system

Abstract

The system according to the embodiment aims to provide a virtual pet that allows easy interaction. [Solution] A system according to an embodiment includes a receiving unit, an interpretation unit, and a control unit. The receiving unit receives a user's operation. The interpretation unit interprets the operation received by the receiving unit. The control unit causes a virtual pet to move based on the operation interpreted by the interpretation unit.

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 made it difficult to keep pets easily due to concerns about allergies, pet odors, and the sense of responsibility.

[0005] The system according to the embodiment aims to provide a virtual pet that allows easy interaction. [Means for solving the problem]

[0006] The system according to the embodiment includes a receiving unit, an interpretation unit, and a control unit. The receiving unit receives a user's operation. The interpretation unit interprets the operation received by the receiving unit. The control unit causes the virtual pet to move based on the operation interpreted by the interpretation unit. [Effects of the Invention]

[0007] The system according to the embodiment can provide a virtual pet that can be easily interacted with. [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 system according to an embodiment of the present invention is a virtual pet system that enables various interactions using a smartphone. This virtual pet system is designed for people who find it difficult to keep a real pet due to allergies, pet odors, and the sense of responsibility. The virtual pet system utilizes the interpretive capabilities of a large-scale language model (LLM) to interpret user actions on the display and convey them to the virtual pet. This allows users to seamlessly interact with their virtual pet through their smartphone, alleviating feelings of loneliness. For example, a user installs a virtual pet app on their smartphone and launches the app. The user can select and name a virtual pet. For example, pets can be dogs, cats, birds, or other pets. The user then performs various operations on the display, such as petting, feeding, and playing with the pet. The LLM interprets the user's operations and conveys them to the virtual pet. For example, when a user pets a pet on the display, the LLM interprets the operation and causes the virtual pet to feel like it is being petted. Similarly, when a user feeds a pet, the LLM interprets the operation and causes the virtual pet to eat the food. Furthermore, the virtual pet system is also equipped with the ability to recognize the user's voice and facial expressions. For example, when a user speaks to their pet, the LLM interprets the voice and the virtual pet responds. Also, when the user smiles, the virtual pet behaves in a happy manner. This allows users to enjoy a more realistic interaction experience. The virtual pet system also has the ability to record the time the user spends with the pet and track the pet's growth. For example, as the user feeds and plays with the pet, the pet grows and learns new skills. This allows users to deepen their bond with their pet. In this way, the virtual pet system allows users to seamlessly interact with their virtual pet through their smartphone, making it an effective way to alleviate feelings of loneliness.As a result, the virtual pet system allows users to alleviate feelings of loneliness through virtual pets even if they find it difficult to keep a real pet.

[0029] The virtual pet system according to the embodiment includes a reception unit, an interpretation unit, and a control unit. The reception unit receives user operations. Examples of user operations include, but are not limited to, touch operations, voice operations, and gesture operations. For example, the reception unit uses a touchscreen of a smartphone to receive touch operations. The reception unit can also use a microphone of the smartphone to receive voice operations. The reception unit can also use a camera of the smartphone to receive gesture operations. For example, the reception unit receives operations in which the user taps on the touchscreen of the smartphone. The reception unit can also receive operations in which the user speaks into the microphone of the smartphone. The reception unit can also receive operations in which the user makes gestures toward the camera of the smartphone. The interpretation unit interprets the operations received by the reception unit. The interpretation unit interprets the user operations using, for example, LLM. The LLM is a large-scale language model that can interpret user operations using natural language processing technology. For example, the interpretation unit interprets a user tapping on the touchscreen of the smartphone and determines that the operation is an operation to pet a pet. The interpretation unit also interprets an operation in which the user speaks into the smartphone's microphone and determines that the operation is an operation to talk to the pet. The interpretation unit also interprets an operation in which the user makes a gesture toward the smartphone's camera and determines that the operation is an operation to feed the pet. The control unit causes the virtual pet to operate based on the operation interpreted by the interpretation unit. For example, when the user performs an operation to pet the pet, the control unit causes the virtual pet to operate so as to feel that it is being petted. When the user performs an operation to talk to the pet, the control unit causes the virtual pet to operate so as to respond. When the user performs an operation to feed the pet, the control unit causes the virtual pet to eat the food. For example, when the interpretation unit interprets an operation in which the user taps on the smartphone's touchscreen and determines that the operation is an operation to pet the pet, the control unit causes the virtual pet to operate so as to feel that it is being petted.Furthermore, the control unit causes the virtual pet to respond when the interpretation unit interprets a user's operation of speaking into the smartphone's microphone and determines that the operation is an operation to talk to the pet. Furthermore, the control unit causes the virtual pet to eat the food when the interpretation unit interprets a user's operation of making a gesture toward the smartphone's camera and determines that the operation is an operation to feed the pet. In this way, the virtual pet system according to the embodiment interprets the user's operation and causes the virtual pet to behave, allowing the user to seamlessly interact with the virtual pet.

[0030] The interpretation unit can interpret user operations using an LLM. The LLM (Large-Scale Language Model) interprets user operations using natural language processing technologies such as GPT-4 (registered trademark) and Gemini. For example, the interpretation unit can interpret a user tapping on a smartphone touchscreen using an LLM and determine that the operation is an operation to pet a pet. The interpretation unit can also interpret a user speaking into a smartphone microphone using an LLM and determine that the operation is an operation to talk to a pet. The interpretation unit can also interpret a user gesturing toward a smartphone camera using an LLM and determine that the operation is an operation to feed a pet. Thus, the use of an LLM improves the accuracy of interpretation of user operations. Some or all of the above-described processing in the interpretation unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the interpretation unit can interpret operations using a generative AI model that receives a user operation as input and outputs an interpretation result of the operation.

[0031] The control unit may include a recognition unit that recognizes the user's voice or facial expression and reflects it in the virtual pet. The recognition unit recognizes the user's voice and facial expression using, for example, voice recognition technology or facial expression recognition technology. For example, the recognition unit may use voice recognition technology to recognize the user's voice speaking into the smartphone's microphone and reflect that voice on the virtual pet. The recognition unit may also use facial expression recognition technology to recognize the user's facial expression when smiling at the smartphone's camera and reflect that facial expression on the virtual pet. In this way, by recognizing the user's voice and facial expression, the virtual pet will show a more realistic reaction. Some or all of the above-described processing in the recognition unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the recognition unit may recognize the user's voice and facial expression using a generation AI model that inputs the user's voice and facial expression and outputs a recognition result.

[0032] The control unit may include a tracking unit that records operations performed by the user on the pet and tracks the pet's growth. The tracking unit records operations performed by the user on the pet, for example, by saving the operations in a log file or by recording them in a database. For example, the tracking unit saves the user's operation of feeding the pet in a log file. The tracking unit can also record the user's operation of playing with the pet in a database. Furthermore, the tracking unit records growth points such as level-ups and skill improvements to track the pet's growth. For example, the tracking unit records the number of times the user feeds the pet and raises the pet's level accordingly. The tracking unit also records the number of times the user plays with the pet and improves the pet's skills accordingly. In this way, tracking the pet's growth allows the user to deepen their bond with the pet. Some or all of the above-described processing in the tracking unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the tracking unit may track the pet's growth using a generation AI model that receives user operations as input and outputs growth points.

[0033] The control unit may include a providing unit that provides feedback to the user. The providing unit provides feedback to the user using, for example, voice feedback or text messages. For example, the providing unit provides voice feedback in response to the user's operation of feeding the pet. The providing unit may also provide text messages in response to the user's operation of playing with the pet. Furthermore, the providing unit may customize the content and method of feedback according to the user's preferences. For example, if the user prefers voice feedback, the providing unit may preferentially provide voice feedback. Also, if the user prefers text messages, the providing unit may preferentially provide text messages. By providing feedback to the user, the user can more enjoy interacting with the virtual pet. Some or all of the above-described processing by the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit may provide feedback using a generation AI model that receives user operations as input and outputs feedback.

[0034] The recognition unit can interpret the user's voice and reflect it in the virtual pet. The recognition unit interprets the user's voice using, for example, voice recognition technology. For example, the recognition unit can interpret the user's voice speaking into a smartphone microphone using voice recognition technology and reflect that voice in the virtual pet. Voice recognition technology, for example, extracts voice characteristics and converts voice data into text data. The recognition unit interprets the user's voice using voice recognition technology and reflects the interpretation result in the virtual pet. In this way, by interpreting the user's voice, the virtual pet can react more naturally. Some or all of the above-mentioned processing in the recognition unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the recognition unit can interpret the voice using a generation AI model that receives the user's voice as input and outputs an interpretation result.

[0035] The recognition unit can interpret the user's facial expressions and reflect them in the virtual pet. The recognition unit interprets the user's facial expressions using, for example, facial expression recognition technology. For example, the recognition unit can interpret the user's facial expression when smiling at the smartphone camera using facial expression recognition technology and reflect that expression in the virtual pet. The facial expression recognition technology, for example, detects facial feature points and analyzes facial expression data. The recognition unit interprets the user's facial expressions using facial expression recognition technology and reflects the interpretation results in the virtual pet. In this way, by interpreting the user's facial expressions, the virtual pet can show more emotional reactions. Some or all of the above-described processing in the recognition unit can be performed using, for example, a generative AI, or can be performed without using a generative AI. For example, the recognition unit can interpret facial expressions using a generative AI model that receives the user's facial expressions as input and outputs an interpretation result.

[0036] The reception unit can analyze the user's past operation history and select the optimal reception method. The reception unit can analyze the user's past operation history using, for example, data mining technology or a machine learning algorithm. For example, the reception unit can prioritize and receive operations that the user frequently performed in the past. The reception unit can also predict and receive operations that will be performed during a specific time period based on the user's past operation history. Furthermore, the reception unit can analyze the user's past operation patterns and propose the optimal reception method. For example, the reception unit can collect data on operations performed by the user in the past and select the optimal reception method based on that data. This enables the optimal operation reception for the user by analyzing the past operation history. Some or all of the above-described processing in the reception unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the reception unit can select the operation reception method using a generation AI model that inputs the user's past operation history data and outputs the optimal reception method.

[0037] The reception unit can filter operations based on the user's current situation or area of ​​interest when receiving the operations. The reception unit filters operations taking into account, for example, the user's current situation or area of ​​interest. For example, the reception unit preferentially receives operations related to topics in which the user is currently interested. The reception unit can also filter appropriate operations based on the user's current situation (e.g., at work, on break, etc.). Furthermore, the reception unit proposes and receives related operations based on the user's area of ​​interest. For example, the reception unit preferentially receives operations related to topics in which the user is currently interested. The reception unit also filters appropriate operations based on the user's current situation. For example, when the user is at work, the reception unit preferentially receives work-related operations. When the user is on break, the reception unit preferentially receives relaxing operations. In this way, by filtering operations based on the user's situation or area of ​​interest, more appropriate operations can be received. Some or all of the above-described processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit can filter operations using a generative AI model that takes the user's current situation and area of ​​interest data as input and outputs filtering results.

[0038] When receiving an operation, the reception unit can prioritize receiving highly relevant operations by taking into account the user's geographical location information. The reception unit acquires the user's geographical location information using, for example, GPS data or a location information service. For example, when the user is in a specific location, the reception unit prioritizes receiving operations related to that location. Furthermore, when the user is traveling, the reception unit can also prioritize receiving operations related to the travel destination. Furthermore, when the user is at home, the reception unit prioritizes receiving operations that can be performed at home. For example, when the user is at home, the reception unit prioritizes receiving operations that can be performed at home. Furthermore, when the user is in a park, the reception unit prioritizes receiving operations that can be performed in the park. In this way, by taking the user's geographical location information into account, more relevant operations can be received. Some or all of the above-described processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit can receive operations using a generation AI model that inputs the user's geographical location information data and outputs highly relevant operations.

[0039] The reception unit can analyze the user's social media activity when receiving an operation and receive related operations. The reception unit can analyze, for example, the content of social media posts and the number of likes. For example, the reception unit can suggest and receive related operations based on content shared by the user on social media. The reception unit can also refer to operations performed by the user's social media friends and suggest and receive similar operations. Furthermore, the reception unit can analyze the user's social media activity history and suggest and receive operations that are likely to interest the user. For example, the reception unit can suggest and receive related operations based on content shared by the user on social media. The reception unit can also refer to operations performed by the user's social media friends and suggest and receive similar operations. In this way, by analyzing social media activity, operations related to the user can be received. Some or all of the above-described processing by the reception unit can be performed using, for example, a generative AI. For example, the reception unit can receive operations using a generative AI model that inputs the user's social media activity data and outputs related operations.

[0040] During interpretation, the interpretation unit can adjust the level of detail of the interpretation based on the importance of the operation. The interpretation unit, for example, evaluates the importance of the operation and adjusts the level of detail of the interpretation based on the evaluation. For example, the interpretation unit provides a detailed interpretation for an operation with high importance and accurately reflects the operation. The interpretation unit also provides a concise interpretation for an operation with low importance and responds quickly. Furthermore, the interpretation unit dynamically adjusts the level of detail of the interpretation according to the importance of the operation. For example, the interpretation unit may determine that an operation in which the user feeds a pet is a high-importance operation and provide a detailed interpretation. The interpretation unit may also determine that an operation in which the user pets a pet is a low-importance operation and provide a concise interpretation. This allows for more appropriate interpretation by adjusting the level of detail of the interpretation based on the importance of the operation. Some or all of the above-described processing in the interpretation unit may be performed, for example, using a generation AI or without a generation AI. For example, the interpretation unit may adjust the level of detail of the interpretation using a generation AI model that inputs operation importance data and outputs the level of detail of the interpretation.

[0041] The interpretation unit can apply different interpretation algorithms depending on the category of the operation during interpretation. The interpretation unit, for example, classifies the category of the operation and applies different interpretation algorithms depending on the category. For example, the interpretation unit applies an interpretation algorithm dedicated to play to an operation related to play. The interpretation unit can also apply an interpretation algorithm dedicated to feeding to an operation related to feeding. The interpretation unit also applies an interpretation algorithm dedicated to stroking to a petting operation. For example, the interpretation unit classifies an operation in which the user plays with a pet into the play category and applies an interpretation algorithm dedicated to play. The interpretation unit also classifies an operation in which the user feeds a pet into the feeding category and applies an interpretation algorithm dedicated to feeding. This allows for more appropriate interpretation by applying different interpretation algorithms depending on the category of the operation. Some or all of the above-mentioned processing in the interpretation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the interpretation unit can apply the interpretation algorithm using a generation AI model that inputs operation category data and outputs an interpretation algorithm.

[0042] During interpretation, the interpretation unit can determine the priority of interpretation based on the time of submission of the operation. The interpretation unit, for example, evaluates the time of submission of the operation and determines the priority of interpretation based on the evaluation. For example, the interpretation unit prioritizes interpretation of recently submitted operations. The interpretation unit can also postpone interpretation of operations submitted earlier. Furthermore, the interpretation unit dynamically adjusts the priority of interpretation according to the time of submission. For example, the interpretation unit prioritizes interpretation of operations recently submitted by the user and quickly reflects them. The interpretation unit also postpones interpretation of operations submitted earlier by the user. In this way, determining the priority of interpretation based on the time of submission of the operation enables more appropriate interpretation. Some or all of the above-described processing in the interpretation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the interpretation unit can determine the priority of interpretation using a generation AI model that inputs data on the time of submission of the operation and outputs a priority.

[0043] The interpretation unit can adjust the order of interpretation based on the relevance of operations during interpretation. The interpretation unit, for example, evaluates the relevance of operations and adjusts the order of interpretation based on the evaluation. For example, the interpretation unit prioritizes interpretation of highly relevant operations. The interpretation unit can also postpone interpretation of less relevant operations. Furthermore, the interpretation unit dynamically adjusts the order of interpretation according to the relevance of operations. For example, the interpretation unit determines an operation in which a user feeds a pet as a highly relevant operation and interprets it preferentially. The interpretation unit also determines an operation in which a user pets a pet as a less relevant operation and interprets it later. This enables more appropriate interpretation by adjusting the order of interpretation based on the relevance of operations. Some or all of the above-described processing in the interpretation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the interpretation unit can adjust the order of interpretation using a generation AI model that inputs operation relevance data and outputs an interpretation order.

[0044] When the virtual pet operates, the control unit can select the optimal action by referring to the user's past operation history. The control unit can refer to the user's past operation history, for example, by searching a database or analyzing a log file. For example, the control unit can cause the virtual pet to perform an action that the user previously preferred. The control unit can also predict a specific action from the user's past operation history and cause the virtual pet to perform it. Furthermore, the control unit can analyze the user's past operation patterns and cause the virtual pet to perform the optimal action. For example, the control unit can collect data on operations performed by the user in the past and select the optimal action based on that data. This makes it possible to perform the optimal action for the user by referring to the past operation history. Some or all of the above-described processing by the control unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the control unit can select the action of the virtual pet using a generation AI model that inputs the user's past operation history data and outputs the optimal action.

[0045] The control unit can customize the virtual pet's behavior based on the user's current situation. The control unit, for example, evaluates the user's current situation and customizes the behavior based on the evaluation. For example, the control unit performs a quiet behavior when the user is at work. The control unit can also perform a relaxed behavior when the user is on a break. Furthermore, the control unit performs a simple behavior when the user is out. For example, the control unit performs a quiet behavior when the user is at work. The control unit performs a relaxed behavior when the user is on a break. This enables more appropriate interaction by customizing the behavior based on the user's current situation. Some or all of the above-described processing in the control unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the control unit can customize the virtual pet's behavior using a generation AI model that inputs data about the user's current situation and outputs a behavior.

[0046] When the virtual pet operates, the control unit can select an optimal action taking into account the user's geographical location information. The control unit acquires the user's geographical location information, for example, using GPS data or a location information service. For example, the control unit performs a relaxing action when the user is at home. Furthermore, the control unit can perform a play action when the user is in a park. Furthermore, the control unit performs an action related to the travel destination when the user is traveling. For example, the control unit performs a relaxing action when the user is at home. Furthermore, the control unit performs a play action when the user is in a park. This enables more appropriate actions by taking the user's geographical location information into account. Some or all of the above-described processing in the control unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the control unit can select an action for the virtual pet using a generation AI model that inputs the user's geographical location information data and outputs an optimal action.

[0047] The control unit can analyze the user's social media activity to suggest actions when the virtual pet moves. The control unit can analyze, for example, the content of social media posts and the number of likes. For example, the control unit can suggest relevant actions based on content shared by the user on social media. The control unit can also suggest similar actions by referring to actions performed by the user's social media friends. Furthermore, the control unit can analyze the user's social media activity history to suggest actions that the user might be interested in. For example, the control unit can suggest relevant actions based on content shared by the user on social media. The control unit can also suggest similar actions by referring to actions performed by the user's social media friends. In this way, actions relevant to the user can be suggested by analyzing social media activity. Some or all of the above-described processing by the control unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the control unit can suggest actions for the virtual pet using a generative AI model that inputs the user's social media activity data and outputs actions.

[0048] During recognition, the recognition unit can select the optimal recognition method by referring to the user's past voice and facial expression history. The recognition unit can refer to the user's past voice and facial expression history, for example, by searching a database or analyzing a log file. For example, the recognition unit selects the optimal recognition method based on the user's past voice and facial expression history. The recognition unit can also predict and recognize specific patterns from the user's past voice and facial expression history. Furthermore, the recognition unit analyzes the user's past voice and facial expression patterns to select the optimal recognition method. For example, the recognition unit collects data on the user's past voice and facial expression history and selects the optimal recognition method based on that data. This enables optimal recognition for the user by referring to the past voice and facial expression history. Some or all of the above-described processing in the recognition unit may be performed, for example, using a generation AI or may be performed without using a generation AI. For example, the recognition unit can recognize voice and facial expression using a generation AI model that inputs the user's past voice and facial expression history data and outputs the optimal recognition method.

[0049] The recognition unit can select the optimal recognition method during recognition by taking into account the user's device information. The recognition unit, for example, acquires the user's device information and selects the optimal recognition method based on that information. For example, if the user is using a smartphone, the recognition unit can perform recognition by utilizing the smartphone's microphone and camera. Furthermore, if the user is using a tablet, the recognition unit can also perform recognition by utilizing a large screen and high-performance camera. Furthermore, if the user is using a smartwatch, the recognition unit provides a simple and highly visible recognition method. For example, if the user is using a smartphone, the recognition unit can perform recognition by utilizing the smartphone's microphone and camera. Furthermore, if the user is using a tablet, the recognition unit can perform recognition by utilizing a large screen and high-performance camera. This enables optimal recognition for the user by taking the device information into account. Some or all of the above-described processing in the recognition unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the recognition unit can select the recognition method using a generative AI model that inputs the user's device information data and outputs the optimal recognition method.

[0050] During tracking, the tracking unit can select the optimal tracking method by referring to the user's past operation history. The tracking unit can refer to the user's past operation history, for example, by searching a database or analyzing a log file. For example, the tracking unit can prioritize the use of a tracking method that the user has previously preferred. The tracking unit can also predict and use a specific tracking method from the user's past operation history. Furthermore, the tracking unit can analyze the user's past operation patterns and select the optimal tracking method. For example, the tracking unit can collect data on operations performed by the user in the past and select the optimal tracking method based on that data. This enables optimal tracking for the user by referring to the past operation history. Some or all of the above-described processing in the tracking unit can be performed, for example, using a generation AI or without using a generation AI. For example, the tracking unit can select the tracking method using a generation AI model that inputs the user's past operation history data and outputs the optimal tracking method.

[0051] During tracking, the tracking unit can select an optimal tracking method by taking into account the user's geographical location information. The tracking unit acquires the user's geographical location information using, for example, GPS data or a location information service. For example, when the user is at home, the tracking unit uses a tracking method that can be performed at home. Furthermore, when the user is in a park, the tracking unit can also use a tracking method that can be performed in the park. Furthermore, when the user is traveling, the tracking unit uses a tracking method that can be performed at the travel destination. For example, when the user is at home, the tracking unit uses a tracking method that can be performed at home. Furthermore, when the user is in a park, the tracking unit uses a tracking method that can be performed in the park. This enables optimal tracking of the user by taking into account the geographical location information. Some or all of the above-described processing in the tracking unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the tracking unit can select a tracking method using a generation AI model that inputs the user's geographical location information data and outputs an optimal tracking method.

[0052] When providing feedback, the providing unit can select optimal feedback by referring to the user's past operation history. The providing unit can refer to the user's past operation history, for example, by using a database search or log file analysis. For example, the providing unit can prioritize the use of a feedback method that the user has previously preferred. The providing unit can also predict and use a specific feedback method from the user's past operation history. Furthermore, the providing unit can analyze the user's past operation patterns and select an optimal feedback method. For example, the providing unit can collect data on operations performed by the user in the past and select an optimal feedback method based on the data. This makes it possible to provide optimal feedback to the user by referring to the past operation history. Some or all of the above-described processing by the providing unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the providing unit can provide feedback using a generation AI model that inputs the user's past operation history data and outputs an optimal feedback method.

[0053] When providing feedback, the providing unit can provide optimal feedback by taking into account device information of the user. The providing unit, for example, acquires device information of the user and provides optimal feedback based on the information. For example, if the user is using a smartphone, the providing unit can provide feedback optimized for the smartphone. Furthermore, if the user is using a tablet, the providing unit can also provide feedback optimized for the tablet. Furthermore, if the user is using a smartwatch, the providing unit can provide feedback optimized for the smartwatch. For example, if the user is using a smartphone, the providing unit can provide feedback optimized for the smartphone. Furthermore, if the user is using a tablet, the providing unit can provide feedback optimized for the tablet. This enables optimal feedback to be provided to the user by taking device information into account. Some or all of the above-described processing by the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit can provide feedback using a generation AI model that inputs device information data of the user and outputs optimal feedback.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The reception unit not only receives user operations, but also learns the user's operation patterns and can predict the next operation. For example, if the user feeds the virtual pet every morning, the reception unit can learn that pattern and automatically suggest feeding the pet the next morning. Also, if the user plays with the pet at a specific time of day, the reception unit can suggest playtimes at that time. Furthermore, if the user frequently performs a specific operation, the operation can be registered as a shortcut so that it can be executed with one tap. This makes user operations smoother and improves interaction with the virtual pet.

[0056] The interpretation unit not only interprets the user's operation, but also infers the intention of the operation and provides appropriate feedback. For example, if the user performs an operation to pet a pet, the interpretation unit infers that the operation is intended to comfort the pet, and the virtual pet performs an action that pleases the user. If the user performs an operation to feed a pet, the interpretation unit infers that the operation is intended to care for the pet's health, and the virtual pet performs an action that shows gratitude. Furthermore, if the user performs an operation to play with a pet, the interpretation unit infers that the operation is intended to deepen the bond with the pet, and the virtual pet performs an action that is enjoyable. This provides more appropriate feedback for the user's operation and improves interaction with the virtual pet.

[0057] The tracking unit not only records the user's operations, but also analyzes the frequency and patterns of the operations and reflects the results in the pet's growth. For example, if the user frequently feeds the pet, the pet's growth rate can be increased. Also, if the user regularly plays with the pet, the pet's skill improvement can be promoted. Furthermore, if the user repeatedly performs a specific operation, the pet can be given special skills or abilities corresponding to that operation. This allows the user's operations to directly affect the pet's growth, providing a more interactive experience.

[0058] The recognition unit not only recognizes the user's voice and facial expressions, but can also learn the user's past voice and facial expression data to improve recognition accuracy. For example, if the user speaks in a particular tone of voice, the recognition unit can learn that tone and improve recognition accuracy from the next time onwards. Also, if the user frequently displays a particular facial expression, the recognition unit can learn that facial expression and improve recognition accuracy from the next time onwards. Furthermore, the recognition unit can analyze the user's voice and facial expression patterns and create an individual recognition model. This improves the recognition accuracy of the user's voice and facial expressions, resulting in more appropriate interactions.

[0059] The reception unit not only accepts user operations, but also understands the context of the operations and suggests appropriate actions. For example, after a user performs an operation to feed a pet, the reception unit can suggest the next activity to play with. Also, after a user performs an operation to play with a pet, the reception unit can suggest the next activity to take a break. Furthermore, before a user performs a specific operation, the reception unit can suggest an action related to that operation. This makes user operations smoother and improves interaction with the virtual pet.

[0060] The interpretation unit not only interprets the user's operation, but can also improve the accuracy of the interpretation by taking into account background information of the operation. For example, if the user performs an operation to feed a pet, the interpretation unit interprets the operation as being based on the pet's health condition. If the user performs an operation to play with a pet, the interpretation unit interprets the operation as being for the purpose of relieving the pet's stress. Furthermore, if the user performs an operation to pet a pet, the interpretation unit interprets the operation as being for the purpose of deepening the bond with the pet. This allows for more accurate interpretation of the user's operation and improves interaction with the virtual pet.

[0061] The processing flow of the first embodiment will be briefly explained below.

[0062] Step 1: The reception unit receives user operations. User operations include touch operations, voice operations, gesture operations, etc. For example, these operations are received using the smartphone's touch screen, microphone, and camera. Step 2: The interpretation unit interprets the operations received by the reception unit. For example, it uses a large-scale language model (LLM) to interpret the user's operations and determine the meaning of each operation, such as determining that a tap operation is an operation to pet a pet. Step 3: The control unit controls the virtual pet based on the operation interpreted by the interpretation unit. For example, the control unit controls the virtual pet to behave in a way that makes it feel like it is being petted in response to a petting operation, to react to a talking operation, or to eat food in response to a feeding operation.

[0063] (Example 2) A system according to an embodiment of the present invention is a virtual pet system that enables various interactions using a smartphone. This virtual pet system is designed for people who find it difficult to keep a real pet due to allergies, pet odors, and the sense of responsibility. The virtual pet system utilizes the interpretive capabilities of a large-scale language model (LLM) to interpret user actions on the display and convey them to the virtual pet. This allows users to seamlessly interact with their virtual pet through their smartphone, alleviating feelings of loneliness. For example, a user installs a virtual pet app on their smartphone and launches the app. The user can select and name a virtual pet. For example, pets can be dogs, cats, birds, or other pets. The user then performs various operations on the display, such as petting, feeding, and playing with the pet. The LLM interprets the user's operations and conveys them to the virtual pet. For example, when a user pets a pet on the display, the LLM interprets the operation and causes the virtual pet to feel like it is being petted. Similarly, when a user feeds a pet, the LLM interprets the operation and causes the virtual pet to eat the food. Furthermore, the virtual pet system is also equipped with the ability to recognize the user's voice and facial expressions. For example, when a user speaks to their pet, the LLM interprets the voice and the virtual pet responds. Also, when the user smiles, the virtual pet behaves in a happy manner. This allows users to enjoy a more realistic interaction experience. The virtual pet system also has the ability to record the time the user spends with the pet and track the pet's growth. For example, as the user feeds and plays with the pet, the pet grows and learns new skills. This allows users to deepen their bond with their pet. In this way, the virtual pet system allows users to seamlessly interact with their virtual pet through their smartphone, making it an effective way to alleviate feelings of loneliness.As a result, the virtual pet system allows users to alleviate feelings of loneliness through virtual pets even if they find it difficult to keep a real pet.

[0064] The virtual pet system according to the embodiment includes a reception unit, an interpretation unit, and a control unit. The reception unit receives user operations. Examples of user operations include, but are not limited to, touch operations, voice operations, and gesture operations. For example, the reception unit uses a touchscreen of a smartphone to receive touch operations. The reception unit can also use a microphone of the smartphone to receive voice operations. The reception unit can also use a camera of the smartphone to receive gesture operations. For example, the reception unit receives operations in which the user taps on the touchscreen of the smartphone. The reception unit can also receive operations in which the user speaks into the microphone of the smartphone. The reception unit can also receive operations in which the user makes gestures toward the camera of the smartphone. The interpretation unit interprets the operations received by the reception unit. The interpretation unit interprets the user operations using, for example, LLM. The LLM is a large-scale language model that can interpret user operations using natural language processing technology. For example, the interpretation unit interprets a user tapping on the touchscreen of the smartphone and determines that the operation is an operation to pet a pet. The interpretation unit also interprets an operation in which the user speaks into the smartphone's microphone and determines that the operation is an operation to talk to the pet. The interpretation unit also interprets an operation in which the user makes a gesture toward the smartphone's camera and determines that the operation is an operation to feed the pet. The control unit causes the virtual pet to operate based on the operation interpreted by the interpretation unit. For example, when the user performs an operation to pet the pet, the control unit causes the virtual pet to operate so as to feel that it is being petted. When the user performs an operation to talk to the pet, the control unit causes the virtual pet to operate so as to respond. When the user performs an operation to feed the pet, the control unit causes the virtual pet to eat the food. For example, when the interpretation unit interprets an operation in which the user taps on the smartphone's touchscreen and determines that the operation is an operation to pet the pet, the control unit causes the virtual pet to operate so as to feel that it is being petted.Furthermore, the control unit causes the virtual pet to respond when the interpretation unit interprets a user's operation of speaking into the smartphone's microphone and determines that the operation is an operation to talk to the pet. Furthermore, the control unit causes the virtual pet to eat the food when the interpretation unit interprets a user's operation of making a gesture toward the smartphone's camera and determines that the operation is an operation to feed the pet. In this way, the virtual pet system according to the embodiment interprets the user's operation and causes the virtual pet to behave, allowing the user to seamlessly interact with the virtual pet.

[0065] The interpretation unit can interpret user operations using an LLM. The LLM (Large-Scale Language Model) interprets user operations using natural language processing technologies such as GPT-4 and Gemini. For example, the interpretation unit can interpret a user tapping on a smartphone touchscreen using an LLM and determine that the operation is an operation to pet a pet. The interpretation unit can also interpret a user speaking into a smartphone microphone using an LLM and determine that the operation is an operation to talk to a pet. The interpretation unit can also interpret a user gesturing toward a smartphone camera using an LLM and determine that the operation is an operation to feed a pet. Thus, the use of an LLM improves the accuracy of interpreting user operations. Some or all of the above-described processing in the interpretation unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the interpretation unit can interpret operations using a generative AI model that receives user operations as input and outputs an interpretation result of the operation.

[0066] The control unit may include a recognition unit that recognizes the user's voice or facial expression and reflects it in the virtual pet. The recognition unit recognizes the user's voice and facial expression using, for example, voice recognition technology or facial expression recognition technology. For example, the recognition unit may use voice recognition technology to recognize the user's voice speaking into the smartphone's microphone and reflect that voice on the virtual pet. The recognition unit may also use facial expression recognition technology to recognize the user's facial expression when smiling at the smartphone's camera and reflect that facial expression on the virtual pet. In this way, by recognizing the user's voice and facial expression, the virtual pet will show a more realistic reaction. Some or all of the above-described processing in the recognition unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the recognition unit may recognize the user's voice and facial expression using a generation AI model that inputs the user's voice and facial expression and outputs a recognition result.

[0067] The control unit may include a tracking unit that records operations performed by the user on the pet and tracks the pet's growth. The tracking unit records operations performed by the user on the pet, for example, by saving the operations in a log file or by recording them in a database. For example, the tracking unit saves the user's operation of feeding the pet in a log file. The tracking unit can also record the user's operation of playing with the pet in a database. Furthermore, the tracking unit records growth points such as level-ups and skill improvements to track the pet's growth. For example, the tracking unit records the number of times the user feeds the pet and raises the pet's level accordingly. The tracking unit also records the number of times the user plays with the pet and improves the pet's skills accordingly. In this way, tracking the pet's growth allows the user to deepen their bond with the pet. Some or all of the above-described processing in the tracking unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the tracking unit may track the pet's growth using a generation AI model that receives user operations as input and outputs growth points.

[0068] The control unit may include a providing unit that provides feedback to the user. The providing unit provides feedback to the user using, for example, voice feedback or text messages. For example, the providing unit provides voice feedback in response to the user's operation of feeding the pet. The providing unit may also provide text messages in response to the user's operation of playing with the pet. Furthermore, the providing unit may customize the content and method of feedback according to the user's preferences. For example, if the user prefers voice feedback, the providing unit may preferentially provide voice feedback. Also, if the user prefers text messages, the providing unit may preferentially provide text messages. By providing feedback to the user, the user can more enjoy interacting with the virtual pet. Some or all of the above-described processing by the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit may provide feedback using a generation AI model that receives user operations as input and outputs feedback.

[0069] The recognition unit can interpret the user's voice and reflect it in the virtual pet. The recognition unit interprets the user's voice using, for example, voice recognition technology. For example, the recognition unit can interpret the user's voice speaking into a smartphone microphone using voice recognition technology and reflect that voice in the virtual pet. Voice recognition technology, for example, extracts voice characteristics and converts voice data into text data. The recognition unit interprets the user's voice using voice recognition technology and reflects the interpretation result in the virtual pet. In this way, by interpreting the user's voice, the virtual pet can react more naturally. Some or all of the above-mentioned processing in the recognition unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the recognition unit can interpret the voice using a generation AI model that receives the user's voice as input and outputs an interpretation result.

[0070] The recognition unit can interpret the user's facial expressions and reflect them in the virtual pet. The recognition unit interprets the user's facial expressions using, for example, facial expression recognition technology. For example, the recognition unit can interpret the user's facial expression when smiling at the smartphone camera using facial expression recognition technology and reflect that expression in the virtual pet. The facial expression recognition technology, for example, detects facial feature points and analyzes facial expression data. The recognition unit interprets the user's facial expressions using facial expression recognition technology and reflects the interpretation results in the virtual pet. In this way, by interpreting the user's facial expressions, the virtual pet can show more emotional reactions. Some or all of the above-described processing in the recognition unit can be performed using, for example, a generative AI, or can be performed without using a generative AI. For example, the recognition unit can interpret facial expressions using a generative AI model that receives the user's facial expressions as input and outputs an interpretation result.

[0071] The reception unit can estimate the user's emotions and adjust the timing of operation reception based on the estimated user emotions. The reception unit estimates the user's emotions using, for example, facial expression analysis or voice analysis. For example, the reception unit uses facial expression analysis technology to analyze the facial expressions the user shows toward the smartphone camera and estimate the user's emotions. The reception unit also uses voice analysis technology to analyze the voice the user speaks into the smartphone microphone and estimate the user's emotions. The reception unit adjusts the timing of operation reception based on the estimated emotions. For example, if the user is stressed, the reception unit delays the timing of operation reception and waits until the user is relaxed. If the user is excited, the reception unit accelerates the timing of operation reception and responds quickly. Furthermore, if the user is tired, the reception unit adjusts the timing of operation reception to allow the user to take a break. This enables more appropriate interaction by adjusting the timing of operation reception according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative 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-described processing in the reception unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the reception unit can adjust the timing of receiving an operation using a generation AI model that receives user emotion data as input and outputs the timing of receiving the operation.

[0072] The reception unit can analyze the user's past operation history and select the optimal reception method. The reception unit can analyze the user's past operation history using, for example, data mining technology or a machine learning algorithm. For example, the reception unit can prioritize and receive operations that the user frequently performed in the past. The reception unit can also predict and receive operations that will be performed during a specific time period based on the user's past operation history. Furthermore, the reception unit can analyze the user's past operation patterns and propose the optimal reception method. For example, the reception unit can collect data on operations performed by the user in the past and select the optimal reception method based on that data. This enables the optimal operation reception for the user by analyzing the past operation history. Some or all of the above-described processing in the reception unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the reception unit can select the operation reception method using a generation AI model that inputs the user's past operation history data and outputs the optimal reception method.

[0073] The reception unit can filter operations based on the user's current situation or area of ​​interest when receiving the operations. The reception unit filters operations taking into account, for example, the user's current situation or area of ​​interest. For example, the reception unit preferentially receives operations related to topics in which the user is currently interested. The reception unit can also filter appropriate operations based on the user's current situation (e.g., at work, on break, etc.). Furthermore, the reception unit proposes and receives related operations based on the user's area of ​​interest. For example, the reception unit preferentially receives operations related to topics in which the user is currently interested. The reception unit also filters appropriate operations based on the user's current situation. For example, when the user is at work, the reception unit preferentially receives work-related operations. When the user is on break, the reception unit preferentially receives relaxing operations. In this way, by filtering operations based on the user's situation or area of ​​interest, more appropriate operations can be received. Some or all of the above-described processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit can filter operations using a generative AI model that takes the user's current situation and area of ​​interest data as input and outputs filtering results.

[0074] The reception unit can estimate the user's emotions and prioritize operations to be accepted based on the estimated user's emotions. The reception unit estimates the user's emotions using, for example, facial expression analysis or voice analysis. For example, the reception unit uses facial expression analysis technology to analyze the facial expressions the user shows toward the smartphone camera to estimate the user's emotions. The reception unit also uses voice analysis technology to analyze the voice the user speaks into the smartphone microphone to estimate the user's emotions. The reception unit prioritizes operations to be accepted based on the estimated emotions. For example, if the user is stressed, the reception unit prioritizes operations that are relaxing. If the user is excited, the reception unit prioritizes operations that are energetic. If the user is tired, the reception unit prioritizes operations that are easy and less stressful. This enables more appropriate interactions by prioritizing operations according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative 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-described processing in the reception unit may be performed using the generation AI, for example, or may be performed without using the generation AI. For example, the reception unit may determine the priority of operations using a generation AI model that receives user emotion data as input and outputs a priority.

[0075] When receiving an operation, the reception unit can prioritize receiving highly relevant operations by taking into account the user's geographical location information. The reception unit acquires the user's geographical location information using, for example, GPS data or a location information service. For example, when the user is in a specific location, the reception unit prioritizes receiving operations related to that location. Furthermore, when the user is traveling, the reception unit can also prioritize receiving operations related to the travel destination. Furthermore, when the user is at home, the reception unit prioritizes receiving operations that can be performed at home. For example, when the user is at home, the reception unit prioritizes receiving operations that can be performed at home. Furthermore, when the user is in a park, the reception unit prioritizes receiving operations that can be performed in the park. In this way, by taking the user's geographical location information into account, more relevant operations can be received. Some or all of the above-described processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit can receive operations using a generation AI model that inputs the user's geographical location information data and outputs highly relevant operations.

[0076] The reception unit can analyze the user's social media activity when receiving an operation and receive related operations. The reception unit can analyze, for example, the content of social media posts and the number of likes. For example, the reception unit can suggest and receive related operations based on content shared by the user on social media. The reception unit can also refer to operations performed by the user's social media friends and suggest and receive similar operations. Furthermore, the reception unit can analyze the user's social media activity history and suggest and receive operations that are likely to interest the user. For example, the reception unit can suggest and receive related operations based on content shared by the user on social media. The reception unit can also refer to operations performed by the user's social media friends and suggest and receive similar operations. In this way, by analyzing social media activity, operations related to the user can be received. Some or all of the above-described processing by the reception unit can be performed using, for example, a generative AI. For example, the reception unit can receive operations using a generative AI model that inputs the user's social media activity data and outputs related operations.

[0077] The interpretation unit can estimate the user's emotions and adjust the interpretation method of the operation based on the estimated user's emotions. The interpretation unit estimates the user's emotions using, for example, facial expression analysis or voice analysis. For example, the interpretation unit uses facial expression analysis technology to analyze the facial expressions the user shows toward the smartphone camera to estimate the user's emotions. The interpretation unit also uses voice analysis technology to analyze the voice the user speaks into the smartphone microphone to estimate the user's emotions. Based on the estimated emotions, the interpretation unit adjusts the interpretation method of the operation. For example, if the user is relaxed, the interpretation unit provides a detailed interpretation to deeply understand the intention of the operation. If the user is in a hurry, the interpretation unit provides a concise interpretation to respond quickly. Furthermore, if the user is excited, the interpretation unit provides an energetic interpretation to actively reflect the intention of the operation. This allows for more appropriate interpretation by adjusting the interpretation method of the operation according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generative AI may be, but is not limited to, a text generative AI (e.g., LLM) or a multimodal generative AI. Some or all of the above-described processing in the interpretation unit may be performed using, for example, the generative AI, or may be performed without using the generative AI. For example, the interpretation unit may adjust the interpretation method of an operation using a generative AI model that inputs user emotion data and outputs an interpretation method.

[0078] During interpretation, the interpretation unit can adjust the level of detail of the interpretation based on the importance of the operation. The interpretation unit, for example, evaluates the importance of the operation and adjusts the level of detail of the interpretation based on the evaluation. For example, the interpretation unit provides a detailed interpretation for an operation with high importance and accurately reflects the operation. The interpretation unit also provides a concise interpretation for an operation with low importance and responds quickly. Furthermore, the interpretation unit dynamically adjusts the level of detail of the interpretation according to the importance of the operation. For example, the interpretation unit may determine that an operation in which the user feeds a pet is a high-importance operation and provide a detailed interpretation. The interpretation unit may also determine that an operation in which the user pets a pet is a low-importance operation and provide a concise interpretation. This allows for more appropriate interpretation by adjusting the level of detail of the interpretation based on the importance of the operation. Some or all of the above-described processing in the interpretation unit may be performed, for example, using a generation AI or without a generation AI. For example, the interpretation unit may adjust the level of detail of the interpretation using a generation AI model that inputs operation importance data and outputs the level of detail of the interpretation.

[0079] The interpretation unit can apply different interpretation algorithms depending on the category of the operation during interpretation. The interpretation unit, for example, classifies the category of the operation and applies different interpretation algorithms depending on the category. For example, the interpretation unit applies an interpretation algorithm dedicated to play to an operation related to play. The interpretation unit can also apply an interpretation algorithm dedicated to feeding to an operation related to feeding. The interpretation unit also applies an interpretation algorithm dedicated to stroking to a petting operation. For example, the interpretation unit classifies an operation in which the user plays with a pet into the play category and applies an interpretation algorithm dedicated to play. The interpretation unit also classifies an operation in which the user feeds a pet into the feeding category and applies an interpretation algorithm dedicated to feeding. This allows for more appropriate interpretation by applying different interpretation algorithms depending on the category of the operation. Some or all of the above-mentioned processing in the interpretation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the interpretation unit can apply the interpretation algorithm using a generation AI model that inputs operation category data and outputs an interpretation algorithm.

[0080] The interpretation unit can estimate the user's emotion and adjust the length of the interpretation based on the estimated user emotion. The interpretation unit estimates the user's emotion using, for example, facial expression analysis or voice analysis. For example, the interpretation unit uses facial expression analysis technology to analyze the facial expressions the user shows toward the smartphone camera and estimate the user's emotion. The interpretation unit also uses voice analysis technology to analyze the voice the user speaks into the smartphone microphone and estimate the user's emotion. The interpretation unit adjusts the length of the interpretation based on the estimated emotion. For example, if the user is in a hurry, the interpretation unit provides a short, concise interpretation. If the user is relaxed, the interpretation unit provides a longer interpretation with detailed explanations. Furthermore, if the user is excited, the interpretation unit provides an interpretation with visually stimulating effects. This allows for a more appropriate interpretation by adjusting the length of the interpretation according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or 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-described processing in the interpretation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the interpretation unit may adjust the length of the interpretation using a generation AI model that receives user emotion data as input and outputs the length of the interpretation.

[0081] During interpretation, the interpretation unit can determine the priority of interpretation based on the time of submission of the operation. The interpretation unit, for example, evaluates the time of submission of the operation and determines the priority of interpretation based on the evaluation. For example, the interpretation unit prioritizes interpretation of recently submitted operations. The interpretation unit can also postpone interpretation of operations submitted earlier. Furthermore, the interpretation unit dynamically adjusts the priority of interpretation according to the time of submission. For example, the interpretation unit prioritizes interpretation of operations recently submitted by the user and quickly reflects them. The interpretation unit also postpones interpretation of operations submitted earlier by the user. In this way, determining the priority of interpretation based on the time of submission of the operation enables more appropriate interpretation. Some or all of the above-described processing in the interpretation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the interpretation unit can determine the priority of interpretation using a generation AI model that inputs data on the time of submission of the operation and outputs a priority.

[0082] The interpretation unit can adjust the order of interpretation based on the relevance of operations during interpretation. The interpretation unit, for example, evaluates the relevance of operations and adjusts the order of interpretation based on the evaluation. For example, the interpretation unit prioritizes interpretation of highly relevant operations. The interpretation unit can also postpone interpretation of less relevant operations. Furthermore, the interpretation unit dynamically adjusts the order of interpretation according to the relevance of operations. For example, the interpretation unit determines an operation in which a user feeds a pet as a highly relevant operation and interprets it preferentially. The interpretation unit also determines an operation in which a user pets a pet as a less relevant operation and interprets it later. This enables more appropriate interpretation by adjusting the order of interpretation based on the relevance of operations. Some or all of the above-described processing in the interpretation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the interpretation unit can adjust the order of interpretation using a generation AI model that inputs operation relevance data and outputs an interpretation order.

[0083] The control unit can estimate the user's emotions and adjust the virtual pet's behavior based on the estimated user's emotions. The control unit estimates the user's emotions using, for example, facial expression analysis or voice analysis. For example, the control unit uses facial expression analysis technology to analyze the facial expressions the user shows toward the smartphone camera and estimate the user's emotions. The control unit also uses voice analysis technology to analyze the user's voice speaking into the smartphone microphone and estimate the user's emotions. The control unit adjusts the virtual pet's behavior based on the estimated emotions. For example, if the user is relaxed, the control unit causes the virtual pet to behave in a relaxed manner. If the user is excited, the control unit causes the virtual pet to behave in an energetic manner. Furthermore, if the user is sad, the control unit causes the virtual pet to behave in a comforting manner. This allows for more appropriate interaction by adjusting the virtual pet's behavior according to the user's emotions. 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-described processing in the control unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the control unit may adjust the behavior of the virtual pet using a generative AI model that takes user emotional data as input and outputs behavior.

[0084] When the virtual pet operates, the control unit can select the optimal action by referring to the user's past operation history. The control unit can refer to the user's past operation history, for example, by searching a database or analyzing a log file. For example, the control unit can cause the virtual pet to perform an action that the user previously preferred. The control unit can also predict a specific action from the user's past operation history and cause the virtual pet to perform it. Furthermore, the control unit can analyze the user's past operation patterns and cause the virtual pet to perform the optimal action. For example, the control unit can collect data on operations performed by the user in the past and select the optimal action based on that data. This makes it possible to perform the optimal action for the user by referring to the past operation history. Some or all of the above-described processing by the control unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the control unit can select the action of the virtual pet using a generation AI model that inputs the user's past operation history data and outputs the optimal action.

[0085] The control unit can customize the virtual pet's behavior based on the user's current situation. The control unit, for example, evaluates the user's current situation and customizes the behavior based on the evaluation. For example, the control unit performs a quiet behavior when the user is at work. The control unit can also perform a relaxed behavior when the user is on a break. Furthermore, the control unit performs a simple behavior when the user is out. For example, the control unit performs a quiet behavior when the user is at work. The control unit performs a relaxed behavior when the user is on a break. This enables more appropriate interaction by customizing the behavior based on the user's current situation. Some or all of the above-described processing in the control unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the control unit can customize the virtual pet's behavior using a generation AI model that inputs data about the user's current situation and outputs a behavior.

[0086] The control unit can estimate the user's emotions and prioritize the virtual pet's actions based on the estimated user's emotions. The control unit estimates the user's emotions using, for example, facial expression analysis or voice analysis. For example, the control unit uses facial expression analysis technology to analyze the user's facial expressions toward the smartphone camera and estimate the user's emotions. The control unit also uses voice analysis technology to analyze the user's voice speaking into the smartphone microphone and estimate the user's emotions. Based on the estimated emotions, the control unit prioritizes the virtual pet's actions. For example, if the user is relaxed, the control unit prioritizes relaxing actions. If the user is excited, the control unit prioritizes energetic actions. If the user is sad, the control unit prioritizes comforting actions. This enables more appropriate interaction by prioritizing actions according to the user's emotions. 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-described processing in the control unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the control unit may determine the priority of the virtual pet's actions using a generation AI model that receives user emotion data as input and outputs the priority of actions.

[0087] When the virtual pet operates, the control unit can select an optimal action taking into account the user's geographical location information. The control unit acquires the user's geographical location information, for example, using GPS data or a location information service. For example, the control unit performs a relaxing action when the user is at home. Furthermore, the control unit can perform a play action when the user is in a park. Furthermore, the control unit performs an action related to the travel destination when the user is traveling. For example, the control unit performs a relaxing action when the user is at home. Furthermore, the control unit performs a play action when the user is in a park. This enables more appropriate actions by taking the user's geographical location information into account. Some or all of the above-described processing in the control unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the control unit can select an action for the virtual pet using a generation AI model that inputs the user's geographical location information data and outputs an optimal action.

[0088] The control unit can analyze the user's social media activity to suggest actions when the virtual pet moves. The control unit can analyze, for example, the content of social media posts and the number of likes. For example, the control unit can suggest relevant actions based on content shared by the user on social media. The control unit can also suggest similar actions by referring to actions performed by the user's social media friends. Furthermore, the control unit can analyze the user's social media activity history to suggest actions that the user might be interested in. For example, the control unit can suggest relevant actions based on content shared by the user on social media. The control unit can also suggest similar actions by referring to actions performed by the user's social media friends. In this way, actions relevant to the user can be suggested by analyzing social media activity. Some or all of the above-described processing by the control unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the control unit can suggest actions for the virtual pet using a generative AI model that inputs the user's social media activity data and outputs actions.

[0089] The recognition unit can estimate the user's emotions and adjust the voice and facial expression recognition method based on the estimated user's emotions. The recognition unit estimates the user's emotions using, for example, facial expression analysis or voice analysis. For example, the recognition unit uses facial expression analysis technology to analyze the facial expressions the user shows toward the smartphone camera and estimate the user's emotions. The recognition unit also uses voice analysis technology to analyze the voice the user speaks into the smartphone microphone and estimate the user's emotions. Based on the estimated emotions, the recognition unit adjusts the voice and facial expression recognition method. For example, if the user is relaxed, the recognition unit recognizes detailed voice and facial expressions. If the user is in a hurry, the recognition unit recognizes concise voice and facial expressions. Furthermore, if the user is excited, the recognition unit recognizes energetic voice and facial expressions. This allows for more appropriate recognition by adjusting the voice and facial expression recognition method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generative AI may be, but is not limited to, a text generative AI (e.g., LLM) or a multimodal generative AI. Some or all of the above-described processing in the recognition unit may be performed using, for example, the generative AI, or may be performed without using the generative AI. For example, the recognition unit may adjust the recognition method for voice or facial expression using a generative AI model that inputs user emotion data and outputs a recognition method.

[0090] During recognition, the recognition unit can select the optimal recognition method by referring to the user's past voice and facial expression history. The recognition unit can refer to the user's past voice and facial expression history, for example, by searching a database or analyzing a log file. For example, the recognition unit selects the optimal recognition method based on the user's past voice and facial expression history. The recognition unit can also predict and recognize specific patterns from the user's past voice and facial expression history. Furthermore, the recognition unit analyzes the user's past voice and facial expression patterns to select the optimal recognition method. For example, the recognition unit collects data on the user's past voice and facial expression history and selects the optimal recognition method based on that data. This enables optimal recognition for the user by referring to the past voice and facial expression history. Some or all of the above-described processing in the recognition unit may be performed, for example, using a generation AI or without a generation AI. For example, the recognition unit can recognize voice and facial expression using a generation AI model that inputs the user's past voice and facial expression history data and outputs the optimal recognition method.

[0091] The recognition unit can estimate the user's emotions and determine recognition priorities based on the estimated user emotions. The recognition unit estimates the user's emotions using, for example, facial expression analysis or voice analysis. For example, the recognition unit uses facial expression analysis technology to analyze the facial expressions the user shows toward the smartphone camera and estimate the user's emotions. The recognition unit also uses voice analysis technology to analyze the voice the user speaks into the smartphone microphone and estimate the user's emotions. The recognition unit determines recognition priorities based on the estimated emotions. For example, if the user is relaxed, the recognition unit prioritizes recognition of relaxed voices and facial expressions. If the user is excited, the recognition unit prioritizes recognition of energetic voices and facial expressions. If the user is sad, the recognition unit prioritizes recognition of comforting voices and facial expressions. This enables more appropriate recognition by determining recognition priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation 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 recognition unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the recognition unit may determine the recognition priority using a generation AI model that receives user emotion data as input and outputs the recognition priority.

[0092] The recognition unit can select the optimal recognition method during recognition by taking into account the user's device information. The recognition unit, for example, acquires the user's device information and selects the optimal recognition method based on that information. For example, if the user is using a smartphone, the recognition unit can perform recognition by utilizing the smartphone's microphone and camera. Furthermore, if the user is using a tablet, the recognition unit can also perform recognition by utilizing a large screen and high-performance camera. Furthermore, if the user is using a smartwatch, the recognition unit provides a simple and highly visible recognition method. For example, if the user is using a smartphone, the recognition unit can perform recognition by utilizing the smartphone's microphone and camera. Furthermore, if the user is using a tablet, the recognition unit can perform recognition by utilizing a large screen and high-performance camera. This enables optimal recognition for the user by taking the device information into account. Some or all of the above-described processing in the recognition unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the recognition unit can select the recognition method using a generative AI model that inputs the user's device information data and outputs the optimal recognition method.

[0093] The tracking unit can estimate the user's emotions and adjust the pet's growth tracking method based on the estimated user's emotions. The tracking unit estimates the user's emotions using, for example, facial expression analysis or voice analysis. For example, the tracking unit uses facial expression analysis technology to analyze the user's facial expressions toward the smartphone camera to estimate the user's emotions. The tracking unit also uses voice analysis technology to analyze the user's voice speaking into the smartphone microphone to estimate the user's emotions. Based on the estimated emotions, the tracking unit adjusts the pet's growth tracking method. For example, if the user is relaxed, the tracking unit performs detailed growth tracking to record the pet's growth in detail. If the user is in a hurry, the tracking unit performs concise growth tracking to record only major growth points. If the user is excited, the tracking unit performs energetic growth tracking to actively record the pet's growth. This allows for more appropriate tracking by adjusting the growth tracking method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generating AI may be, but is not limited to, a text generating AI (e.g., LLM) or a multimodal generating AI. Some or all of the above-described processing in the tracking unit may be performed using, for example, the generating AI. For example, the tracking unit may adjust the pet's growth tracking method using a generating AI model that receives user emotion data as input and outputs a growth tracking method.

[0094] During tracking, the tracking unit can select the optimal tracking method by referring to the user's past operation history. The tracking unit can refer to the user's past operation history, for example, by searching a database or analyzing a log file. For example, the tracking unit can prioritize the use of a tracking method that the user has previously preferred. The tracking unit can also predict and use a specific tracking method from the user's past operation history. Furthermore, the tracking unit can analyze the user's past operation patterns and select the optimal tracking method. For example, the tracking unit can collect data on operations performed by the user in the past and select the optimal tracking method based on that data. This enables optimal tracking for the user by referring to the past operation history. Some or all of the above-described processing in the tracking unit can be performed, for example, using a generation AI or without using a generation AI. For example, the tracking unit can select the tracking method using a generation AI model that inputs the user's past operation history data and outputs the optimal tracking method.

[0095] The tracking unit can estimate the user's emotions and determine tracking priorities based on the estimated user emotions. The tracking unit estimates the user's emotions using, for example, facial expression analysis or voice analysis. For example, the tracking unit uses facial expression analysis technology to analyze the facial expressions the user shows toward the smartphone camera and estimate the user's emotions. The tracking unit also uses voice analysis technology to analyze the voice the user speaks into the smartphone microphone and estimate the user's emotions. The tracking unit determines tracking priorities based on the estimated emotions. For example, if the user is relaxed, the tracking unit prioritizes relaxed tracking. If the user is excited, the tracking unit prioritizes energetic tracking. If the user is sad, the tracking unit prioritizes comforting tracking. This enables more appropriate tracking by determining tracking priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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-described processing in the tracking unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the tracking unit may determine tracking priorities using a generative AI model that receives user emotion data as input and outputs tracking priorities.

[0096] During tracking, the tracking unit can select an optimal tracking method by taking into account the user's geographical location information. The tracking unit acquires the user's geographical location information using, for example, GPS data or a location information service. For example, when the user is at home, the tracking unit uses a tracking method that can be performed at home. Furthermore, when the user is in a park, the tracking unit can also use a tracking method that can be performed in the park. Furthermore, when the user is traveling, the tracking unit uses a tracking method that can be performed at the travel destination. For example, when the user is at home, the tracking unit uses a tracking method that can be performed at home. Furthermore, when the user is in a park, the tracking unit uses a tracking method that can be performed in the park. This enables optimal tracking of the user by taking into account the geographical location information. Some or all of the above-described processing in the tracking unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the tracking unit can select a tracking method using a generation AI model that inputs the user's geographical location information data and outputs an optimal tracking method.

[0097] The providing unit can estimate the user's emotion and adjust the feedback provision method based on the estimated user's emotion. The providing unit estimates the user's emotion using, for example, facial expression analysis or voice analysis. For example, the providing unit uses facial expression analysis technology to analyze the facial expressions the user shows toward the smartphone camera and estimate the user's emotion. The providing unit also uses voice analysis technology to analyze the voice the user speaks into the smartphone microphone and estimate the user's emotion. The providing unit adjusts the feedback provision method based on the estimated emotion. For example, if the user is relaxed, the providing unit provides detailed feedback. If the user is in a hurry, the providing unit provides concise feedback. If the user is excited, the providing unit provides energetic feedback. This enables more appropriate feedback by adjusting the feedback provision method according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using 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-described processing in the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit may adjust the feedback providing method using a generation AI model that receives user emotion data as input and outputs a feedback providing method.

[0098] When providing feedback, the providing unit can select optimal feedback by referring to the user's past operation history. The providing unit can refer to the user's past operation history, for example, by using a database search or log file analysis. For example, the providing unit can prioritize the use of a feedback method that the user has previously preferred. The providing unit can also predict and use a specific feedback method from the user's past operation history. Furthermore, the providing unit can analyze the user's past operation patterns and select an optimal feedback method. For example, the providing unit can collect data on operations performed by the user in the past and select an optimal feedback method based on the data. This makes it possible to provide optimal feedback to the user by referring to the past operation history. Some or all of the above-described processing by the providing unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the providing unit can provide feedback using a generation AI model that inputs the user's past operation history data and outputs an optimal feedback method.

[0099] The providing unit can estimate the user's emotions and determine the priority of feedback based on the estimated user's emotions. The providing unit estimates the user's emotions using, for example, facial expression analysis or voice analysis. For example, the providing unit uses facial expression analysis technology to analyze the facial expressions the user shows toward the smartphone camera and estimate the user's emotions. The providing unit also uses voice analysis technology to analyze the voice the user speaks into the smartphone microphone and estimate the user's emotions. The providing unit determines the priority of feedback based on the estimated emotions. For example, if the user is relaxed, the providing unit prioritizes relaxed feedback. If the user is excited, the providing unit prioritizes energetic feedback. If the user is sad, the providing unit prioritizes comforting feedback. This enables more appropriate feedback by determining the priority of feedback according to the user's emotions. Emotion estimation is realized 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-described processing in the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit may determine the priority of feedback using a generation AI model that receives user emotion data as input and outputs feedback priorities.

[0100] When providing feedback, the providing unit can provide optimal feedback by taking into account device information of the user. The providing unit, for example, acquires device information of the user and provides optimal feedback based on the information. For example, if the user is using a smartphone, the providing unit can provide feedback optimized for the smartphone. Furthermore, if the user is using a tablet, the providing unit can also provide feedback optimized for the tablet. Furthermore, if the user is using a smartwatch, the providing unit can provide feedback optimized for the smartwatch. For example, if the user is using a smartphone, the providing unit can provide feedback optimized for the smartphone. Furthermore, if the user is using a tablet, the providing unit can provide feedback optimized for the tablet. This enables optimal feedback to be provided to the user by taking device information into account. Some or all of the above-described processing by the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit can provide feedback using a generation AI model that inputs device information data of the user and outputs optimal feedback. === Hard Collateral 1-1 === Each of the above-described elements, including the reception unit, interpretation unit, and control unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit receives a user's operation using the touch screen, microphone, and camera of the smart device 14. The interpretation unit is realized by the specific processing unit 290 of the data processing device 12 and interprets the user's operation using the LLM. The control unit is realized, for example, by the control unit 46A of the smart device 14 and controls the virtual pet based on the interpreted operation. === Hard Collateral 1-2 === Each of the multiple elements including the above-described reception unit, interpretation unit, and control unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit receives a user's operation using the microphone, camera, and touch interface of the smart glasses 214. The interpretation unit is realized by the specific processing unit 290 of the data processing device 12 and interprets the user's operation using the LLM. The control unit is realized, for example, by the control unit 46A of the smart glasses 214 and causes the virtual pet to operate based on the interpreted operation. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, interpretation unit, and control unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit receives a user's operation using the microphone, camera, and touch interface of the headset-type terminal 314. The interpretation unit is realized by the specific processing unit 290 of the data processing device 12 and interprets the user's operation using the LLM. The control unit is realized, for example, by the control unit 46A of the headset-type terminal 314 and causes the virtual pet to operate based on the interpreted operation. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, interpretation unit, and control unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit receives a user's operation using the microphone, camera, and touch interface of the robot 414. The interpretation unit is realized by the specific processing unit 290 of the data processing device 12 and interprets the user's operation using the LLM. The control unit is realized, for example, by the control unit 46A of the robot 414 and causes the virtual pet to operate based on the interpreted operation.

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

[0102] The reception unit not only receives user operations, but also learns the user's operation patterns and can predict the next operation. For example, if the user feeds the virtual pet every morning, the reception unit can learn that pattern and automatically suggest feeding the pet the next morning. Also, if the user plays with the pet at a specific time of day, the reception unit can suggest playtimes at that time. Furthermore, if the user frequently performs a specific operation, the operation can be registered as a shortcut so that it can be executed with one tap. This makes user operations smoother and improves interaction with the virtual pet.

[0103] The interpretation unit not only interprets the user's operation, but also infers the intention of the operation and provides appropriate feedback. For example, if the user performs an operation to pet a pet, the interpretation unit infers that the operation is intended to comfort the pet, and the virtual pet performs an action that pleases the user. If the user performs an operation to feed a pet, the interpretation unit infers that the operation is intended to care for the pet's health, and the virtual pet performs an action that shows gratitude. Furthermore, if the user performs an operation to play with a pet, the interpretation unit infers that the operation is intended to deepen the bond with the pet, and the virtual pet performs an action that is enjoyable. This provides more appropriate feedback for the user's operation and improves interaction with the virtual pet.

[0104] The control unit can not only recognize the user's voice and facial expressions, but also estimate the user's emotions and adjust the virtual pet's behavior accordingly. For example, if the user is feeling stressed, the control unit adjusts the virtual pet to perform a relaxing behavior. If the user is happy, the control unit adjusts the virtual pet to perform a joyful behavior to share the user's happiness. If the user is sad, the control unit adjusts the virtual pet to perform a comforting behavior. This allows the virtual pet to perform actions that correspond to the user's emotions, resulting in more appropriate interactions.

[0105] The tracking unit not only records the user's operations, but also analyzes the frequency and patterns of the operations and reflects the results in the pet's growth. For example, if the user frequently feeds the pet, the pet's growth rate can be increased. Also, if the user regularly plays with the pet, the pet's skill improvement can be promoted. Furthermore, if the user repeatedly performs a specific operation, the pet can be given special skills or abilities corresponding to that operation. This allows the user's operations to directly affect the pet's growth, providing a more interactive experience.

[0106] The providing unit not only provides feedback to the user, but can also customize the content of the feedback based on the user's emotions. For example, if the user is feeling stressed, the providing unit provides relaxing feedback. If the user is happy, the providing unit provides feedback that shares that joy. Furthermore, if the user is sad, the providing unit provides comforting feedback. In this way, feedback according to the user's emotions is provided, and more appropriate interactions are realized.

[0107] The recognition unit not only recognizes the user's voice and facial expressions, but can also learn the user's past voice and facial expression data to improve recognition accuracy. For example, if the user speaks in a particular tone of voice, the recognition unit can learn that tone and improve recognition accuracy from the next time onwards. Also, if the user frequently displays a particular facial expression, the recognition unit can learn that facial expression and improve recognition accuracy from the next time onwards. Furthermore, the recognition unit can analyze the user's voice and facial expression patterns and create an individual recognition model. This improves the recognition accuracy of the user's voice and facial expressions, resulting in more appropriate interactions.

[0108] The recognition unit not only interprets the user's facial expression, but also infers the user's emotions and adjusts the virtual pet's response based on those emotions. For example, if the user smiles, the recognition unit infers the smile as a happy emotion, and the virtual pet behaves in a joyful manner. If the user looks sad, the recognition unit infers the expression as a sad emotion, and the virtual pet behaves in a comforting manner. If the user looks surprised, the recognition unit infers the expression as a surprised emotion, and the virtual pet behaves in a surprised manner. This allows the virtual pet to respond according to the user's emotions, resulting in more realistic interactions.

[0109] The reception unit not only accepts user operations, but also understands the context of the operations and suggests appropriate actions. For example, after a user performs an operation to feed a pet, the reception unit can suggest the next activity to play with. Also, after a user performs an operation to play with a pet, the reception unit can suggest the next activity to take a break. Furthermore, before a user performs a specific operation, the reception unit can suggest an action related to that operation. This makes user operations smoother and improves interaction with the virtual pet.

[0110] The interpretation unit not only interprets the user's operation, but can also improve the accuracy of the interpretation by taking into account background information of the operation. For example, if the user performs an operation to feed a pet, the interpretation unit interprets the operation as being based on the pet's health condition. If the user performs an operation to play with a pet, the interpretation unit interprets the operation as being for the purpose of relieving the pet's stress. Furthermore, if the user performs an operation to pet a pet, the interpretation unit interprets the operation as being for the purpose of deepening the bond with the pet. This allows for more accurate interpretation of the user's operation and improves interaction with the virtual pet.

[0111] The control unit can estimate the user's emotions and customize the virtual pet's behavior based on the estimated emotions. For example, if the user is relaxed, the control unit adjusts the virtual pet's behavior to be calm. If the user is excited, the control unit adjusts the virtual pet's behavior to be lively. If the user is sad, the control unit adjusts the virtual pet's behavior to be comforting. This allows the virtual pet to behave in accordance with the user's emotions, resulting in more appropriate interaction.

[0112] The processing flow of the second embodiment will be briefly explained below.

[0113] Step 1: The reception unit receives user operations. User operations include touch operations, voice operations, gesture operations, etc. For example, these operations are received using the smartphone's touch screen, microphone, and camera. Step 2: The interpretation unit interprets the operations received by the reception unit. For example, it uses a large-scale language model (LLM) to interpret the user's operations and determine the meaning of each operation, such as determining that a tap operation is an operation to pet a pet. Step 3: The control unit controls the virtual pet based on the operation interpreted by the interpretation unit. For example, the control unit controls the virtual pet to behave in a way that makes it feel like it is being petted in response to a petting operation, to react to a talking operation, or to eat food in response to a feeding operation.

[0114] 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.

[0115] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0116] 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.

[0117] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0118] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0132] 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.

[0133] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0134] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0135] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

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

[0137] The 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.

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

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

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

[0141] Fig. 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.

[0142] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0144] In the 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.

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

[0146] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0147] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0148] 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.

[0149] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0150] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0151] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0165] 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.

[0166] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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).

[0171] 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.

[0172] 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."

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] [Explanation of symbols]

[0186] 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 reception unit that receives user operations; an interpretation unit that interprets the operation accepted by the acceptance unit; a control unit that causes a virtual pet to move based on the operation interpreted by the interpretation unit; Equipped with A system characterized by:

2. The interpretation unit Interpreting user actions using LLM 2. The system of claim 1.

3. The control unit It has a recognition unit that recognizes the user's voice or facial expression and reflects it in the virtual pet.

2. The system of claim 1.

4. The control unit A tracking unit is provided that records the operations performed by the user on the pet and tracks the pet's growth.

2. The system of claim 1.

5. The control unit A providing unit for providing feedback to the user is provided.

2. The system of claim 1.

6. The recognition unit Interpret user feedback and incorporate it into your virtual pet 4. The system of claim 3.

7. The recognition unit Interprets the user's facial expressions and reflects them on the virtual pet 4. The system of claim 3.

8. The reception unit Estimates the user's emotions and adjusts the timing of accepting operations based on the estimated user emotions.

2. The system of claim 1.

9. The reception unit Analyze the user's past operation history and select the optimal reception method 2. The system of claim 1.

Images