust the level of detail of the analysis.

[0045] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the bark or behavior. For example, if a dog's bark is related to play, the analysis unit can apply an analysis algorithm specialized for play. For example, if a cat's behavior is related to stress, the analysis unit can apply an analysis algorithm specialized for stress. For example, if a dog's bark is related to vigilance, the analysis unit can apply an analysis algorithm specialized for vigilance. By applying different analysis algorithms depending on the category, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input category data of the bark or behavior into the generation AI and cause the generation AI to perform an analysis to select an appropriate analysis algorithm.

[0046] During analysis, the analysis unit can improve the accuracy of the analysis by referring to past analysis results of the pet. The analysis unit can improve the current analysis accuracy by referring to, for example, past analysis results of the barks of a dog. The analysis unit can improve the current analysis accuracy by referring to, for example, past analysis results of the behavior of a cat. The analysis unit can improve the current analysis accuracy by referring to, for example, past analysis results of the barks and behavior of a dog. In this way, by referring to past analysis results, the analysis accuracy is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past analysis result data into the generation AI and cause the generation AI to perform analysis to improve the analysis accuracy.

[0047] The analysis unit can estimate the emotion of the dog or cat and determine the analysis priority based on the estimated emotion. For example, if the dog is excited, the analysis unit can prioritize the analysis of the dog's meow. For example, if the cat is relaxed, the analysis unit can prioritize the analysis of the dog's behavior. For example, if the dog is anxious, the analysis unit can prioritize the analysis of both the dog's meow and its behavior. This allows important data to be analyzed preferentially by determining the analysis priority based on emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can estimate the emotion of the dog or cat using an emotion estimation algorithm and determine the analysis priority based on the result.

[0048] During analysis, the analysis unit can determine the priority of analysis based on the time when the barks and behaviors were collected. For example, the analysis unit can prioritize analysis immediately after a dog's bark is collected. For example, the analysis unit can prioritize analysis immediately after a cat's behavior is collected. For example, if a dog's bark and behavior are collected simultaneously, the analysis unit can prioritize analysis of both. This enables timely analysis by determining the priority of analysis based on the time of collection. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input collection time data into the generation AI and have the generation AI perform an analysis to determine the priority of analysis.

[0049] During analysis, the analysis unit can adjust the order of analysis based on the relevance of barks and behaviors. For example, if a dog's bark and behavior are related, the analysis unit can analyze both simultaneously. For example, if a cat's bark and behavior are related, the analysis unit can analyze both simultaneously. For example, if a dog's bark and behavior are not related, the analysis unit can analyze them separately. This enables efficient analysis by adjusting the order of analysis based on the relevance. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input relevance data of barks and behaviors into the generation AI and cause the generation AI to perform an analysis to adjust the order of analysis.

[0050] During analysis, the analysis unit can adjust the level of detail of the analysis according to the pet owner's level of expertise. For example, if the owner has expertise, the analysis unit can provide detailed analysis results. For example, if the owner does not have expertise, the analysis unit can provide concise analysis results. For example, if the owner has medium expertise, the analysis unit can provide medium-level analysis results. This allows appropriate analysis results to be provided by adjusting the level of detail of the analysis according to the owner's level of expertise. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input the owner's expertise level data into the generation AI and cause the generation AI to perform an analysis to adjust the level of detail of the analysis.

[0051] The estimation unit can estimate the emotion of the dog or cat and adjust the intention or emotion estimation method based on the estimated emotion. For example, if the dog is excited, the estimation unit can prioritize an intention to play. For example, if the cat is relaxed, the estimation unit can prioritize an emotion of relief. For example, if the dog is anxious, the estimation unit can prioritize the cause of the anxiety. This improves estimation accuracy by adjusting the estimation method based on the emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the estimation unit may be performed using an AI, or may be performed without using an AI. For example, the estimation unit can estimate the emotion of the dog or cat using an emotion estimation algorithm and adjust the intention or emotion estimation method based on the result.

[0052] The estimation unit can adjust the level of detail of the estimation based on the analysis results of the bark and behavior during estimation. For example, if the analysis result of a dog's bark is detailed, the estimation unit can estimate a detailed intention. For example, if the analysis result of a cat's behavior is detailed, the estimation unit can estimate a detailed emotion. For example, if the analysis result of both the dog's bark and behavior is detailed, the estimation unit can estimate the detailed intention and emotion of both. This improves the estimation accuracy by adjusting the level of detail of the estimation based on the analysis results. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input analysis result data to a generation AI and cause the generation AI to perform an analysis to adjust the level of detail of the estimation.

[0053] The estimation unit can apply different estimation algorithms depending on the category of the bark or behavior during estimation. For example, if a dog's bark is related to play, the estimation unit can apply an estimation algorithm specialized for play. For example, if a cat's behavior is related to stress, the estimation unit can apply an estimation algorithm specialized for stress. For example, if a dog's bark is related to vigilance, the estimation unit can apply an estimation algorithm specialized for vigilance. In this way, by applying different estimation algorithms depending on the category, estimation accuracy is improved. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input category data of the bark or behavior into the generation AI and cause the generation AI to perform an analysis to select an appropriate estimation algorithm.

[0054] The estimation unit can improve the accuracy of estimation by referring to past estimation results of the pet during estimation. The estimation unit can improve the current estimation accuracy by referring to, for example, past estimation results of the dog's barks. The estimation unit can improve the current estimation accuracy by referring to, for example, past estimation results of the cat's behavior. The estimation unit can improve the current estimation accuracy by referring to, for example, past estimation results of the dog's barks and behavior. In this way, by referring to past estimation results, the estimation accuracy is improved. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input past estimation result data into the generation AI and cause the generation AI to perform analysis to improve the estimation accuracy.

[0055] The estimation unit can estimate the emotion of the dog or cat and determine the priority of estimation based on the estimated emotion. For example, if the dog is excited, the estimation unit can prioritize estimating an intention to play. For example, if the cat is relaxed, the estimation unit can prioritize estimating an emotion of relief. For example, if the dog is anxious, the estimation unit can prioritize estimating the cause of the anxiety. In this way, by determining the priority of estimation based on emotion, important intentions and emotions can be preferentially estimated. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the estimation unit can estimate the emotion of the dog or cat using an emotion estimation algorithm and determine the priority of estimation based on the result.

[0056] During estimation, the estimation unit can determine the priority of estimations based on the time when the barks and behaviors were collected. For example, the estimation unit can prioritize estimation immediately after a dog's bark is collected. For example, the estimation unit can prioritize estimation immediately after a cat's behavior is collected. For example, if a dog's bark and behavior are collected simultaneously, the estimation unit can prioritize both estimates. This enables timely estimation by determining the priority of estimations based on the time of collection. Some or all of the above-described processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input collection time data into the generation AI and cause the generation AI to perform an analysis to determine the priority of estimations.

[0057] The estimation unit can adjust the order of estimation based on the relevance of barks and behaviors during estimation. For example, if a dog's bark and behavior are related, the estimation unit can estimate both simultaneously. For example, if a cat's bark and behavior are related, the estimation unit can estimate both simultaneously. For example, if a dog's bark and behavior are not related, the estimation unit can estimate them separately. This enables efficient estimation by adjusting the order of estimation based on the relevance. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input relevance data of barks and behaviors into the generation AI and cause the generation AI to perform analysis to adjust the order of estimation.

[0058] During estimation, the estimation unit can adjust the level of detail of the estimation according to the pet owner's level of expertise. For example, if the owner has expertise, the estimation unit can provide a detailed estimation result. For example, if the owner does not have expertise, the estimation unit can provide a concise estimation result. For example, if the owner has medium expertise, the estimation unit can provide a medium-level of detail estimation result. This allows for adjusting the level of detail of the estimation according to the owner's level of expertise to provide an appropriate estimation result. Some or all of the above-described processing in the estimation unit may be performed using AI, for example, or may be performed without using AI. For example, the estimation unit can input the owner's expertise level data into the generation AI and cause the generation AI to perform an analysis to adjust the level of detail of the estimation.

[0059] The conversion unit can estimate the emotion of the dog or cat and adjust the intent or emotion conversion method based on the estimated emotion. For example, if the dog is excited, the conversion unit can prioritize converting the intent to play. For example, if the cat is relaxed, the conversion unit can prioritize converting the emotion of relief. For example, if the dog is anxious, the conversion unit can prioritize converting the cause of the anxiety. This improves conversion accuracy by adjusting the conversion method based on the emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the conversion unit can estimate the emotion of the dog or cat using an emotion estimation algorithm and adjust the intent or emotion conversion method based on the result.

[0060] The conversion unit can adjust the level of detail of the conversion based on the importance of the intention or emotion during conversion. For example, if the intention of the dog is very important, the conversion unit can perform a detailed conversion. For example, if the emotion of the cat is very important, the conversion unit can perform a detailed conversion. For example, if both the intention and emotion of the dog are important, the conversion unit can perform a detailed conversion of both. This improves the conversion accuracy by adjusting the level of detail of the conversion based on the importance. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input importance data of the intention or emotion into the generation AI and cause the generation AI to perform an analysis to adjust the level of detail of the conversion.

[0061] During conversion, the conversion unit can apply different conversion algorithms depending on the category of the intention or emotion. For example, if a dog's intention is related to play, the conversion unit can apply a conversion algorithm specialized for play. For example, if a cat's emotion is related to stress, the conversion unit can apply a conversion algorithm specialized for stress. For example, if a dog's intention is related to vigilance, the conversion unit can apply a conversion algorithm specialized for vigilance. In this way, by applying different conversion algorithms depending on the category, conversion accuracy is improved. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input category data of intentions and emotions into the generation AI and cause the generation AI to perform analysis to select an appropriate conversion algorithm.

[0062] During conversion, the conversion unit can improve the accuracy of the conversion by referring to past conversion results for pets. The conversion unit can improve the current conversion accuracy by referring to, for example, past intention conversion results for dogs. The conversion unit can improve the current conversion accuracy by referring to, for example, past emotion conversion results for cats. The conversion unit can improve the current conversion accuracy by referring to, for example, past intention and emotion conversion results for dogs. In this way, by referring to past conversion results, the conversion accuracy is improved. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input past conversion result data into the generation AI and cause the generation AI to perform analysis to improve the conversion accuracy.

[0063] The conversion unit can estimate the emotion of the dog or cat and determine the priority of conversion based on the estimated emotion. For example, if the dog is excited, the conversion unit can prioritize converting an intention to play. For example, if the cat is relaxed, the conversion unit can prioritize converting an emotion of relief. For example, if the dog is anxious, the conversion unit can prioritize converting the cause of the anxiety. In this way, by determining the priority of conversion based on emotion, important intentions and emotions can be preferentially converted. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can estimate the emotion of the dog or cat using an emotion estimation algorithm and determine the priority of conversion based on the result.

[0064] During conversion, the conversion unit can determine the priority of conversion based on the time when the intention or emotion was collected. For example, the conversion unit can prioritize conversion immediately after the dog's intention is collected. For example, the conversion unit can prioritize conversion immediately after the cat's emotion is collected. For example, if the dog's intention and emotion are collected simultaneously, the conversion unit can prioritize conversion of both. This enables timely conversion by determining the priority of conversion based on the time of collection. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input collection time data into a generation AI and cause the generation AI to perform analysis to determine the priority of conversion.

[0065] The conversion unit can adjust the order of conversion based on the relevance of the intention or emotion during conversion. For example, if the intention and emotion of a dog are related, the conversion unit can perform both conversions simultaneously. For example, if the intention and emotion of a cat are related, the conversion unit can perform both conversions simultaneously. For example, if the intention and emotion of a dog are not related, the conversion unit can perform the conversions separately. This enables efficient conversion by adjusting the order of conversion based on the relevance. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input relevance data of intentions and emotions into a generation AI and cause the generation AI to perform an analysis to adjust the order of conversion.

[0066] During conversion, the conversion unit can adjust the level of detail of the conversion according to the pet owner's level of expertise. For example, if the owner has expertise, the conversion unit can provide a detailed conversion result. For example, if the owner does not have expertise, the conversion unit can provide a concise conversion result. For example, if the owner has medium expertise, the conversion unit can provide a medium-level of detail conversion result. This allows for adjusting the level of detail of the conversion according to the owner's level of expertise to provide an appropriate conversion result. Some or all of the above-described processing in the conversion unit may be performed using AI, for example, or may be performed without using AI. For example, the conversion unit can input the owner's expertise level data into the generation AI and cause the generation AI to perform an analysis to adjust the level of detail of the conversion.

[0067] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0068] The pet translation system can also include a health management unit that monitors the pet's health. The health management unit collects biometric data such as the pet's body temperature, heart rate, and activity level and sends it to the analysis unit. The analysis unit evaluates the pet's health based on this data and can notify the owner if an abnormality is detected. For example, if a dog's body temperature is higher than normal, the analysis unit can predict the possibility of a fever and notify the owner, "The body temperature is high, so please be careful." Similarly, if a cat's heart rate is abnormally high, the analysis unit can predict the possibility of stress or excitement and notify the owner, "The heart rate is high, so please help the cat relax." This allows for real-time monitoring of the pet's health and early detection of abnormalities.

[0069] The pet translation system can also include a history management unit that records the pet's behavioral history. The history management unit chronologically records the meows and behavioral data obtained from the collection unit and provides it to the analysis unit. The analysis unit analyzes the pet's behavioral patterns based on this history data and can notify the owner if abnormal behavior occurs. For example, if a dog starts barking frequently at times when it normally does not bark, the analysis unit can infer the cause and notify the owner that "there is something abnormal in the recent behavioral pattern." Similarly, if a cat starts sharpening its claws frequently in a specific place, the analysis unit can infer that there may be some kind of stress factor in that place and notify the owner that "you need to be careful about your behavior in that particular place." This allows for understanding pet behavior patterns and early detection of abnormalities.

[0070] The pet translation system may further include a preference learning unit that learns the pet's preferences. The preference learning unit learns the pet's preferences based on the data obtained from the collection unit and provides the learned preferences to the analysis unit. The analysis unit can estimate the pet's preferences based on this data and make suggestions to the owner. For example, if a dog wags its tail in response to a certain piece of music, the analysis unit may estimate that the dog likes that music and suggest to the owner, "Play this music, your dog will be happy." Similarly, if a cat shows interest in a certain toy, the analysis unit may estimate that the toy is the cat's favorite and suggest to the owner, "Your cat will enjoy playing with this toy." This allows for understanding pet preferences and improving communication.

[0071] The pet translation system can further include a prediction unit that predicts the pet's behavior. The prediction unit predicts the pet's next behavior based on the data obtained from the collection unit and the data from the history management unit, and notifies the owner. For example, if a dog repeatedly requests walks at a specific time of day, the prediction unit can estimate that the dog is likely to request walks at that time and notify the owner that "it's almost time for a walk." Similarly, if a cat repeatedly requests food at a specific time of day, the prediction unit can estimate that the cat is likely to request food at that time and notify the owner that "it's almost time for food." This allows the pet's behavior to be predicted, allowing the owner to take appropriate action.

[0072] The processing flow of the first embodiment will be briefly explained below.

[0073] Step 1: The collection unit collects the meows and behaviors of dogs and cats. The collection unit can collect the meows and behaviors using, for example, a microphone or a camera. Specifically, the sound of a dog barking is collected using a microphone, and the behavior of a cat sharpening its claws or a dog wagging its tail is recorded using a camera. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the data using algorithms for sound wave pattern analysis and behavioral pattern analysis. Specifically, the analysis unit uses sound wave pattern analysis to analyze the sound of a dog barking, and behavioral pattern analysis to analyze the behavior of a cat sharpening its claws. It is also possible to analyze data by combining sound wave pattern analysis and behavioral pattern analysis. Step 3: The estimation unit infers the intention and emotion based on the analysis results obtained by the analysis unit. Specifically, based on the analysis results, it can infer the intention of "wanting to play" from the sound of a dog barking, and the emotion of "feeling stressed" from the behavior of a cat sharpening its claws. It can also infer the emotion of "happiness" from the behavior of a dog wagging its tail. Step 4: The conversion unit converts the intention and emotion estimated by the estimation unit into human language. The conversion unit uses natural language processing technology to convert the intention and emotion into human language. Specifically, the conversion unit converts the intention "I want to play" to "I want to play," and the emotion "I'm feeling stressed" to "I'm feeling stressed." It can also convert the emotion "I'm happy" to "I'm happy."

[0074] (Example 2) A pet translation system according to an embodiment of the present invention uses a generation AI to translate the meows and behaviors of dogs and cats. The pet translation system collects the meows and behaviors of dogs and cats, analyzes them, infers their intentions and emotions, and converts them into human language. For example, the pet translation system records behaviors such as dogs barking, cats meowing, dogs wagging their tails, and cats sharpening their claws. This data is input into the generation AI. The generation AI then analyzes the collected data to infer the intentions and emotions of the dogs and cats. The generation AI analyzes the sonic patterns of the meows and behavioral characteristics and, based on the analysis, infers what the dogs and cats are thinking and doing. For example, a dog's barking sonic pattern can be used to infer that the dog or cat "wants to play," and a cat's claw sharpening behavior can be used to infer that the dog or cat "is stressed." The generation AI then converts the inferred intentions and emotions into human language. For example, if the inferred intention is "I want to play," the system translates it into "I want to play." This translation result is provided to the pet owner. This allows owners to understand what their pets are thinking and what they want to do. This deepens communication with their pets and strengthens the bond between them. Pet translation systems can deepen communication between owners and pets and build better relationships. For example, when an owner inputs their dog's bark into a translator, the generating AI analyzes the bark and provides a translation result such as "I want to play." This allows the owner to understand that their dog wants to play and play together. Similarly, when a cat sharpens its claws into a translator, the generating AI analyzes the behavior and provides a translation result such as "I'm stressed." This allows the owner to understand that their cat is stressed and take appropriate measures. In this way, pet translation systems using generating AI can be a powerful tool for deepening communication between owners and pets and building better relationships.

[0075] The pet translation system according to the embodiment includes a collection unit, an analysis unit, an estimation unit, and a conversion unit. The collection unit collects sounds and behaviors of dogs and cats. The collection unit can collect the sounds and behaviors using, for example, a microphone or a camera. The collection unit can collect, for example, the sound of a dog barking using a microphone. The collection unit can also record the behavior of a cat sharpening its claws using a camera. The collection unit can also record the behavior of a dog wagging its tail using a camera. The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the data using, for example, algorithms for sound pattern analysis and behavior pattern analysis. The analysis unit can analyze the sound of a dog barking using sound pattern analysis. The analysis unit can also analyze the behavior of a cat sharpening its claws using behavior pattern analysis. The analysis unit can also analyze the data by combining sound pattern analysis and behavior pattern analysis. The estimation unit estimates intentions and emotions based on the analysis results obtained by the analysis unit. For example, the estimation unit estimates the intention of "wanting to play" from the sound of a dog barking based on the analysis result. The estimation unit can also estimate the emotion of "feeling stressed" from the behavior of a cat sharpening its claws based on the analysis result. The estimation unit can also estimate the emotion of "happy" from the behavior of a dog wagging its tail based on the analysis result. The conversion unit converts the intention and emotion estimated by the estimation unit into human language. The conversion unit converts the intention and emotion into human language using, for example, natural language processing technology. For example, the conversion unit converts the intention of "wanting to play" into "I want to play." The conversion unit can also convert the emotion of "feeling stressed" into "I'm stressed." The conversion unit can also convert the emotion of "happy" into "I'm happy." In this way, the pet translation system according to the embodiment can deepen communication between owners and pets.

[0076] The collection unit can collect sounds or behaviors using a microphone or a camera. For example, the collection unit can collect the sound of a dog barking using a microphone. For example, the collection unit can collect sounds from a specific direction using a directional microphone. The collection unit can also record the behavior of a cat using a wide-angle camera. For example, the collection unit can record the behavior of a cat sharpening its claws using a wide-angle camera. The collection unit can also combine a microphone and a camera to simultaneously collect the sound of a dog barking and the behavior of a dog wagging its tail using a combination of a microphone and a camera. In this way, the use of a microphone or a camera improves the accuracy of collecting sounds and behaviors. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input audio data collected by a microphone to a generation AI and have the generation AI analyze the audio data.

[0077] The analysis unit can analyze data using an algorithm for sound pattern analysis or behavioral pattern analysis. For example, the analysis unit analyzes the sound of a dog barking using sound pattern analysis. For example, the analysis unit can analyze sound patterns using FFT (Fast Fourier Transform) analysis. The analysis unit can also analyze cat behavior using behavioral pattern analysis. For example, the analysis unit analyzes behavioral patterns using a machine learning algorithm. The analysis unit can also analyze data by combining sound pattern analysis and behavioral pattern analysis. For example, the analysis unit combines sound pattern analysis and behavioral pattern analysis to analyze the sound of a dog barking and its tail wagging. In this way, the accuracy of data analysis is improved by using an algorithm for sound pattern analysis or behavioral pattern analysis. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the data collected by the collection unit into a generation AI and have the generation AI analyze the data.

[0078] The estimation unit can use an algorithm that estimates intentions or emotions based on the analysis results. For example, the estimation unit estimates an intention of "wanting to play" from the sound of a dog barking based on the analysis results. The estimation unit can estimate intentions using, for example, a neural network. The estimation unit can also estimate an emotion of "feeling stressed" from a cat's behavior of sharpening its claws based on the analysis results. The estimation unit can estimate emotions using, for example, Bayesian estimation. The estimation unit can also estimate an emotion of "happy" from a dog's behavior of wagging its tail based on the analysis results. The estimation unit can also estimate intentions or emotions using, for example, a machine learning algorithm. Thus, by using an algorithm that estimates intentions or emotions based on the analysis results, the accuracy of estimation is improved. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input the analysis results obtained by the analysis unit to a generation AI and cause the generation AI to estimate intentions and emotions.

[0079] The conversion unit can convert intentions or emotions into human language using natural language processing technology. The conversion unit can convert intentions or emotions into human language using, for example, natural language processing technology. The conversion unit can convert intentions using, for example, morphological analysis. The conversion unit can also convert emotions using grammatical analysis. The conversion unit can also convert intentions or emotions using, for example, semantic analysis. For example, the conversion unit can convert the intention "I want to play" to "I want to play." The conversion unit can also convert the emotion "I'm feeling stressed" to "I'm feeling stressed." The conversion unit can also convert the emotion "happy" to "I'm happy." Thus, the use of natural language processing technology improves the accuracy of intention and emotion conversion. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the intention and emotion data obtained by the estimation unit into a generation AI and have the generation AI convert the data into human language.

[0080] The collection unit uses data on dog or cat meows or behavior as training data, which the generation AI can learn from. The collection unit, for example, uses dog bark data as training data, which the generation AI can learn from. The collection unit, for example, can also use cat behavior data as training data, which the generation AI can learn from. The collection unit, for example, can also use data on dog barks and behavior as training data, which the generation AI can learn from. In this way, the generation AI learns data on dog or cat meows and behavior, which improves the accuracy of translation. The generation AI can perform training using techniques such as GAN (generative adversarial network) and Transformer model. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the collected data into the generation AI and cause the generation AI to perform training.

[0081] The collection unit can estimate the emotion of the dog or cat and adjust the timing of collecting meows or behaviors based on the estimated emotion. For example, if the dog is excited, the collection unit can increase the frequency of meow collection to acquire detailed data. For example, if the cat is relaxed, the collection unit can reduce the frequency of behavior collection to acquire the minimum necessary data. For example, if the dog is anxious, the collection unit can simultaneously collect both meows and behaviors to acquire more diverse data. This allows for more appropriate data to be collected by adjusting the collection timing based on the emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or without AI. For example, the collection unit can estimate the emotion of the dog or cat using an emotion estimation algorithm and adjust the collection timing based on the result.

[0082] When collecting barks and behaviors, the collection unit can analyze the pet's past behavioral history and select the optimal collection method. For example, if a dog has tended to bark during a specific time period in the past, the collection unit can concentrate collection on that time period. For example, if a cat has frequently performed a specific behavior in the past, the collection unit can focus collection on that behavior. For example, if a dog has tended to bark in a specific environment in the past, the collection unit can prioritize collection in that environment. In this way, the optimal collection method can be selected by analyzing the past behavioral history. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input past behavioral history data into a generation AI and have the generation AI perform an analysis to select the optimal collection method.

[0083] When collecting meows and behaviors, the collection unit can filter them based on the pet's current health condition and environment. For example, if a dog's health condition is poor, the collection unit reduces the collection of meows. For example, if a cat is in a new environment, the collection unit can increase the collection of behaviors to obtain data on environmental adaptation. For example, if a dog is in a hospital, the collection unit can adjust the collection frequency to avoid stress. This allows appropriate data to be collected by filtering based on the pet's health condition and environment. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input health condition and environmental data into the generation AI and have the generation AI perform filtering.

[0084] When collecting meows and behaviors, the collection unit can select the optimal collection method depending on the type and age of the pet. For example, in the case of a puppy, the collection unit can collect meows using a high-sensitivity microphone. For example, in the case of an elderly cat, the collection unit can use a camera to record behavior in detail. For example, in the case of a specific dog breed, the collection unit can focus on collecting behaviors unique to that breed. This improves collection accuracy by selecting the optimal collection method depending on the type and age. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data on the type and age of the pet into the generation AI and have the generation AI perform an analysis to select the optimal collection method.

[0085] The collection unit can estimate the emotion of the dog or cat and determine the priority of data to be collected based on the estimated emotion. For example, if the dog is excited, the collection unit can prioritize collecting meow data. For example, if the cat is relaxed, the collection unit can prioritize collecting behavioral data. For example, if the dog is anxious, the collection unit can simultaneously collect both meow data and behavioral data. This allows important data to be collected preferentially by determining the priority of data based on emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or without AI. For example, the collection unit can estimate the emotion of the dog or cat using an emotion estimation algorithm and determine the priority of data to be collected based on the result.

[0086] When collecting sounds and behaviors, the collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the pet. For example, if a dog is in a park, the collection unit can prioritize collecting behavioral data related to play. For example, if a cat is indoors, the collection unit can prioritize collecting relaxed behavioral data. For example, if a dog is at a veterinary clinic, the collection unit can prioritize collecting sound data related to stress. In this way, highly relevant data can be collected preferentially by taking the geographical location information into account. Some or all of the above-described processing in the collection unit may be performed using, or without, AI. For example, the collection unit can input geographical location information data to the generation AI and cause the generation AI to perform an analysis to preferentially collect highly relevant data.

[0087] The collection unit can analyze the social media activity of the pet owner when collecting the pet's sounds and behaviors, and collect related data. For example, when the owner posts a photo of the pet on social media, the collection unit collects the pet's sounds and behaviors at that time. For example, when the owner reports the pet's health condition on social media, the collection unit can collect data at that time. For example, when the owner records the pet's behavior on social media, the collection unit can collect data related to that behavior. In this way, related data can be collected by analyzing the owner's social media activity. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the owner's social media activity data into the generation AI and cause the generation AI to perform an analysis to collect related data.

[0088] When collecting sounds and behaviors, the collection unit can customize the collection method by reflecting the pet's past feedback. For example, if the owner has placed importance on a particular sound in the past, the collection unit can focus on collecting that sound. For example, if the owner has placed importance on a particular behavior in the past, the collection unit can focus on collecting that behavior. For example, the collection unit can adjust the collection method based on feedback provided by the owner in the past. This allows the collection method to be customized by reflecting past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input past feedback data into the generation AI and cause the generation AI to perform analysis to customize the collection method.

[0089] The analysis unit can estimate the emotion of a dog or cat and adjust the analysis method of the sound wave pattern and behavior pattern based on the estimated emotion. For example, if a dog is excited, the analysis unit can focus on analyzing high-frequency sound wave patterns. For example, if a cat is relaxed, the analysis unit can focus on analyzing low-frequency sound wave patterns. For example, if a dog is anxious, the analysis unit can simultaneously analyze both the sound wave pattern and the behavior pattern. This improves analysis accuracy by adjusting the analysis method based on the emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can estimate the emotion of a dog or cat using an emotion estimation algorithm and adjust the analysis method based on the result.

[0090] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the barks and behavior. For example, if a dog's bark is very important, the analysis unit can perform a detailed sound wave analysis. For example, if a cat's behavior is very important, the analysis unit can perform a detailed behavior analysis. For example, if both a dog's bark and behavior are important, the analysis unit can perform a detailed analysis of both. This improves the accuracy of the analysis by adjusting the level of detail of the analysis based on the importance. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input importance data of the barks and behavior into the generation AI and cause the generation AI to perform an analysis to adjust the level of detail of the analysis.

[0091] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the bark or behavior. For example, if a dog's bark is related to play, the analysis unit can apply an analysis algorithm specialized for play. For example, if a cat's behavior is related to stress, the analysis unit can apply an analysis algorithm specialized for stress. For example, if a dog's bark is related to vigilance, the analysis unit can apply an analysis algorithm specialized for vigilance. By applying different analysis algorithms depending on the category, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input category data of the bark or behavior into the generation AI and cause the generation AI to perform an analysis to select an appropriate analysis algorithm.

[0092] During analysis, the analysis unit can improve the accuracy of the analysis by referring to past analysis results of the pet. The analysis unit can improve the current analysis accuracy by referring to, for example, past analysis results of the barks of a dog. The analysis unit can improve the current analysis accuracy by referring to, for example, past analysis results of the behavior of a cat. The analysis unit can improve the current analysis accuracy by referring to, for example, past analysis results of the barks and behavior of a dog. In this way, by referring to past analysis results, the analysis accuracy is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past analysis result data into the generation AI and cause the generation AI to perform analysis to improve the analysis accuracy.

[0093] The analysis unit can estimate the emotion of the dog or cat and determine the analysis priority based on the estimated emotion. For example, if the dog is excited, the analysis unit can prioritize the analysis of the dog's meow. For example, if the cat is relaxed, the analysis unit can prioritize the analysis of the dog's behavior. For example, if the dog is anxious, the analysis unit can prioritize the analysis of both the dog's meow and its behavior. This allows important data to be analyzed preferentially by determining the analysis priority based on emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can estimate the emotion of the dog or cat using an emotion estimation algorithm and determine the analysis priority based on the result.

[0094] During analysis, the analysis unit can determine the priority of analysis based on the time when the barks and behaviors were collected. For example, the analysis unit can prioritize analysis immediately after a dog's bark is collected. For example, the analysis unit can prioritize analysis immediately after a cat's behavior is collected. For example, if a dog's bark and behavior are collected simultaneously, the analysis unit can prioritize analysis of both. This enables timely analysis by determining the priority of analysis based on the time of collection. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input collection time data into the generation AI and have the generation AI perform an analysis to determine the priority of analysis.

[0095] During analysis, the analysis unit can adjust the order of analysis based on the relevance of barks and behaviors. For example, if a dog's bark and behavior are related, the analysis unit can analyze both simultaneously. For example, if a cat's bark and behavior are related, the analysis unit can analyze both simultaneously. For example, if a dog's bark and behavior are not related, the analysis unit can analyze them separately. This enables efficient analysis by adjusting the order of analysis based on the relevance. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input relevance data of barks and behaviors into the generation AI and cause the generation AI to perform an analysis to adjust the order of analysis.

[0096] During analysis, the analysis unit can adjust the level of detail of the analysis according to the pet owner's level of expertise. For example, if the owner has expertise, the analysis unit can provide detailed analysis results. For example, if the owner does not have expertise, the analysis unit can provide concise analysis results. For example, if the owner has medium expertise, the analysis unit can provide medium-level analysis results. This allows appropriate analysis results to be provided by adjusting the level of detail of the analysis according to the owner's level of expertise. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input the owner's expertise level data into the generation AI and cause the generation AI to perform an analysis to adjust the level of detail of the analysis.

[0097] The estimation unit can estimate the emotion of the dog or cat and adjust the intention or emotion estimation method based on the estimated emotion. For example, if the dog is excited, the estimation unit can prioritize an intention to play. For example, if the cat is relaxed, the estimation unit can prioritize an emotion of relief. For example, if the dog is anxious, the estimation unit can prioritize the cause of the anxiety. This improves estimation accuracy by adjusting the estimation method based on the emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the estimation unit may be performed using an AI, or may be performed without using an AI. For example, the estimation unit can estimate the emotion of the dog or cat using an emotion estimation algorithm and adjust the intention or emotion estimation method based on the result.

[0098] The estimation unit can adjust the level of detail of the estimation based on the analysis results of the bark and behavior during estimation. For example, if the analysis result of a dog's bark is detailed, the estimation unit can estimate a detailed intention. For example, if the analysis result of a cat's behavior is detailed, the estimation unit can estimate a detailed emotion. For example, if the analysis result of both the dog's bark and behavior is detailed, the estimation unit can estimate the detailed intention and emotion of both. This improves the estimation accuracy by adjusting the level of detail of the estimation based on the analysis results. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input analysis result data to a generation AI and cause the generation AI to perform an analysis to adjust the level of detail of the estimation.

[0099] The estimation unit can apply different estimation algorithms depending on the category of the bark or behavior during estimation. For example, if a dog's bark is related to play, the estimation unit can apply an estimation algorithm specialized for play. For example, if a cat's behavior is related to stress, the estimation unit can apply an estimation algorithm specialized for stress. For example, if a dog's bark is related to vigilance, the estimation unit can apply an estimation algorithm specialized for vigilance. In this way, by applying different estimation algorithms depending on the category, estimation accuracy is improved. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input category data of the bark or behavior into the generation AI and cause the generation AI to perform an analysis to select an appropriate estimation algorithm.

[0100] The estimation unit can improve the accuracy of estimation by referring to past estimation results of the pet during estimation. The estimation unit can improve the current estimation accuracy by referring to, for example, past estimation results of the dog's barks. The estimation unit can improve the current estimation accuracy by referring to, for example, past estimation results of the cat's behavior. The estimation unit can improve the current estimation accuracy by referring to, for example, past estimation results of the dog's barks and behavior. In this way, by referring to past estimation results, the estimation accuracy is improved. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input past estimation result data into the generation AI and cause the generation AI to perform analysis to improve the estimation accuracy.

[0101] The estimation unit can estimate the emotion of the dog or cat and determine the priority of estimation based on the estimated emotion. For example, if the dog is excited, the estimation unit can prioritize estimating an intention to play. For example, if the cat is relaxed, the estimation unit can prioritize estimating an emotion of relief. For example, if the dog is anxious, the estimation unit can prioritize estimating the cause of the anxiety. In this way, by determining the priority of estimation based on emotion, important intentions and emotions can be preferentially estimated. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the estimation unit can estimate the emotion of the dog or cat using an emotion estimation algorithm and determine the priority of estimation based on the result.

[0102] During estimation, the estimation unit can determine the priority of estimations based on the time when the barks and behaviors were collected. For example, the estimation unit can prioritize estimation immediately after a dog's bark is collected. For example, the estimation unit can prioritize estimation immediately after a cat's behavior is collected. For example, if a dog's bark and behavior are collected simultaneously, the estimation unit can prioritize both estimates. This enables timely estimation by determining the priority of estimations based on the time of collection. Some or all of the above-described processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input collection time data into the generation AI and cause the generation AI to perform an analysis to determine the priority of estimations.

[0103] The estimation unit can adjust the order of estimation based on the relevance of barks and behaviors during estimation. For example, if a dog's bark and behavior are related, the estimation unit can estimate both simultaneously. For example, if a cat's bark and behavior are related, the estimation unit can estimate both simultaneously. For example, if a dog's bark and behavior are not related, the estimation unit can estimate them separately. This enables efficient estimation by adjusting the order of estimation based on the relevance. Some or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input relevance data of barks and behaviors into the generation AI and cause the generation AI to perform analysis to adjust the order of estimation.

[0104] During estimation, the estimation unit can adjust the level of detail of the estimation according to the pet owner's level of expertise. For example, if the owner has expertise, the estimation unit can provide a detailed estimation result. For example, if the owner does not have expertise, the estimation unit can provide a concise estimation result. For example, if the owner has medium expertise, the estimation unit can provide a medium-level of detail estimation result. This allows for adjusting the level of detail of the estimation according to the owner's level of expertise to provide an appropriate estimation result. Some or all of the above-described processing in the estimation unit may be performed using AI, for example, or may be performed without using AI. For example, the estimation unit can input the owner's expertise level data into the generation AI and cause the generation AI to perform an analysis to adjust the level of detail of the estimation.

[0105] The conversion unit can estimate the emotion of the dog or cat and adjust the intent or emotion conversion method based on the estimated emotion. For example, if the dog is excited, the conversion unit can prioritize converting the intent to play. For example, if the cat is relaxed, the conversion unit can prioritize converting the emotion of relief. For example, if the dog is anxious, the conversion unit can prioritize converting the cause of the anxiety. This improves conversion accuracy by adjusting the conversion method based on the emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the conversion unit can estimate the emotion of the dog or cat using an emotion estimation algorithm and adjust the intent or emotion conversion method based on the result.

[0106] The conversion unit can adjust the level of detail of the conversion based on the importance of the intention or emotion during conversion. For example, if the intention of the dog is very important, the conversion unit can perform a detailed conversion. For example, if the emotion of the cat is very important, the conversion unit can perform a detailed conversion. For example, if both the intention and emotion of the dog are important, the conversion unit can perform a detailed conversion of both. This improves the conversion accuracy by adjusting the level of detail of the conversion based on the importance. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input importance data of the intention or emotion into the generation AI and cause the generation AI to perform an analysis to adjust the level of detail of the conversion.

[0107] During conversion, the conversion unit can apply different conversion algorithms depending on the category of the intention or emotion. For example, if a dog's intention is related to play, the conversion unit can apply a conversion algorithm specialized for play. For example, if a cat's emotion is related to stress, the conversion unit can apply a conversion algorithm specialized for stress. For example, if a dog's intention is related to vigilance, the conversion unit can apply a conversion algorithm specialized for vigilance. In this way, by applying different conversion algorithms depending on the category, conversion accuracy is improved. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input category data of intentions and emotions into the generation AI and cause the generation AI to perform analysis to select an appropriate conversion algorithm.

[0108] During conversion, the conversion unit can improve the accuracy of the conversion by referring to past conversion results for pets. The conversion unit can improve the current conversion accuracy by referring to, for example, past intention conversion results for dogs. The conversion unit can improve the current conversion accuracy by referring to, for example, past emotion conversion results for cats. The conversion unit can improve the current conversion accuracy by referring to, for example, past intention and emotion conversion results for dogs. In this way, by referring to past conversion results, the conversion accuracy is improved. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input past conversion result data into the generation AI and cause the generation AI to perform analysis to improve the conversion accuracy.

[0109] The conversion unit can estimate the emotion of the dog or cat and determine the priority of conversion based on the estimated emotion. For example, if the dog is excited, the conversion unit can prioritize converting an intention to play. For example, if the cat is relaxed, the conversion unit can prioritize converting an emotion of relief. For example, if the dog is anxious, the conversion unit can prioritize converting the cause of the anxiety. In this way, by determining the priority of conversion based on emotion, important intentions and emotions can be preferentially converted. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can estimate the emotion of the dog or cat using an emotion estimation algorithm and determine the priority of conversion based on the result.

[0110] During conversion, the conversion unit can determine the priority of conversion based on the time when the intention or emotion was collected. For example, the conversion unit can prioritize conversion immediately after the dog's intention is collected. For example, the conversion unit can prioritize conversion immediately after the cat's emotion is collected. For example, if the dog's intention and emotion are collected simultaneously, the conversion unit can prioritize conversion of both. This enables timely conversion by determining the priority of conversion based on the time of collection. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input collection time data into a generation AI and cause the generation AI to perform analysis to determine the priority of conversion.

[0111] The conversion unit can adjust the order of conversion based on the relevance of the intention or emotion during conversion. For example, if the intention and emotion of a dog are related, the conversion unit can perform both conversions simultaneously. For example, if the intention and emotion of a cat are related, the conversion unit can perform both conversions simultaneously. For example, if the intention and emotion of a dog are not related, the conversion unit can perform the conversions separately. This enables efficient conversion by adjusting the order of conversion based on the relevance. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input relevance data of intentions and emotions into a generation AI and cause the generation AI to perform an analysis to adjust the order of conversion.

[0112] During conversion, the conversion unit can adjust the level of detail of the conversion according to the pet owner's level of expertise. For example, if the owner has expertise, the conversion unit can provide a detailed conversion result. For example, if the owner does not have expertise, the conversion unit can provide a concise conversion result. For example, if the owner has medium expertise, the conversion unit can provide a medium-level of detail conversion result. This allows for adjusting the level of detail of the conversion according to the owner's level of expertise to provide an appropriate conversion result. Some or all of the above-described processing in the conversion unit may be performed using AI, for example, or may be performed without using AI. For example, the conversion unit can input the owner's expertise level data into the generation AI and cause the generation AI to perform an analysis to adjust the level of detail of the conversion. === Hard Collateral 1-1 === Each of the multiple elements including the collection unit, analysis unit, estimation unit, and conversion unit described above is realized, for example, in at least one of the smart device 14 and the data processing device 12. For example, the collection unit can collect the meows and behaviors of dogs and cats using the camera 42 and microphone 38B of the smart device 14. For example, the analysis unit can analyze the data collected by the specific processing unit 290 of the data processing device 12. For example, the estimation unit can infer intentions and emotions based on the analysis results by the specific processing unit 290 of the data processing device 12. For example, the conversion unit can convert the intentions and emotions inferred by the specific processing unit 290 of the data processing device 12 into human language. === Hard Collateral 1-2 === Each of the multiple elements including the collection unit, analysis unit, estimation unit, and conversion unit described above is realized, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit can collect the meows and behaviors of dogs and cats using the camera 42 and microphone 238 of the smart glasses 214. For example, the analysis unit can analyze the data collected by the specific processing unit 290 of the data processing device 12. For example, the estimation unit can infer intentions and emotions based on the analysis results by the specific processing unit 290 of the data processing device 12. For example, the conversion unit can convert the intentions and emotions estimated by the specific processing unit 290 of the data processing device 12 into human language. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned collection unit, analysis unit, estimation unit, and conversion unit is realized, for example, in at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit can collect the meows and behaviors of dogs and cats using the camera 42 and microphone 238 of the headset-type terminal 314. For example, the analysis unit can analyze the data collected by the specific processing unit 290 of the data processing device 12. For example, the estimation unit can infer intentions and emotions based on the analysis results by the specific processing unit 290 of the data processing device 12. For example, the conversion unit can convert the intentions and emotions inferred by the specific processing unit 290 of the data processing device 12 into human language. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned collection unit, analysis unit, estimation unit, and conversion unit is realized, for example, in at least one of the robot 414 and the data processing device 12. For example, the collection unit can collect the meows and behaviors of dogs and cats using the camera 42 and microphone 238 of the robot 414. For example, the analysis unit can analyze the data collected by the specific processing unit 290 of the data processing device 12. For example, the estimation unit can infer intentions and emotions based on the analysis results by the specific processing unit 290 of the data processing device 12. For example, the conversion unit can convert the intentions and emotions inferred by the specific processing unit 290 of the data processing device 12 into human language.

[0113] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0114] The pet translation system can also include a health management unit that monitors the pet's health. The health management unit collects biometric data such as the pet's body temperature, heart rate, and activity level and sends it to the analysis unit. The analysis unit evaluates the pet's health based on this data and can notify the owner if an abnormality is detected. For example, if a dog's body temperature is higher than normal, the analysis unit can predict the possibility of a fever and notify the owner, "The body temperature is high, so please be careful." Similarly, if a cat's heart rate is abnormally high, the analysis unit can predict the possibility of stress or excitement and notify the owner, "The heart rate is high, so please help the cat relax." This allows for real-time monitoring of the pet's health and early detection of abnormalities.

[0115] The pet translation system can also include a history management unit that records the pet's behavioral history. The history management unit chronologically records the meows and behavioral data obtained from the collection unit and provides it to the analysis unit. The analysis unit analyzes the pet's behavioral patterns based on this history data and can notify the owner if abnormal behavior occurs. For example, if a dog starts barking frequently at times when it normally does not bark, the analysis unit can infer the cause and notify the owner that "there is something abnormal in the recent behavioral pattern." Similarly, if a cat starts sharpening its claws frequently in a specific place, the analysis unit can infer that there may be some kind of stress factor in that place and notify the owner that "you need to be careful about your behavior in that particular place." This allows for understanding pet behavior patterns and early detection of abnormalities.

[0116] The pet translation system may further include a preference learning unit that learns the pet's preferences. The preference learning unit learns the pet's preferences based on the data obtained from the collection unit and provides the learned preferences to the analysis unit. The analysis unit can estimate the pet's preferences based on this data and make suggestions to the owner. For example, if a dog wags its tail in response to a certain piece of music, the analysis unit may estimate that the dog likes that music and suggest to the owner, "Play this music, your dog will be happy." Similarly, if a cat shows interest in a certain toy, the analysis unit may estimate that the toy is the cat's favorite and suggest to the owner, "Your cat will enjoy playing with this toy." This allows for understanding pet preferences and improving communication.

[0117] The pet translation system can further include a prediction unit that predicts the pet's behavior. The prediction unit predicts the pet's next behavior based on the data obtained from the collection unit and the data from the history management unit, and notifies the owner. For example, if a dog repeatedly requests walks at a specific time of day, the prediction unit can estimate that the dog is likely to request walks at that time and notify the owner that "it's almost time for a walk." Similarly, if a cat repeatedly requests food at a specific time of day, the prediction unit can estimate that the cat is likely to request food at that time and notify the owner that "it's almost time for food." This allows the pet's behavior to be predicted, allowing the owner to take appropriate action.

[0118] The pet translation system may further include a visualization unit that visualizes the pet's emotions. Based on the emotion data obtained from the estimation unit, the visualization unit displays the pet's emotions in a visual format, such as a graph or icon, and provides it to the owner. For example, if a dog is excited, the visualization unit displays an icon indicating that emotion and notifies the owner, "The dog is excited." Similarly, if a cat is relaxed, the visualization unit may display a graph indicating that emotion and notify the owner, "The cat is relaxed." This makes it easier for the owner to visually grasp the pet's emotions, allowing them to take appropriate action.

[0119] The pet translation system can further include a voice notification unit that notifies the pet's emotions by voice. The voice notification unit notifies the pet's emotions by voice based on the emotion data obtained from the estimation unit and provides the notification to the owner. For example, if a dog is excited, the voice notification unit can notify the owner by voice, saying, "The dog is excited." If a cat is relaxed, the voice notification unit can notify the owner by voice, saying, "The cat is relaxed." This allows the owner to understand the pet's emotions by voice and take appropriate action.

[0120] The pet translation system can further include a sharing unit that shares the pet's emotions. Based on the emotion data obtained from the estimation unit, the sharing unit can share the pet's emotions with other pet owners via social media or a dedicated app. For example, if a dog is excited, the sharing unit can post that emotion on social media to share with other pet owners. Also, if a cat is relaxed, the sharing unit can post that emotion on a dedicated app to share with other pet owners. This allows pet owners to share their pet's emotions and deepen communication with each other.

[0121] The pet translation system can further include an emotion recording unit that records the pet's emotions. The emotion recording unit records the emotion data obtained from the estimation unit in chronological order and provides it to the owner. For example, if a dog is excited, the emotion recording unit records that emotion and notifies the owner, "The dog was excited at this time." Similarly, if a cat is relaxed, the emotion recording unit can record that emotion and notify the owner, "The cat was relaxed at this time." This allows the system to understand changes in a pet's emotions over time and take appropriate action.

[0122] The pet translation system can further include an emotion analysis unit that analyzes the pet's emotions. The emotion analysis unit analyzes the pet's emotional tendencies and patterns based on the emotional data obtained from the estimation unit and provides the results to the owner. For example, if a dog tends to get excited at a certain time of day, the emotion analysis unit can analyze that tendency and notify the owner, "Dogs tend to get excited at this time of day." Similarly, if a cat tends to relax in a certain environment, the emotion analysis unit can analyze that tendency and notify the owner, "Cats tend to relax in this environment." This allows the pet's emotional tendencies and patterns to be understood and appropriate responses to be taken.

[0123] The pet translation system can further include an emotion prediction unit that predicts the pet's emotions. The emotion prediction unit predicts the pet's next emotion based on the emotion data obtained from the estimation unit and the data from the history management unit, and notifies the owner. For example, if a dog tends to get excited at a certain time of day, the emotion prediction unit can estimate that the dog is likely to get excited at that time and notify the owner, "It's about time for your dog to get excited." Similarly, if a cat tends to relax in a certain environment, the emotion prediction unit can estimate that the cat is likely to relax in that environment and notify the owner, "Cats tend to relax in this environment." This allows the pet's emotions to be predicted, allowing the owner to take appropriate action.

[0124] The processing flow of the second embodiment will be briefly explained below.

[0125] Step 1: The collection unit collects the meows and behaviors of dogs and cats. The collection unit can collect the meows and behaviors using, for example, a microphone or a camera. Specifically, the sound of a dog barking is collected using a microphone, and the behavior of a cat sharpening its claws or a dog wagging its tail is recorded using a camera. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the data using algorithms for sound wave pattern analysis and behavioral pattern analysis. Specifically, the analysis unit uses sound wave pattern analysis to analyze the sound of a dog barking, and behavioral pattern analysis to analyze the behavior of a cat sharpening its claws. It is also possible to analyze data by combining sound wave pattern analysis and behavioral pattern analysis. Step 3: The estimation unit infers the intention and emotion based on the analysis results obtained by the analysis unit. Specifically, based on the analysis results, it can infer the intention of "wanting to play" from the sound of a dog barking, and the emotion of "feeling stressed" from the behavior of a cat sharpening its claws. It can also infer the emotion of "happiness" from the behavior of a dog wagging its tail. Step 4: The conversion unit converts the intention and emotion estimated by the estimation unit into human language. The conversion unit uses natural language processing technology to convert the intention and emotion into human language. Specifically, the conversion unit converts the intention "I want to play" to "I want to play," and the emotion "I'm feeling stressed" to "I'm feeling stressed." It can also convert the emotion "I'm happy" to "I'm happy."

[0126] 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.

[0127] 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> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0128] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0129] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0130] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0131] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0132] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0133] 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.

[0134] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0140] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0141] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0142] 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.

[0143] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0144] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0145] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0146] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0147] 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.

[0148] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0149] 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.

[0150] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0152] 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.

[0153] 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.

[0154] 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.

[0155] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0156] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0157] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0158] 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.

[0159] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0160] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0161] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0162] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0163] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0164] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0165] 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.

[0166] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0167] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0168] 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.

[0169] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0170] 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.

[0171] 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.

[0172] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0173] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0174] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0175] 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.

[0176] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0177] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0178] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0179] 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.

[0180] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0181] 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.

[0182] 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).

[0183] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0184] 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."

[0185] 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.

[0186] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0191] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0192] 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.

[0193] 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.

[0194] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0195] 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.

[0196] 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.

[0197] [Explanation of symbols]

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

Claims

1. a collection unit that collects sounds or behaviors; an analysis unit that analyzes the data collected by the collection unit; an estimation unit that estimates an intention or emotion based on the analysis result obtained by the analysis unit; a conversion unit that converts the intention or emotion estimated by the estimation unit into a human language; Equipped with A system characterized by:

2. The collecting unit Use a microphone or camera to collect sounds or behaviors 2. The system of claim 1.

3. The analysis unit Analyze the data using sound wave pattern analysis or behavioral pattern analysis algorithms 2. The system of claim 1.

4. The estimation unit Uses algorithms to infer intent or emotion based on analysis results 2. The system of claim 1.

5. The conversion unit Use natural language processing technology to translate intent or emotion into human language 2. The system of claim 1.

6. The collecting unit Data on the meows or behavior of dogs or cats is used as training data, and the generative AI learns from it.

2. The system of claim 1.

Images