System

Abstract

To provide a system that shares computing resources between edge terminals and efficiently disperses AI processing.SOLUTION: A system according to the embodiment comprises a sharing unit, a dispersion unit, a monitoring unit, and an efficiency improvement unit. The sharing unit shares computational resources possessed by each edge terminal. The dispersion unit disperses AI processing based on the computational resources shared by the sharing unit. The monitoring unit monitors the load of the processing dispersed by the dispersion unit. The efficiency improvement unit uses the computational resources based on the load monitored by the monitoring unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it is difficult to implement high-performance AI on edge devices, and a lack of computing resources is an issue.

[0005] The system according to the embodiment aims to share computing resources between edge terminals and efficiently distribute AI processing. [Means for solving the problem]

[0006] The system according to the embodiment includes a sharing unit, a distribution unit, a monitoring unit, and an efficiency improvement unit. The sharing unit shares the computational resources possessed by each edge terminal. The distribution unit distributes AI processing based on the computational resources shared by the sharing unit. The monitoring unit monitors the load of the processing distributed by the distribution unit. The efficiency improvement unit utilizes the computational resources based on the load monitored by the monitoring unit. Effect of the Invention

[0007] The system according to the embodiment can share computing resources between edge terminals and efficiently distribute AI processing. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The distributed network AI protocol system according to the embodiment of the present invention is a system for providing society with AI that anyone can use. In order to solve the problem that it is difficult to implement high-performance generation AI all the way to edge terminals, this system enables the use of AI in devices with low load distribution, availability, and processing power. For example, a mechanism is constructed for sharing the computing resources of each edge terminal on a network. This makes it possible to efficiently use the resources of each terminal and improve the overall computing power. For example, the computing resources of edge terminals such as smartphones and tablets are shared on a network, and AI processing is distributed. Next, a protocol for distributing AI processing is designed. This protocol determines rules for efficiently using the computing resources of each edge terminal and distributing AI processing. For example, a mechanism is provided for monitoring the status of the computing resources of each terminal in real time and distributing processing from terminals with high load to terminals with low load. Furthermore, software for implementing the distributed network AI protocol is developed. This software is installed on each edge terminal, and realizes resource sharing on the network and AI processing distribution. For example, software will be developed to share the computing resources of each terminal over a network and distribute AI processing. This mechanism will enable AI load balancing, availability, and use on devices with low processing power. For example, by sharing the computing resources of edge terminals such as smartphones and tablets over a network and distributing AI processing, the overall computing power can be improved. In addition, by monitoring the status of the computing resources of each terminal in real time and distributing processing from terminals with high load to terminals with low load, the availability of AI can be improved. As a result, the distributed network AI protocol system will be able to provide society with AI that anyone can use, and will enable AI load balancing, availability, and use on devices with low processing power.

[0029] The distributed network-type AI protocol system according to the embodiment includes a sharing unit, a distribution unit, a monitoring unit, and an efficiency improvement unit. The sharing unit shares the computational resources of each edge terminal. For example, the sharing unit shares the computational resources of each edge terminal using a P2P (peer-to-peer) network. A P2P network is a mechanism in which each terminal directly communicates with each other to share resources without going through a central server. For example, the sharing unit shares computational resources such as the CPU (central processing unit) and memory (storage device) of each terminal on the network. The distribution unit distributes AI processing based on the computational resources shared by the sharing unit. For example, the distribution unit monitors the CPU usage rate and memory usage rate of each terminal in real time, and distributes processing to other terminals when a certain threshold is exceeded. Real time refers to an extremely short delay time and processing being performed almost instantly. For example, the distribution unit distributes processing to other terminals when the CPU usage rate exceeds 80%. The monitoring unit monitors the load of processing distributed by the distribution unit. For example, the monitoring unit monitors the resource status of each terminal in real time and distributes processing from terminals with high load to terminals with low load. The resource status refers to the usage status of resources such as CPU usage rate and memory usage rate. For example, the monitoring unit distributes processing to other terminals when the CPU usage rate exceeds 90%. The efficiency improvement unit efficiently uses the computational resources based on the load monitored by the monitoring unit. For example, the efficiency improvement unit efficiently uses the computational resources of each terminal to improve the overall computational capacity. The overall computational capacity refers to the total amount of computational resources available in the entire system. For example, the efficiency improvement unit improves the overall computational capacity by optimizing the CPU usage rate and memory usage rate of each terminal. As a result, the distributed network type AI protocol system according to the embodiment can efficiently use the computational resources of each edge terminal and enable load distribution, availability, and utilization of AI in devices with low processing capacity.

[0030] The sharing unit shares the computational resources of each edge terminal. For example, the sharing unit shares the computational resources of each edge terminal using a P2P (peer-to-peer) network. A P2P network is a mechanism in which each terminal communicates directly with each other to share resources without going through a central server. Specifically, each terminal shares its computational resources, such as its CPU (central processing unit) and memory (storage device), with other terminals on the network. This allows each terminal to provide its resources to other terminals and simultaneously receive resources from other terminals. For example, if a terminal is performing high-load processing, the terminal can borrow additional computational resources from other terminals. This allows the overall computational resources to be used efficiently and the processing speed to be improved. In addition, the sharing unit monitors the resource usage status of each terminal in real time and redistributes resources as necessary. This prevents waste of resources and maximizes overall efficiency. Furthermore, the sharing unit also takes security measures, and communication between each terminal is encrypted to prevent data leakage and unauthorized access. This allows the sharing unit to safely and efficiently share computational resources and improve the performance of the entire system.

[0031] The distribution unit distributes the AI ​​processing based on the computing resources shared by the sharing unit. For example, the distribution unit monitors the CPU usage and memory usage of each terminal in real time, and distributes processing to other terminals when a certain threshold is exceeded. Specifically, the distribution unit continuously monitors the resource usage of each terminal and moves processing from a terminal with a high load to a terminal with a low load. For example, if the CPU usage of a certain terminal exceeds 80%, the overall load is evenly distributed by moving part of the processing of that terminal to other terminals. This prevents excessive load on a specific terminal and improves the stability of the entire system. In addition, the distribution unit realizes optimal load distribution using an AI algorithm. For example, it can learn the resource usage pattern of each terminal using machine learning and distribute the load at the optimal timing. As a result, the distribution unit can use resources efficiently and effectively and maximize the performance of the entire system. In addition, the distribution unit also has an anomaly detection function, and can take immediate action when it detects an abnormal resource usage pattern. This enables the distribution unit to not only distribute load in real time, but also detect anomalies and take preventive measures, improving the reliability and security of the entire system.

[0032] The monitoring unit monitors the load of the processing distributed by the distribution unit. For example, the monitoring unit monitors the resource status of each terminal in real time and distributes processing from terminals with high load to terminals with low load. Specifically, the monitoring unit continuously monitors resource usage such as CPU usage, memory usage, and network bandwidth of each terminal. This allows the resource usage of each terminal to be accurately grasped and appropriate measures to be taken for terminals with high load. For example, if the CPU usage of a certain terminal exceeds 90%, the monitoring unit immediately issues an instruction to distribute processing to other terminals. This prevents excessive load from being placed on a specific terminal and maintains the stability of the entire system. The monitoring unit also has an anomaly detection function, and if it detects an abnormal resource usage pattern, it can immediately issue an alert and take appropriate measures. For example, if the resource usage rate rises sharply or a pattern that differs from the normal pattern is detected, the monitoring unit immediately issues an alert and notifies the system administrator. This allows the monitoring unit to not only monitor the load in real time, but also detect anomalies and take preventive measures, thereby improving the reliability and safety of the entire system. In addition, the monitoring unit can analyze historical resource usage data and predict future resource demands, thereby assisting in long-term resource management and planned resource allocation to maximize overall system efficiency.

[0033] The efficiency improvement unit efficiently uses the computational resources based on the load monitored by the monitoring unit. For example, the efficiency improvement unit efficiently uses the computational resources of each terminal in order to improve the overall computational capacity. Specifically, the efficiency improvement unit improves the overall computational capacity by optimizing the CPU utilization rate and memory utilization rate of each terminal. For example, the efficiency improvement unit monitors the resource utilization status of each terminal in real time and performs appropriate resource allocation to prevent resource waste. As a result, the overall computational resources are used efficiently and the performance of the entire system is improved. In addition, the efficiency improvement unit realizes optimal resource allocation using an AI algorithm. For example, the resource utilization pattern of each terminal can be learned using machine learning, and resource allocation can be performed at the optimal timing. As a result, the efficiency improvement unit can use resources efficiently and effectively, and maximize the performance of the entire system. Furthermore, the efficiency improvement unit also has an anomaly detection function, and can immediately respond when an abnormal resource utilization pattern is detected. As a result, the efficiency improvement unit can not only optimize resources in real time, but also detect anomalies and take preventive measures, thereby improving the reliability and safety of the entire system. Furthermore, the efficiency improvement unit can analyze past resource utilization data and predict future resource demands. This enables the efficiency improvement unit to support long-term resource management and planned resource allocation, maximizing the efficiency of the entire system.

[0034] The sharing unit can share the computational resources of each edge terminal based on the P2P network. The P2P network is a mechanism in which each terminal communicates with each other directly to share resources without going through a central server. For example, the sharing unit shares computational resources such as the CPU and memory of each terminal on the network. Specific examples of P2P networks include BitTorrent and Gnutella. BitTorrent is a P2P protocol for file sharing, and each terminal downloads a part of a file while uploading it to other terminals, thereby achieving efficient file sharing. Gnutella is a distributed P2P network protocol, and each terminal communicates with each other directly to share files and resources without going through a central server. As a result, by using the P2P network, the computational resources of each edge terminal can be efficiently shared. Some or all of the above-mentioned processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit can input the resource usage status of each terminal into AI and have AI select the optimal resource sharing method.

[0035] The distribution unit monitors the CPU usage rate and memory usage rate of each terminal in real time, and can distribute processing to other terminals when the threshold is exceeded. Real time means that the delay time is extremely short and processing is performed almost instantly. For example, the distribution unit distributes processing to other terminals when the CPU usage rate exceeds 80%. The CPU usage rate is an index showing the proportion of the CPU used, and is usually expressed as a percentage. The memory usage rate is an index showing the proportion of the memory used, and is usually expressed as a percentage. For example, the distribution unit distributes processing to other terminals when the memory usage rate exceeds 70%. This makes it possible to monitor the resource usage status of each terminal in real time and distribute processing efficiently. Some or all of the above-mentioned processing in the distribution unit may be performed, for example, using AI, or may be performed without using AI. For example, the distribution unit can input the resource usage status of each terminal to AI and have AI select the optimal processing distribution method.

[0036] The efficiency improvement unit can use the computational resources of each terminal to improve the overall computational capacity. The overall computational capacity refers to the total amount of computational resources available in the entire system. For example, the efficiency improvement unit improves the overall computational capacity by optimizing the CPU utilization rate and memory utilization rate of each terminal. The CPU utilization rate is an index indicating the proportion of the CPU being used, and is usually expressed as a percentage. The memory utilization rate is an index indicating the proportion of the memory being used, and is usually expressed as a percentage. For example, the efficiency improvement unit distributes processing to other terminals when the CPU utilization rate exceeds 90%. This makes it possible to improve the overall computational capacity by efficiently using the computational resources of each terminal. Some or all of the above-mentioned processing in the efficiency improvement unit may be performed, for example, using AI, or may be performed without using AI. For example, the efficiency improvement unit inputs the resource usage status of each terminal into AI, and allows AI to select the optimal resource usage method.

[0037] The monitoring unit monitors the resource status of each terminal in real time, and can distribute processing from a terminal with a high load to other terminals. The resource status refers to the resource usage status such as CPU usage rate and memory usage rate. For example, the monitoring unit distributes processing to other terminals when the CPU usage rate exceeds 90%. The CPU usage rate is an index showing the percentage of the CPU used, and is usually expressed as a percentage. The memory usage rate is an index showing the percentage of the memory used, and is usually expressed as a percentage. For example, the monitoring unit distributes processing to other terminals when the memory usage rate exceeds 80%. This makes it possible to monitor the resource status of each terminal in real time and distribute the load efficiently. A part or all of the above-mentioned processing in the monitoring unit may be performed, for example, using AI, or may be performed without using AI. For example, the monitoring unit inputs the resource usage status of each terminal to AI, and allows AI to select the optimal load distribution method.

[0038] The sharing unit can analyze the past resource usage history of each edge terminal and select the optimal sharing method. The sharing unit, for example, analyzes the past CPU usage rate of each terminal and determines the optimal sharing timing. The CPU usage rate is an index indicating the proportion of the CPU used, and is usually expressed as a percentage. For example, the sharing unit shares resources by avoiding time periods when the CPU usage rate is high. The sharing unit can also select an efficient resource sharing method based on the memory usage history of each terminal. The memory usage history is data indicating the proportion of the memory used, and is usually recorded by time. For example, the sharing unit shares resources during time periods when the memory usage rate is low. The sharing unit can also analyze the network usage history of each terminal and propose the optimal sharing method. The network usage history is data indicating the proportion of the network used, and is usually recorded by time. For example, the sharing unit shares resources during time periods when the network usage rate is low. In this way, the optimal resource sharing method can be selected by analyzing the past resource usage history. A part or all of the above-mentioned processing in the sharing unit may be performed, for example, using AI, or may be performed without using AI. For example, the sharing unit can input the resource usage history of each terminal into the AI ​​and have the AI ​​select the optimal sharing method.

[0039] The sharing unit can filter resources based on the current usage status and priority of each terminal when sharing computation resources. The sharing unit filters resources to be shared based on, for example, the current CPU usage of each terminal. CPU usage is an index indicating the proportion of the CPU being used, and is usually expressed as a percentage. For example, the sharing unit limits resource sharing from terminals with high CPU usage. The sharing unit can also select resources to be shared taking into account the memory usage status of each terminal. Memory usage is an index indicating the proportion of the memory being used, and is usually expressed as a percentage. For example, the sharing unit limits resource sharing from terminals with high memory usage. The sharing unit can also filter resources to be shared based on the priority of each terminal. Priority is an index indicating the importance and urgency of tasks held by each terminal, and is usually expressed as a numerical value or a rank. For example, the sharing unit prioritizes resource sharing from terminals with high priority. This enables efficient resource sharing by filtering resources based on the current usage status and priority of each terminal. Some or all of the above-mentioned processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit may input the usage status and priority data of each terminal to the AI ​​and have the AI ​​select the optimal resource filtering method.

[0040] When sharing computational resources, the sharing unit can preferentially share highly relevant resources by considering the geographical location information of each terminal. The sharing unit, for example, preferentially shares computational resources between nearby terminals. The geographical location information is data indicating the physical location of each terminal, and is usually obtained using GPS (Global Positioning System) data or location information services. For example, the sharing unit shares resources between geographically close terminals to minimize communication delays. The communication delay refers to the time difference between when data is transmitted and when it is received, and is usually measured in milliseconds. For example, the sharing unit preferentially shares highly relevant resources based on the geographical location information. As a result, highly relevant resources can be shared efficiently by considering the geographical location information. A part or all of the above-mentioned processing in the sharing unit may be performed, for example, using AI, or may be performed without using AI. For example, the sharing unit inputs the geographical location information of each terminal into AI, and allows AI to select an optimal resource sharing method.

[0041] The sharing unit can analyze the social media activity of each terminal and share related resources when sharing computational resources. The sharing unit, for example, analyzes the social media activity of each terminal and shares related resources preferentially. Social media activity refers to actions such as posts, comments, and likes made by users on social media. For example, the sharing unit shares highly relevant resources based on trend information on social media. Trend information refers to keywords and hashtags that are trending on social media. For example, the sharing unit analyzes the social media activity history of each terminal and proposes an optimal resource sharing method. The social media activity history is data that records actions on social media that users have taken in the past, and is usually recorded by time. For example, the sharing unit preferentially shares highly relevant resources based on the past social media activity history. In this way, highly relevant resources can be shared efficiently by analyzing social media activities. A part or all of the above-mentioned processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit inputs the social media activity data of each terminal into AI and allows AI to select the optimal resource sharing method.

[0042] The distribution unit can analyze the CPU usage rate and memory usage rate of each terminal and select the optimal distribution method. The distribution unit selects the optimal distribution method based on, for example, the CPU usage rate of each terminal. The CPU usage rate is an index indicating the proportion of the CPU used, and is usually expressed as a percentage. For example, the distribution unit limits the distribution of processing from terminals with high CPU usage rates. The distribution unit can also analyze the memory usage rate of each terminal and select an efficient distribution method. The memory usage rate is an index indicating the proportion of the memory used, and is usually expressed as a percentage. For example, the distribution unit limits the distribution of processing from terminals with high memory usage rates. The distribution unit can also propose the optimal distribution method taking into account the network usage rate of each terminal. The network usage rate is an index indicating the proportion of the network used, and is usually expressed as a percentage. For example, the distribution unit limits the distribution of processing from terminals with high network usage rates. In this way, the optimal processing distribution method can be selected by analyzing the resource usage status of each terminal. A part or all of the above-mentioned processing in the distribution unit may be performed, for example, using AI, or may be performed without using AI. For example, the distribution unit can input the resource usage status of each terminal into the AI ​​and have the AI ​​select the optimal processing distribution method.

[0043] The distribution unit can adjust the level of detail of distribution based on the current task status of each terminal when distributing processing. The distribution unit adjusts the level of detail of distribution based on, for example, the current task status of each terminal. The task status is data indicating the number, type, and priority of tasks currently being executed by each terminal. For example, the distribution unit limits processing distribution from a terminal having a large number of tasks. The distribution unit can also determine the level of detail of distribution based on the priority of each terminal. Priority is an index indicating the importance and urgency of tasks held by each terminal, and is usually expressed as a numerical value or a rank. For example, the distribution unit prioritizes processing distribution from a terminal having a task with a high priority. The distribution unit can also adjust the level of detail of distribution taking into account the resource usage status of each terminal. Resource usage status refers to resource usage status such as CPU usage rate and memory usage rate. For example, the distribution unit limits processing distribution from a terminal with a high CPU usage rate. As a result, efficient processing distribution is possible by adjusting the level of detail of distribution based on the task status of each terminal. A part or all of the above-mentioned processing in the distribution unit may be performed using, for example, AI, or may be performed without using AI. For example, the distribution unit can input task status data from each terminal into the AI ​​and have the AI ​​select the optimal distribution method.

[0044] When distributing processing, the distribution unit can select the optimal distribution method by taking into account the geographical location information of each terminal. For example, the distribution unit distributes processing preferentially among nearby terminals. The geographical location information is data indicating the physical location of each terminal, and is usually obtained using GPS (Global Positioning System) data or location information services. For example, the distribution unit distributes processing among geographically close terminals to minimize communication delays. Communication delays refer to the time difference between when data is transmitted and when it is received, and are usually measured in milliseconds. For example, the distribution unit selects the optimal distribution method based on the geographical location information. In this way, the optimal processing distribution method can be selected by taking the geographical location information into account. A part or all of the above-mentioned processing in the distribution unit may be performed, for example, using AI, or may be performed without using AI. For example, the distribution unit can input the geographical location information of each terminal into AI and have AI select the optimal processing distribution method.

[0045] The distribution unit can improve the accuracy of distribution by referring to the related literature of each terminal when distributing processing. The distribution unit, for example, refers to the related literature of each terminal and selects the optimal distribution method. The related literature refers to literature and database information that each terminal has referred to in the past. For example, the distribution unit improves the accuracy of distribution based on the related literature. The accuracy of distribution is an index that indicates how efficiently the distribution of processing is performed, and is usually expressed as a percentage or a score. For example, the distribution unit analyzes the past processing history of each terminal and proposes the optimal distribution method. The processing history refers to the record of processing that each terminal has performed in the past, and is usually recorded by time. For example, the distribution unit selects the optimal distribution method based on the past processing history. As a result, the accuracy of distribution can be improved by referring to the related literature. Part or all of the above-mentioned processing in the distribution unit may be performed using, for example, AI, or may be performed without using AI. For example, the distribution unit can input the related literature data of each terminal into AI and have AI select the optimal distribution method.

[0046] The monitoring unit can analyze the resource status of each terminal and select the optimal monitoring method. The monitoring unit selects the optimal monitoring method based on, for example, the CPU usage rate of each terminal. The CPU usage rate is an index indicating the percentage of the CPU usage rate, and is usually expressed as a percentage. For example, the monitoring unit increases the monitoring frequency of a terminal with a high CPU usage rate. The monitoring unit can also analyze the memory usage rate of each terminal and select an efficient monitoring method. The memory usage rate is an index indicating the percentage of the memory usage rate, and is usually expressed as a percentage. For example, the monitoring unit increases the monitoring frequency of a terminal with a high memory usage rate. The monitoring unit can also propose the optimal monitoring method in consideration of the network usage rate of each terminal. The network usage rate is an index indicating the percentage of the network usage rate, and is usually expressed as a percentage. For example, the monitoring unit increases the monitoring frequency of a terminal with a high network usage rate. In this way, the optimal monitoring method can be selected by analyzing the resource status of each terminal. A part or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input resource status data for each terminal into the AI ​​and have the AI ​​select the optimal monitoring method.

[0047] The monitoring unit can adjust the level of detail of monitoring by referring to the past resource usage history of each terminal when monitoring the load. The monitoring unit adjusts the level of detail of monitoring based on, for example, the past CPU usage history of each terminal. The CPU usage history is data indicating the percentage of CPU usage in the past, and is usually recorded by time. For example, the monitoring unit increases the monitoring frequency during time periods when CPU usage is high. The monitoring unit can also determine the level of detail of monitoring by referring to the memory usage history of each terminal. The memory usage history is data indicating the percentage of memory usage in the past, and is usually recorded by time. For example, the monitoring unit increases the monitoring frequency during time periods when memory usage is high. The monitoring unit can also analyze the network usage history of each terminal and propose an optimal monitoring method. The network usage history is data indicating the percentage of network usage in the past, and is usually recorded by time. For example, the monitoring unit increases the monitoring frequency during time periods when network usage is high. In this way, the optimal monitoring method can be selected by referring to the past resource usage history. A part or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input resource usage history data for each terminal into the AI ​​and have the AI ​​select the optimal monitoring method.

[0048] The monitoring unit can select the optimal monitoring method by considering the geographical location information of each terminal when monitoring the load. For example, the monitoring unit prioritizes monitoring the load between nearby terminals. The geographical location information is data indicating the physical location of each terminal, and is usually acquired using GPS (Global Positioning System) data or location information services. For example, the monitoring unit monitors the load between geographically close terminals to minimize communication delays. The communication delay refers to the time difference between when data is transmitted and when it is received, and is usually measured in milliseconds. For example, the monitoring unit selects the optimal monitoring method based on the geographical location information. In this way, the optimal load monitoring method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the monitoring unit may be performed, for example, using AI, or may be performed without using AI. For example, the monitoring unit can input the geographical location information of each terminal to AI and have AI select the optimal load monitoring method.

[0049] The monitoring unit can improve the accuracy of monitoring by referring to the related literature of each terminal when monitoring the load. The monitoring unit, for example, refers to the related literature of each terminal and selects the optimal monitoring method. The related literature refers to the literature or database information that each terminal has referred to in the past. For example, the monitoring unit improves the accuracy of monitoring based on the related literature. The accuracy of monitoring is an index that indicates how efficiently the load monitoring is performed, and is usually expressed as a percentage or a score. For example, the monitoring unit analyzes the past load history of each terminal and proposes the optimal monitoring method. The load history refers to the record of the load that each terminal has experienced in the past, and is usually recorded by time. For example, the monitoring unit selects the optimal monitoring method based on the past load history. As a result, the accuracy of monitoring can be improved by referring to the related literature. A part or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input the related literature data of each terminal into AI and have AI select the optimal monitoring method.

[0050] The efficiency unit can analyze the resource usage history of each terminal and select the optimal efficiency improvement method. The efficiency unit selects the optimal efficiency improvement method based on, for example, the CPU usage history of each terminal. The CPU usage history is data indicating the percentage of CPU usage in the past, and is usually recorded by time. For example, the efficiency unit selects an efficiency improvement method for a time period when the CPU usage rate is high. The efficiency unit can also analyze the memory usage history of each terminal and select an efficient resource usage method. The memory usage history is data indicating the percentage of memory usage in the past, and is usually recorded by time. For example, the efficiency unit selects an efficiency improvement method for a time period when the memory usage rate is high. The efficiency unit can also propose the optimal efficiency improvement method by taking into account the network usage history of each terminal. The network usage history is data indicating the percentage of network usage in the past, and is usually recorded by time. For example, the efficiency unit selects an efficiency improvement method for a time period when the network usage rate is high. In this way, the optimal efficiency improvement method can be selected by analyzing the resource usage history. A part or all of the above-mentioned processing in the efficiency unit may be performed using, for example, AI, or may be performed without using AI. For example, the efficiency unit can input resource usage history data for each terminal into the AI ​​and have the AI ​​select the optimal efficiency method.

[0051] The efficiency unit can adjust the degree of detail of the efficiency based on the current usage status of each terminal when the computational resource is made more efficient. The efficiency unit adjusts the degree of detail of the efficiency based on, for example, the current CPU usage status of each terminal. The CPU usage status is data indicating the current proportion of the CPU being used, and is usually expressed as a percentage. For example, the efficiency unit increases the efficiency degree of detail of a terminal with a high CPU usage rate. The efficiency unit can also determine the degree of detail of the efficiency in consideration of the memory usage status of each terminal. The memory usage status is data indicating the current proportion of the memory being used, and is usually expressed as a percentage. For example, the efficiency unit increases the efficiency degree of detail of a terminal with a high memory usage rate. The efficiency unit can also analyze the network usage status of each terminal and propose an optimal efficiency method. The network usage status is data indicating the current proportion of the network being used, and is usually expressed as a percentage. For example, the efficiency unit increases the efficiency degree of detail of a terminal with a high network usage rate. This allows efficient resource use by adjusting the degree of detail of the efficiency based on the usage status of each terminal. Some or all of the above-mentioned processes in the efficiency improvement unit may be performed using AI, for example, or may be performed without using AI. For example, the efficiency improvement unit may input the usage status data of each terminal to AI and have the AI ​​select the optimal efficiency improvement method.

[0052] The efficiency improvement unit can select an optimal efficiency improvement method by considering the geographical location information of each terminal when improving the efficiency of computational resources. For example, the efficiency improvement unit prioritizes resource efficiency between nearby terminals. The geographical location information is data indicating the physical location of each terminal, and is usually obtained using GPS (Global Positioning System) data or location information services. For example, the efficiency improvement unit improves resource efficiency between geographically close terminals to minimize communication delays. Communication delays refer to the time difference between when data is transmitted and when it is received, and are usually measured in milliseconds. For example, the efficiency improvement unit selects an optimal efficiency improvement method based on the geographical location information. In this way, the optimal efficiency improvement method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the efficiency improvement unit may be performed, for example, using AI, or may be performed without using AI. For example, the efficiency improvement unit can input the geographical location information of each terminal to AI and cause AI to select an optimal efficiency improvement method.

[0053] The efficiency unit can improve the accuracy of efficiency by referring to the related literature of each terminal when improving the efficiency of computational resources. The efficiency unit, for example, refers to the related literature of each terminal and selects the optimal efficiency method. The related literature refers to the literature and database information that each terminal has referred to in the past. For example, the efficiency unit improves the accuracy of efficiency based on the related literature. The accuracy of efficiency is an index that indicates how effectively resource efficiency is performed, and is usually expressed as a percentage or a score. For example, the efficiency unit analyzes the past resource usage history of each terminal and proposes the optimal efficiency method. The resource usage history is data that indicates how much resource each terminal has used in the past, and is usually recorded by time. For example, the efficiency unit selects the optimal efficiency method based on the past resource usage history. As a result, the accuracy of efficiency can be improved by referring to the related literature. A part or all of the above-mentioned processing in the efficiency unit may be performed using, for example, AI, or may be performed without using AI. For example, the efficiency unit inputs the related literature data of each terminal into AI and allows AI to select the optimal efficiency method.

[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 sharing unit can adjust the sharing of computational resources taking into account the remaining battery level of each edge terminal. For example, the sharing unit can limit resource sharing from a terminal with a low remaining battery level. The sharing unit can also prioritize resource sharing with a terminal with a high remaining battery level. Furthermore, the sharing unit can suspend resource sharing when the remaining battery level falls below a certain threshold. This enables efficient resource sharing by taking into account the remaining battery level of each terminal. Some or all of the above-mentioned processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit can input remaining battery level data of each terminal to AI and have AI select an optimal resource sharing method.

[0056] The distribution unit can analyze the usage patterns of users of each terminal and select the optimal distribution method. For example, the distribution unit distributes processing by avoiding time periods when users frequently use the terminal. The distribution unit can also concentrate processing during time periods when users are not using the terminal. Furthermore, the distribution unit can determine the priority of processing based on the usage patterns of users. This allows efficient processing distribution by taking into account the usage patterns of users. Some or all of the above-mentioned processing in the distribution unit may be performed using, for example, AI, or may be performed without using AI. For example, the distribution unit can input usage pattern data of each terminal into AI and have AI select the optimal processing distribution method.

[0057] The efficiency improvement unit can adjust the efficiency improvement method of the computational resources by taking into account the hardware characteristics of each terminal. For example, the efficiency improvement unit selects the optimal efficiency improvement method based on hardware characteristics such as the CPU clock speed, the number of cores, and the memory capacity. The efficiency improvement unit can also adjust the resource allocation according to the hardware characteristics of each terminal. Furthermore, the efficiency improvement unit can also determine the priority of processing based on the hardware characteristics. This enables efficient resource utilization by taking into account the hardware characteristics of each terminal. A part or all of the above-mentioned processing in the efficiency improvement unit may be performed, for example, using AI or may be performed without using AI. For example, the efficiency improvement unit can input the hardware characteristic data of each terminal to AI and have AI select the optimal efficiency improvement method.

[0058] The monitoring unit can monitor the security status of each terminal in real time and restrict resource sharing from terminals with a high security risk. For example, the monitoring unit restricts resource sharing from terminals with a high risk of virus infection or unauthorized access. The monitoring unit can also resume resource sharing when the security status has improved. Furthermore, the monitoring unit can also share resources by prioritizing terminals with a low security risk. This enables safe resource sharing by taking into account the security status of each terminal. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input security status data of each terminal to AI and have the AI ​​select the optimal resource sharing method.

[0059] The sharing unit can monitor the energy consumption of each terminal in real time and limit resource sharing from terminals with high energy consumption. For example, the sharing unit can suspend resource sharing from terminals with high energy consumption. The sharing unit can also prioritize resource sharing with terminals with low energy consumption. Furthermore, the sharing unit can resume resource sharing when the energy consumption falls below a certain threshold. This enables efficient resource sharing by taking into account the energy consumption of each terminal. Some or all of the above-mentioned processing in the sharing unit may be performed, for example, using AI or may be performed without using AI. For example, the sharing unit can input energy consumption data of each terminal to AI and have the AI ​​select the optimal resource sharing method.

[0060] The distribution unit can monitor the communication speed of each terminal in real time and limit the distribution of processing from terminals with low communication speeds. For example, the distribution unit can temporarily suspend the distribution of processing from terminals with low communication speeds. The distribution unit can also distribute processing by prioritizing terminals with high communication speeds. Furthermore, the distribution unit can resume the distribution of processing when the communication speed falls below a certain threshold. This enables efficient distribution of processing by taking into account the communication speed of each terminal. Some or all of the above-mentioned processing in the distribution unit may be performed, for example, using AI or may be performed without using AI. For example, the distribution unit can input communication speed data of each terminal to AI and have AI select the optimal distribution method of processing.

[0061] The process flow of the first embodiment will be briefly described below.

[0062] Step 1: The sharing unit shares the computing resources held by each edge terminal. For example, the sharing unit uses a P2P (peer-to-peer) network to share the computing resources held by each edge terminal. A P2P network is a mechanism in which each terminal communicates with each other directly, sharing resources without going through a central server. Specifically, the computing resources such as each terminal's CPU (central processing unit) and memory (storage device) are shared over the network. Step 2: The distribution unit distributes the AI ​​processing based on the computing resources shared by the sharing unit. For example, the distribution unit monitors the CPU usage and memory usage of each terminal in real time, and distributes processing to other terminals if a certain threshold is exceeded. Specifically, if CPU usage exceeds 80%, processing is distributed to other terminals. Step 3: The monitoring unit monitors the processing load distributed by the distribution unit. For example, the monitoring unit monitors the resource status of each terminal in real time and distributes processing from terminals with high loads to terminals with low loads. Specifically, if the CPU usage rate exceeds 90%, the processing is distributed to other terminals. Step 4: The efficiency improvement unit efficiently uses the computing resources based on the load monitored by the monitoring unit. For example, the efficiency improvement unit efficiently uses the computing resources of each terminal in order to improve the overall computing capacity. Specifically, the overall computing capacity is improved by optimizing the CPU usage and memory usage of each terminal.

[0063] (Example 2) The distributed network AI protocol system according to the embodiment of the present invention is a system for providing society with AI that anyone can use. In order to solve the problem that it is difficult to implement high-performance generation AI all the way to edge terminals, this system enables the use of AI in devices with low load distribution, availability, and processing power. For example, a mechanism is constructed for sharing the computing resources of each edge terminal on a network. This makes it possible to efficiently use the resources of each terminal and improve the overall computing power. For example, the computing resources of edge terminals such as smartphones and tablets are shared on a network, and AI processing is distributed. Next, a protocol for distributing AI processing is designed. This protocol determines rules for efficiently using the computing resources of each edge terminal and distributing AI processing. For example, a mechanism is provided for monitoring the status of the computing resources of each terminal in real time and distributing processing from terminals with high load to terminals with low load. Furthermore, software for implementing the distributed network AI protocol is developed. This software is installed on each edge terminal, and realizes resource sharing on the network and AI processing distribution. For example, software will be developed to share the computing resources of each terminal over a network and distribute AI processing. This mechanism will enable AI load balancing, availability, and use on devices with low processing power. For example, by sharing the computing resources of edge terminals such as smartphones and tablets over a network and distributing AI processing, the overall computing power can be improved. In addition, by monitoring the status of the computing resources of each terminal in real time and distributing processing from terminals with high load to terminals with low load, the availability of AI can be improved. As a result, the distributed network AI protocol system will be able to provide society with AI that anyone can use, and will enable AI load balancing, availability, and use on devices with low processing power.

[0064] The distributed network-type AI protocol system according to the embodiment includes a sharing unit, a distribution unit, a monitoring unit, and an efficiency improvement unit. The sharing unit shares the computational resources of each edge terminal. For example, the sharing unit shares the computational resources of each edge terminal using a P2P (peer-to-peer) network. A P2P network is a mechanism in which each terminal directly communicates with each other to share resources without going through a central server. For example, the sharing unit shares computational resources such as the CPU (central processing unit) and memory (storage device) of each terminal on the network. The distribution unit distributes AI processing based on the computational resources shared by the sharing unit. For example, the distribution unit monitors the CPU usage rate and memory usage rate of each terminal in real time, and distributes processing to other terminals when a certain threshold is exceeded. Real time refers to an extremely short delay time and processing being performed almost instantly. For example, the distribution unit distributes processing to other terminals when the CPU usage rate exceeds 80%. The monitoring unit monitors the load of processing distributed by the distribution unit. For example, the monitoring unit monitors the resource status of each terminal in real time and distributes processing from terminals with high load to terminals with low load. The resource status refers to the usage status of resources such as CPU usage rate and memory usage rate. For example, the monitoring unit distributes processing to other terminals when the CPU usage rate exceeds 90%. The efficiency improvement unit efficiently uses the computational resources based on the load monitored by the monitoring unit. For example, the efficiency improvement unit efficiently uses the computational resources of each terminal to improve the overall computational capacity. The overall computational capacity refers to the total amount of computational resources available in the entire system. For example, the efficiency improvement unit improves the overall computational capacity by optimizing the CPU usage rate and memory usage rate of each terminal. As a result, the distributed network type AI protocol system according to the embodiment can efficiently use the computational resources of each edge terminal and enable load distribution, availability, and utilization of AI in devices with low processing capacity.

[0065] The sharing unit shares the computational resources of each edge terminal. For example, the sharing unit shares the computational resources of each edge terminal using a P2P (peer-to-peer) network. A P2P network is a mechanism in which each terminal communicates directly with each other to share resources without going through a central server. Specifically, each terminal shares its computational resources, such as its CPU (central processing unit) and memory (storage device), with other terminals on the network. This allows each terminal to provide its resources to other terminals and simultaneously receive resources from other terminals. For example, if a terminal is performing high-load processing, the terminal can borrow additional computational resources from other terminals. This allows the overall computational resources to be used efficiently and the processing speed to be improved. In addition, the sharing unit monitors the resource usage status of each terminal in real time and redistributes resources as necessary. This prevents waste of resources and maximizes overall efficiency. Furthermore, the sharing unit also takes security measures, and communication between each terminal is encrypted to prevent data leakage and unauthorized access. This allows the sharing unit to safely and efficiently share computational resources and improve the performance of the entire system.

[0066] The distribution unit distributes the AI ​​processing based on the computing resources shared by the sharing unit. For example, the distribution unit monitors the CPU usage and memory usage of each terminal in real time, and distributes processing to other terminals when a certain threshold is exceeded. Specifically, the distribution unit continuously monitors the resource usage of each terminal and moves processing from a terminal with a high load to a terminal with a low load. For example, if the CPU usage of a certain terminal exceeds 80%, the overall load is evenly distributed by moving part of the processing of that terminal to other terminals. This prevents excessive load on a specific terminal and improves the stability of the entire system. In addition, the distribution unit realizes optimal load distribution using an AI algorithm. For example, it can learn the resource usage pattern of each terminal using machine learning and distribute the load at the optimal timing. As a result, the distribution unit can use resources efficiently and effectively and maximize the performance of the entire system. In addition, the distribution unit also has an anomaly detection function, and can take immediate action when it detects an abnormal resource usage pattern. This enables the distribution unit to not only distribute load in real time, but also detect anomalies and take preventive measures, improving the reliability and security of the entire system.

[0067] The monitoring unit monitors the load of the processing distributed by the distribution unit. For example, the monitoring unit monitors the resource status of each terminal in real time and distributes processing from terminals with high load to terminals with low load. Specifically, the monitoring unit continuously monitors resource usage such as CPU usage, memory usage, and network bandwidth of each terminal. This allows the resource usage of each terminal to be accurately grasped and appropriate measures to be taken for terminals with high load. For example, if the CPU usage of a certain terminal exceeds 90%, the monitoring unit immediately issues an instruction to distribute processing to other terminals. This prevents excessive load from being placed on a specific terminal and maintains the stability of the entire system. The monitoring unit also has an anomaly detection function, and if it detects an abnormal resource usage pattern, it can immediately issue an alert and take appropriate measures. For example, if the resource usage rate rises sharply or a pattern that differs from the normal pattern is detected, the monitoring unit immediately issues an alert and notifies the system administrator. This allows the monitoring unit to not only monitor the load in real time, but also detect anomalies and take preventive measures, thereby improving the reliability and safety of the entire system. In addition, the monitoring unit can analyze historical resource usage data and predict future resource demands, thereby assisting in long-term resource management and planned resource allocation to maximize overall system efficiency.

[0068] The efficiency improvement unit efficiently uses the computational resources based on the load monitored by the monitoring unit. For example, the efficiency improvement unit efficiently uses the computational resources of each terminal in order to improve the overall computational capacity. Specifically, the efficiency improvement unit improves the overall computational capacity by optimizing the CPU utilization rate and memory utilization rate of each terminal. For example, the efficiency improvement unit monitors the resource utilization status of each terminal in real time and performs appropriate resource allocation to prevent resource waste. As a result, the overall computational resources are used efficiently and the performance of the entire system is improved. In addition, the efficiency improvement unit realizes optimal resource allocation using an AI algorithm. For example, the resource utilization pattern of each terminal can be learned using machine learning, and resource allocation can be performed at the optimal timing. As a result, the efficiency improvement unit can use resources efficiently and effectively, and maximize the performance of the entire system. Furthermore, the efficiency improvement unit also has an anomaly detection function, and can immediately respond when an abnormal resource utilization pattern is detected. As a result, the efficiency improvement unit can not only optimize resources in real time, but also detect anomalies and take preventive measures, thereby improving the reliability and safety of the entire system. Furthermore, the efficiency improvement unit can analyze past resource utilization data and predict future resource demands. This enables the efficiency improvement unit to support long-term resource management and planned resource allocation, maximizing the efficiency of the entire system.

[0069] The sharing unit can share the computational resources of each edge terminal based on the P2P network. The P2P network is a mechanism in which each terminal communicates with each other directly to share resources without going through a central server. For example, the sharing unit shares computational resources such as the CPU and memory of each terminal on the network. Specific examples of P2P networks include BitTorrent and Gnutella. BitTorrent is a P2P protocol for file sharing, and each terminal downloads a part of a file while uploading it to other terminals, thereby achieving efficient file sharing. Gnutella is a distributed P2P network protocol, and each terminal communicates with each other directly to share files and resources without going through a central server. As a result, by using the P2P network, the computational resources of each edge terminal can be efficiently shared. Some or all of the above-mentioned processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit can input the resource usage status of each terminal into AI and have AI select the optimal resource sharing method.

[0070] The distribution unit monitors the CPU usage rate and memory usage rate of each terminal in real time, and can distribute processing to other terminals when the threshold is exceeded. Real time means that the delay time is extremely short and processing is performed almost instantly. For example, the distribution unit distributes processing to other terminals when the CPU usage rate exceeds 80%. The CPU usage rate is an index showing the proportion of the CPU used, and is usually expressed as a percentage. The memory usage rate is an index showing the proportion of the memory used, and is usually expressed as a percentage. For example, the distribution unit distributes processing to other terminals when the memory usage rate exceeds 70%. This makes it possible to monitor the resource usage status of each terminal in real time and distribute processing efficiently. Some or all of the above-mentioned processing in the distribution unit may be performed, for example, using AI, or may be performed without using AI. For example, the distribution unit can input the resource usage status of each terminal to AI and have AI select the optimal processing distribution method.

[0071] The efficiency improvement unit can use the computational resources of each terminal to improve the overall computational capacity. The overall computational capacity refers to the total amount of computational resources available in the entire system. For example, the efficiency improvement unit improves the overall computational capacity by optimizing the CPU utilization rate and memory utilization rate of each terminal. The CPU utilization rate is an index indicating the proportion of the CPU being used, and is usually expressed as a percentage. The memory utilization rate is an index indicating the proportion of the memory being used, and is usually expressed as a percentage. For example, the efficiency improvement unit distributes processing to other terminals when the CPU utilization rate exceeds 90%. This makes it possible to improve the overall computational capacity by efficiently using the computational resources of each terminal. Some or all of the above-mentioned processing in the efficiency improvement unit may be performed, for example, using AI, or may be performed without using AI. For example, the efficiency improvement unit inputs the resource usage status of each terminal into AI, and allows AI to select the optimal resource usage method.

[0072] The monitoring unit monitors the resource status of each terminal in real time, and can distribute processing from a terminal with a high load to other terminals. The resource status refers to the resource usage status such as CPU usage rate and memory usage rate. For example, the monitoring unit distributes processing to other terminals when the CPU usage rate exceeds 90%. The CPU usage rate is an index showing the percentage of the CPU used, and is usually expressed as a percentage. The memory usage rate is an index showing the percentage of the memory used, and is usually expressed as a percentage. For example, the monitoring unit distributes processing to other terminals when the memory usage rate exceeds 80%. This makes it possible to monitor the resource status of each terminal in real time and distribute the load efficiently. A part or all of the above-mentioned processing in the monitoring unit may be performed, for example, using AI, or may be performed without using AI. For example, the monitoring unit inputs the resource usage status of each terminal to AI, and allows AI to select the optimal load distribution method.

[0073] The sharing unit can estimate the user's emotion and adjust the timing of sharing the computational resources based on the estimated user's emotion. For example, when the user is feeling stressed, the sharing unit delays sharing of the computational resources to reduce the burden on the user. The user's emotion is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the sharing unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the sharing unit calculates an emotion score based on the change in facial expression. The sharing unit can also record the user's voice and estimate the emotion using a voice analysis technology. For example, the sharing unit analyzes the tone and speed of the voice and calculates the emotion score. The sharing unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the sharing unit calculates an emotion score based on the fluctuation of the heart rate. This allows the burden on the user to be reduced by adjusting the timing of sharing computational resources according to the user's emotions. Some or all of the above-mentioned processing in the sharing unit may be performed, for example, using AI, or may be performed without using AI. For example, the sharing unit may input the user's emotion data to the AI ​​and have the AI ​​select the optimal sharing timing.

[0074] The sharing unit can analyze the past resource usage history of each edge terminal and select the optimal sharing method. The sharing unit, for example, analyzes the past CPU usage rate of each terminal and determines the optimal sharing timing. The CPU usage rate is an index indicating the proportion of the CPU used, and is usually expressed as a percentage. For example, the sharing unit shares resources by avoiding time periods when the CPU usage rate is high. The sharing unit can also select an efficient resource sharing method based on the memory usage history of each terminal. The memory usage history is data indicating the proportion of the memory used, and is usually recorded by time. For example, the sharing unit shares resources during time periods when the memory usage rate is low. The sharing unit can also analyze the network usage history of each terminal and propose the optimal sharing method. The network usage history is data indicating the proportion of the network used, and is usually recorded by time. For example, the sharing unit shares resources during time periods when the network usage rate is low. In this way, the optimal resource sharing method can be selected by analyzing the past resource usage history. A part or all of the above-mentioned processing in the sharing unit may be performed, for example, using AI, or may be performed without using AI. For example, the sharing unit can input the resource usage history of each terminal into the AI ​​and have the AI ​​select the optimal sharing method.

[0075] The sharing unit can filter resources based on the current usage status and priority of each terminal when sharing computation resources. The sharing unit filters resources to be shared based on, for example, the current CPU usage of each terminal. CPU usage is an index indicating the proportion of the CPU being used, and is usually expressed as a percentage. For example, the sharing unit limits resource sharing from terminals with high CPU usage. The sharing unit can also select resources to be shared taking into account the memory usage status of each terminal. Memory usage is an index indicating the proportion of the memory being used, and is usually expressed as a percentage. For example, the sharing unit limits resource sharing from terminals with high memory usage. The sharing unit can also filter resources to be shared based on the priority of each terminal. Priority is an index indicating the importance and urgency of tasks held by each terminal, and is usually expressed as a numerical value or a rank. For example, the sharing unit prioritizes resource sharing from terminals with high priority. This enables efficient resource sharing by filtering resources based on the current usage status and priority of each terminal. Some or all of the above-mentioned processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit may input the usage status and priority data of each terminal to the AI ​​and have the AI ​​select the optimal resource filtering method.

[0076] The sharing unit can estimate the user's emotion and determine the priority of the computational resources to be shared based on the estimated user's emotion. For example, when the user is feeling stressed, the sharing unit preferentially shares resources with a lower importance. The user's emotion is realized by using an emotion estimation function using an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI. For example, the sharing unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the sharing unit calculates an emotion score based on the change in facial expression. The sharing unit can also record the user's voice and estimate the emotion using a voice analysis technology. For example, the sharing unit analyzes the tone and speed of the voice and calculates the emotion score. The sharing unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the sharing unit calculates an emotion score based on the fluctuation of the heart rate. This enables efficient resource sharing by determining the priority of computational resources according to the user's emotion. Some or all of the above-mentioned processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit may input user emotion data to AI and have the AI ​​select an optimal resource sharing method.

[0077] When sharing computational resources, the sharing unit can preferentially share highly relevant resources by considering the geographical location information of each terminal. The sharing unit, for example, preferentially shares computational resources between nearby terminals. The geographical location information is data indicating the physical location of each terminal, and is usually obtained using GPS (Global Positioning System) data or location information services. For example, the sharing unit shares resources between geographically close terminals to minimize communication delays. The communication delay refers to the time difference between when data is transmitted and when it is received, and is usually measured in milliseconds. For example, the sharing unit preferentially shares highly relevant resources based on the geographical location information. As a result, highly relevant resources can be shared efficiently by considering the geographical location information. A part or all of the above-mentioned processing in the sharing unit may be performed, for example, using AI, or may be performed without using AI. For example, the sharing unit inputs the geographical location information of each terminal into AI, and allows AI to select an optimal resource sharing method.

[0078] The sharing unit can analyze the social media activity of each terminal and share related resources when sharing computational resources. The sharing unit, for example, analyzes the social media activity of each terminal and shares related resources preferentially. Social media activity refers to actions such as posts, comments, and likes made by users on social media. For example, the sharing unit shares highly relevant resources based on trend information on social media. Trend information refers to keywords and hashtags that are trending on social media. For example, the sharing unit analyzes the social media activity history of each terminal and proposes an optimal resource sharing method. The social media activity history is data that records actions on social media that users have taken in the past, and is usually recorded by time. For example, the sharing unit preferentially shares highly relevant resources based on the past social media activity history. In this way, highly relevant resources can be shared efficiently by analyzing social media activities. A part or all of the above-mentioned processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit inputs the social media activity data of each terminal into AI and allows AI to select the optimal resource sharing method.

[0079] The distribution unit can estimate the user's emotion and adjust the distribution method of the processing based on the estimated user's emotion. For example, when the user is feeling stressed, the distribution unit delays the distribution of the processing to reduce the burden on the user. The user's emotion is realized by using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the distribution unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the distribution unit calculates an emotion score based on the change in the facial expression. The distribution unit can also record the user's voice and estimate the emotion using a voice analysis technology. For example, the distribution unit analyzes the tone and speed of the voice and calculates the emotion score. The distribution unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the distribution unit calculates an emotion score based on the fluctuation of the heart rate. In this way, the distribution method of the processing can be adjusted according to the user's emotion, thereby reducing the burden on the user. Some or all of the above-mentioned processing in the distribution unit may be performed using AI, or may be performed without using AI. For example, the distribution unit may input user emotion data to AI and have the AI ​​select the optimal processing distribution method.

[0080] The distribution unit can analyze the CPU usage rate and memory usage rate of each terminal and select the optimal distribution method. The distribution unit selects the optimal distribution method based on, for example, the CPU usage rate of each terminal. The CPU usage rate is an index indicating the proportion of the CPU used, and is usually expressed as a percentage. For example, the distribution unit limits the distribution of processing from terminals with high CPU usage rates. The distribution unit can also analyze the memory usage rate of each terminal and select an efficient distribution method. The memory usage rate is an index indicating the proportion of the memory used, and is usually expressed as a percentage. For example, the distribution unit limits the distribution of processing from terminals with high memory usage rates. The distribution unit can also propose the optimal distribution method taking into account the network usage rate of each terminal. The network usage rate is an index indicating the proportion of the network used, and is usually expressed as a percentage. For example, the distribution unit limits the distribution of processing from terminals with high network usage rates. In this way, the optimal processing distribution method can be selected by analyzing the resource usage status of each terminal. A part or all of the above-mentioned processing in the distribution unit may be performed, for example, using AI, or may be performed without using AI. For example, the distribution unit can input the resource usage status of each terminal into the AI ​​and have the AI ​​select the optimal processing distribution method.

[0081] The distribution unit can adjust the level of detail of distribution based on the current task status of each terminal when distributing processing. The distribution unit adjusts the level of detail of distribution based on, for example, the current task status of each terminal. The task status is data indicating the number, type, and priority of tasks currently being executed by each terminal. For example, the distribution unit limits processing distribution from a terminal having a large number of tasks. The distribution unit can also determine the level of detail of distribution based on the priority of each terminal. Priority is an index indicating the importance and urgency of tasks held by each terminal, and is usually expressed as a numerical value or a rank. For example, the distribution unit prioritizes processing distribution from a terminal having a task with a high priority. The distribution unit can also adjust the level of detail of distribution taking into account the resource usage status of each terminal. Resource usage status refers to resource usage status such as CPU usage rate and memory usage rate. For example, the distribution unit limits processing distribution from a terminal with a high CPU usage rate. As a result, efficient processing distribution is possible by adjusting the level of detail of distribution based on the task status of each terminal. A part or all of the above-mentioned processing in the distribution unit may be performed using, for example, AI, or may be performed without using AI. For example, the distribution unit can input task status data from each terminal into the AI ​​and have the AI ​​select the optimal distribution method.

[0082] The distribution unit can estimate the user's emotion and determine the priority of the processes to be distributed based on the estimated user's emotion. For example, when the user is feeling stressed, the distribution unit preferentially distributes processes with low importance. The user's emotion is realized by using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the distribution unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the distribution unit calculates an emotion score based on the change in facial expression. The distribution unit can also record the user's voice and estimate the emotion using a voice analysis technology. For example, the distribution unit analyzes the tone and speed of the voice and calculates the emotion score. The distribution unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the distribution unit calculates an emotion score based on the fluctuation of the heart rate. This enables efficient processing distribution by determining the priority of the processing according to the user's emotion. Some or all of the above-mentioned processing in the distribution unit may be performed using AI, or may be performed without using AI. For example, the distribution unit may input user emotion data to AI and have the AI ​​select the optimal processing distribution method.

[0083] When distributing processing, the distribution unit can select the optimal distribution method by taking into account the geographical location information of each terminal. For example, the distribution unit distributes processing preferentially among nearby terminals. The geographical location information is data indicating the physical location of each terminal, and is usually obtained using GPS (Global Positioning System) data or location information services. For example, the distribution unit distributes processing among geographically close terminals to minimize communication delays. Communication delays refer to the time difference between when data is transmitted and when it is received, and are usually measured in milliseconds. For example, the distribution unit selects the optimal distribution method based on the geographical location information. In this way, the optimal processing distribution method can be selected by taking the geographical location information into account. A part or all of the above-mentioned processing in the distribution unit may be performed, for example, using AI, or may be performed without using AI. For example, the distribution unit can input the geographical location information of each terminal into AI and have AI select the optimal processing distribution method.

[0084] The distribution unit can improve the accuracy of distribution by referring to the related literature of each terminal when distributing processing. The distribution unit, for example, refers to the related literature of each terminal and selects the optimal distribution method. The related literature refers to literature and database information that each terminal has referred to in the past. For example, the distribution unit improves the accuracy of distribution based on the related literature. The accuracy of distribution is an index that indicates how efficiently the distribution of processing is performed, and is usually expressed as a percentage or a score. For example, the distribution unit analyzes the past processing history of each terminal and proposes the optimal distribution method. The processing history refers to the record of processing that each terminal has performed in the past, and is usually recorded by time. For example, the distribution unit selects the optimal distribution method based on the past processing history. As a result, the accuracy of distribution can be improved by referring to the related literature. Part or all of the above-mentioned processing in the distribution unit may be performed using, for example, AI, or may be performed without using AI. For example, the distribution unit can input the related literature data of each terminal into AI and have AI select the optimal distribution method.

[0085] The monitoring unit can estimate the user's emotion and adjust the load monitoring method based on the estimated user's emotion. For example, when the user is feeling stressed, the monitoring unit delays load monitoring to reduce the user's burden. The user's emotion is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI. For example, the monitoring unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the monitoring unit calculates an emotion score based on the change in facial expression. The monitoring unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the monitoring unit analyzes the tone and speed of the voice and calculates an emotion score. The monitoring unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the monitoring unit calculates an emotion score based on the fluctuation of the heart rate. This makes it possible to reduce the user's burden by adjusting the load monitoring method according to the user's emotion. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit may input user emotion data to AI and have the AI ​​select the optimal load monitoring method.

[0086] The monitoring unit can analyze the resource status of each terminal and select the optimal monitoring method. The monitoring unit selects the optimal monitoring method based on, for example, the CPU usage rate of each terminal. The CPU usage rate is an index indicating the percentage of the CPU usage rate, and is usually expressed as a percentage. For example, the monitoring unit increases the monitoring frequency of a terminal with a high CPU usage rate. The monitoring unit can also analyze the memory usage rate of each terminal and select an efficient monitoring method. The memory usage rate is an index indicating the percentage of the memory usage rate, and is usually expressed as a percentage. For example, the monitoring unit increases the monitoring frequency of a terminal with a high memory usage rate. The monitoring unit can also propose the optimal monitoring method in consideration of the network usage rate of each terminal. The network usage rate is an index indicating the percentage of the network usage rate, and is usually expressed as a percentage. For example, the monitoring unit increases the monitoring frequency of a terminal with a high network usage rate. In this way, the optimal monitoring method can be selected by analyzing the resource status of each terminal. A part or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input resource status data for each terminal into the AI ​​and have the AI ​​select the optimal monitoring method.

[0087] The monitoring unit can adjust the level of detail of monitoring by referring to the past resource usage history of each terminal when monitoring the load. The monitoring unit adjusts the level of detail of monitoring based on, for example, the past CPU usage history of each terminal. The CPU usage history is data indicating the percentage of CPU usage in the past, and is usually recorded by time. For example, the monitoring unit increases the monitoring frequency during time periods when CPU usage is high. The monitoring unit can also determine the level of detail of monitoring by referring to the memory usage history of each terminal. The memory usage history is data indicating the percentage of memory usage in the past, and is usually recorded by time. For example, the monitoring unit increases the monitoring frequency during time periods when memory usage is high. The monitoring unit can also analyze the network usage history of each terminal and propose an optimal monitoring method. The network usage history is data indicating the percentage of network usage in the past, and is usually recorded by time. For example, the monitoring unit increases the monitoring frequency during time periods when network usage is high. In this way, the optimal monitoring method can be selected by referring to the past resource usage history. A part or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input resource usage history data for each terminal into the AI ​​and have the AI ​​select the optimal monitoring method.

[0088] The monitoring unit can estimate the user's emotion and determine the priority of the loads to be monitored based on the estimated user's emotion. For example, when the user is feeling stressed, the monitoring unit preferentially monitors loads with low importance. The user's emotion is realized by using an emotion estimation function using an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI. For example, the monitoring unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the monitoring unit calculates an emotion score based on the change in facial expression. The monitoring unit can also record the user's voice and estimate the emotion using a voice analysis technology. For example, the monitoring unit analyzes the tone and speed of the voice and calculates an emotion score. The monitoring unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the monitoring unit calculates an emotion score based on the fluctuation of the heart rate. This enables efficient load monitoring by determining the priority of the loads according to the user's emotion. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit may input user emotion data to AI and have the AI ​​select the optimal load monitoring method.

[0089] The monitoring unit can select the optimal monitoring method by considering the geographical location information of each terminal when monitoring the load. For example, the monitoring unit prioritizes monitoring the load between nearby terminals. The geographical location information is data indicating the physical location of each terminal, and is usually acquired using GPS (Global Positioning System) data or location information services. For example, the monitoring unit monitors the load between geographically close terminals to minimize communication delays. The communication delay refers to the time difference between when data is transmitted and when it is received, and is usually measured in milliseconds. For example, the monitoring unit selects the optimal monitoring method based on the geographical location information. In this way, the optimal load monitoring method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the monitoring unit may be performed, for example, using AI, or may be performed without using AI. For example, the monitoring unit can input the geographical location information of each terminal to AI and have AI select the optimal load monitoring method.

[0090] The monitoring unit can improve the accuracy of monitoring by referring to the related literature of each terminal when monitoring the load. The monitoring unit, for example, refers to the related literature of each terminal and selects the optimal monitoring method. The related literature refers to the literature or database information that each terminal has referred to in the past. For example, the monitoring unit improves the accuracy of monitoring based on the related literature. The accuracy of monitoring is an index that indicates how efficiently the load monitoring is performed, and is usually expressed as a percentage or a score. For example, the monitoring unit analyzes the past load history of each terminal and proposes the optimal monitoring method. The load history refers to the record of the load that each terminal has experienced in the past, and is usually recorded by time. For example, the monitoring unit selects the optimal monitoring method based on the past load history. As a result, the accuracy of monitoring can be improved by referring to the related literature. A part or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input the related literature data of each terminal into AI and have AI select the optimal monitoring method.

[0091] The efficiency improvement unit can estimate the user's emotion and adjust the method of improving the efficiency of the computational resources based on the estimated user's emotion. For example, when the user is feeling stressed, the efficiency improvement unit delays the efficiency of the computational resources to reduce the burden on the user. The user's emotion is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the efficiency improvement unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the efficiency improvement unit calculates an emotion score based on the change in facial expression. The efficiency improvement unit can also record the user's voice and estimate the emotion using a voice analysis technology. For example, the efficiency improvement unit analyzes the tone and speed of the voice and calculates the emotion score. The efficiency improvement unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the efficiency improvement unit calculates an emotion score based on the fluctuation of the heart rate. This allows the burden on the user to be reduced by adjusting the efficiency of computational resources according to the user's emotions. Some or all of the above-mentioned processing in the efficiency improvement unit may be performed using AI, for example, or may be performed without using AI. For example, the efficiency improvement unit may input the user's emotion data to the AI ​​and have the AI ​​select the optimal efficiency improvement method.

[0092] The efficiency unit can analyze the resource usage history of each terminal and select the optimal efficiency improvement method. The efficiency unit selects the optimal efficiency improvement method based on, for example, the CPU usage history of each terminal. The CPU usage history is data indicating the percentage of CPU usage in the past, and is usually recorded by time. For example, the efficiency unit selects an efficiency improvement method for a time period when the CPU usage rate is high. The efficiency unit can also analyze the memory usage history of each terminal and select an efficient resource usage method. The memory usage history is data indicating the percentage of memory usage in the past, and is usually recorded by time. For example, the efficiency unit selects an efficiency improvement method for a time period when the memory usage rate is high. The efficiency unit can also propose the optimal efficiency improvement method by taking into account the network usage history of each terminal. The network usage history is data indicating the percentage of network usage in the past, and is usually recorded by time. For example, the efficiency unit selects an efficiency improvement method for a time period when the network usage rate is high. In this way, the optimal efficiency improvement method can be selected by analyzing the resource usage history. A part or all of the above-mentioned processing in the efficiency unit may be performed using, for example, AI, or may be performed without using AI. For example, the efficiency unit can input resource usage history data for each terminal into the AI ​​and have the AI ​​select the optimal efficiency method.

[0093] The efficiency unit can adjust the degree of detail of the efficiency based on the current usage status of each terminal when the computational resource is made more efficient. The efficiency unit adjusts the degree of detail of the efficiency based on, for example, the current CPU usage status of each terminal. The CPU usage status is data indicating the current proportion of the CPU being used, and is usually expressed as a percentage. For example, the efficiency unit increases the efficiency degree of detail of a terminal with a high CPU usage rate. The efficiency unit can also determine the degree of detail of the efficiency in consideration of the memory usage status of each terminal. The memory usage status is data indicating the current proportion of the memory being used, and is usually expressed as a percentage. For example, the efficiency unit increases the efficiency degree of detail of a terminal with a high memory usage rate. The efficiency unit can also analyze the network usage status of each terminal and propose an optimal efficiency method. The network usage status is data indicating the current proportion of the network being used, and is usually expressed as a percentage. For example, the efficiency unit increases the efficiency degree of detail of a terminal with a high network usage rate. This allows efficient resource use by adjusting the degree of detail of the efficiency based on the usage status of each terminal. Some or all of the above-mentioned processes in the efficiency improvement unit may be performed using AI, for example, or may be performed without using AI. For example, the efficiency improvement unit may input the usage status data of each terminal to AI and have the AI ​​select the optimal efficiency improvement method.

[0094] The efficiency improvement unit can estimate the user's emotion and determine the priority of resources to be made more efficient based on the estimated user's emotion. For example, when the user is feeling stressed, the efficiency improvement unit prioritizes the efficiency of resources with low importance. The user's emotion is realized by using an emotion estimation function using an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI. For example, the efficiency improvement unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the efficiency improvement unit calculates an emotion score based on a change in facial expression. The efficiency improvement unit can also record the user's voice and estimate the emotion using a voice analysis technology. For example, the efficiency improvement unit analyzes the tone and speed of the voice and calculates an emotion score. The efficiency improvement unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the efficiency improvement unit calculates an emotion score based on the fluctuation of the heart rate. As a result, the priority of resources is determined according to the user's emotion, enabling efficient resource use. A part or all of the above-mentioned processing in the efficiency improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the efficiency improvement unit may input the user's emotion data to the AI ​​and have the AI ​​select the optimal efficiency improvement method.

[0095] The efficiency improvement unit can select an optimal efficiency improvement method by considering the geographical location information of each terminal when improving the efficiency of computational resources. For example, the efficiency improvement unit prioritizes resource efficiency between nearby terminals. The geographical location information is data indicating the physical location of each terminal, and is usually obtained using GPS (Global Positioning System) data or location information services. For example, the efficiency improvement unit improves resource efficiency between geographically close terminals to minimize communication delays. Communication delays refer to the time difference between when data is transmitted and when it is received, and are usually measured in milliseconds. For example, the efficiency improvement unit selects an optimal efficiency improvement method based on the geographical location information. In this way, the optimal efficiency improvement method can be selected by considering the geographical location information. A part or all of the above-mentioned processing in the efficiency improvement unit may be performed, for example, using AI, or may be performed without using AI. For example, the efficiency improvement unit can input the geographical location information of each terminal to AI and cause AI to select an optimal efficiency improvement method.

[0096] The efficiency unit can improve the accuracy of efficiency by referring to the related literature of each terminal when improving the efficiency of computational resources. The efficiency unit, for example, refers to the related literature of each terminal and selects the optimal efficiency method. The related literature refers to the literature and database information that each terminal has referred to in the past. For example, the efficiency unit improves the accuracy of efficiency based on the related literature. The accuracy of efficiency is an index that indicates how effectively resource efficiency is performed, and is usually expressed as a percentage or a score. For example, the efficiency unit analyzes the past resource usage history of each terminal and proposes the optimal efficiency method. The resource usage history is data that indicates how much resource each terminal has used in the past, and is usually recorded by time. For example, the efficiency unit selects the optimal efficiency method based on the past resource usage history. As a result, the accuracy of efficiency can be improved by referring to the related literature. A part or all of the above-mentioned processing in the efficiency unit may be performed using, for example, AI, or may be performed without using AI. For example, the efficiency unit inputs the related literature data of each terminal into AI and allows AI to select the optimal efficiency method.

[0097] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0098] The sharing unit can adjust the sharing of computational resources taking into account the remaining battery level of each edge terminal. For example, the sharing unit can limit resource sharing from a terminal with a low remaining battery level. The sharing unit can also prioritize resource sharing with a terminal with a high remaining battery level. Furthermore, the sharing unit can suspend resource sharing when the remaining battery level falls below a certain threshold. This enables efficient resource sharing by taking into account the remaining battery level of each terminal. Some or all of the above-mentioned processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit can input remaining battery level data of each terminal to AI and have AI select an optimal resource sharing method.

[0099] The distribution unit can analyze the usage patterns of users of each terminal and select the optimal distribution method. For example, the distribution unit distributes processing by avoiding time periods when users frequently use the terminal. The distribution unit can also concentrate processing during time periods when users are not using the terminal. Furthermore, the distribution unit can determine the priority of processing based on the usage patterns of users. This allows efficient processing distribution by taking into account the usage patterns of users. Some or all of the above-mentioned processing in the distribution unit may be performed using, for example, AI, or may be performed without using AI. For example, the distribution unit can input usage pattern data of each terminal into AI and have AI select the optimal processing distribution method.

[0100] The efficiency improvement unit can adjust the efficiency improvement method of the computational resources by taking into account the hardware characteristics of each terminal. For example, the efficiency improvement unit selects the optimal efficiency improvement method based on hardware characteristics such as the CPU clock speed, the number of cores, and the memory capacity. The efficiency improvement unit can also adjust the resource allocation according to the hardware characteristics of each terminal. Furthermore, the efficiency improvement unit can also determine the priority of processing based on the hardware characteristics. This enables efficient resource utilization by taking into account the hardware characteristics of each terminal. A part or all of the above-mentioned processing in the efficiency improvement unit may be performed, for example, using AI or may be performed without using AI. For example, the efficiency improvement unit can input the hardware characteristic data of each terminal to AI and have AI select the optimal efficiency improvement method.

[0101] The monitoring unit can monitor the security status of each terminal in real time and restrict resource sharing from terminals with a high security risk. For example, the monitoring unit restricts resource sharing from terminals with a high risk of virus infection or unauthorized access. The monitoring unit can also resume resource sharing when the security status has improved. Furthermore, the monitoring unit can also share resources by prioritizing terminals with a low security risk. This enables safe resource sharing by taking into account the security status of each terminal. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input security status data of each terminal to AI and have the AI ​​select the optimal resource sharing method.

[0102] The sharing unit can estimate the user's emotions and adjust the resource sharing method based on the estimated user's emotions. For example, when the user is relaxed, resource sharing can be actively performed. In addition, when the user is concentrating, resource sharing can be temporarily restricted. Furthermore, when the user is tired, resource sharing can be delayed. In this way, the resource sharing method can be adjusted according to the user's emotions, thereby reducing the burden on the user. A part or all of the above-mentioned processing in the sharing unit may be performed using, for example, AI, or may be performed without using AI. For example, the sharing unit can input the user's emotion data to AI and have the AI ​​select the optimal resource sharing method.

[0103] The distribution unit can estimate the user's emotions and adjust the distribution timing of the processing based on the estimated user's emotions. For example, if the user is feeling stressed, the distribution of the processing is delayed. Also, if the user is relaxed, the distribution of the processing can be actively performed. Furthermore, if the user is concentrating, the distribution of the processing can be temporarily restricted. In this way, the burden on the user can be reduced by adjusting the distribution timing of the processing according to the user's emotions. Some or all of the above-mentioned processing in the distribution unit may be performed, for example, using AI or may be performed without using AI. For example, the distribution unit can input the user's emotion data to AI and have the AI ​​select the optimal processing distribution method.

[0104] The efficiency improvement unit can estimate the user's emotions and adjust the timing of resource efficiency improvement based on the estimated user's emotions. For example, when the user is relaxed, the efficiency improvement of resources is actively performed. In addition, when the user is concentrating, the efficiency improvement of resources can be temporarily restricted. Furthermore, when the user is tired, the efficiency improvement of resources can be delayed. In this way, the burden on the user can be reduced by adjusting the timing of resource efficiency improvement according to the user's emotions. A part or all of the above-mentioned processing in the efficiency improvement unit may be performed, for example, using AI or may be performed without using AI. For example, the efficiency improvement unit can input the user's emotion data into AI and have the AI ​​select the optimal efficiency method.

[0105] The monitoring unit can estimate the user's emotions and adjust the frequency of monitoring based on the estimated user's emotions. For example, when the user is feeling stressed, the monitoring frequency can be reduced. Also, when the user is relaxed, the monitoring frequency can be increased. Furthermore, when the user is concentrating, the monitoring frequency can be temporarily reduced. In this way, the burden on the user can be reduced by adjusting the monitoring frequency according to the user's emotions. A part or all of the above-mentioned processing in the monitoring unit may be performed, for example, using AI, or may be performed without using AI. For example, the monitoring unit can input the user's emotion data into AI and have the AI ​​select the optimal monitoring method.

[0106] The sharing unit can monitor the energy consumption of each terminal in real time and limit resource sharing from terminals with high energy consumption. For example, the sharing unit can suspend resource sharing from terminals with high energy consumption. The sharing unit can also prioritize resource sharing with terminals with low energy consumption. Furthermore, the sharing unit can resume resource sharing when the energy consumption falls below a certain threshold. This enables efficient resource sharing by taking into account the energy consumption of each terminal. Some or all of the above-mentioned processing in the sharing unit may be performed, for example, using AI or may be performed without using AI. For example, the sharing unit can input energy consumption data of each terminal to AI and have the AI ​​select the optimal resource sharing method.

[0107] The distribution unit can monitor the communication speed of each terminal in real time and limit the distribution of processing from terminals with low communication speeds. For example, the distribution unit can temporarily suspend the distribution of processing from terminals with low communication speeds. The distribution unit can also distribute processing by prioritizing terminals with high communication speeds. Furthermore, the distribution unit can resume the distribution of processing when the communication speed falls below a certain threshold. This enables efficient distribution of processing by taking into account the communication speed of each terminal. Some or all of the above-mentioned processing in the distribution unit may be performed, for example, using AI or may be performed without using AI. For example, the distribution unit can input communication speed data of each terminal to AI and have AI select the optimal distribution method of processing.

[0108] The process flow of the second embodiment will be briefly described below.

[0109] Step 1: The sharing unit shares the computing resources held by each edge terminal. For example, the sharing unit uses a P2P (peer-to-peer) network to share the computing resources held by each edge terminal. A P2P network is a mechanism in which each terminal communicates with each other directly, sharing resources without going through a central server. Specifically, the computing resources such as each terminal's CPU (central processing unit) and memory (storage device) are shared over the network. Step 2: The distribution unit distributes the AI ​​processing based on the computing resources shared by the sharing unit. For example, the distribution unit monitors the CPU usage and memory usage of each terminal in real time, and distributes processing to other terminals if a certain threshold is exceeded. Specifically, if CPU usage exceeds 80%, processing is distributed to other terminals. Step 3: The monitoring unit monitors the processing load distributed by the distribution unit. For example, the monitoring unit monitors the resource status of each terminal in real time and distributes processing from terminals with high loads to terminals with low loads. Specifically, if the CPU usage rate exceeds 90%, the processing is distributed to other terminals. Step 4: The efficiency improvement unit efficiently uses the computing resources based on the load monitored by the monitoring unit. For example, the efficiency improvement unit efficiently uses the computing resources of each terminal in order to improve the overall computing capacity. Specifically, the overall computing capacity is improved by optimizing the CPU usage and memory usage of each terminal.

[0110] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0111] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0112] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0113] Each of the multiple elements including the sharing unit, distribution unit, monitoring unit, and efficiency improvement unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the sharing unit is realized by the control unit 46A of the smart device 14, and shares the computational resources of each edge terminal via a P2P network. The distribution unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and distributes the AI ​​processing based on the shared computational resources. The monitoring unit is realized, for example, by the control unit 46A of the smart device 14, and monitors the resource status of each terminal in real time. The efficiency improvement unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and efficiently uses the resources of each terminal to improve the overall computational capacity. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0114] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0115] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0116] 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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0117] 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.

[0118] 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 the voice according to instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0120] 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 performed in a secure state.

[0121] Fig. 4 shows an example of 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.

[0122] 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.

[0123] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0124] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0125] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0126] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0127] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0128] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, 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, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0129] Each of the multiple elements including the sharing unit, distribution unit, monitoring unit, and efficiency improvement unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the sharing unit is realized by the control unit 46A of the smart glasses 214, and shares the computational resources of each edge terminal via a P2P network. The distribution unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and distributes AI processing based on the shared computational resources. The monitoring unit is realized, for example, by the control unit 46A of the smart glasses 214, and monitors the resource status of each terminal in real time. The efficiency improvement unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and efficiently uses the resources of each terminal to improve the overall computational capacity. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0130] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0131] 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.

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

[0133] 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.

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

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0136] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0137] 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.

[0138] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0140] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific 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 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.

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

[0142] 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 voice indicating a user input for 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.

[0143] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0144] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0145] Each of the multiple elements including the sharing unit, distribution unit, monitoring unit, and efficiency improvement unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the sharing unit is realized by the control unit 46A of the headset type terminal 314, and shares the computational resources of each edge terminal via a P2P network. The distribution unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and distributes the AI ​​processing based on the shared computational resources. The monitoring unit is realized, for example, by the control unit 46A of the headset type terminal 314, and monitors the resource status of each terminal in real time. The efficiency improvement unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and efficiently uses the resources of each terminal to improve the overall computational capacity. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0146] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0147] 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.

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

[0149] 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. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

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

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

[0152] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0153] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0154] 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.

[0155] 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.

[0156] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0157] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0158] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0159] 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 a voice indicating a user input for 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.

[0160] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0161] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, 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.

[0162] Each of the multiple elements including the sharing unit, distribution unit, monitoring unit, and efficiency improvement unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the sharing unit is realized by the control unit 46A of the robot 414, and shares the computational resources of each edge terminal via a P2P network. The distribution unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and distributes the AI ​​processing based on the shared computational resources. The monitoring unit is realized, for example, by the control unit 46A of the robot 414, and monitors the resource status of each terminal in real time. The efficiency improvement unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and efficiently uses the resources of each terminal to improve the overall computational capacity. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0163] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0164] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0165] These emotions are distributed in the three o'clock direction of emotion map 400 and usually 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.

[0166] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0167] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0168] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0170] 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.

[0171] 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 Universal Serial Bus (USB) 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.

[0172] In addition, 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 upon request from the data processing device 12.

[0173] 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.

[0174] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0175] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0176] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0177] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0178] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0179] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0180] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0181] (Appendix 1) A sharing part that shares the computing resources of each edge device; A distribution unit that distributes AI processing based on the computational resources shared by the sharing unit; a monitoring unit that monitors the load of the processing distributed by the distribution unit; an efficiency unit that utilizes computing resources based on the load monitored by the monitoring unit; A system characterized by: (Appendix 2) The common part is Share computing resources owned by edge terminals based on P2P network 2. The system of claim 1, (Appendix 3) The dispersion unit is Monitors the CPU and memory usage of each terminal in real time, and distributes processing to other terminals if a threshold is exceeded. 2. The system of claim 1, (Appendix 4) The efficiency improvement unit includes: Utilizing the computing resources of each device to improve overall computing power 2. The system of claim 1, (Appendix 5) The monitoring unit is Monitor the resource status of each terminal in real time and distribute processing from terminals with high loads to other terminals. 2. The system of claim 1, (Appendix 6) The common part is Estimate the user's emotions and adjust the timing of sharing computing resources based on the estimated user's emotions. 2. The system of claim 1, (Appendix 7) The common part is Analyze the past resource usage history of each edge device and select the optimal sharing method 2. The system of claim 1, (Appendix 8) The common part is When sharing computing resources, filtering is performed based on each device's current usage and priority. 2. The system of claim 1, (Appendix 9) The common part is A user's emotion is estimated, and a priority order for sharing computational resources is determined based on the estimated user's emotion. 2. The system of claim 1, (Appendix 10) The common part is When sharing computing resources, the geographic location information of each device is taken into consideration to prioritize sharing of highly relevant resources. 2. The system of claim 1, (Appendix 11) The common part is When sharing computing resources, analyze the social media activity of each device and share relevant resources. 2. The system of claim 1, (Appendix 12) The dispersion unit is Inferring user emotions and adjusting the distribution method of processing based on the estimated user emotions 2. The system of claim 1, (Appendix 13) The dispersion unit is Analyze the CPU usage and memory usage of each terminal and select the optimal distribution method. 2. The system of claim 1, (Appendix 14) The dispersion unit is When distributing processing, adjust the distribution level based on the current task status of each terminal. 2. The system of claim 1, (Appendix 15) The dispersion unit is Estimate the user's emotions and determine the priority of distributed processing based on the estimated user's emotions. 2. The system of claim 1, (Appendix 16) The dispersion unit is When distributing processing, the optimal distribution method is selected taking into account the geographic location information of each terminal. 2. The system of claim 1, (Appendix 17) The dispersion unit is When distributing processing, improve the accuracy of distribution by referring to relevant literature on each terminal. 2. The system of claim 1, (Appendix 18) The monitoring unit is To estimate a user's emotion and adjust a load monitoring method based on the estimated user's emotion. 2. The system of claim 1, (Appendix 19) The monitoring unit is Analyze the resource status of each device and select the optimal monitoring method 2. The system of claim 1, (Appendix 20) The monitoring unit is When monitoring load, adjust the level of detail by referring to the past resource usage history of each device 2. The system of claim 1, (Appendix 21) The monitoring unit is To estimate a user's emotion and determine a priority of a load to be monitored based on the estimated user's emotion. 2. The system of claim 1, (Appendix 22) The monitoring unit is When monitoring load, the optimal monitoring method is selected taking into account the geographic location information of each device. 2. The system of claim 1, (Appendix 23) The monitoring unit is When monitoring load, improve the accuracy of monitoring by referring to the related literature of each terminal. 2. The system of claim 1, (Appendix 24) The efficiency improvement unit includes: A method for estimating a user's emotion and adjusting a method for efficient use of computational resources based on the estimated user's emotion. 2. The system of claim 1, (Appendix 25) The efficiency improvement unit includes: Analyze the resource usage history of each device and select the most efficient method 2. The system of claim 1, (Appendix 26) The efficiency improvement unit includes: When optimizing computing resources, adjust the granularity of efficiency based on each device's current usage 2. The system of claim 1, (Appendix 27) The efficiency improvement unit includes: To estimate a user's emotion and determine the priority of resources to be made efficient based on the estimated user's emotion. 2. The system of claim 1, (Appendix 28) The efficiency improvement unit includes: When optimizing computing resources, the geographic location information of each device is taken into consideration to select the optimal method of efficiency. 2. The system of claim 1, (Appendix 29) The efficiency improvement unit includes: When optimizing computing resources, the accuracy of the optimization is improved by referring to the relevant literature for each device. 2. The system of claim 1, [Explanation of symbols]

[0182] 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 sharing part that shares the computing resources of each edge device; A distribution unit that distributes AI processing based on the computational resources shared by the sharing unit; a monitoring unit that monitors the load of the processing distributed by the distribution unit; an efficiency unit that utilizes computing resources based on the load monitored by the monitoring unit; A system characterized by:

2. The common part is Share computing resources owned by edge terminals based on P2P network 2. The system of claim 1 .

3. The dispersion unit is Monitors the CPU and memory usage of each terminal in real time, and distributes processing to other terminals if a threshold is exceeded.

2. The system of claim 1 .

4. The efficiency improvement unit includes: Utilizing the computing resources of each device to improve overall computing power 2. The system of claim 1 .

5. The monitoring unit is Monitor the resource status of each terminal in real time and distribute processing from terminals with high loads to other terminals.

2. The system of claim 1 .

6. The common part is Estimate the user's emotions and adjust the timing of sharing computing resources based on the estimated user's emotions.

2. The system of claim 1 .

7. The common part is Analyze the past resource usage history of each edge device and select the optimal sharing method 2. The system of claim 1 .

8. The common part is When sharing computing resources, filtering is performed based on each device's current usage and priority.

2. The system of claim 1 .

Images