system

Abstract

We provide the system. [Solution] A means of analyzing tactical situation data in real time and generating feedback using a generative model, A means of delivering tactical instructions to terminals based on analysis results, A system that includes a terminal that immediately translates received instructions into action.

Description

Technical Field

[0005] , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern battlefields, it is necessary to improve the survival rate of troops by quickly and appropriately responding to environmental changes and enemy actions. However, analyzing a huge amount of information in real time and providing appropriate tactical feedback is a heavy burden on human commanders. Therefore, a system for improving the immediate response ability and combat efficiency of troops is required.

Means for Solving the Problems

[0005] This invention provides a means for analyzing tactical situation data in real time using a generative model and generating feedback. Furthermore, by constructing a system that includes a terminal that distributes tactical instructions based on the analysis results and immediately reflects the received instructions in action, it enables rapid decision-making and action adaptation by units. This system analyzes location information, video information, and acoustic information, expresses the generated feedback in natural language, and prepares it for distribution.

[0006] A "generative model" is a type of algorithm that can learn patterns from data and generate new data.

[0007] "Tactical situation data" refers to data necessary for understanding the battle situation, including location information, video information, and audio information on the battlefield.

[0008] "Feedback" refers to specific instructions and information based on analysis results, generated to support tactical decision-making.

[0009] A "terminal" refers to a device or system that takes action based on the feedback received.

[0010] "Real-time" refers to the ability to process data within a very short time from the moment it is generated. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] The system of the present invention analyzes tactical situation data in real time using a generative model and generates feedback in order to improve the survival rate and combat efficiency of troops on the battlefield. The processing of the program of this system is described below as an embodiment.

[0033] The server receives real-time tactical situation data from sensors, cameras, and acoustic devices deployed on the battlefield. This data includes location information, video information, and acoustic information. The server collects this data and immediately analyzes it using generative models. This analysis determines tactical risk assessments based on the current battle situation, predictions of enemy movements, and optimal troop deployment.

[0034] Based on the analysis results, the server generates feedback corresponding to the troops and robots. This feedback consists of specific action instructions and tactical advice written in natural language. The generated feedback is then delivered from the server to the terminals.

[0035] The terminal immediately takes action based on feedback received from the server. For example, a robot can move to a safe location or take a defensive position according to the given instructions. If the user is the commander, they can accurately grasp the situation and issue additional instructions by checking the feedback through monitors or dedicated devices.

[0036] For example, if analysis indicates that enemy reinforcements are approaching, the server immediately generates feedback recommending a retreat. The terminal then receives the instruction and quickly begins to retreat to a safe position. This entire process enables rapid decision-making and response by the unit, resulting in effective action on the battlefield.

[0037] The following describes the processing flow.

[0038] Step 1:

[0039] The server collects tactical situational data, including location, video, and audio information, in real time from sensors and cameras deployed on the battlefield. The data is securely received via communication channels and prepared for analysis.

[0040] Step 2:

[0041] The server inputs the collected tactical situation data into a generative model and performs immediate analysis. This analysis helps determine the positions of allies and enemies, predict risks, and derive the optimal tactical deployment.

[0042] Step 3:

[0043] Based on the analysis results, the server generates feedback expressed in natural language. This includes specific action instructions and tactical advice, organizing the information obtained from the generative model.

[0044] Step 4:

[0045] The server distributes the generated feedback to the terminals. The feedback is sent to each terminal in real time, immediately conveying any necessary instructions.

[0046] Step 5:

[0047] The terminal analyzes the feedback received from the server and takes action according to the instructions. For example, a robot can immediately move to a safe location or respond to a designated attack target.

[0048] Step 6:

[0049] The user (commander) monitors the terminal's execution results and checks the effectiveness of the feedback provided by the server. Tactics can be further improved by the user issuing additional instructions as needed.

[0050] (Example 1)

[0051] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0052] In today's tactical environment, there is a need to respond quickly to rapidly changing situations in real time and improve troop survival rates and combat efficiency. However, existing systems have the challenge of not being able to instantly analyze large amounts of situational data and quickly generate and distribute accurate tactical instructions.

[0053] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0054] In this invention, the server includes means for analyzing tactical situation data in real time using a generative model and generating feedback; means for inputting prompt sentences into a generative AI model to perform analysis and perform tactical risk assessment and prediction of enemy movements; and means for delivering tactical instructions to terminals based on the analysis results. This enables effective and rapid decision-making on the battlefield through rapid analysis of the tactical situation and immediate delivery of instructions to units.

[0055] A "generative model" is an artificial intelligence model that analyzes input data and generates new data or predictions.

[0056] "Tactical situation data" refers to data such as location information, video information, and audio information that is collected to make tactical decisions.

[0057] "Real-time analysis" refers to the process of performing analysis immediately the moment data is received.

[0058] "Feedback" refers to information sent to the device as specific action instructions or tactical advice, based on the results analyzed by the generative model.

[0059] "Entering prompt statements into a generative AI model to perform analysis" refers to the operation of inputting specific commands or questions into an AI model, which then performs data analysis and outputs results based on those inputs.

[0060] "Tactical risk assessment" means analyzing the current tactical situation and evaluating potential threats and problems.

[0061] "Predicting enemy movements" refers to the process of predicting the enemy's actions and intentions based on collected data.

[0062] A "terminal" refers to an electronic device that receives generated feedback and performs actions based on instructions.

[0063] This invention relates to a system that analyzes tactical situation data in real time to improve troop survival rates and combat efficiency. This system is realized through the cooperation of a server, terminals, and users.

[0064] The server receives tactical situation data from hardware such as sensors, cameras, and acoustic data collection devices. This data includes location information, video information, and audio information. The server first converts this data into a standard format and then performs data analysis by inputting prompts into a generative AI model. The generative AI model used is a high-performance model that excels at natural language processing, for example. An example of a prompt is, "Please suggest the optimal action strategy based on the current data."

[0065] Once the analysis is complete, the server generates feedback in natural language based on the results obtained, which includes specific action instructions and tactical advice. For example, it might generate something like, "Enemy is approaching from the south. The safest route is to retreat north."

[0066] The terminal receives feedback delivered from the server. Upon receiving the feedback, the terminal, such as a robot, immediately acts in accordance with the feedback, engaging in activities such as moving to a safe position or tactical deployment.

[0067] When a user participates in the system as a commander, they can accurately grasp the situation and issue additional instructions by reviewing feedback through dedicated devices and monitors. This allows for a rapid response to changes in the tactical situation and improves the safety and combat effectiveness of the troops.

[0068] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0069] Step 1:

[0070] The server receives tactical situational data from sensors, cameras, and acoustic devices deployed on the battlefield. This input data includes location information, video information, and acoustic information. The server aggregates this data and processes it into a standard format suitable for analysis. Specifically, the server divides the video data into frames and performs noise reduction processing.

[0071] Step 2:

[0072] The server passes pre-processed data to the generating AI model and performs the analysis by inputting prompt messages. These prompt messages typically include phrases like, "Please suggest the optimal action strategy based on the current data." Based on these prompts, the AI ​​model performs a tactical risk assessment and predicts enemy movements, generating the results as analysis output. The server receives the enemy's movement routes and recommended actions obtained from the analysis as output data.

[0073] Step 3:

[0074] The server generates feedback based on the analysis results obtained from the generated AI model. This feedback is in natural language and includes specific action instructions and tactical advice. For example, the server generates the instruction "Enemy approaching from the south. The safest route is to retreat north," and prepares this as output data.

[0075] Step 4:

[0076] The server distributes the generated feedback to the terminal. The terminal receives this feedback and immediately acts upon its contents. The robot, having received the feedback as output data, performs the specified action. Specifically, the feedback distributed to the commander's terminal is displayed on a monitor, and the commander confirms it.

[0077] Step 5:

[0078] If the user is a commander, they utilize the delivered feedback to accurately assess the situation and issue additional instructions. Users receive feedback through monitors or dedicated devices and make immediate tactical decisions. For example, a commander who has reviewed the feedback may take specific actions such as ordering new troop deployments.

[0079] (Application Example 1)

[0080] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0081] In modern commercial facilities and event venues, security management is crucial in situations where large numbers of people gather. However, detecting suspicious behavior and abnormal situations in real time and responding appropriately has been difficult with traditional methods. Furthermore, relying solely on the intuition and experience of security personnel can lead to delays in prompt and appropriate responses. Therefore, an efficient information system is needed to ensure safe and smooth operations.

[0082] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0083] In this invention, the server includes means for analyzing dynamic situation data in real time and generating feedback using a generative model, means for distributing action instructions to an information terminal based on the analysis results, and an information terminal that immediately reflects the received instructions in action. This enables security personnel to efficiently monitor the flow of people and abnormal behavior at events and commercial facilities, and to provide appropriate action instructions and safety responses.

[0084] A "generative model" is a type of artificial intelligence that uses input data to generate output in a specific format.

[0085] "Dynamic situation data" refers to real-time information about the movement of people and objects in a specific location and time.

[0086] "Feedback" refers to instructions or information generated based on analysis results, intended to encourage specific actions.

[0087] An "information terminal" refers to an electronic device with communication capabilities that can send, receive, and display data.

[0088] "Action instructions" refer to directives that indicate the actions to be taken in a specific situation.

[0089] "Natural language" refers to the language that humans use on a daily basis, and is a form that enables natural conversation in machine dialogue.

[0090] A "security officer" refers to a person whose job is to ensure safety at a specific facility or event.

[0091] This invention is a system that streamlines safety measures required in markets, event venues, and other similar locations. This system utilizes generative models to analyze situations in real time and provide appropriate feedback.

[0092] The server integrates a generative AI model and a data analysis engine, receiving dynamic situational data collected from cameras and acoustic sensors installed in commercial facilities and event venues. This data includes location, visual, and auditory information. The server analyzes this data to assess the situation, specifically detecting pedestrian flow and suspicious behavioral patterns.

[0093] Based on the analysis results, the server generates action instructions and sends them to an information terminal. This information terminal refers to a smartphone or tablet, which security personnel can carry around within the facility. The received instructions are expressed in natural language and presented to the security personnel in a format that can be quickly understood. The instructions include actions such as patrolling a specific area, checking for suspicious activity, or sealing off an area.

[0094] For example, if an unusual gathering of people or suspicious behavior is detected, the server will immediately generate feedback such as, "There is a gathering in the designated area. Please increase patrols," prompting increased patrols in the specified area. This prompt helps identify areas within the facility that require security.

[0095] In this way, the system enables security personnel to accurately grasp the situation and take swift and appropriate action to maintain security.

[0096] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0097] Step 1:

[0098] The server collects dynamic situational data from cameras and acoustic sensors installed in commercial facilities and event venues. The data obtained as input includes location information, visual information, and sound information. This data is temporarily stored in the server's internal storage.

[0099] Step 2:

[0100] The server inputs the collected dynamic situational data into a generative model and performs real-time analysis. Data processing includes pixel data conversion of visual information and frequency analysis of sound information. The analyzed output identifies areas within the facility where anomalies are occurring and patterns of pedestrian flow.

[0101] Step 3:

[0102] The server generates action instructions based on the analysis results. This output consists of specific instructions necessary to ensure the safety of the facility. For example, it might say, "Increase patrols near the entrance." The server expresses this in natural language and prepares it in text format.

[0103] Step 4:

[0104] The generated operational instructions are distributed from the server to the information terminal. The terminal receives these operational instructions in text format as input and displays them visually to the security personnel. The notification function of smartphones and tablets is used for display.

[0105] Step 5:

[0106] Security personnel, acting as users, can grasp the situation from their terminals and take immediate action according to the instructions. Users can implement security measures by intensifying patrols on site or checking areas identified as abnormal. This enables appropriate security measures based on real-time feedback.

[0107] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0108] This invention is a system that combines the analysis of tactical situation data and the generation of feedback using a generative model with an emotion engine that recognizes user emotions. The aim of this system is to improve the survival rate and combat efficiency of troops on the battlefield and to enhance the quality of decision-making.

[0109] The server first collects tactical situational data, including location, video, and audio information, from sensors and cameras. This data is analyzed in real time using generative models to generate tactical risk assessments and specific action instructions.

[0110] Next, the emotion engine analyzes the user's emotional state, particularly the commander's, voice and facial expressions. This analysis allows for an assessment of the user's mental state and stress level. The server takes this emotional data into consideration and adjusts the content and tone of the feedback to generate an optimized response.

[0111] The terminal receives feedback from the server. This feedback includes instructions adjusted by an emotion engine, which allows robots and soldiers to take optimal actions. For example, if the user is under high stress, the feedback can provide clearer and simpler instructions.

[0112] Users can view visual feedback on their emotional state provided by the server, along with the results of their actions. This enriches the information available when giving instructions, enabling them to make more accurate tactical decisions.

[0113] As a concrete example, the server predicts enemy movements while simultaneously evaluating the commander's stress level using an emotion engine. Based on the data obtained, it generates feedback suggesting a smooth retreat plan to avoid confusion. Using this system, troops can flexibly adjust their tactics at the appropriate time, improving their mission success rate.

[0114] The following describes the processing flow.

[0115] Step 1:

[0116] The server collects tactical situational data, such as location information, video information, and audio information, in real time from sensors and cameras deployed on the battlefield. The data is organized using secure communication protocols and prepared for analysis.

[0117] Step 2:

[0118] The server inputs the collected tactical situation data into a generative model and performs real-time analysis. This analysis enables risk assessment of the battle situation and predictions of enemy movements, leading to the generation of necessary new tactical instructions.

[0119] Step 3:

[0120] The emotion engine analyzes the user's (commander's) voice and video to evaluate their emotional state in real time. The server receives the recognized emotion data and understands the commander's stress level and feelings.

[0121] Step 4:

[0122] The server integrates the analysis results from the generative model with the evaluation from the emotion engine to generate tactical feedback. The feedback reflects adjustments in tone and content based on the commander's emotional state.

[0123] Step 5:

[0124] The server delivers the generated feedback to the terminal. Based on the received feedback, the terminal initiates actions that the robot or soldier can immediately perform.

[0125] Step 6:

[0126] Users review the results of their device actions as feedback. Simultaneously, visual feedback based on the emotion engine's analysis is displayed to aid in further decision-making.

[0127] This series of steps allows units to respond flexibly and quickly to changing situations and maximize tactical effectiveness.

[0128] (Example 2)

[0129] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0130] Tactical decisions on the battlefield heavily rely on real-time situational awareness and human emotional factors. However, conventional systems struggle to provide rapid and accurate feedback, and often ignore the emotional state of commanders. As a result, tactical instructions can become ineffective. Therefore, there is a need to improve the accuracy of tactical situational data analysis and provide flexible feedback that responds to the commander's emotions.

[0131] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0132] In this invention, the server includes means for analyzing tactical situation data in real time using a generative model and generating feedback, means for delivering tactical instructions to terminals based on the analysis results and emotional state, and means for immediately reflecting the received instructions in actions. This makes it possible to provide highly accurate feedback according to the situation and flexible instructions that are adapted to the commander's emotional state.

[0133] A "generative model" is an algorithm or software that generates new information based on a vast amount of data.

[0134] "Tactical situation data" refers to information that shows the current situation on the battlefield, and includes location information, video information, and audio information.

[0135] "Real-time analysis" is a process in which data is analyzed immediately upon collection, and the results are provided instantly.

[0136] "Feedback" refers to instructions and recommendations provided based on analysis results, which are information used to optimize actions.

[0137] "Emotional state" refers to the psychological and emotional state of the user or commander, including stress levels and heightened emotions.

[0138] A "terminal" is a hardware device that receives data and presents instructions either visually or audibly.

[0139] "Representing information in natural language" refers to a method of presenting computer-generated information in a format that humans can understand, which is usually in the form of text.

[0140] This invention is a system that analyzes tactical situation data and generates feedback, providing real-time situation analysis and user-centric feedback based on a generative model. First, the server collects tactical situation data such as location information, video information, and audio information using sensors and cameras. Hardware such as high-resolution video cameras and directional microphones are used. Software such as TENSORFLOW® and PyTorch is used for data analysis.

[0141] Next, the server inputs the collected tactical situation data into a generative AI model for real-time analysis. Here, the generative model generates tactical risk assessments and specific action instructions. Based on these analysis results, an emotion engine is used to deduce the emotional state of the user, particularly the commander, from their voice and facial expressions. Voice recognition uses speech analysis software, and facial expression recognition uses visual analysis software. Specific software options include Google® Cloud Speech-to-Text and Microsoft® Azure® Face API.

[0142] The generated feedback is sent to a terminal, which presents the feedback to the user visually or audibly. Natural language processing technology is used to generate the feedback, and a generative AI model (e.g., GPT-3®) is applied. This feedback is used by robots and soldiers as instructions when performing tactical actions. If the commander is under high stress, the feedback is adjusted to be concise and clear.

[0143] As a concrete example, the server analyzes tactical situation data, predicts enemy movements, and uses an emotion engine to assess the commander's stress level. Based on the data obtained, it generates feedback that proposes appropriate action plans to promote peaceful resolution or avoid unnecessary risks. As an example of a prompt, it is possible to give specific instructions such as, "Based on tactical situation data, predict enemy movements and generate a retreat plan that takes the commander's stress level into consideration."

[0144] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0145] Step 1:

[0146] The server collects location, video, and acoustic information through sensors and cameras. This data is used to understand the tactical situation on the battlefield and is obtained using high-performance drones, fixed cameras, and acoustic sensors. The input is physical sensors, and the output is digitized location, video, and acoustic data.

[0147] Step 2:

[0148] The server inputs collected tactical situation data into a generating AI model for real-time analysis. This analysis uses TensorFlow and PyTorch to predict enemy positions and activities and assess tactical risks. The input is digital tactical situation data, and the output is information on enemy positions, predicted activities, and risk assessment.

[0149] Step 3:

[0150] The server acquires the commander's voice and facial expression data and analyzes it using an emotion engine. Input data is acquired via microphones and cameras and analyzed using Google Cloud Speech-to-Text and Microsoft Azure Face APIs. The output is an evaluation of the commander's stress level and emotional state. Specifically, it monitors changes in the commander's voice tone and facial expressions.

[0151] Step 4:

[0152] The server generates feedback based on analysis results and emotional assessments. Using a generative AI model (e.g., GPT-3), it creates natural language feedback appropriate to the user's emotional state. The input is the tactical analysis results and emotional state, and the output is the adjusted feedback content. Specifically, if the commander is under high stress, the server generates instructions that are concise and clear.

[0153] Step 5:

[0154] The server sends the generated feedback to the terminal, which then communicates the feedback to the robot or soldier visually or audibly. The input is the generated feedback data, and the output is the instructions provided as a display or audio message on the terminal. In terms of specific actions, the device autonomously begins to act based on the feedback.

[0155] Step 6:

[0156] Users can review the results of their feedback actions through their devices and receive visual feedback on their emotional state from the server, which helps them in making decisions. The input is the feedback and its results, and the output is feedback information that can be used for decision-making. In concrete terms, this allows commanders to make calmer and more appropriate decisions.

[0157] (Application Example 2)

[0158] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0159] In modern work environments, it is crucial to consider the impact of workers' emotional states in order to ensure efficient work progress. However, there is a lack of means to analyze workers' emotions in real time and adjust work instructions accordingly, making it difficult to improve efficiency and safety.

[0160] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0161] In this invention, the server includes means for analyzing work environment data in real time using a generative model and generating feedback, means for analyzing the emotional state of the worker and adjusting work instructions according to the emotions, and means for distributing work instructions to an information device based on the analysis results. This enables efficient and safe work that is tailored to the worker's condition.

[0162] A "generative model" is a general term for algorithms and models that learn features from data and generate new data.

[0163] "Work environment data" refers to various types of information related to the progress of work, such as location information, image information, and sound information within the workplace.

[0164] "Feedback" refers to information and instructions given to workers based on analysis and evaluation.

[0165] "Emotional state" refers to data that indicates the stress levels, fatigue, and mental state of workers.

[0166] "Information device" refers to electronic devices such as terminals and other devices that receive and display data.

[0167] This invention is a system that enables efficient and safe work execution in a work environment. The server acquires work environment data such as location information, image information, and sound information from sensors and cameras installed in factories and work sites. This data is analyzed in real time using generative models such as TensorFlow to generate feedback for improving work procedures.

[0168] In parallel, the server uses emotion analysis technologies such as OpenCV to analyze the emotional state of the worker from their face and voice. This allows the server to understand the level of stress and fatigue the worker is experiencing and adjust instructions accordingly. The feedback generated based on the analysis is delivered to information devices via smartphones or wearable devices. The receiving information devices immediately display work instructions based on the feedback, helping the worker to act efficiently.

[0169] As a concrete example, when a worker on a production line is feeling fatigued, the system could detect that emotion and provide instructions to reduce the workload. In this case, the feedback delivered would be tailored to the worker's condition, such as "Take a short break before your next task." Another example of a prompt message that might be input to the generating AI model is, "Suggest ways to improve safety based on the worker's emotions."

[0170] Thus, this invention contributes to improving production efficiency and the working environment.

[0171] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0172] Step 1:

[0173] The server acquires location, image, and sound information in real time from sensors and cameras installed within the factory. The input is this sensor data, and the output is raw data for analysis, which is passed to a generative model. This prepares the foundational data necessary to understand the situation on-site in detail.

[0174] Step 2:

[0175] The server analyzes raw data acquired by a generative AI model using TensorFlow. The input is sensor data obtained in step 1, and the output is potential feedback for improving work procedures. In this process, the model performs pattern recognition and extracts information necessary for efficient work progress.

[0176] Step 3:

[0177] The server analyzes the emotional state of workers from their facial expressions and voice, separate from the AI ​​models generated using OpenCV. Inputs are camera footage and microphone audio, and output is a numerical value or category indicating emotional state (e.g., fatigue level or stress level). This allows for real-time assessment of the worker's mental load.

[0178] Step 4:

[0179] The server integrates the information obtained in steps 2 and 3 and adjusts the feedback content according to the emotional state. The input is candidate feedback for the work procedure and the emotional state, and the output is optimized instruction information. This generates instructions that are easy for the worker to understand and execute.

[0180] Step 5:

[0181] The server distributes the generated instruction information to the information device. The input is the optimization instructions obtained in step 4, and the output is the feedback displayed on the information device. The terminal displays instructions to the user at the appropriate time to support the smooth progress of the work.

[0182] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0183] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0184] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0185] [Second Embodiment]

[0186] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0187] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0188] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0189] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0190] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0191] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0192] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0193] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0194] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0195] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0196] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0197] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0198] The system of the present invention analyzes tactical situation data in real time using a generative model and generates feedback in order to improve the survival rate and combat efficiency of troops on the battlefield. The processing of the program of this system is described below as an embodiment.

[0199] The server receives real-time tactical situation data from sensors, cameras, and acoustic devices deployed on the battlefield. This data includes location information, video information, and acoustic information. The server collects this data and immediately analyzes it using generative models. This analysis determines tactical risk assessments based on the current battle situation, predictions of enemy movements, and optimal troop deployment.

[0200] Based on the analysis results, the server generates feedback corresponding to the troops and robots. This feedback consists of specific action instructions and tactical advice written in natural language. The generated feedback is then delivered from the server to the terminals.

[0201] The terminal immediately takes action based on feedback received from the server. For example, a robot can move to a safe location or take a defensive position according to the given instructions. If the user is the commander, they can accurately grasp the situation and issue additional instructions by checking the feedback through monitors or dedicated devices.

[0202] For example, if analysis indicates that enemy reinforcements are approaching, the server immediately generates feedback recommending a retreat. The terminal then receives the instruction and quickly begins to retreat to a safe position. This entire process enables rapid decision-making and response by the unit, resulting in effective action on the battlefield.

[0203] The following describes the processing flow.

[0204] Step 1:

[0205] The server collects tactical situational data, including location, video, and audio information, in real time from sensors and cameras deployed on the battlefield. The data is securely received via communication channels and prepared for analysis.

[0206] Step 2:

[0207] The server inputs the collected tactical situation data into a generative model and performs immediate analysis. This analysis helps determine the positions of allies and enemies, predict risks, and derive the optimal tactical deployment.

[0208] Step 3:

[0209] Based on the analysis results, the server generates feedback expressed in natural language. This includes specific action instructions and tactical advice, organizing the information obtained from the generative model.

[0210] Step 4:

[0211] The server distributes the generated feedback to the terminals. The feedback is sent to each terminal in real time, immediately conveying any necessary instructions.

[0212] Step 5:

[0213] The terminal analyzes the feedback received from the server and takes action according to the instructions. For example, a robot can immediately move to a safe location or respond to a designated attack target.

[0214] Step 6:

[0215] The user (commander) monitors the terminal's execution results and checks the effectiveness of the feedback provided by the server. Tactics can be further improved by the user issuing additional instructions as needed.

[0216] (Example 1)

[0217] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0218] In today's tactical environment, there is a need to respond quickly to rapidly changing situations in real time and improve troop survival rates and combat efficiency. However, existing systems have the challenge of not being able to instantly analyze large amounts of situational data and quickly generate and distribute accurate tactical instructions.

[0219] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0220] In this invention, the server includes means for analyzing tactical situation data in real time using a generative model and generating feedback; means for inputting prompt sentences into a generative AI model to perform analysis and perform tactical risk assessment and prediction of enemy movements; and means for delivering tactical instructions to terminals based on the analysis results. This enables effective and rapid decision-making on the battlefield through rapid analysis of the tactical situation and immediate delivery of instructions to units.

[0221] A "generative model" is an artificial intelligence model that analyzes input data and generates new data or predictions.

[0222] "Tactical situation data" refers to data such as location information, video information, and audio information that is collected to make tactical decisions.

[0223] "Real-time analysis" refers to the process of performing analysis immediately the moment data is received.

[0224] "Feedback" refers to information sent to the device as specific action instructions or tactical advice, based on the results analyzed by the generative model.

[0225] "Entering prompt statements into a generative AI model to perform analysis" refers to the operation of inputting specific commands or questions into an AI model, which then performs data analysis and outputs results based on those inputs.

[0226] "Tactical risk assessment" means analyzing the current tactical situation and evaluating potential threats and problems.

[0227] "Predicting enemy movements" refers to the process of predicting the enemy's actions and intentions based on collected data.

[0228] A "terminal" refers to an electronic device that receives generated feedback and performs actions based on instructions.

[0229] This invention relates to a system that analyzes tactical situation data in real time to improve troop survival rates and combat efficiency. This system is realized through the cooperation of a server, terminals, and users.

[0230] The server receives tactical situation data from hardware such as sensors, cameras, and acoustic data collection devices. This data includes location information, video information, and audio information. The server first converts this data into a standard format and then performs data analysis by inputting prompts into a generative AI model. The generative AI model used is a high-performance model that excels at natural language processing, for example. An example of a prompt is, "Please suggest the optimal action strategy based on the current data."

[0231] Once the analysis is complete, the server generates feedback in natural language based on the results obtained, which includes specific action instructions and tactical advice. For example, it might generate something like, "Enemy is approaching from the south. The safest route is to retreat north."

[0232] The terminal receives feedback delivered from the server. Upon receiving the feedback, the terminal, such as a robot, immediately acts in accordance with the feedback, engaging in activities such as moving to a safe position or tactical deployment.

[0233] When a user participates in the system as a commander, they can accurately grasp the situation and issue additional instructions by reviewing feedback through dedicated devices and monitors. This allows for a rapid response to changes in the tactical situation and improves the safety and combat effectiveness of the troops.

[0234] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0235] Step 1:

[0236] The server receives tactical situational data from sensors, cameras, and acoustic devices deployed on the battlefield. This input data includes location information, video information, and acoustic information. The server aggregates this data and processes it into a standard format suitable for analysis. Specifically, the server divides the video data into frames and performs noise reduction processing.

[0237] Step 2:

[0238] The server passes pre-processed data to the generating AI model and performs the analysis by inputting prompt messages. These prompt messages typically include phrases like, "Please suggest the optimal action strategy based on the current data." Based on these prompts, the AI ​​model performs a tactical risk assessment and predicts enemy movements, generating the results as analysis output. The server receives the enemy's movement routes and recommended actions obtained from the analysis as output data.

[0239] Step 3:

[0240] The server generates feedback based on the analysis results obtained from the generated AI model. This feedback is in natural language and includes specific action instructions and tactical advice. For example, the server generates the instruction "Enemy approaching from the south. The safest route is to retreat north," and prepares this as output data.

[0241] Step 4:

[0242] The server distributes the generated feedback to the terminal. The terminal receives this feedback and immediately acts upon its contents. The robot, having received the feedback as output data, performs the specified action. Specifically, the feedback distributed to the commander's terminal is displayed on a monitor, and the commander confirms it.

[0243] Step 5:

[0244] If the user is a commander, they utilize the delivered feedback to accurately assess the situation and issue additional instructions. Users receive feedback through monitors or dedicated devices and make immediate tactical decisions. For example, a commander who has reviewed the feedback may take specific actions such as ordering new troop deployments.

[0245] (Application Example 1)

[0246] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0247] In modern commercial facilities and event venues, security management is crucial in situations where large numbers of people gather. However, detecting suspicious behavior and abnormal situations in real time and responding appropriately has been difficult with traditional methods. Furthermore, relying solely on the intuition and experience of security personnel can lead to delays in prompt and appropriate responses. Therefore, an efficient information system is needed to ensure safe and smooth operations.

[0248] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0249] In this invention, the server includes means for analyzing dynamic situation data in real time and generating feedback using a generative model, means for distributing action instructions to an information terminal based on the analysis results, and an information terminal that immediately reflects the received instructions in action. This enables security personnel to efficiently monitor the flow of people and abnormal behavior at events and commercial facilities, and to provide appropriate action instructions and safety responses.

[0250] A "generative model" is a type of artificial intelligence that uses input data to generate output in a specific format.

[0251] "Dynamic situation data" refers to real-time information about the movement of people and objects in a specific location and time.

[0252] "Feedback" refers to instructions or information generated based on analysis results, intended to encourage specific actions.

[0253] An "information terminal" refers to an electronic device with communication capabilities that can send, receive, and display data.

[0254] "Action instructions" refer to directives that indicate the actions to be taken in a specific situation.

[0255] "Natural language" refers to the language that humans use on a daily basis, and is a form that enables natural conversation in machine dialogue.

[0256] A "security officer" refers to a person whose job is to ensure safety at a specific facility or event.

[0257] This invention is a system that streamlines safety measures required in markets, event venues, and other similar locations. This system utilizes generative models to analyze situations in real time and provide appropriate feedback.

[0258] The server integrates a generative AI model and a data analysis engine, receiving dynamic situational data collected from cameras and acoustic sensors installed in commercial facilities and event venues. This data includes location, visual, and auditory information. The server analyzes this data to assess the situation, specifically detecting pedestrian flow and suspicious behavioral patterns.

[0259] Based on the analysis results, the server generates action instructions and sends them to an information terminal. This information terminal refers to a smartphone or tablet, which security personnel can carry around within the facility. The received instructions are expressed in natural language and presented to the security personnel in a format that can be quickly understood. The instructions include actions such as patrolling a specific area, checking for suspicious activity, or sealing off an area.

[0260] For example, if an unusual gathering of people or suspicious behavior is detected, the server will immediately generate feedback such as, "There is a gathering in the designated area. Please increase patrols," prompting increased patrols in the specified area. This prompt helps identify areas within the facility that require security.

[0261] In this way, the system enables security personnel to accurately grasp the situation and take swift and appropriate action to maintain security.

[0262] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0263] Step 1:

[0264] The server collects dynamic situational data from cameras and acoustic sensors installed in commercial facilities and event venues. The data obtained as input includes location information, visual information, and sound information. This data is temporarily stored in the server's internal storage.

[0265] Step 2:

[0266] The server inputs the collected dynamic situational data into a generative model and performs real-time analysis. Data processing includes pixel data conversion of visual information and frequency analysis of sound information. The analyzed output identifies areas within the facility where anomalies are occurring and patterns of pedestrian flow.

[0267] Step 3:

[0268] The server generates action instructions based on the analysis results. This output consists of specific instructions necessary to ensure the safety of the facility. For example, it might say, "Increase patrols near the entrance." The server expresses this in natural language and prepares it in text format.

[0269] Step 4:

[0270] The generated operational instructions are distributed from the server to the information terminal. The terminal receives these operational instructions in text format as input and displays them visually to the security personnel. The notification function of smartphones and tablets is used for display.

[0271] Step 5:

[0272] Security personnel, acting as users, can grasp the situation from their terminals and take immediate action according to the instructions. Users can implement security measures by intensifying patrols on site or checking areas identified as abnormal. This enables appropriate security measures based on real-time feedback.

[0273] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0274] This invention is a system that combines the analysis of tactical situation data and the generation of feedback using a generative model with an emotion engine that recognizes user emotions. The aim of this system is to improve the survival rate and combat efficiency of troops on the battlefield and to enhance the quality of decision-making.

[0275] The server first collects tactical situational data, including location, video, and audio information, from sensors and cameras. This data is analyzed in real time using generative models to generate tactical risk assessments and specific action instructions.

[0276] Next, the emotion engine analyzes the user's emotional state, particularly the commander's, voice and facial expressions. This analysis allows for an assessment of the user's mental state and stress level. The server takes this emotional data into consideration and adjusts the content and tone of the feedback to generate an optimized response.

[0277] The terminal incorporates the feedback received from the server. The feedback contains instructions adjusted by the emotion engine, based on which robots or soldiers can take optimal actions. For example, when the user is in a high-stress state, the feedback can provide clearer and simpler instructions.

[0278] The user checks the visual feedback of the emotional state provided by the server together with the execution results of the feedback. This enriches the basis for judgment when giving commands and enables more accurate tactical judgments.

[0279] As a specific example, the server predicts the movements of the enemy while evaluating the stress level of the commander with the emotion engine. Based on the obtained data, it generates feedback that proposes a smooth retreat plan to avoid confusion. By using this system, the troops can flexibly adjust their tactics at the appropriate time and improve the mission success rate.

[0280] The following describes the processing flow.

[0281] Step 1:

[0282] The server collects tactical situation data such as position information, video information, and acoustic information in real time from sensors and cameras deployed on the battlefield. The data is organized using a secure communication protocol and prepared for analysis.

[0283] Step 2:

[0284] The server inputs the collected tactical situation data into the generation model and performs real-time analysis. Through this analysis, risk assessment of the battle situation and prediction of enemy movements are carried out, and newly required tactical instructions are derived.

[0285] Step 3:

[0286] The emotion engine analyzes the voice and video of the user (the commander) and evaluates the emotional state in real time. The server receives the recognized emotion data to understand the stress level and mood of the commander.

[0287] Step 4:

[0288] The server integrates the analysis result by the generation model and the evaluation of the emotion engine to generate tactical feedback. The feedback reflects the adjustment of tone and content according to the emotional state of the commander.

[0289] Step 5:

[0290] The server distributes the generated feedback to the terminal. Based on the received feedback, the terminal initiates actions that can be immediately executed by robots or soldiers.

[0291] Step 6:

[0292] The user checks the action result of the terminal as feedback. At the same time, visual feedback based on the analysis result of the emotion engine is also displayed to assist in further command decisions.

[0293] Through this series of steps, the troops can respond flexibly and quickly to changes in the situation and maximize tactical effectiveness.

[0294] (Example 2)

[0295] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0296] Tactical decisions on the battlefield heavily rely on real-time situational awareness and human emotional factors. However, conventional systems struggle to provide rapid and accurate feedback, and often ignore the emotional state of commanders. As a result, tactical instructions can become ineffective. Therefore, there is a need to improve the accuracy of tactical situational data analysis and provide flexible feedback that responds to the commander's emotions.

[0297] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0298] In this invention, the server includes means for analyzing tactical situation data in real time using a generative model and generating feedback, means for delivering tactical instructions to terminals based on the analysis results and emotional state, and means for immediately reflecting the received instructions in actions. This makes it possible to provide highly accurate feedback according to the situation and flexible instructions that are adapted to the commander's emotional state.

[0299] A "generative model" is an algorithm or software that generates new information based on a vast amount of data.

[0300] "Tactical situation data" refers to information that shows the current situation on the battlefield, and includes location information, video information, and audio information.

[0301] "Real-time analysis" is a process in which data is analyzed immediately upon collection, and the results are provided instantly.

[0302] "Feedback" refers to instructions and recommendations provided based on analysis results, which are information used to optimize actions.

[0303] "Emotional state" refers to the psychological and emotional state of the user or commander, including stress levels and heightened emotions.

[0304] A "terminal" is a hardware device that receives data and presents instructions visually or audibly.

[0305] "Expression in natural language" is a method of presenting information generated by a computer in a form understandable by humans, usually in text form.

[0306] This invention is a system that analyzes tactical situation data and generates feedback. Based on a generation model, it provides real-time analysis of the situation and feedback considering the user's emotions. First, the server collects tactical situation data such as location information, video information, and acoustic information using sensors and cameras. As hardware, high-resolution video cameras and directional microphones are used. Also, software such as TensorFlow and PyTorch is used for data analysis.

[0307] Next, the server inputs the collected tactical situation data into a generation AI model for real-time analysis. Here, the generation model generates an assessment of tactical risks and specific action instructions. Based on this analysis result, an emotion engine uses the voice and expression of the user, especially the commander, to determine the emotional state. Voice analysis software is used for voice recognition, and visual analysis software is used for expression recognition. Specific software such as Google Cloud Speech-to-Text and Microsoft Azure Face API can be considered.

[0308] The generated feedback is sent to the terminal, and the terminal presents the feedback to the user visually or audibly. Natural language processing technology is used for generating feedback, and a generation AI model (e.g., GPT-3) is applied. This feedback can be used by robots and soldiers as instructions when performing tactical actions. When the commander is in a high-stress state, the feedback is adjusted to be concise and clear.

[0309] As a concrete example, the server analyzes tactical situation data, predicts enemy movements, and uses an emotion engine to assess the commander's stress level. Based on the data obtained, it generates feedback that proposes appropriate action plans to promote peaceful resolution or avoid unnecessary risks. As an example of a prompt, it is possible to give specific instructions such as, "Based on tactical situation data, predict enemy movements and generate a retreat plan that takes the commander's stress level into consideration."

[0310] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0311] Step 1:

[0312] The server collects location, video, and acoustic information through sensors and cameras. This data is used to understand the tactical situation on the battlefield and is obtained using high-performance drones, fixed cameras, and acoustic sensors. The input is physical sensors, and the output is digitized location, video, and acoustic data.

[0313] Step 2:

[0314] The server inputs collected tactical situation data into a generating AI model for real-time analysis. This analysis uses TensorFlow and PyTorch to predict enemy positions and activities and assess tactical risks. The input is digital tactical situation data, and the output is information on enemy positions, predicted activities, and risk assessment.

[0315] Step 3:

[0316] The server acquires the commander's voice and facial expression data and analyzes it using an emotion engine. Input data is acquired via microphones and cameras and analyzed using Google Cloud Speech-to-Text and Microsoft Azure Face APIs. The output is an evaluation of the commander's stress level and emotional state. Specifically, it monitors changes in the commander's voice tone and facial expressions.

[0317] Step 4:

[0318] The server generates feedback based on analysis results and emotional assessments. Using a generative AI model (e.g., GPT-3), it creates natural language feedback appropriate to the user's emotional state. The input is the tactical analysis results and emotional state, and the output is the adjusted feedback content. Specifically, if the commander is under high stress, the server generates instructions that are concise and clear.

[0319] Step 5:

[0320] The server sends the generated feedback to the terminal, which then communicates the feedback to the robot or soldier visually or audibly. The input is the generated feedback data, and the output is the instructions provided as a display or audio message on the terminal. In terms of specific actions, the device autonomously begins to act based on the feedback.

[0321] Step 6:

[0322] Users can review the results of their feedback actions through their devices and receive visual feedback on their emotional state from the server, which helps them in making decisions. The input is the feedback and its results, and the output is feedback information that can be used for decision-making. In concrete terms, this allows commanders to make calmer and more appropriate decisions.

[0323] (Application Example 2)

[0324] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0325] In modern work environments, it is crucial to consider the impact of workers' emotional states in order to ensure efficient work progress. However, there is a lack of means to analyze workers' emotions in real time and adjust work instructions accordingly, making it difficult to improve efficiency and safety.

[0326] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0327] In this invention, the server includes means for analyzing work environment data in real time using a generative model and generating feedback, means for analyzing the emotional state of the worker and adjusting work instructions according to the emotions, and means for distributing work instructions to an information device based on the analysis results. This enables efficient and safe work that is tailored to the worker's condition.

[0328] A "generative model" is a general term for algorithms and models that learn features from data and generate new data.

[0329] "Work environment data" refers to various types of information related to the progress of work, such as location information, image information, and sound information within the workplace.

[0330] "Feedback" refers to information and instructions given to workers based on analysis and evaluation.

[0331] "Emotional state" refers to data that indicates the stress levels, fatigue, and mental state of workers.

[0332] "Information device" refers to electronic devices such as terminals and other devices that receive and display data.

[0333] This invention is a system that enables efficient and safe work execution in a work environment. The server acquires work environment data such as location information, image information, and sound information from sensors and cameras installed in factories and work sites. This data is analyzed in real time using generative models such as TensorFlow to generate feedback for improving work procedures.

[0334] In parallel, the server uses emotion analysis technologies such as OpenCV to analyze the emotional state of the worker from their face and voice. This allows the server to understand the level of stress and fatigue the worker is experiencing and adjust instructions accordingly. The feedback generated based on the analysis is delivered to information devices via smartphones or wearable devices. The receiving information devices immediately display work instructions based on the feedback, helping the worker to act efficiently.

[0335] As a concrete example, when a worker on a production line is feeling fatigued, the system could detect that emotion and provide instructions to reduce the workload. In this case, the feedback delivered would be tailored to the worker's condition, such as "Take a short break before your next task." Another example of a prompt message that might be input to the generating AI model is, "Suggest ways to improve safety based on the worker's emotions."

[0336] Thus, this invention contributes to improving production efficiency and the working environment.

[0337] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0338] Step 1:

[0339] The server acquires location, image, and sound information in real time from sensors and cameras installed within the factory. The input is this sensor data, and the output is raw data for analysis, which is passed to a generative model. This prepares the foundational data necessary to understand the situation on-site in detail.

[0340] Step 2:

[0341] The server analyzes raw data acquired by a generative AI model using TensorFlow. The input is sensor data obtained in step 1, and the output is potential feedback for improving work procedures. In this process, the model performs pattern recognition and extracts information necessary for efficient work progress.

[0342] Step 3:

[0343] The server analyzes the emotional state of workers from their facial expressions and voice, separate from the AI ​​models generated using OpenCV. Inputs are camera footage and microphone audio, and output is a numerical value or category indicating emotional state (e.g., fatigue level or stress level). This allows for real-time assessment of the worker's mental load.

[0344] Step 4:

[0345] The server integrates the information obtained in steps 2 and 3 and adjusts the feedback content according to the emotional state. The input is candidate feedback for the work procedure and the emotional state, and the output is optimized instruction information. This generates instructions that are easy for the worker to understand and execute.

[0346] Step 5:

[0347] The server distributes the generated instruction information to the information device. The input is the optimization instructions obtained in step 4, and the output is the feedback displayed on the information device. The terminal displays instructions to the user at the appropriate time to support the smooth progress of the work.

[0348] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0349] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0350] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0351] [Third Embodiment]

[0352] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0353] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0354] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0355] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0356] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0357] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0358] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0359] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0360] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0361] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0362] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0363] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0364] The system of the present invention analyzes tactical situation data in real time using a generative model and generates feedback in order to improve the survival rate and combat efficiency of troops on the battlefield. The processing of the program of this system is described below as an embodiment.

[0365] The server receives real-time tactical situation data from sensors, cameras, and acoustic devices deployed on the battlefield. This data includes location information, video information, and acoustic information. The server collects this data and immediately analyzes it using generative models. This analysis determines tactical risk assessments based on the current battle situation, predictions of enemy movements, and optimal troop deployment.

[0366] Based on the analysis results, the server generates feedback corresponding to the troops and robots. This feedback consists of specific action instructions and tactical advice written in natural language. The generated feedback is then delivered from the server to the terminals.

[0367] The terminal immediately takes action based on feedback received from the server. For example, a robot can move to a safe location or take a defensive position according to the given instructions. If the user is the commander, they can accurately grasp the situation and issue additional instructions by checking the feedback through monitors or dedicated devices.

[0368] For example, if analysis indicates that enemy reinforcements are approaching, the server immediately generates feedback recommending a retreat. The terminal then receives the instruction and quickly begins to retreat to a safe position. This entire process enables rapid decision-making and response by the unit, resulting in effective action on the battlefield.

[0369] The following describes the processing flow.

[0370] Step 1:

[0371] The server collects tactical situational data, including location, video, and audio information, in real time from sensors and cameras deployed on the battlefield. The data is securely received via communication channels and prepared for analysis.

[0372] Step 2:

[0373] The server inputs the collected tactical situation data into a generative model and performs immediate analysis. This analysis helps determine the positions of allies and enemies, predict risks, and derive the optimal tactical deployment.

[0374] Step 3:

[0375] Based on the analysis results, the server generates feedback expressed in natural language. This includes specific action instructions and tactical advice, organizing the information obtained from the generative model.

[0376] Step 4:

[0377] The server distributes the generated feedback to the terminals. The feedback is sent to each terminal in real time, immediately conveying any necessary instructions.

[0378] Step 5:

[0379] The terminal analyzes the feedback received from the server and takes action according to the instructions. For example, a robot can immediately move to a safe location or respond to a designated attack target.

[0380] Step 6:

[0381] The user (commander) monitors the terminal's execution results and checks the effectiveness of the feedback provided by the server. Tactics can be further improved by the user issuing additional instructions as needed.

[0382] (Example 1)

[0383] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0384] In today's tactical environment, there is a need to respond quickly to rapidly changing situations in real time and improve troop survival rates and combat efficiency. However, existing systems have the challenge of not being able to instantly analyze large amounts of situational data and quickly generate and distribute accurate tactical instructions.

[0385] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0386] In this invention, the server includes means for analyzing tactical situation data in real time using a generative model and generating feedback; means for inputting prompt sentences into a generative AI model to perform analysis and perform tactical risk assessment and prediction of enemy movements; and means for delivering tactical instructions to terminals based on the analysis results. This enables effective and rapid decision-making on the battlefield through rapid analysis of the tactical situation and immediate delivery of instructions to units.

[0387] A "generative model" is an artificial intelligence model that analyzes input data and generates new data or predictions.

[0388] "Tactical situation data" refers to data such as location information, video information, and audio information that is collected to make tactical decisions.

[0389] "Real-time analysis" refers to the process of performing analysis immediately the moment data is received.

[0390] "Feedback" refers to information sent to the device as specific action instructions or tactical advice, based on the results analyzed by the generative model.

[0391] "Entering prompt statements into a generative AI model to perform analysis" refers to the operation of inputting specific commands or questions into an AI model, which then performs data analysis and outputs results based on those inputs.

[0392] "Tactical risk assessment" means analyzing the current tactical situation and evaluating potential threats and problems.

[0393] "Predicting enemy movements" refers to the process of predicting the enemy's actions and intentions based on collected data.

[0394] A "terminal" refers to an electronic device that receives generated feedback and performs actions based on instructions.

[0395] This invention relates to a system that analyzes tactical situation data in real time to improve troop survival rates and combat efficiency. This system is realized through the cooperation of a server, terminals, and users.

[0396] The server receives tactical situation data from hardware such as sensors, cameras, and acoustic data collection devices. This data includes location information, video information, and audio information. The server first converts this data into a standard format and then performs data analysis by inputting prompts into a generative AI model. The generative AI model used is a high-performance model that excels at natural language processing, for example. An example of a prompt is, "Please suggest the optimal action strategy based on the current data."

[0397] Once the analysis is complete, the server generates feedback in natural language based on the results obtained, which includes specific action instructions and tactical advice. For example, it might generate something like, "Enemy is approaching from the south. The safest route is to retreat north."

[0398] The terminal receives feedback delivered from the server. Upon receiving the feedback, the terminal, such as a robot, immediately acts in accordance with the feedback, engaging in activities such as moving to a safe position or tactical deployment.

[0399] When a user participates in the system as a commander, they can accurately grasp the situation and issue additional instructions by reviewing feedback through dedicated devices and monitors. This allows for a rapid response to changes in the tactical situation and improves the safety and combat effectiveness of the troops.

[0400] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0401] Step 1:

[0402] The server receives tactical situational data from sensors, cameras, and acoustic devices deployed on the battlefield. This input data includes location information, video information, and acoustic information. The server aggregates this data and processes it into a standard format suitable for analysis. Specifically, the server divides the video data into frames and performs noise reduction processing.

[0403] Step 2:

[0404] The server passes pre-processed data to the generating AI model and performs the analysis by inputting prompt messages. These prompt messages typically include phrases like, "Please suggest the optimal action strategy based on the current data." Based on these prompts, the AI ​​model performs a tactical risk assessment and predicts enemy movements, generating the results as analysis output. The server receives the enemy's movement routes and recommended actions obtained from the analysis as output data.

[0405] Step 3:

[0406] The server generates feedback based on the analysis results obtained from the generated AI model. This feedback is in natural language and includes specific action instructions and tactical advice. For example, the server generates the instruction "Enemy approaching from the south. The safest route is to retreat north," and prepares this as output data.

[0407] Step 4:

[0408] The server distributes the generated feedback to the terminal. The terminal receives this feedback and immediately acts upon its contents. The robot, having received the feedback as output data, performs the specified action. Specifically, the feedback distributed to the commander's terminal is displayed on a monitor, and the commander confirms it.

[0409] Step 5:

[0410] If the user is a commander, they utilize the delivered feedback to accurately assess the situation and issue additional instructions. Users receive feedback through monitors or dedicated devices and make immediate tactical decisions. For example, a commander who has reviewed the feedback may take specific actions such as ordering new troop deployments.

[0411] (Application Example 1)

[0412] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0413] In modern commercial facilities and event venues, security management is crucial in situations where large numbers of people gather. However, detecting suspicious behavior and abnormal situations in real time and responding appropriately has been difficult with traditional methods. Furthermore, relying solely on the intuition and experience of security personnel can lead to delays in prompt and appropriate responses. Therefore, an efficient information system is needed to ensure safe and smooth operations.

[0414] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0415] In this invention, the server includes means for analyzing dynamic situation data in real time and generating feedback using a generative model, means for distributing action instructions to an information terminal based on the analysis results, and an information terminal that immediately reflects the received instructions in action. This enables security personnel to efficiently monitor the flow of people and abnormal behavior at events and commercial facilities, and to provide appropriate action instructions and safety responses.

[0416] A "generative model" is a type of artificial intelligence that uses input data to generate output in a specific format.

[0417] "Dynamic situation data" refers to real-time information about the movement of people and objects in a specific location and time.

[0418] "Feedback" refers to instructions or information generated based on analysis results, intended to encourage specific actions.

[0419] An "information terminal" refers to an electronic device with communication capabilities that can send, receive, and display data.

[0420] "Action instructions" refer to directives that indicate the actions to be taken in a specific situation.

[0421] "Natural language" refers to the language that humans use on a daily basis, and is a form that enables natural conversation in machine dialogue.

[0422] A "security officer" refers to a person whose job is to ensure safety at a specific facility or event.

[0423] This invention is a system that streamlines safety measures required in markets, event venues, and other similar locations. This system utilizes generative models to analyze situations in real time and provide appropriate feedback.

[0424] The server integrates a generative AI model and a data analysis engine, receiving dynamic situational data collected from cameras and acoustic sensors installed in commercial facilities and event venues. This data includes location, visual, and auditory information. The server analyzes this data to assess the situation, specifically detecting pedestrian flow and suspicious behavioral patterns.

[0425] Based on the analysis results, the server generates action instructions and sends them to an information terminal. This information terminal refers to a smartphone or tablet, which security personnel can carry around within the facility. The received instructions are expressed in natural language and presented to the security personnel in a format that can be quickly understood. The instructions include actions such as patrolling a specific area, checking for suspicious activity, or sealing off an area.

[0426] For example, if an unusual gathering of people or suspicious behavior is detected, the server will immediately generate feedback such as, "There is a gathering in the designated area. Please increase patrols," prompting increased patrols in the specified area. This prompt helps identify areas within the facility that require security.

[0427] In this way, the system enables security personnel to accurately grasp the situation and take swift and appropriate action to maintain security.

[0428] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0429] Step 1:

[0430] The server collects dynamic situational data from cameras and acoustic sensors installed in commercial facilities and event venues. The data obtained as input includes location information, visual information, and sound information. This data is temporarily stored in the server's internal storage.

[0431] Step 2:

[0432] The server inputs the collected dynamic situational data into a generative model and performs real-time analysis. Data processing includes pixel data conversion of visual information and frequency analysis of sound information. The analyzed output identifies areas within the facility where anomalies are occurring and patterns of pedestrian flow.

[0433] Step 3:

[0434] The server generates action instructions based on the analysis results. This output consists of specific instructions necessary to ensure the safety of the facility. For example, it might say, "Increase patrols near the entrance." The server expresses this in natural language and prepares it in text format.

[0435] Step 4:

[0436] The generated operational instructions are distributed from the server to the information terminal. The terminal receives these operational instructions in text format as input and displays them visually to the security personnel. The notification function of smartphones and tablets is used for display.

[0437] Step 5:

[0438] Security personnel, acting as users, can grasp the situation from their terminals and take immediate action according to the instructions. Users can implement security measures by intensifying patrols on site or checking areas identified as abnormal. This enables appropriate security measures based on real-time feedback.

[0439] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0440] This invention is a system that combines the analysis of tactical situation data and the generation of feedback using a generative model with an emotion engine that recognizes user emotions. The aim of this system is to improve the survival rate and combat efficiency of troops on the battlefield and to enhance the quality of decision-making.

[0441] The server first collects tactical situational data, including location, video, and audio information, from sensors and cameras. This data is analyzed in real time using generative models to generate tactical risk assessments and specific action instructions.

[0442] Next, the emotion engine analyzes the user's emotional state, particularly the commander's, voice and facial expressions. This analysis allows for an assessment of the user's mental state and stress level. The server takes this emotional data into consideration and adjusts the content and tone of the feedback to generate an optimized response.

[0443] The terminal receives feedback from the server. This feedback includes instructions adjusted by an emotion engine, which allows robots and soldiers to take optimal actions. For example, if the user is under high stress, the feedback can provide clearer and simpler instructions.

[0444] Users can view visual feedback on their emotional state provided by the server, along with the results of their actions. This enriches the information available when giving instructions, enabling them to make more accurate tactical decisions.

[0445] As a concrete example, the server predicts enemy movements while simultaneously evaluating the commander's stress level using an emotion engine. Based on the data obtained, it generates feedback suggesting a smooth retreat plan to avoid confusion. Using this system, troops can flexibly adjust their tactics at the appropriate time, improving their mission success rate.

[0446] The following describes the processing flow.

[0447] Step 1:

[0448] The server collects tactical situational data, such as location information, video information, and audio information, in real time from sensors and cameras deployed on the battlefield. The data is organized using secure communication protocols and prepared for analysis.

[0449] Step 2:

[0450] The server inputs the collected tactical situation data into a generative model and performs real-time analysis. This analysis enables risk assessment of the battle situation and predictions of enemy movements, leading to the generation of necessary new tactical instructions.

[0451] Step 3:

[0452] The emotion engine analyzes the user's (commander's) voice and video to evaluate their emotional state in real time. The server receives the recognized emotion data and understands the commander's stress level and feelings.

[0453] Step 4:

[0454] The server integrates the analysis results from the generative model with the evaluation from the emotion engine to generate tactical feedback. The feedback reflects adjustments in tone and content based on the commander's emotional state.

[0455] Step 5:

[0456] The server delivers the generated feedback to the terminal. Based on the received feedback, the terminal initiates actions that the robot or soldier can immediately perform.

[0457] Step 6:

[0458] Users review the results of their device actions as feedback. Simultaneously, visual feedback based on the emotion engine's analysis is displayed to aid in further decision-making.

[0459] This series of steps allows units to respond flexibly and quickly to changing situations and maximize tactical effectiveness.

[0460] (Example 2)

[0461] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0462] Tactical decisions on the battlefield heavily rely on real-time situational awareness and human emotional factors. However, conventional systems struggle to provide rapid and accurate feedback, and often ignore the emotional state of commanders. As a result, tactical instructions can become ineffective. Therefore, there is a need to improve the accuracy of tactical situational data analysis and provide flexible feedback that responds to the commander's emotions.

[0463] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0464] In this invention, the server includes means for analyzing tactical situation data in real time using a generative model and generating feedback, means for delivering tactical instructions to terminals based on the analysis results and emotional state, and means for immediately reflecting the received instructions in actions. This makes it possible to provide highly accurate feedback according to the situation and flexible instructions that are adapted to the commander's emotional state.

[0465] A "generative model" is an algorithm or software that generates new information based on a vast amount of data.

[0466] "Tactical situation data" refers to information that shows the current situation on the battlefield, and includes location information, video information, and audio information.

[0467] "Real-time analysis" is a process in which data is analyzed immediately upon collection, and the results are provided instantly.

[0468] "Feedback" refers to instructions and recommendations provided based on analysis results, which are information used to optimize actions.

[0469] "Emotional state" refers to the psychological and emotional state of the user or commander, including stress levels and heightened emotions.

[0470] A "terminal" is a hardware device that receives data and presents instructions either visually or audibly.

[0471] "Representing information in natural language" refers to a method of presenting computer-generated information in a format that humans can understand, which is usually in the form of text.

[0472] This invention is a system that analyzes tactical situation data and generates feedback, providing real-time situation analysis and user-centric feedback based on a generative model. First, the server collects tactical situation data such as location information, video information, and audio information using sensors and cameras. Hardware such as high-resolution video cameras and directional microphones are used. Software such as TensorFlow and PyTorch is used for data analysis.

[0473] Next, the server inputs the collected tactical situation data into a generative AI model for real-time analysis. Here, the generative model generates tactical risk assessments and specific action instructions. Based on these analysis results, an emotion engine is used to deduce the emotional state of the user, particularly the commander, from their voice and facial expressions. Voice recognition uses speech analysis software, and facial expression recognition uses visual analysis software. Specific software options include Google Cloud Speech-to-Text and Microsoft Azure Face API.

[0474] The generated feedback is sent to a terminal, which presents the feedback to the user visually or audibly. Natural language processing technology is used to generate the feedback, and a generative AI model (e.g., GPT-3) is applied. This feedback is used by robots and soldiers as instructions when performing tactical actions. If the commander is under high stress, the feedback is adjusted to be concise and clear.

[0475] As a concrete example, the server analyzes tactical situation data, predicts enemy movements, and uses an emotion engine to assess the commander's stress level. Based on the data obtained, it generates feedback that proposes appropriate action plans to promote peaceful resolution or avoid unnecessary risks. As an example of a prompt, it is possible to give specific instructions such as, "Based on tactical situation data, predict enemy movements and generate a retreat plan that takes the commander's stress level into consideration."

[0476] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0477] Step 1:

[0478] The server collects location, video, and acoustic information through sensors and cameras. This data is used to understand the tactical situation on the battlefield and is obtained using high-performance drones, fixed cameras, and acoustic sensors. The input is physical sensors, and the output is digitized location, video, and acoustic data.

[0479] Step 2:

[0480] The server inputs collected tactical situation data into a generating AI model for real-time analysis. This analysis uses TensorFlow and PyTorch to predict enemy positions and activities and assess tactical risks. The input is digital tactical situation data, and the output is information on enemy positions, predicted activities, and risk assessment.

[0481] Step 3:

[0482] The server acquires the commander's voice and facial expression data and analyzes it using an emotion engine. Input data is acquired via microphones and cameras and analyzed using Google Cloud Speech-to-Text and Microsoft Azure Face APIs. The output is an evaluation of the commander's stress level and emotional state. Specifically, it monitors changes in the commander's voice tone and facial expressions.

[0483] Step 4:

[0484] The server generates feedback based on analysis results and emotional assessments. Using a generative AI model (e.g., GPT-3), it creates natural language feedback appropriate to the user's emotional state. The input is the tactical analysis results and emotional state, and the output is the adjusted feedback content. Specifically, if the commander is under high stress, the server generates instructions that are concise and clear.

[0485] Step 5:

[0486] The server sends the generated feedback to the terminal, which then communicates the feedback to the robot or soldier visually or audibly. The input is the generated feedback data, and the output is the instructions provided as a display or audio message on the terminal. In terms of specific actions, the device autonomously begins to act based on the feedback.

[0487] Step 6:

[0488] Users can review the results of their feedback actions through their devices and receive visual feedback on their emotional state from the server, which helps them in making decisions. The input is the feedback and its results, and the output is feedback information that can be used for decision-making. In concrete terms, this allows commanders to make calmer and more appropriate decisions.

[0489] (Application Example 2)

[0490] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0491] In modern work environments, it is crucial to consider the impact of workers' emotional states in order to ensure efficient work progress. However, there is a lack of means to analyze workers' emotions in real time and adjust work instructions accordingly, making it difficult to improve efficiency and safety.

[0492] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0493] In this invention, the server includes means for analyzing work environment data in real time using a generative model and generating feedback, means for analyzing the emotional state of the worker and adjusting work instructions according to the emotions, and means for distributing work instructions to an information device based on the analysis results. This enables efficient and safe work that is tailored to the worker's condition.

[0494] A "generative model" is a general term for algorithms and models that learn features from data and generate new data.

[0495] "Work environment data" refers to various types of information related to the progress of work, such as location information, image information, and sound information within the workplace.

[0496] "Feedback" refers to information and instructions given to workers based on analysis and evaluation.

[0497] "Emotional state" refers to data that indicates the stress levels, fatigue, and mental state of workers.

[0498] "Information device" refers to electronic devices such as terminals and other devices that receive and display data.

[0499] This invention is a system that enables efficient and safe work execution in a work environment. The server acquires work environment data such as location information, image information, and sound information from sensors and cameras installed in factories and work sites. This data is analyzed in real time using generative models such as TensorFlow to generate feedback for improving work procedures.

[0500] In parallel, the server uses emotion analysis technologies such as OpenCV to analyze the emotional state of the worker from their face and voice. This allows the server to understand the level of stress and fatigue the worker is experiencing and adjust instructions accordingly. The feedback generated based on the analysis is delivered to information devices via smartphones or wearable devices. The receiving information devices immediately display work instructions based on the feedback, helping the worker to act efficiently.

[0501] As a concrete example, when a worker on a production line is feeling fatigued, the system could detect that emotion and provide instructions to reduce the workload. In this case, the feedback delivered would be tailored to the worker's condition, such as "Take a short break before your next task." Another example of a prompt message that might be input to the generating AI model is, "Suggest ways to improve safety based on the worker's emotions."

[0502] Thus, this invention contributes to improving production efficiency and the working environment.

[0503] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0504] Step 1:

[0505] The server acquires location, image, and sound information in real time from sensors and cameras installed within the factory. The input is this sensor data, and the output is raw data for analysis, which is passed to a generative model. This prepares the foundational data necessary to understand the situation on-site in detail.

[0506] Step 2:

[0507] The server analyzes raw data acquired by a generative AI model using TensorFlow. The input is sensor data obtained in step 1, and the output is potential feedback for improving work procedures. In this process, the model performs pattern recognition and extracts information necessary for efficient work progress.

[0508] Step 3:

[0509] The server analyzes the emotional state of workers from their facial expressions and voice, separate from the AI ​​models generated using OpenCV. Inputs are camera footage and microphone audio, and output is a numerical value or category indicating emotional state (e.g., fatigue level or stress level). This allows for real-time assessment of the worker's mental load.

[0510] Step 4:

[0511] The server integrates the information obtained in steps 2 and 3 and adjusts the feedback content according to the emotional state. The input is candidate feedback for the work procedure and the emotional state, and the output is optimized instruction information. This generates instructions that are easy for the worker to understand and execute.

[0512] Step 5:

[0513] The server distributes the generated instruction information to the information device. The input is the optimization instructions obtained in step 4, and the output is the feedback displayed on the information device. The terminal displays instructions to the user at the appropriate time to support the smooth progress of the work.

[0514] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0515] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0516] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0517] [Fourth Embodiment]

[0518] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0519] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0520] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0521] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0522] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0523] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0524] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0525] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0526] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0527] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0528] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0529] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0530] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0531] The system of the present invention analyzes tactical situation data in real time using a generative model and generates feedback in order to improve the survival rate and combat efficiency of troops on the battlefield. The processing of the program of this system is described below as an embodiment.

[0532] The server receives real-time tactical situation data from sensors, cameras, and acoustic devices deployed on the battlefield. This data includes location information, video information, and acoustic information. The server collects this data and immediately analyzes it using generative models. This analysis determines tactical risk assessments based on the current battle situation, predictions of enemy movements, and optimal troop deployment.

[0533] Based on the analysis results, the server generates feedback corresponding to the troops and robots. This feedback consists of specific action instructions and tactical advice written in natural language. The generated feedback is then delivered from the server to the terminals.

[0534] The terminal immediately takes action based on feedback received from the server. For example, a robot can move to a safe location or take a defensive position according to the given instructions. If the user is the commander, they can accurately grasp the situation and issue additional instructions by checking the feedback through monitors or dedicated devices.

[0535] For example, if analysis indicates that enemy reinforcements are approaching, the server immediately generates feedback recommending a retreat. The terminal then receives the instruction and quickly begins to retreat to a safe position. This entire process enables rapid decision-making and response by the unit, resulting in effective action on the battlefield.

[0536] The following describes the processing flow.

[0537] Step 1:

[0538] The server collects tactical situational data, including location, video, and audio information, in real time from sensors and cameras deployed on the battlefield. The data is securely received via communication channels and prepared for analysis.

[0539] Step 2:

[0540] The server inputs the collected tactical situation data into a generative model and performs immediate analysis. This analysis helps determine the positions of allies and enemies, predict risks, and derive the optimal tactical deployment.

[0541] Step 3:

[0542] Based on the analysis results, the server generates feedback expressed in natural language. This includes specific action instructions and tactical advice, organizing the information obtained from the generative model.

[0543] Step 4:

[0544] The server distributes the generated feedback to the terminals. The feedback is sent to each terminal in real time, immediately conveying any necessary instructions.

[0545] Step 5:

[0546] The terminal analyzes the feedback received from the server and takes action according to the instructions. For example, a robot can immediately move to a safe location or respond to a designated attack target.

[0547] Step 6:

[0548] The user (commander) monitors the terminal's execution results and checks the effectiveness of the feedback provided by the server. Tactics can be further improved by the user issuing additional instructions as needed.

[0549] (Example 1)

[0550] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0551] In today's tactical environment, there is a need to respond quickly to rapidly changing situations in real time and improve troop survival rates and combat efficiency. However, existing systems have the challenge of not being able to instantly analyze large amounts of situational data and quickly generate and distribute accurate tactical instructions.

[0552] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0553] In this invention, the server includes means for analyzing tactical situation data in real time using a generative model and generating feedback; means for inputting prompt sentences into a generative AI model to perform analysis and perform tactical risk assessment and prediction of enemy movements; and means for delivering tactical instructions to terminals based on the analysis results. This enables effective and rapid decision-making on the battlefield through rapid analysis of the tactical situation and immediate delivery of instructions to units.

[0554] A "generative model" is an artificial intelligence model that analyzes input data and generates new data or predictions.

[0555] "Tactical situation data" refers to data such as location information, video information, and audio information that is collected to make tactical decisions.

[0556] "Real-time analysis" refers to the process of performing analysis immediately the moment data is received.

[0557] "Feedback" refers to information sent to the terminal as specific action instructions or tactical advice, based on the results analyzed by the generative model.

[0558] "Entering prompt statements into a generative AI model to perform analysis" refers to the operation of inputting specific commands or questions into an AI model, which then performs data analysis and outputs results based on those inputs.

[0559] "Tactical risk assessment" means analyzing the current tactical situation and evaluating potential threats and problems.

[0560] "Predicting enemy movements" refers to the process of predicting the enemy's actions and intentions based on collected data.

[0561] A "terminal" refers to an electronic device that receives generated feedback and performs actions based on instructions.

[0562] This invention relates to a system that analyzes tactical situation data in real time to improve troop survival rates and combat efficiency. This system is realized through the cooperation of a server, terminals, and users.

[0563] The server receives tactical situation data from hardware such as sensors, cameras, and acoustic data collection devices. This data includes location information, video information, and audio information. The server first converts this data into a standard format and then performs data analysis by inputting prompts into a generative AI model. The generative AI model used is a high-performance model that excels at natural language processing, for example. An example of a prompt is, "Please suggest the optimal action strategy based on the current data."

[0564] Once the analysis is complete, the server generates feedback in natural language based on the results obtained, which includes specific action instructions and tactical advice. For example, it might generate something like, "Enemy is approaching from the south. The safest route is to retreat north."

[0565] The terminal receives feedback delivered from the server. Upon receiving the feedback, the terminal, such as a robot, immediately acts in accordance with the feedback, engaging in activities such as moving to a safe position or tactical deployment.

[0566] When a user participates in the system as a commander, they can accurately grasp the situation and issue additional instructions by reviewing feedback through dedicated devices and monitors. This allows for a rapid response to changes in the tactical situation and improves the safety and combat effectiveness of the troops.

[0567] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0568] Step 1:

[0569] The server receives tactical situational data from sensors, cameras, and acoustic devices deployed on the battlefield. This input data includes location information, video information, and acoustic information. The server aggregates this data and processes it into a standard format suitable for analysis. Specifically, the server divides the video data into frames and performs noise reduction processing.

[0570] Step 2:

[0571] The server passes pre-processed data to the generating AI model and performs the analysis by inputting prompt messages. These prompt messages typically include phrases like, "Please suggest the optimal action strategy based on the current data." Based on these prompts, the AI ​​model performs a tactical risk assessment and predicts enemy movements, generating the results as analysis output. The server receives the enemy's movement routes and recommended actions obtained from the analysis as output data.

[0572] Step 3:

[0573] The server generates feedback based on the analysis results obtained from the generated AI model. This feedback is in natural language and includes specific action instructions and tactical advice. For example, the server generates the instruction "Enemy approaching from the south. The safest route is to retreat north," and prepares this as output data.

[0574] Step 4:

[0575] The server distributes the generated feedback to the terminal. The terminal receives this feedback and immediately acts upon its contents. The robot, having received the feedback as output data, performs the specified action. Specifically, the feedback distributed to the commander's terminal is displayed on a monitor, and the commander confirms it.

[0576] Step 5:

[0577] If the user is a commander, they utilize the delivered feedback to accurately assess the situation and issue additional instructions. Users receive feedback through monitors or dedicated devices and make immediate tactical decisions. For example, a commander who has reviewed the feedback may take specific actions such as ordering new troop deployments.

[0578] (Application Example 1)

[0579] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0580] In modern commercial facilities and event venues, security management is crucial in situations where large numbers of people gather. However, detecting suspicious behavior and abnormal situations in real time and responding appropriately has been difficult with traditional methods. Furthermore, relying solely on the intuition and experience of security personnel can lead to delays in prompt and appropriate responses. Therefore, an efficient information system is needed to ensure safe and smooth operations.

[0581] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0582] In this invention, the server includes means for analyzing dynamic situation data in real time and generating feedback using a generative model, means for distributing action instructions to an information terminal based on the analysis results, and an information terminal that immediately reflects the received instructions in action. This enables security personnel to efficiently monitor the flow of people and abnormal behavior at events and commercial facilities, and to provide appropriate action instructions and safety responses.

[0583] A "generative model" is a type of artificial intelligence that uses input data to generate output in a specific format.

[0584] "Dynamic situation data" refers to real-time information about the movement of people and objects in a specific location and time.

[0585] "Feedback" refers to instructions or information generated based on analysis results, intended to encourage specific actions.

[0586] An "information terminal" refers to an electronic device with communication capabilities that can send, receive, and display data.

[0587] "Action instructions" refer to directives that indicate the actions to be taken in a specific situation.

[0588] "Natural language" refers to the language that humans use on a daily basis, and is a form that enables natural conversation in machine dialogue.

[0589] A "security officer" refers to a person whose job is to ensure safety at a specific facility or event.

[0590] This invention is a system that streamlines safety measures required in markets, event venues, and other similar locations. This system utilizes generative models to analyze situations in real time and provide appropriate feedback.

[0591] The server integrates a generative AI model and a data analysis engine, receiving dynamic situational data collected from cameras and acoustic sensors installed in commercial facilities and event venues. This data includes location, visual, and auditory information. The server analyzes this data to assess the situation, specifically detecting pedestrian flow and suspicious behavioral patterns.

[0592] Based on the analysis results, the server generates action instructions and sends them to an information terminal. This information terminal refers to a smartphone or tablet, which security personnel can carry around within the facility. The received instructions are expressed in natural language and presented to the security personnel in a format that can be quickly understood. The instructions include actions such as patrolling a specific area, checking for suspicious activity, or sealing off an area.

[0593] For example, if an unusual gathering of people or suspicious behavior is detected, the server will immediately generate feedback such as, "There is a gathering in the designated area. Please increase patrols," prompting increased patrols in the specified area. This prompt helps identify areas within the facility that require security.

[0594] In this way, the system enables security personnel to accurately grasp the situation and take swift and appropriate action to maintain security.

[0595] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0596] Step 1:

[0597] The server collects dynamic situational data from cameras and acoustic sensors installed in commercial facilities and event venues. The data obtained as input includes location information, visual information, and sound information. This data is temporarily stored in the server's internal storage.

[0598] Step 2:

[0599] The server inputs the collected dynamic situational data into a generative model and performs real-time analysis. Data processing includes pixel data conversion of visual information and frequency analysis of sound information. The analyzed output identifies areas within the facility where anomalies are occurring and patterns of pedestrian flow.

[0600] Step 3:

[0601] The server generates action instructions based on the analysis results. This output consists of specific instructions necessary to ensure the safety of the facility. For example, it might say, "Increase patrols near the entrance." The server expresses this in natural language and prepares it in text format.

[0602] Step 4:

[0603] The generated operational instructions are distributed from the server to the information terminal. The terminal receives these operational instructions in text format as input and displays them visually to the security personnel. The notification function of a smartphone or tablet is used for the display.

[0604] Step 5:

[0605] Security personnel, acting as users, can grasp the situation from their terminals and take immediate action according to the instructions. Users can implement security measures by intensifying patrols on site or checking areas identified as abnormal. This enables appropriate security measures based on real-time feedback.

[0606] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0607] This invention is a system that combines the analysis of tactical situation data and the generation of feedback using a generative model with an emotion engine that recognizes user emotions. The aim of this system is to improve the survival rate and combat efficiency of troops on the battlefield and to enhance the quality of decision-making.

[0608] The server first collects tactical situational data, including location, video, and audio information, from sensors and cameras. This data is analyzed in real time using generative models to generate tactical risk assessments and specific action instructions.

[0609] Next, the emotion engine analyzes the user's emotional state, particularly the commander's, voice and facial expressions. This analysis allows for an assessment of the user's mental state and stress level. The server takes this emotional data into consideration and adjusts the content and tone of the feedback to generate an optimized response.

[0610] The terminal receives feedback from the server. This feedback includes instructions adjusted by an emotion engine, which allows robots and soldiers to take optimal actions. For example, if the user is under high stress, the feedback can provide clearer and simpler instructions.

[0611] Users can view visual feedback on their emotional state provided by the server, along with the results of their actions. This enriches the information available when giving instructions, enabling them to make more accurate tactical decisions.

[0612] As a concrete example, the server predicts enemy movements while simultaneously evaluating the commander's stress level using an emotion engine. Based on the data obtained, it generates feedback suggesting a smooth retreat plan to avoid confusion. Using this system, troops can flexibly adjust their tactics at the appropriate time, improving their mission success rate.

[0613] The following describes the processing flow.

[0614] Step 1:

[0615] The server collects tactical situational data, such as location information, video information, and audio information, in real time from sensors and cameras deployed on the battlefield. The data is organized using secure communication protocols and prepared for analysis.

[0616] Step 2:

[0617] The server inputs the collected tactical situation data into a generative model and performs real-time analysis. This analysis enables risk assessment of the battle situation and predictions of enemy movements, leading to the generation of necessary new tactical instructions.

[0618] Step 3:

[0619] The emotion engine analyzes the user's (commander's) voice and video to evaluate their emotional state in real time. The server receives the recognized emotion data and understands the commander's stress level and feelings.

[0620] Step 4:

[0621] The server integrates the analysis results from the generative model with the evaluation from the emotion engine to generate tactical feedback. The feedback reflects adjustments in tone and content based on the commander's emotional state.

[0622] Step 5:

[0623] The server delivers the generated feedback to the terminal. Based on the received feedback, the terminal initiates actions that the robot or soldier can immediately perform.

[0624] Step 6:

[0625] Users review the results of their device actions as feedback. Simultaneously, visual feedback based on the emotion engine's analysis is displayed to aid in further decision-making.

[0626] This series of steps allows units to respond flexibly and quickly to changing situations and maximize tactical effectiveness.

[0627] (Example 2)

[0628] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0629] Tactical decisions on the battlefield heavily rely on real-time situational awareness and human emotional factors. However, conventional systems struggle to provide rapid and accurate feedback, and often ignore the emotional state of commanders. As a result, tactical instructions can become ineffective. Therefore, there is a need to improve the accuracy of tactical situational data analysis and provide flexible feedback that responds to the commander's emotions.

[0630] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0631] In this invention, the server includes means for analyzing tactical situation data in real time using a generative model and generating feedback, means for delivering tactical instructions to terminals based on the analysis results and emotional state, and means for immediately reflecting the received instructions in actions. This makes it possible to provide highly accurate feedback according to the situation and flexible instructions that are adapted to the commander's emotional state.

[0632] A "generative model" is an algorithm or software that generates new information based on a vast amount of data.

[0633] "Tactical situation data" refers to information that shows the current situation on the battlefield, and includes location information, video information, and audio information.

[0634] "Real-time analysis" is a process in which data is analyzed immediately upon collection, and the results are provided instantly.

[0635] "Feedback" refers to instructions and recommendations provided based on analysis results, which are information used to optimize actions.

[0636] "Emotional state" refers to the psychological and emotional state of the user or commander, including stress levels and heightened emotions.

[0637] A "terminal" is a hardware device that receives data and presents instructions either visually or audibly.

[0638] "Representing information in natural language" refers to a method of presenting computer-generated information in a format that humans can understand, which is usually in the form of text.

[0639] This invention is a system that analyzes tactical situation data and generates feedback, providing real-time situation analysis and user-centric feedback based on a generative model. First, the server collects tactical situation data such as location information, video information, and audio information using sensors and cameras. Hardware such as high-resolution video cameras and directional microphones are used. Software such as TensorFlow and PyTorch is used for data analysis.

[0640] Next, the server inputs the collected tactical situation data into a generative AI model for real-time analysis. Here, the generative model generates tactical risk assessments and specific action instructions. Based on these analysis results, an emotion engine is used to deduce the emotional state of the user, particularly the commander, from their voice and facial expressions. Voice recognition uses speech analysis software, and facial expression recognition uses visual analysis software. Specific software options include Google Cloud Speech-to-Text and Microsoft Azure Face API.

[0641] The generated feedback is sent to a terminal, which presents the feedback to the user visually or audibly. Natural language processing technology is used to generate the feedback, and a generative AI model (e.g., GPT-3) is applied. This feedback is used by robots and soldiers as instructions when performing tactical actions. If the commander is under high stress, the feedback is adjusted to be concise and clear.

[0642] As a concrete example, the server analyzes tactical situation data, predicts enemy movements, and uses an emotion engine to assess the commander's stress level. Based on the data obtained, it generates feedback that proposes appropriate action plans to promote peaceful resolution or avoid unnecessary risks. As an example of a prompt, it is possible to give specific instructions such as, "Based on tactical situation data, predict enemy movements and generate a retreat plan that takes the commander's stress level into consideration."

[0643] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0644] Step 1:

[0645] The server collects location, video, and acoustic information through sensors and cameras. This data is used to understand the tactical situation on the battlefield and is obtained using high-performance drones, fixed cameras, and acoustic sensors. The input is physical sensors, and the output is digitized location, video, and acoustic data.

[0646] Step 2:

[0647] The server inputs collected tactical situation data into a generating AI model for real-time analysis. This analysis uses TensorFlow and PyTorch to predict enemy positions and activities and assess tactical risks. The input is digital tactical situation data, and the output is information on enemy positions, predicted activities, and risk assessment.

[0648] Step 3:

[0649] The server acquires the commander's voice and facial expression data and analyzes it using an emotion engine. Input data is acquired via microphones and cameras and analyzed using Google Cloud Speech-to-Text and Microsoft Azure Face APIs. The output is an evaluation of the commander's stress level and emotional state. Specifically, it monitors changes in the commander's voice tone and facial expressions.

[0650] Step 4:

[0651] The server generates feedback based on analysis results and emotional assessments. Using a generative AI model (e.g., GPT-3), it creates natural language feedback appropriate to the user's emotional state. The input is the tactical analysis results and emotional state, and the output is the adjusted feedback content. Specifically, if the commander is under high stress, the server generates instructions that are concise and clear.

[0652] Step 5:

[0653] The server sends the generated feedback to the terminal, which then communicates the feedback to the robot or soldier visually or audibly. The input is the generated feedback data, and the output is the instructions provided as a display or audio message on the terminal. In terms of specific actions, the device autonomously begins to act based on the feedback.

[0654] Step 6:

[0655] Users can review the results of their feedback actions through their devices and receive visual feedback on their emotional state from the server, which helps them in making decisions. The input is the feedback and its results, and the output is feedback information that can be used for decision-making. In concrete terms, this allows commanders to make calmer and more appropriate decisions.

[0656] (Application Example 2)

[0657] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0658] In modern work environments, it is crucial to consider the impact of workers' emotional states in order to ensure efficient work progress. However, there is a lack of means to analyze workers' emotions in real time and adjust work instructions accordingly, making it difficult to improve efficiency and safety.

[0659] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0660] In this invention, the server includes means for analyzing work environment data in real time using a generative model and generating feedback, means for analyzing the emotional state of the worker and adjusting work instructions according to the emotions, and means for distributing work instructions to an information device based on the analysis results. This enables efficient and safe work that is tailored to the worker's condition.

[0661] A "generative model" is a general term for algorithms and models that learn features from data and generate new data.

[0662] "Work environment data" refers to various types of information related to the progress of work, such as location information, image information, and sound information within the workplace.

[0663] "Feedback" refers to information and instructions given to workers based on analysis and evaluation.

[0664] "Emotional state" refers to data that indicates the stress levels, fatigue, and mental state of workers.

[0665] "Information device" refers to electronic devices such as terminals and other devices that receive and display data.

[0666] This invention is a system that enables efficient and safe work execution in a work environment. The server acquires work environment data such as location information, image information, and sound information from sensors and cameras installed in factories and work sites. This data is analyzed in real time using generative models such as TensorFlow to generate feedback for improving work procedures.

[0667] In parallel, the server uses emotion analysis technologies such as OpenCV to analyze the emotional state of the worker from their face and voice. This allows the server to understand the level of stress and fatigue the worker is experiencing and adjust instructions accordingly. The feedback generated based on the analysis is delivered to information devices via smartphones or wearable devices. The receiving information devices immediately display work instructions based on the feedback, helping the worker to act efficiently.

[0668] As a concrete example, when a worker on a production line is feeling fatigued, the system could detect that emotion and provide instructions to reduce the workload. In this case, the feedback delivered would be tailored to the worker's condition, such as "Take a short break before your next task." Another example of a prompt message that might be input to the generating AI model is, "Suggest ways to improve safety based on the worker's emotions."

[0669] Thus, this invention contributes to improving production efficiency and the working environment.

[0670] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0671] Step 1:

[0672] The server acquires location, image, and sound information in real time from sensors and cameras installed within the factory. The input is this sensor data, and the output is raw data for analysis, which is passed to a generative model. This prepares the foundational data necessary to understand the situation on-site in detail.

[0673] Step 2:

[0674] The server analyzes raw data acquired by a generative AI model using TensorFlow. The input is sensor data obtained in step 1, and the output is potential feedback for improving work procedures. In this process, the model performs pattern recognition and extracts information necessary for efficient work progress.

[0675] Step 3:

[0676] The server analyzes the emotional state of workers from their facial expressions and voice, separate from the AI ​​models generated using OpenCV. Inputs are camera footage and microphone audio, and output is a numerical value or category indicating emotional state (e.g., fatigue level or stress level). This allows for real-time assessment of the worker's mental load.

[0677] Step 4:

[0678] The server integrates the information obtained in steps 2 and 3 and adjusts the feedback content according to the emotional state. The input is candidate feedback for the work procedure and the emotional state, and the output is optimized instruction information. This generates instructions that are easy for the worker to understand and execute.

[0679] Step 5:

[0680] The server distributes the generated instruction information to the information device. The input is the optimization instructions obtained in step 4, and the output is the feedback displayed on the information device. The terminal displays instructions to the user at the appropriate time to support the smooth progress of the work.

[0681] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0682] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0683] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0684] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0685] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0686] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0687] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0688] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0689] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0690] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0691] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0692] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0693] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0694] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0695] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0696] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0697] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0698] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0699] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0700] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0701] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0702] The following is further disclosed regarding the embodiments described above.

[0703] (Claim 1)

[0704] A means of analyzing tactical situation data in real time and generating feedback using a generative model,

[0705] A means of delivering tactical instructions to terminals based on analysis results,

[0706] A system that includes a terminal that immediately translates received instructions into action.

[0707] (Claim 2)

[0708] The system according to claim 1, wherein the tactical situation data to be analyzed includes location information, video information, and acoustic information.

[0709] (Claim 3)

[0710] The system according to claim 1, further comprising means for expressing the generated feedback in natural language and preparing it for distribution.

[0711] "Example 1"

[0712] (Claim 1)

[0713] A means of analyzing tactical situation data in real time using a generative model and generating feedback,

[0714] A means of inputting prompt text into a generative AI model to perform analysis and perform tactical risk assessment and prediction of enemy movements,

[0715] A means of delivering tactical instructions to terminals based on analysis results,

[0716] A system that includes a terminal that immediately translates received instructions into action.

[0717] (Claim 2)

[0718] The system according to claim 1, which includes location information, video information, and audio information as tactical situation data to be analyzed, and converts the received data into a standard format.

[0719] (Claim 3)

[0720] The system according to claim 1, further comprising means for expressing the generated feedback in natural language and providing specific action instructions to a robot or commander.

[0721] "Application Example 1"

[0722] (Claim 1)

[0723] A means of analyzing dynamic situation data in real time and generating feedback using a generative model,

[0724] A means for distributing operation instructions to an information terminal based on the analysis results,

[0725] A system that includes an information terminal that immediately translates received instructions into action.

[0726] (Claim 2)

[0727] The system according to claim 1, wherein the dynamic situation data to be analyzed includes location information, visual information, and sound information.

[0728] (Claim 3)

[0729] The system according to claim 1, further comprising means for expressing the generated feedback in natural language and preparing it for distribution.

[0730] (Claim 4)

[0731] The system according to claim 1, further comprising means for analyzing the flow of people and abnormal behavior at events and commercial facilities, and generating appropriate action instructions for security personnel.

[0732] "Example 2 of combining an emotion engine"

[0733] (Claim 1)

[0734] A means of analyzing tactical situation data in real time and generating feedback using a generative model,

[0735] A means for delivering tactical instructions to a terminal based on analysis results and emotional state,

[0736] A system that includes a terminal that immediately translates received instructions into action.

[0737] (Claim 2)

[0738] The system according to claim 1, characterized in that the tactical situation data to be analyzed includes location information, video information, and audio information.

[0739] (Claim 3)

[0740] The system according to claim 1, further comprising means for expressing the generated feedback in natural language and optimizing it for delivery according to the user's emotional state.

[0741] "Application example 2 when combining with an emotional engine"

[0742] (Claim 1)

[0743] A means of analyzing work environment data in real time using a generative model and generating feedback,

[0744] A means of analyzing the emotional state of workers and adjusting work instructions according to their emotions,

[0745] A means for distributing work instructions to an information device based on the analysis results,

[0746] A system that includes an information device that immediately incorporates received instructions into the work.

[0747] (Claim 2)

[0748] The system according to claim 1, wherein the work environment data to be analyzed includes location information, image information, and sound information.

[0749] (Claim 3)

[0750] The system according to claim 1, further comprising means for expressing the generated feedback in natural language and preparing it for distribution. [Explanation of Symbols]

[0751] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of analyzing tactical situation data in real time and generating feedback using a generative model, A means of delivering tactical instructions to terminals based on analysis results, A system that includes a terminal that immediately translates received instructions into action.

2. The system according to claim 1, wherein the tactical situation data to be analyzed includes location information, video information, and sound information.

3. The system according to claim 1, further comprising means for expressing the generated feedback in natural language and preparing it for distribution.

Images