System

Abstract

The system provided by the embodiment of the invention aims at efficiently detecting suspicious persons from the image of the anti-theft camera and only extracting required parts. A system according to an embodiment includes an acquisition unit, a detection unit, a clip unit, and a report generation unit. The acquisition part acquires an image of the anti-theft camera. The detection unit analyzes the image acquired by the acquisition unit and detects a suspicious person. The editing unit edits only the desired portion on the basis of the suspicious person detected by the detection unit. The report generation unit generates a report on the basis of the video clipped by the clipping unit.

Description

Technical Field

[0001] The technology disclosed herein relates to a system. Background Technology

[0002] Patent Document 1 discloses a personalized chatbot control method executed by at least one processor, the method comprising: receiving user speech; adding the user speech to a prompt containing instructions related to a chatbot role; encoding the prompt; and inputting the encoded prompt into a language model to generate chatbot speech in response to the user speech.

[0003] Patent document 1: Japanese Patent Application Publication No. 2022-180282. Summary of the Invention

[0004] In existing technologies, the amount of images captured by security cameras is enormous, making it difficult to efficiently detect suspicious individuals and extract only the necessary portions, thus posing a challenge.

[0005] The system involved in this technical solution is designed to efficiently detect suspicious persons from images of anti-theft cameras and extract only the necessary parts.

[0006] The system involved in this technical solution includes an acquisition unit, a detection unit, an editing unit, and a report generation unit. The acquisition unit acquires images from the security cameras. The detection unit analyzes the images acquired by the acquisition unit to detect suspicious individuals. The editing unit, based on the suspicious individuals detected by the detection unit, edits only the necessary portions. The report generation unit generates a report based on the edited images from the editing unit.

[0007] The system involved in this technical solution can efficiently detect suspicious persons from the images of anti-theft cameras and extract only the required parts. Attached Figure Description

[0008] Figure 1 This is a conceptual diagram illustrating an example of the configuration of a data processing system according to the first embodiment.

[0009] Figure 2 This is a conceptual diagram illustrating an example of the main functions of the data processing apparatus and smart device according to the first embodiment.

[0010] Figure 3 This is a conceptual diagram illustrating an example of the data processing system configuration in the second embodiment.

[0011] Figure 4 This is a conceptual diagram illustrating an example of the main functions of the data processing device and smart glasses according to the second embodiment.

[0012] Figure 5 This is a conceptual diagram illustrating an example of the data processing system configuration in the third embodiment.

[0013] Figure 6 This is a conceptual diagram illustrating an example of the main functions of the data processing device and head-mounted terminal according to the third embodiment.

[0014] Figure 7 This is a conceptual diagram illustrating an example of the data processing system configuration in the fourth embodiment.

[0015] Figure 8 This is a conceptual diagram illustrating an example of the functions of the main parts of the data processing device and robot according to the fourth embodiment.

[0016] Figure 9 It represents an emotion graph that maps multiple emotions.

[0017] Figure 10 It represents an emotion graph that maps multiple emotions.

[0018] Explanation of reference numerals in the attached figures

[0019] Data processing systems 10, 210, 310, and 410

[0020] 12 Data processing devices

[0021] 14 Smart devices

[0022] 214 Smart Glasses

[0023] 314 Head-mounted terminal

[0024] 414 Robot. Detailed Implementation

[0025] Hereinafter, an example of an implementation of the system involved in this disclosure will be described with reference to the accompanying drawings.

[0026] First, let's explain the terms used in the following description.

[0027] In the following embodiments, the processor (hereinafter referred to as "processor"), as indicated by the reference numerals, can be a single computing device or a combination of multiple computing devices. Furthermore, a processor can be a single computing device or a combination of multiple computing devices. Examples of computing devices include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit), etc.

[0028] In the following embodiments, RAM (Random Access Memory), as indicated in the figures, is a memory for temporary information storage that is used by the processor as working memory.

[0029] In the following embodiments, the memory, as indicated by the reference numerals, is one or more non-volatile storage devices used to store various programs and parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), disks (e.g., hard disks), or magnetic tapes, etc.

[0030] In the following embodiments, the communication I / F (Interface) with reference numerals is an interface including a communication processor and an antenna, etc. The communication I / F is responsible for communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0031] In the following implementation, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it can be only A, only B, or a combination of A and B. Furthermore, in this specification, when "and / or" connects more than three items, the same approach as "A and / or B" applies.

[0032] First Implementation Method

[0033] Figure 1 An example of the configuration of the data processing system 10 according to the first embodiment is shown.

[0034] like Figure 1 As shown, the data processing system 10 includes a data processing device 12 and an intelligent device 14. An example of the data processing device 12 is a server.

[0035] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. An example of the network 54 includes a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0036] The smart device 14 includes a computer 36, a receiver 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. In addition, the receiver 38, output device 40, and camera 42 are also connected to the bus 52.

[0037] The receiving device 38 includes a touchscreen 38A and a microphone 38B, etc., for receiving user input. The touchscreen 38A receives user input generated by contact with an indicator (e.g., a pen or finger). The microphone 38B receives user input generated by sound by detecting the user's voice. The control unit 46A sends data representing user input received via the touchscreen 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, a specific processing unit 290 (see reference...) Figure 2 Get the data that represents the user input.

[0038] The output device 40 includes a display 40A and a speaker 40B, etc., and presents data to the user by outputting data in a user-perceptible form (e.g., sound and / or text). The display 40A displays visual information such as text and images according to instructions from the processor 46. The speaker 40B outputs sound 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 imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0039] Communication I / F 44 is connected to network 54. Communication I / F 44 and 26 are responsible for sending and receiving various information between processor 46 and processor 28 via network 54.

[0040] Figure 2 An example of the main functions of the data processing device 12 and the smart device 14 is shown.

[0041] like Figure 2 As shown, in the data processing apparatus 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the memory 32. The specific processing program 56 is an example of a "program" as understood in this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 based on the specific processing program 56 executed on the RAM 30.

[0042] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. The emotion inference function using the emotion-specific model 59 (emotion-specific function) includes inferring and predicting the user's emotions, performing various inferences and predictions related to the user's emotions, but is not limited to this example. Furthermore, emotion inference and prediction also include, for example, emotion analysis (analysis).

[0043] In the smart device 14, specific processing is performed by the processor 46. A specific processing program 60 is stored in the memory 50. The specific processing program 60 is used in conjunction with the data processing system 10. The processor 46 reads the specific processing program 60 from the memory 50 and executes the read specific processing program 60 on the RAM 48. Specific processing is implemented by the processor 46 operating as a control unit 46A based on the specific processing program 60 executed on the RAM 48. Furthermore, the smart device 14 may also have the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and use these models to perform the same processing as the specific processing unit 290.

[0044] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. Furthermore, the data processing device 12 may be a server device or a user-owned terminal device (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of the processing performed by the data processing system 10 of the first embodiment will be described.

[0045] Implementation Method 1

[0046] The G-Men AI anti-theft system described in this invention is an anti-theft system for supermarkets and convenience stores. This system reads video from multiple anti-theft cameras and provides the following functions: First, it detects suspicious individuals and notifies the manager. The AI ​​analyzes the images from the anti-theft cameras to identify individuals exhibiting unusual behavior. For example, it detects behaviors such as picking up goods and immediately putting them back, or moving around the store abnormally. This allows for early detection of potential theft suspects and notification to the manager. Second, it edits only the necessary portions from a large amount of video to generate smaller video files. The AI ​​analyzes the images from the anti-theft cameras and extracts only the portions containing the moment of theft or suspicious behavior. This efficiently preserves the portions needed as evidence, reducing data size. Furthermore, it generates suspect-specific reports. The AI ​​records the behavior of detected suspicious individuals in detail and compiles it into a report. For example, it records when, where, and what behavior was performed. This facilitates reporting to the police and submitting evidence to specific suspects. Thus, the G-Men AI anti-theft system, through suspicious individual detection, necessary video editing, and the generation of suspect-specific reports, aims to eliminate theft losses. Therefore, the anti-theft G-Men AI can efficiently collect, analyze, edit, and generate reports of anti-theft camera images.

[0047] The anti-theft G-Men AI described in this embodiment includes a data acquisition unit, a detection unit, an editing unit, and a report generation unit. The acquisition unit acquires images from anti-theft cameras. For example, the acquisition unit can acquire images from multiple anti-theft cameras. The acquisition unit can use cameras covering all areas of the store or cameras concentrated in specific areas. The acquisition unit can also utilize AI to efficiently acquire images from anti-theft cameras. The detection unit analyzes the images acquired by the acquisition unit to detect suspicious individuals. The detection unit can use AI to analyze the images from anti-theft cameras to identify individuals engaging in abnormal behavior. The detection unit can detect behaviors such as immediately putting away goods after picking them up, or moving around the store abnormally. The detection unit can also use AI to detect individuals engaging in abnormal behavior early and notify the responsible person. The editing unit, based on the suspicious individuals detected by the detection unit, edits only the necessary portions. The editing unit can use AI to analyze the images from anti-theft cameras and extract only the portions containing the moment of theft or suspicious behavior. The editing unit can efficiently save the portions needed as evidence, reducing data volume. The report generation unit generates a report based on the images edited by the editing unit. The report generation unit can use AI to record the behavior of detected suspicious individuals in detail and compile it into a report. The report generation unit can record when, where, and what actions were performed. Therefore, the anti-theft G-Men AI according to this embodiment can efficiently collect, analyze, edit, and generate reports of anti-theft camera images.

[0048] The data acquisition department collects images from security cameras. It can acquire images from multiple security cameras. Specifically, it can use cameras covering all areas of the store or cameras concentrated in specific areas. This allows for comprehensive monitoring of every corner of the store, reducing the risk of theft. The acquisition department can utilize AI to efficiently acquire images from security cameras. AI can automatically adjust the quality and resolution of the images for optimal data acquisition. For example, it can compensate for image distortion caused by changes in lighting or camera position, obtaining clear images. Furthermore, the acquisition department can acquire images in real time and send them to a central database. This ensures that the latest images are always stored for subsequent analysis and detection. The acquisition department can also utilize image data compression technology to efficiently manage data volume. This allows for long-term storage of large amounts of image data and traceability of past images. The acquisition department can also collaborate with other systems or departments to share data as needed. For example, it can collaborate with the police or security companies, providing acquired image data for rapid response. Therefore, the acquisition department can efficiently and effectively acquire images from security cameras, improving the overall performance of the system.

[0049] The detection department analyzes images captured by the acquisition department to detect suspicious individuals. The detection department utilizes AI to analyze images from security cameras to identify individuals engaging in unusual behavior. Specifically, it can detect behaviors such as picking up goods and immediately putting them back, or moving around the store abnormally. AI tracks the movements of people in the images and compares them to typical behavioral patterns to detect anomalies. For example, AI analyzes the speed, direction, and duration of a person's movements to identify behaviors that differ from the norm. Furthermore, AI learns from past data to model typical theft patterns, achieving higher detection accuracy. The detection department can identify individuals engaging in unusual behavior early and notify supervisors. Notifications are given in real-time, allowing supervisors to respond immediately. For example, an alert can be sent to a smartphone or tablet, displaying the location and behavior of the suspicious individual. In addition, the detection department can incorporate a feedback loop to continuously improve the accuracy of abnormal behavior detection. Thus, the detection department can retrain the AI ​​model based on the collected data, further enhancing detection accuracy. Therefore, the detection department can quickly and accurately analyze the acquired images and identify suspicious individuals early on.

[0050] The editing department, based on suspicious individuals detected by the detection department, only edits out the necessary portions. The editing department can utilize AI to analyze images from security cameras, extracting only the parts containing the moment of theft or suspicious behavior. Specifically, AI tracks the movements of people in the images, identifying the time periods and locations of specific abnormal behaviors. This allows for efficient editing of the required portions from long-form footage. The editing department can efficiently preserve the portions needed as evidence, reducing data volume. For example, it can edit and save footage from a few minutes before and after the moment of theft or suspicious behavior. Furthermore, the editing department can employ image compression technology to optimize data volume while maintaining image quality. This allows the saved images to be played back in high quality during subsequent verification. Moreover, the editing department can share the edited images with other systems or departments, such as providing them to the police or security companies for rapid response. Thus, the editing department can efficiently extract the necessary portions and preserve them as evidence.

[0051] The report generation department generates reports based on footage edited by the editing department. The department utilizes AI to meticulously record and compile reports of detected suspicious individuals' behavior. Specifically, it records when, where, and what actions were performed. AI analyzes the movements of individuals in the footage, generating a detailed timeline of their actions. For example, it records the time when an item was picked up, the route taken within the store, and the moment of theft. AI can also assess the anomalousness and risk level of the behavior and reflect this in the report. This allows managers to clearly understand the behavior of suspicious individuals. The report generation department can save the generated reports digitally and print them as needed. Furthermore, the department can collaborate with other systems or departments to share reports. For example, it can provide reports to the police or security companies for rapid response. Thus, the report generation department can meticulously record the behavior of suspicious individuals and efficiently generate reports.

[0052] The inspection department can analyze images from security cameras to identify individuals engaging in unusual behavior. The department can utilize AI to analyze these images and pinpoint individuals with suspicious activity. This includes detecting behaviors such as immediately putting away goods after picking them up or moving around the store unnecessarily. The department can also use AI to identify individuals exhibiting unusual behavior early and notify management. Thus, by identifying individuals with unusual behavior, early detection of theft can be achieved. Some or all of the above processing in the inspection department can be performed using AI, or it can be done without AI. For example, the inspection department can input images from security cameras into the AI, which can then handle the processing of individuals exhibiting unusual behavior.

[0053] The editing unit can extract only the necessary portions from the images detected by the detection unit. The editing unit can utilize AI to analyze the images from the security camera, extracting only the parts containing the moment of theft or suspicious behavior. The editing unit can efficiently preserve the portions needed as evidence, reducing data volume. Thus, by efficiently editing the necessary portions, data volume can be reduced. Some or all of the above processing in the editing unit can be performed using AI, or it can be done without AI. For example, the editing unit can input the images from the security camera into the AI, which will then extract the necessary portions.

[0054] The report generation department can generate reports based on images edited by the editing department. The report generation department can utilize AI to record in detail the behavior of detected suspicious individuals and compile it into a report. The report generation department can record when, where, and what actions were performed. This streamlines report generation, making it easier to identify specific suspects. Some or all of the above processing in the report generation department can be performed using AI, or it can be done without AI. For example, the report generation department can input the edited images into the AI, which will then perform report generation.

[0055] The acquisition unit can capture images from multiple security cameras. It can use cameras covering all areas of the store or cameras focused on specific areas. The acquisition unit can also utilize AI to efficiently acquire images from security cameras. Therefore, by acquiring images from multiple security cameras, wide-area monitoring can be achieved. Some or all of the above processing in the acquisition unit can be done using AI, or it can be done without AI. For example, the acquisition unit can input images from multiple security cameras into the AI, which will then perform the image acquisition.

[0056] The inspection department can detect behaviors such as picking up items and immediately putting them back, or unusual movement within the store. It can utilize AI to analyze images from security cameras to detect these behaviors. The department can also use AI to identify individuals engaging in unusual behavior early and notify management. Thus, by detecting specific behavioral patterns, individuals with a high probability of theft can be identified early. Some or all of the above processing in the inspection department can be achieved using AI, or it can be done without AI. For example, the inspection department can input images from security cameras into the AI, which will then perform the detection of specific behavioral patterns.

[0057] The data acquisition department can dynamically adjust the installation positions of security cameras to achieve optimal image capture. The department can utilize AI to dynamically adjust the camera positions for optimal image capture. It can also automatically adjust camera positions based on store congestion levels to capture optimal images. Furthermore, when abnormal behavior is detected in a specific area, the department can concentrate cameras in that area. The department can also dynamically adjust camera positions based on changes in store layout. Therefore, by dynamically adjusting the installation positions of security cameras, optimal image capture can be achieved. Some or all of the above processing in the acquisition department can be achieved using AI, or it can be done without AI. For example, the acquisition department can input the installation positions of the security cameras into the AI, which will then perform the position adjustments.

[0058] The acquisition department can change its acquisition method based on specific time periods or days of the week during image acquisition. The acquisition department can utilize AI to change the acquisition method based on specific time periods or days of the week during image acquisition. The acquisition department can use the usual acquisition method during weekdays and increase the acquisition frequency at night or on weekends. The acquisition department can also enhance the acquisition method on days with specific events to capture more detailed images. The acquisition department can also change the acquisition method based on historical data during periods of high theft activity. Therefore, by changing the acquisition method according to specific time periods or days of the week, efficient image acquisition can be achieved. Some or all of the above processing in the acquisition department can be achieved through AI, or it can be done without AI. For example, the acquisition department can input data for specific time periods or days of the week into the AI, which will then execute the change in acquisition method.

[0059] The acquisition unit can adjust its acquisition method based on weather or lighting conditions during image acquisition. The acquisition unit can utilize AI to adjust the acquisition method according to weather or lighting conditions. For example, it can prioritize indoor image acquisition in rainy weather. It can use an infrared camera to acquire images in low-light conditions. It can enhance outdoor image acquisition in sunny weather. Therefore, by adjusting the acquisition method according to weather or lighting conditions, optimal image acquisition can be achieved. Some or all of the above processing in the acquisition unit can be achieved through AI, or it can be done without AI. For example, the acquisition unit can input weather or lighting condition data into the AI, which will then adjust the acquisition method accordingly.

[0060] The data acquisition department can analyze the store's congestion level during image capture and select the optimal acquisition method. The department can utilize AI to analyze store congestion and select the best acquisition method. The acquisition department can capture wide-area images when the store is crowded, and focus on capturing images of specific areas when the store is empty. The department can also adjust the camera's capture angle based on the congestion level. Therefore, selecting the acquisition method based on store congestion levels enables efficient image acquisition. Some or all of the above processing in the acquisition department can be achieved through AI, or it can be done without AI. For example, the acquisition department can input store congestion data into the AI, which will then select the acquisition method.

[0061] The detection department can optimize its detection algorithms based on past theft data during detection. The department can utilize AI to optimize these algorithms. It can also optimize algorithms for detecting specific behavioral patterns based on past theft data. Furthermore, the department can predict thefts occurring within specific time periods or on specific days of the week based on past data and adjust the detection algorithms accordingly. Additionally, the department can analyze past data to develop algorithms to counter new theft methods. Therefore, by optimizing detection algorithms based on past theft data, detection accuracy can be improved. Some or all of the above processes in the detection department can be implemented using AI, or they can be performed without AI. For example, the detection department can input past theft data into AI, which will then optimize the detection algorithms.

[0062] The detection department can identify specific abnormal behaviors based on an individual's attribute information during detection. The detection department can utilize AI to identify specific abnormal behaviors based on an individual's attribute information during detection. The detection department can perform detection based on specific behavioral patterns such as age and gender. The detection department can also adjust the detection criteria for abnormal behaviors based on attribute information. The detection department can also consider attribute information to detect abnormal behaviors of specific individuals earlier. Therefore, by identifying abnormal behaviors based on an individual's attribute information, detection accuracy can be improved. Some or all of the above processing in the detection department can be achieved through AI, or AI can be used without it. For example, the detection department can input an individual's attribute information into the AI, which will then execute the specific abnormal behavior detection.

[0063] The inspection department can identify specific abnormal behaviors based on store layout information during inspections. The inspection department can utilize AI to identify specific abnormal behaviors based on store layout information. The inspection department can detect abnormal behaviors in specific areas based on store layout information. The inspection department can also adjust the detection standards for abnormal behaviors based on layout changes. The inspection department can also consider layout information to focus on detecting abnormal behaviors in specific areas. Therefore, by identifying specific abnormal behaviors based on store layout information, inspection accuracy can be improved. Some or all of the above processing in the inspection department can be achieved through AI, or AI can be used without it. For example, the inspection department can input store layout information into AI, which will then execute the specific abnormal behavior detection.

[0064] The detection department can coordinate with other security systems to detect specific abnormal behaviors during detection. The detection department can utilize AI to coordinate with other security systems to detect specific abnormal behaviors. The detection department can also coordinate with alarm systems to trigger alarms when abnormal behavior is detected. The detection department can also improve the accuracy of abnormal behavior detection based on data from other security systems. Furthermore, the detection department can coordinate with other security systems to respond quickly when abnormal behavior is detected. Therefore, by coordinating with other security systems, the accuracy of abnormal behavior detection can be improved. Some or all of the above processes in the detection department can be implemented using AI, or AI can be used without it. For example, the detection department can input data from other security systems into the AI, which will then execute specific abnormal behavior detection.

[0065] The editing department can optimize image quality to extract the desired portions during editing. The editing department can utilize AI to optimize image quality and extract the desired portions during editing. The editing department can adjust image resolution for high-quality editing of the desired portions. The editing department can also remove image noise to create clearer images. The editing department can also adjust image brightness and contrast for optimal image quality editing. Therefore, by optimizing image quality, the desired portions can be extracted in high quality. Some or all of the above processing in the editing department can be achieved through AI, or it can be done without AI. For example, the editing department can input image quality data into AI, which will then perform image quality optimization.

[0066] The editing department can integrate multiple camera images for optimal editing. It can utilize AI to integrate multiple camera images during editing, editing footage from different angles. The editing department can also analyze multiple camera images and edit the most important parts. Furthermore, it can combine multiple camera images to achieve panoramic editing. Therefore, by integrating multiple camera images, footage from different angles can be edited efficiently. Some or all of the above processing in the editing department can be achieved through AI, or it can be done without AI. For example, the editing department can input multiple camera images into AI, which will then perform image integration and editing.

[0067] The editing department can adjust the video timeline during editing to extract the optimal parts. The editing department can utilize AI to adjust the video timeline to extract the best parts. The editing department can adjust the video timeline to extract important parts. The editing department can also compress the video timeline to display important parts briefly. The editing department can also expand the video timeline to extract detailed parts. Therefore, by adjusting the video timeline, important parts can be extracted efficiently. Some or all of the above processing in the editing department can be achieved through AI, or it can be done without AI. For example, the editing department can input video timeline data into AI, which will then perform timeline adjustments.

[0068] The editing department can analyze video and audio data during editing to extract desired portions. The editing department can utilize AI to analyze video and audio data during editing to extract the desired portions. The editing department can analyze video and audio data to extract portions containing important dialogue or sounds. The editing department can also detect abnormal sounds based on audio data and edit those portions. The editing department can also analyze audio data to extract portions containing specific keywords. Therefore, by analyzing audio data, portions containing important dialogue or sounds can be extracted efficiently. Some or all of the above processing in the editing department can be achieved using AI, or AI can be used without it. For example, the editing department can input audio data into AI, which will then perform the extraction of the desired portions.

[0069] The report generation department can select the optimal report format based on past report data during report generation. The report generation department can utilize AI to select the optimal report format based on past report data. The report generation department can select the most effective report format based on past report data. The report generation department can also propose report formats suitable for specific situations from past report data. The report generation department can also analyze past report data to develop new report formats. Therefore, by selecting the optimal report format based on past report data, effective reports can be generated efficiently. Some or all of the above processes in the report generation department can be implemented using AI, or AI can be used without it. For example, the report generation department can input past report data into AI, which will then perform the report format selection.

[0070] The report generation department can automatically add image metadata during report generation. This can be achieved using AI. The report generation department can automatically add the image capture date and location to the report. Furthermore, the report generation department can generate detailed reports based on the image metadata. Thus, by automatically adding image metadata, detailed reports can be generated efficiently. Some or all of the above processes in the report generation department can be performed using AI, or they can be performed without AI. For example, the report generation department can input the image metadata into the AI, which will then perform the metadata addition.

[0071] The report generation department can integrate data from other security systems when generating reports. It can utilize AI to integrate data from other security systems during report generation. The department can generate detailed reports based on data from other security systems. It can also collaborate with other security systems to generate reports based on integrated data. Furthermore, the department can analyze data from other security systems to generate optimal reports. Therefore, by integrating data from other security systems, detailed reports can be generated efficiently. Some or all of the above processes in the report generation department can be implemented using AI, or AI can be used without it. For example, the report generation department can input data from other security systems into the AI, which will then perform report generation.

[0072] The report generation department can select the report delivery method when generating a report. This can be done using AI. The report generation department can choose to send the report via email. It can also choose to share the report via the cloud. Furthermore, the report generation department can select the delivery method based on user needs. Therefore, by selecting the delivery method, reports can be sent in a way that meets user requirements. Some or all of the above processes in the report generation department can be implemented using AI, or they can be performed without AI. For example, the report generation department can input the delivery method data into the AI, which will then select the delivery method.

[0073] The system involved in this embodiment is not limited to the above examples. For example, various modifications can be made as follows.

[0074] The G-Men AI anti-theft system also features an audio analysis unit. This unit analyzes audio data contained in the anti-theft camera footage to detect unusual sounds or conversations. For example, it can detect the sound of goods being bagged or unnatural conversations with store clerks. Thus, by utilizing not only video but also audio data, the accuracy of theft detection can be improved. The audio analysis unit can use AI to analyze audio data and detect unusual sounds or conversations. It can also detect conversations containing specific keywords and notify the responsible party. Furthermore, the audio analysis unit can identify individuals exhibiting unusual behavior based on audio data.

[0075] The G-Men AI anti-theft system also features a facial recognition unit. This unit identifies faces appearing in the anti-theft camera footage, specifically targeting individuals with a history of theft suspicion. For example, it can compare the face with a database of past thefts to identify the same person. This allows for early detection of individuals with a high likelihood of repeat offenses and notification to supervisors. The facial recognition unit utilizes AI for facial recognition and compares it with a historical database. It can also detect individuals with specific characteristics and issue warnings. Furthermore, the unit can integrate footage from multiple cameras to improve facial recognition accuracy.

[0076] The G-Men anti-theft AI also features a behavior prediction unit. This unit analyzes images from the anti-theft cameras to predict human behavior. For example, it can predict the next action based on past behavioral patterns. This allows for early detection of high-probability theft activities and notification of supervisors. The behavior prediction unit can utilize AI to analyze behavioral patterns and make predictions. It can also predict behavior in specific areas and adjust the camera focus accordingly. Furthermore, it can issue warnings when abnormal behavior is predicted.

[0077] The G-Men anti-theft AI system also includes a temperature sensor unit. This unit monitors the store temperature and detects abnormal temperature changes. For example, if a sudden temperature change occurs in a specific area, the camera can be focused on that area. This allows for early detection of unusual behavior based on temperature changes, and notification to management. The temperature sensor unit can use AI to analyze temperature data and detect abnormal temperature changes. It can also issue warnings when temperatures exceed specific ranges. Furthermore, the temperature sensor unit can predict the likelihood of unusual behavior based on temperature data.

[0078] The G-Men AI anti-theft system also includes a vibration sensor unit. This unit monitors vibrations within the store and detects abnormal vibrations. For example, it monitors shelf vibrations, and when abnormal vibrations occur, cameras can be focused on that area. This allows for early detection of unusual behavior based on vibration data, enabling notification of management. The vibration sensor unit can use AI to analyze vibration data and detect abnormal vibrations. It can also detect specific vibration patterns and issue warnings. Furthermore, it can predict the likelihood of unusual behavior based on vibration data.

[0079] The following is a brief description of the processing flow of Implementation Method 1.

[0080] Step 1: The acquisition department collects images from security cameras. The acquisition department can collect images from multiple security cameras. It can use cameras covering all areas of the store or cameras focused on specific areas. The acquisition department can also utilize AI to efficiently collect images from security cameras.

[0081] Step 2: The detection department analyzes the images collected by the acquisition department to detect suspicious individuals. The detection department can use AI to analyze images from security cameras to identify individuals engaging in abnormal behavior. This includes detecting behaviors such as picking up items and immediately putting them back, or moving around the store unusually. The detection department can also use AI to identify individuals engaging in abnormal behavior early and notify the responsible personnel.

[0082] Step 3: The editing department, based on the suspicious individuals detected by the detection department, only edits out the necessary portions. The editing department can utilize AI to analyze the images from the security cameras, extracting only the parts containing the moment of theft or suspicious behavior. The editing department can efficiently preserve the portions needed as evidence, reducing data volume.

[0083] Step 4: The report generation department generates a report based on the footage edited by the editing department. The report generation department can utilize AI to record in detail the behavior of detected suspicious individuals and compile it into a report. The report generation department can record when, where, and what kind of behavior was performed.

[0084] Implementation Method 2

[0085] The G-Men AI anti-theft system described in this invention is an anti-theft system for supermarkets and convenience stores. This system reads video from multiple anti-theft cameras and provides the following functions: First, it detects suspicious individuals and notifies the manager. The AI ​​analyzes the images from the anti-theft cameras to identify individuals exhibiting unusual behavior. For example, it detects behaviors such as picking up goods and immediately putting them back, or moving around the store abnormally. This allows for early detection of potential theft suspects and notification to the manager. Second, it edits only the necessary portions from a large amount of video to generate smaller video files. The AI ​​analyzes the images from the anti-theft cameras and extracts only the portions containing the moment of theft or suspicious behavior. This efficiently preserves the portions needed as evidence, reducing data size. Furthermore, it generates suspect-specific reports. The AI ​​records the behavior of detected suspicious individuals in detail and compiles it into a report. For example, it records when, where, and what behavior was performed. This facilitates reporting to the police and submitting evidence to specific suspects. Thus, the G-Men AI anti-theft system, through suspicious individual detection, necessary video editing, and the generation of suspect-specific reports, aims to eliminate theft losses. Therefore, the anti-theft G-Men AI can efficiently collect, analyze, edit, and generate reports of anti-theft camera images.

[0086] The anti-theft G-Men AI described in this embodiment includes a data acquisition unit, a detection unit, an editing unit, and a report generation unit. The acquisition unit acquires images from anti-theft cameras. For example, the acquisition unit can acquire images from multiple anti-theft cameras. The acquisition unit can use cameras covering all areas of the store or cameras concentrated in specific areas. The acquisition unit can also utilize AI to efficiently acquire images from anti-theft cameras. The detection unit analyzes the images acquired by the acquisition unit to detect suspicious individuals. The detection unit can use AI to analyze the images from anti-theft cameras to identify individuals engaging in abnormal behavior. The detection unit can detect behaviors such as immediately putting away goods after picking them up, or moving around the store abnormally. The detection unit can also use AI to detect individuals engaging in abnormal behavior early and notify the responsible person. The editing unit, based on the suspicious individuals detected by the detection unit, edits only the necessary portions. The editing unit can use AI to analyze the images from anti-theft cameras and extract only the portions containing the moment of theft or suspicious behavior. The editing unit can efficiently save the portions needed as evidence, reducing data volume. The report generation unit generates a report based on the images edited by the editing unit. The report generation unit can use AI to record the behavior of detected suspicious individuals in detail and compile it into a report. The report generation unit can record when, where, and what actions were performed. Therefore, the anti-theft G-Men AI according to this embodiment can efficiently collect, analyze, edit, and generate reports of anti-theft camera images.

[0087] The data acquisition department collects images from security cameras. It can acquire images from multiple security cameras. Specifically, it can use cameras covering all areas of the store or cameras concentrated in specific areas. This allows for comprehensive monitoring of every corner of the store, reducing the risk of theft. The acquisition department can utilize AI to efficiently acquire images from security cameras. AI can automatically adjust the quality and resolution of the images for optimal data acquisition. For example, it can compensate for image distortion caused by changes in lighting or camera position, obtaining clear images. Furthermore, the acquisition department can acquire images in real time and send them to a central database. This ensures that the latest images are always stored for subsequent analysis and detection. The acquisition department can also utilize image data compression technology to efficiently manage data volume. This allows for long-term storage of large amounts of image data and traceability of past images. The acquisition department can also collaborate with other systems or departments to share data as needed. For example, it can collaborate with the police or security companies, providing acquired image data for rapid response. Therefore, the acquisition department can efficiently and effectively acquire images from security cameras, improving the overall performance of the system.

[0088] The detection department analyzes images captured by the acquisition department to detect suspicious individuals. The detection department utilizes AI to analyze images from security cameras to identify individuals engaging in unusual behavior. Specifically, it can detect behaviors such as picking up goods and immediately putting them back, or moving around the store abnormally. AI tracks the movements of people in the images and compares them to typical behavioral patterns to detect anomalies. For example, AI analyzes the speed, direction, and duration of a person's movements to identify behaviors that differ from the norm. Furthermore, AI learns from past data to model typical theft patterns, achieving higher detection accuracy. The detection department can identify individuals engaging in unusual behavior early and notify supervisors. Notifications are given in real-time, allowing supervisors to respond immediately. For example, an alert can be sent to a smartphone or tablet, displaying the location and behavior of the suspicious individual. In addition, the detection department can incorporate a feedback loop to continuously improve the accuracy of abnormal behavior detection. Thus, the detection department can retrain the AI ​​model based on the collected data, further enhancing detection accuracy. Therefore, the detection department can quickly and accurately analyze the acquired images and identify suspicious individuals early on.

[0089] The editing department, based on suspicious individuals detected by the detection department, only edits out the necessary portions. The editing department can utilize AI to analyze images from security cameras, extracting only the parts containing the moment of theft or suspicious behavior. Specifically, AI tracks the movements of people in the images, identifying the time periods and locations of specific abnormal behaviors. This allows for efficient editing of the required portions from long-form footage. The editing department can efficiently preserve the portions needed as evidence, reducing data volume. For example, it can edit and save footage from a few minutes before and after the moment of theft or suspicious behavior. Furthermore, the editing department can employ image compression technology to optimize data volume while maintaining image quality. This allows the saved images to be played back in high quality during subsequent verification. Moreover, the editing department can share the edited images with other systems or departments, such as providing them to the police or security companies for rapid response. Thus, the editing department can efficiently extract the necessary portions and preserve them as evidence.

[0090] The report generation department generates reports based on footage edited by the editing department. The department utilizes AI to meticulously record and compile reports of detected suspicious individuals' behavior. Specifically, it records when, where, and what actions were performed. AI analyzes the movements of individuals in the footage, generating a detailed timeline of their actions. For example, it records the time when an item was picked up, the route taken within the store, and the moment of theft. AI can also assess the anomalousness and risk level of the behavior and reflect this in the report. This allows managers to clearly understand the behavior of suspicious individuals. The report generation department can save the generated reports digitally and print them as needed. Furthermore, the department can collaborate with other systems or departments to share reports. For example, it can provide reports to the police or security companies for rapid response. Thus, the report generation department can meticulously record the behavior of suspicious individuals and efficiently generate reports.

[0091] The inspection department can analyze images from security cameras to identify individuals engaging in unusual behavior. The department can utilize AI to analyze these images and pinpoint individuals with suspicious activity. This includes detecting behaviors such as immediately putting away goods after picking them up or moving around the store unnecessarily. The department can also use AI to identify individuals exhibiting unusual behavior early and notify management. Thus, by identifying individuals with unusual behavior, early detection of theft can be achieved. Some or all of the above processing in the inspection department can be performed using AI, or it can be done without AI. For example, the inspection department can input images from security cameras into the AI, which can then handle the processing of individuals exhibiting unusual behavior.

[0092] The editing unit can extract only the necessary portions from the images detected by the detection unit. The editing unit can utilize AI to analyze the images from the security camera, extracting only the parts containing the moment of theft or suspicious behavior. The editing unit can efficiently preserve the portions needed as evidence, reducing data volume. Thus, by efficiently editing the necessary portions, data volume can be reduced. Some or all of the above processing in the editing unit can be performed using AI, or it can be done without AI. For example, the editing unit can input the images from the security camera into the AI, which will then extract the necessary portions.

[0093] The report generation department can generate reports based on images edited by the editing department. The report generation department can utilize AI to record in detail the behavior of detected suspicious individuals and compile it into a report. The report generation department can record when, where, and what actions were performed. This streamlines report generation, making it easier to identify specific suspects. Some or all of the above processing in the report generation department can be performed using AI, or it can be done without AI. For example, the report generation department can input the edited images into the AI, which will then perform report generation.

[0094] The acquisition unit can capture images from multiple security cameras. It can use cameras covering all areas of the store or cameras focused on specific areas. The acquisition unit can also utilize AI to efficiently acquire images from security cameras. Therefore, by acquiring images from multiple security cameras, wide-area monitoring can be achieved. Some or all of the above processing in the acquisition unit can be done using AI, or it can be done without AI. For example, the acquisition unit can input images from multiple security cameras into the AI, which will then perform the image acquisition.

[0095] The inspection department can detect behaviors such as picking up items and immediately putting them back, or unusual movement within the store. It can utilize AI to analyze images from security cameras to detect these behaviors. The department can also use AI to identify individuals engaging in unusual behavior early and notify management. Thus, by detecting specific behavioral patterns, individuals with a high probability of theft can be identified early. Some or all of the above processing in the inspection department can be achieved using AI, or it can be done without AI. For example, the inspection department can input images from security cameras into the AI, which will then perform the detection of specific behavioral patterns.

[0096] The data acquisition unit can infer the user's emotions and adjust the timing of image acquisition by the security camera based on these inferences. The acquisition unit can utilize AI to infer user emotions and adjust the timing of image acquisition based on these inferences. When the user is nervous, the acquisition unit can frequently acquire detailed images. When the user is relaxed, the acquisition unit can acquire images at intervals, capturing only necessary images. When the user is anxious, the acquisition unit can shorten the acquisition interval and quickly acquire images. Therefore, by adjusting the image acquisition timing according to the user's emotions, more effective monitoring can be achieved. Emotion inference can be achieved through emotion engines or emotion-generating AI functions. Generating AI includes, but is not limited to, text-generating AI (such as LLM) or multimodal AI. Some or all of the above processing in the acquisition unit can be achieved through AI, or AI can be used without it. For example, the acquisition unit can input user emotion data into the AI, which will then adjust the image acquisition timing.

[0097] The data acquisition department can dynamically adjust the installation positions of security cameras to achieve optimal image capture. The department can utilize AI to dynamically adjust the camera positions for optimal image capture. It can also automatically adjust camera positions based on store congestion levels to capture optimal images. Furthermore, when abnormal behavior is detected in a specific area, the department can concentrate cameras in that area. The department can also dynamically adjust camera positions based on changes in store layout. Therefore, by dynamically adjusting the installation positions of security cameras, optimal image capture can be achieved. Some or all of the above processing in the acquisition department can be achieved using AI, or it can be done without AI. For example, the acquisition department can input the installation positions of the security cameras into the AI, which will then perform the position adjustments.

[0098] The acquisition department can change its acquisition method based on specific time periods or days of the week during image acquisition. The acquisition department can utilize AI to change the acquisition method based on specific time periods or days of the week during image acquisition. The acquisition department can use the usual acquisition method during weekdays and increase the acquisition frequency at night or on weekends. The acquisition department can also enhance the acquisition method on days with specific events to capture more detailed images. The acquisition department can also change the acquisition method based on historical data during periods of high theft activity. Therefore, by changing the acquisition method according to specific time periods or days of the week, efficient image acquisition can be achieved. Some or all of the above processing in the acquisition department can be achieved through AI, or it can be done without AI. For example, the acquisition department can input data for specific time periods or days of the week into the AI, which will then execute the change in acquisition method.

[0099] The acquisition unit can infer the user's emotions and determine the priority of image acquisition based on these inferred emotions. The acquisition unit can utilize AI to infer the user's emotions and determine the priority of image acquisition based on these inferred emotions. For example, when the user is tense, the acquisition unit can prioritize acquiring images of important areas. When the user is relaxed, the acquisition unit can acquire images with normal priority. When the user is anxious, the acquisition unit can quickly acquire important images. Thus, by determining image priority based on user emotions, important images can be acquired first. Emotion inference can be achieved through emotion inference functions such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (such as LLM) or multimodal generation AI. Some or all of the above processing in the acquisition unit can be achieved through AI, or AI can be used without it. For example, the acquisition unit can input user emotion data into AI, which will then determine the image priority.

[0100] The acquisition unit can adjust its acquisition method based on weather or lighting conditions during image acquisition. The acquisition unit can utilize AI to adjust the acquisition method according to weather or lighting conditions. For example, it can prioritize indoor image acquisition in rainy weather. It can use an infrared camera to acquire images in low-light conditions. It can enhance outdoor image acquisition in sunny weather. Therefore, by adjusting the acquisition method according to weather or lighting conditions, optimal image acquisition can be achieved. Some or all of the above processing in the acquisition unit can be achieved through AI, or it can be done without AI. For example, the acquisition unit can input weather or lighting condition data into the AI, which will then adjust the acquisition method accordingly.

[0101] The data acquisition department can analyze the store's congestion level during image capture and select the optimal acquisition method. The department can utilize AI to analyze store congestion and select the best acquisition method. The acquisition department can capture wide-area images when the store is crowded, and focus on capturing images of specific areas when the store is empty. The department can also adjust the camera's capture angle based on the congestion level. Therefore, selecting the acquisition method based on store congestion levels enables efficient image acquisition. Some or all of the above processing in the acquisition department can be achieved through AI, or it can be done without AI. For example, the acquisition department can input store congestion data into the AI, which will then select the acquisition method.

[0102] The detection department can infer users' emotions and adjust the detection criteria for abnormal behavior based on these inferred emotions. The detection department can utilize AI to infer users' emotions and adjust the detection criteria accordingly. When users are tense, the detection department can tighten the detection criteria to detect abnormal behavior earlier. When users are relaxed, the detection department can use the usual detection criteria. When users are anxious, the detection department can adjust the criteria for rapid detection of abnormal behavior. Therefore, by adjusting the detection criteria based on users' emotions, the accuracy of abnormal behavior detection can be improved. Emotion inference can be achieved through emotion inference functions such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (such as LLM) or multimodal generation AI. Some or all of the above processing in the detection department can be achieved through AI, or AI can be used without it. For example, the detection department can input user emotion data into AI, which will then adjust the detection criteria.

[0103] The detection department can optimize its detection algorithms based on past theft data during detection. The department can utilize AI to optimize these algorithms. It can also optimize algorithms for detecting specific behavioral patterns based on past theft data. Furthermore, the department can predict thefts occurring within specific time periods or on specific days of the week based on past data and adjust the detection algorithms accordingly. Additionally, the department can analyze past data to develop algorithms to counter new theft methods. Therefore, by optimizing detection algorithms based on past theft data, detection accuracy can be improved. Some or all of the above processes in the detection department can be implemented using AI, or they can be performed without AI. For example, the detection department can input past theft data into AI, which will then optimize the detection algorithms.

[0104] The detection department can identify specific abnormal behaviors based on an individual's attribute information during detection. The detection department can utilize AI to identify specific abnormal behaviors based on an individual's attribute information during detection. The detection department can perform detection based on specific behavioral patterns such as age and gender. The detection department can also adjust the detection criteria for abnormal behaviors based on attribute information. The detection department can also consider attribute information to detect abnormal behaviors of specific individuals earlier. Therefore, by identifying abnormal behaviors based on an individual's attribute information, detection accuracy can be improved. Some or all of the above processing in the detection department can be achieved through AI, or AI can be used without it. For example, the detection department can input an individual's attribute information into the AI, which will then execute the specific abnormal behavior detection.

[0105] The detection department can infer users' emotions and adjust the display of detection results based on these inferred emotions. The detection department can utilize AI to infer users' emotions and adjust the display of detection results accordingly. For example, when users are tense, the detection department can provide a concise and highly visual display. When users are relaxed, the detection department can provide a display containing detailed information. When users are anxious, the detection department can provide a display highlighting key points. Thus, by adjusting the display based on users' emotions, visibility can be improved. Emotion inference can be achieved through emotion inference functions such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (such as LLM) or multimodal generation AI. Some or all of the above processing in the detection department can be achieved through AI, or AI can be omitted. For example, the detection department can input user emotion data into AI, which will then adjust the display.

[0106] The inspection department can identify specific abnormal behaviors based on store layout information during inspections. The inspection department can utilize AI to identify specific abnormal behaviors based on store layout information. The inspection department can detect abnormal behaviors in specific areas based on store layout information. The inspection department can also adjust the detection standards for abnormal behaviors based on layout changes. The inspection department can also consider layout information to focus on detecting abnormal behaviors in specific areas. Therefore, by identifying specific abnormal behaviors based on store layout information, inspection accuracy can be improved. Some or all of the above processing in the inspection department can be achieved through AI, or AI can be used without it. For example, the inspection department can input store layout information into AI, which will then execute the specific abnormal behavior detection.

[0107] The detection department can coordinate with other security systems to detect specific abnormal behaviors during detection. The detection department can utilize AI to coordinate with other security systems to detect specific abnormal behaviors. The detection department can also coordinate with alarm systems to trigger alarms when abnormal behavior is detected. The detection department can also improve the accuracy of abnormal behavior detection based on data from other security systems. Furthermore, the detection department can coordinate with other security systems to respond quickly when abnormal behavior is detected. Therefore, by coordinating with other security systems, the accuracy of abnormal behavior detection can be improved. Some or all of the above processes in the detection department can be implemented using AI, or AI can be used without it. For example, the detection department can input data from other security systems into the AI, which will then execute specific abnormal behavior detection.

[0108] The editing department can infer the user's emotions and adjust the editing scope based on these inferences. The editing department can utilize AI to infer user emotions and adjust the editing scope accordingly. When the user is tense, the editing department can cut detailed sections. When the user is relaxed, the editing department can cut within the normal range. When the user is anxious, the editing department can quickly cut the required sections. Thus, by adjusting the editing scope according to the user's emotions, the desired parts can be extracted efficiently. Emotion inference can be achieved through emotion engines or emotion inference functions such as generative AI. Generative AI includes, but is not limited to, text generation AI (such as LLM) or multimodal generation AI. Some or all of the above processing in the editing department can be achieved through AI, or AI can be used without it. For example, the editing department can input user emotion data into AI, which will then perform the adjustment of the editing scope.

[0109] The editing department can optimize image quality to extract the desired portions during editing. The editing department can utilize AI to optimize image quality and extract the desired portions during editing. The editing department can adjust image resolution for high-quality editing of the desired portions. The editing department can also remove image noise to create clearer images. The editing department can also adjust image brightness and contrast for optimal image quality editing. Therefore, by optimizing image quality, the desired portions can be extracted in high quality. Some or all of the above processing in the editing department can be achieved through AI, or it can be done without AI. For example, the editing department can input image quality data into AI, which will then perform image quality optimization.

[0110] The editing department can integrate multiple camera images for optimal editing. It can utilize AI to integrate multiple camera images during editing, editing footage from different angles. The editing department can also analyze multiple camera images and edit the most important parts. Furthermore, it can combine multiple camera images to achieve panoramic editing. Therefore, by integrating multiple camera images, footage from different angles can be edited efficiently. Some or all of the above processing in the editing department can be achieved through AI, or it can be done without AI. For example, the editing department can input multiple camera images into AI, which will then perform image integration and editing.

[0111] The editing department can infer the user's emotions and adjust the display of edited footage based on these inferences. The editing department can utilize AI to infer user emotions and adjust the display of edited footage accordingly. For example, when the user is tense, the editing department can provide a concise and highly visual display. When the user is relaxed, the editing department can provide a display containing detailed information. When the user is in a hurry, the editing department can provide a display highlighting key points. Thus, by adjusting the display based on the user's emotions, visibility can be improved. Emotion inference can be achieved through emotion engines or emotion inference functions such as generative AI. Generative AI includes, but is not limited to, text generation AI (such as LLM) or multimodal generation AI. Some or all of the above processing in the editing department can be achieved through AI, or AI can be omitted. For example, the editing department can input user emotion data into AI, which will then adjust the display.

[0112] The editing department can adjust the video timeline during editing to extract the optimal parts. The editing department can utilize AI to adjust the video timeline to extract the best parts. The editing department can adjust the video timeline to extract important parts. The editing department can also compress the video timeline to display important parts briefly. The editing department can also expand the video timeline to extract detailed parts. Therefore, by adjusting the video timeline, important parts can be extracted efficiently. Some or all of the above processing in the editing department can be achieved through AI, or it can be done without AI. For example, the editing department can input video timeline data into AI, which will then perform timeline adjustments.

[0113] The editing department can analyze video and audio data during editing to extract desired portions. The editing department can utilize AI to analyze video and audio data during editing to extract the desired portions. The editing department can analyze video and audio data to extract portions containing important dialogue or sounds. The editing department can also detect abnormal sounds based on audio data and edit those portions. The editing department can also analyze audio data to extract portions containing specific keywords. Therefore, by analyzing audio data, portions containing important dialogue or sounds can be extracted efficiently. Some or all of the above processing in the editing department can be achieved using AI, or AI can be used without it. For example, the editing department can input audio data into AI, which will then perform the extraction of the desired portions.

[0114] The report generation department can infer users' emotions and adjust the report content based on these inferences. The department can utilize AI to infer user emotions and adjust the report content accordingly. For example, it can generate concise reports highlighting key points when users are stressed, detailed reports when users are relaxed, and rapidly generated reports when users are in a hurry. Thus, by adjusting the report content based on user emotions, more suitable reports can be generated. Emotion inference can be achieved through emotion inference functions such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (such as LLM) or multimodal generation AI. Some or all of the above processing in the report generation department can be achieved using AI, or AI can be omitted. For example, the report generation department can input user emotion data into AI, which will then adjust the report content.

[0115] The report generation department can select the optimal report format based on past report data during report generation. The report generation department can utilize AI to select the optimal report format based on past report data. The report generation department can select the most effective report format based on past report data. The report generation department can also propose report formats suitable for specific situations from past report data. The report generation department can also analyze past report data to develop new report formats. Therefore, by selecting the optimal report format based on past report data, effective reports can be generated efficiently. Some or all of the above processes in the report generation department can be implemented using AI, or AI can be used without it. For example, the report generation department can input past report data into AI, which will then perform the report format selection.

[0116] The report generation department can automatically add image metadata during report generation. This can be achieved using AI. The report generation department can automatically add the image capture date and location to the report. Furthermore, the report generation department can generate detailed reports based on the image metadata. Thus, by automatically adding image metadata, detailed reports can be generated efficiently. Some or all of the above processes in the report generation department can be performed using AI, or they can be performed without AI. For example, the report generation department can input the image metadata into the AI, which will then perform the metadata addition.

[0117] The report generation department can infer users' emotions and determine report priority based on these inferred emotions. The report generation department can utilize AI to infer users' emotions and determine report priority based on these inferred emotions. For example, the report generation department can prioritize generating important reports when users are stressed. It can generate reports with normal priority when users are relaxed. It can quickly generate important reports when users are anxious. Thus, by prioritizing reports based on user emotions, important reports can be generated first. Emotion inference can be achieved through emotion inference functions such as emotion engines or generative AI. Generative AI can be, for example, text generation AI (such as LLM) or multimodal generation AI, but is not limited to these. Some or all of the above processing in the report generation department can be achieved through AI, or AI can be used without it. For example, the report generation department can input user emotion data into AI, which will then determine the report priority.

[0118] The report generation department can integrate data from other security systems when generating reports. It can utilize AI to integrate data from other security systems during report generation. The department can generate detailed reports based on data from other security systems. It can also collaborate with other security systems to generate reports based on integrated data. Furthermore, the department can analyze data from other security systems to generate optimal reports. Therefore, by integrating data from other security systems, detailed reports can be generated efficiently. Some or all of the above processes in the report generation department can be implemented using AI, or AI can be used without it. For example, the report generation department can input data from other security systems into the AI, which will then perform report generation.

[0119] The report generation department can select the report delivery method when generating a report. This can be done using AI. The report generation department can choose to send the report via email. It can also choose to share the report via the cloud. Furthermore, the report generation department can select the delivery method based on user needs. Therefore, by selecting the delivery method, reports can be sent in a way that meets user requirements. Some or all of the above processes in the report generation department can be implemented using AI, or they can be performed without AI. For example, the report generation department can input the delivery method data into the AI, which will then select the delivery method.

[0120] The system involved in this embodiment is not limited to the above examples. For example, various modifications can be made as follows.

[0121] The G-Men AI anti-theft system also features an audio analysis unit. This unit analyzes audio data contained in the anti-theft camera footage to detect unusual sounds or conversations. For example, it can detect the sound of goods being bagged or unnatural conversations with store clerks. Thus, by utilizing not only video but also audio data, the accuracy of theft detection can be improved. The audio analysis unit can use AI to analyze audio data and detect unusual sounds or conversations. It can also detect conversations containing specific keywords and notify the responsible party. Furthermore, the audio analysis unit can identify individuals exhibiting unusual behavior based on audio data.

[0122] The G-Men AI anti-theft system also features a facial recognition unit. This unit identifies faces appearing in the anti-theft camera footage, specifically targeting individuals with a history of theft suspicion. For example, it can compare the face with a database of past thefts to identify the same person. This allows for early detection of individuals with a high likelihood of repeat offenses and notification to supervisors. The facial recognition unit utilizes AI for facial recognition and compares it with a historical database. It can also detect individuals with specific characteristics and issue warnings. Furthermore, the unit can integrate footage from multiple cameras to improve facial recognition accuracy.

[0123] The G-Men anti-theft AI also features a behavior prediction unit. This unit analyzes images from the anti-theft cameras to predict human behavior. For example, it can predict the next action based on past behavioral patterns. This allows for early detection of high-probability theft activities and notification of supervisors. The behavior prediction unit can utilize AI to analyze behavioral patterns and make predictions. It can also predict behavior in specific areas and adjust the camera focus accordingly. Furthermore, it can issue warnings when abnormal behavior is predicted.

[0124] The G-Men anti-theft AI system also includes a temperature sensor unit. This unit monitors the store temperature and detects abnormal temperature changes. For example, if a sudden temperature change occurs in a specific area, the camera can be focused on that area. This allows for early detection of unusual behavior based on temperature changes, and notification to management. The temperature sensor unit can use AI to analyze temperature data and detect abnormal temperature changes. It can also issue warnings when temperatures exceed specific ranges. Furthermore, the temperature sensor unit can predict the likelihood of unusual behavior based on temperature data.

[0125] The G-Men AI anti-theft system also includes a vibration sensor unit. This unit monitors vibrations within the store and detects abnormal vibrations. For example, it monitors shelf vibrations, and when abnormal vibrations occur, cameras can be focused on that area. This allows for early detection of unusual behavior based on vibration data, enabling notification of management. The vibration sensor unit can use AI to analyze vibration data and detect abnormal vibrations. It can also detect specific vibration patterns and issue warnings. Furthermore, it can predict the likelihood of unusual behavior based on vibration data.

[0126] The G-Men anti-theft AI can also infer the user's emotions and adjust the anti-theft camera's image analysis algorithm based on these inferred emotions. For example, when the user is nervous, the analysis algorithm can be more rigorous to detect abnormal behavior early. When the user is relaxed, the normal analysis algorithm can be used. Thus, by adjusting the analysis algorithm according to the user's emotions, the accuracy of abnormal behavior detection can be improved. Emotion inference can be achieved through emotion engines or generative AI, etc. Generative AI includes, but is not limited to, text generation AI (such as LLM) or multimodal generation AI. The adjustment of the analysis algorithm can be achieved through AI, or it can be done without AI. For example, the adjustment of the analysis algorithm can be performed by AI.

[0127] The G-Men anti-theft AI can also infer the user's emotions and adjust the way the anti-theft camera saves images based on these inferred emotions. For example, when the user is nervous, important images can be saved first. When the user is relaxed, the usual saving method can be used. Thus, by adjusting the image saving method according to the user's emotions, important images can be saved efficiently. Emotion inference can be achieved through emotion inference functions such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (such as LLM) or multimodal generation AI. The adjustment of the saving method can be achieved through AI, or it can be done without AI. For example, the adjustment of the saving method can be performed by AI.

[0128] The G-Men anti-theft AI can also infer the user's emotions and adjust the image processing speed of the anti-theft camera based on the inferred emotions. For example, when the user is nervous, the processing speed can be increased to quickly detect abnormal behavior. When the user is relaxed, the normal processing speed can be used. Thus, by adjusting the processing speed according to the user's emotions, the accuracy of abnormal behavior detection can be improved. Emotion inference can be achieved through emotion inference functions such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (such as LLM) or multimodal generation AI. The processing speed adjustment can be achieved through AI, or it can be done without AI. For example, the processing speed adjustment can be performed by AI.

[0129] The G-Men anti-theft AI can also infer the user's emotions and adjust the display of the anti-theft camera image based on the inferred emotions. For example, when the user is nervous, a simple and highly visible display can be provided. When the user is relaxed, a display containing detailed information can be provided. Thus, by adjusting the display according to the user's emotions, visibility can be improved. Emotion inference can be achieved through emotion inference functions such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (such as LLM) or multimodal generation AI. The adjustment of the display can be achieved through AI, or it can be done without AI. For example, the adjustment of the display can be performed by AI.

[0130] The G-Men anti-theft AI can also infer the user's emotions and adjust the retention period of the anti-theft camera images based on the inferred emotions. For example, when the user is nervous, the retention period for important images can be extended. When the user is relaxed, the usual retention period can be used. Thus, by adjusting the retention period according to the user's emotions, important images can be managed efficiently. Emotion inference can be achieved through emotion inference functions such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (such as LLM) or multimodal generation AI. The retention period adjustment can be achieved through AI, or it can be done without AI. For example, the retention period adjustment can be performed by AI.

[0131] The following is a brief description of the processing flow of Implementation Method 2.

[0132] Step 1: The acquisition department collects images from security cameras. The acquisition department can collect images from multiple security cameras. It can use cameras covering all areas of the store or cameras focused on specific areas. The acquisition department can also utilize AI to efficiently collect images from security cameras.

[0133] Step 2: The detection department analyzes the images collected by the acquisition department to detect suspicious individuals. The detection department can use AI to analyze images from security cameras to identify individuals engaging in abnormal behavior. This includes detecting behaviors such as picking up items and immediately putting them back, or moving around the store unusually. The detection department can also use AI to identify individuals engaging in abnormal behavior early and notify the responsible personnel.

[0134] Step 3: The editing department, based on the suspicious individuals detected by the detection department, only edits out the necessary portions. The editing department can utilize AI to analyze the images from the security cameras, extracting only the parts containing the moment of theft or suspicious behavior. The editing department can efficiently preserve the portions needed as evidence, reducing data volume.

[0135] Step 4: The report generation department generates a report based on the footage edited by the editing department. The report generation department can utilize AI to record in detail the behavior of detected suspicious individuals and compile it into a report. The report generation department can record when, where, and what kind of behavior was performed.

[0136] The specific processing unit 290 sends 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 voice representing the user's input to the result of the specific processing. The control unit 46A sends the voice data representing the user's input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0137] Data generation model 58 is what is known as generative AI (Artificial Intelligence). An example of data generation model 58 includes ChatGPT (registered trademark) (Internet search).<URL:https: / / openai.com / blog / chatgpt> Generative AI, such as data generation model 58, is obtained by deep learning through a neural network. The data generation model 58 is input with a prompt containing instructions, and with inference data such as speech data representing speech, text data representing text, and image data representing images (e.g., data of still images or data of moving images). The data generation model 58 infers the input inference data according to the instructions shown in the prompt, and outputs the inference result in one or more data forms such as speech data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the above-described specific processing while using the data generation model 58. The data generation model 58 can also be a fine-tuned model to output inference results from prompts without instructions; in this case, the data generation model 58 can output inference results from prompts without instructions. The data processing device 12, etc., includes multiple data generation models 58, including AI other than generative AI. AI other than generative AI includes, but is not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes. Furthermore, AI can also act as an AI agent. Additionally, when the processing described above is performed by AI, this processing may be partially or entirely performed by AI, but is not limited to this example. Moreover, processing performed by AI, including generative AI, can be replaced by rule-based processing, and vice versa.

[0138] Furthermore, the processing performed by the aforementioned data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it can also be executed jointly by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or external devices, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or external devices.

[0139] Each of the aforementioned elements, including the acquisition unit, detection unit, editing unit, and report generation unit, can be implemented, for example, in at least one of the smart device 14 and the data processing device 12. For example, the acquisition unit can acquire images from a security camera via the camera 42 of the smart device 14 or the communication I / F 26 of the data processing device 12. The detection unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, which analyzes the images from the security camera and identifies individuals engaging in abnormal behavior. The editing unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, which extracts only the portion containing the moment of theft or suspicious behavior. The report generation unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, which records in detail the behavior of the detected suspicious individuals and compiles it into a report. The correspondence between each unit and the device or control unit is not limited to the above examples and can be modified in various ways.

[0140] Second Implementation Method

[0141] Figure 3 An example of the configuration of the data processing system 210 according to the second embodiment is shown.

[0142] like Figure 3 As shown, the data processing system 210 includes a data processing device 12 and smart glasses 214. One example of the data processing device 12 is a server.

[0143] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. An example of the network 54 includes a WAN and / or LAN, etc.

[0144] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Additionally, the microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0145] Microphone 238 receives user commands by receiving the user's voice. Microphone 238 captures the user's voice, converts the captured sound into speech data, and outputs it to processor 46. Speaker 240 outputs sound according to commands from processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, used to capture the user's surroundings (e.g., the shooting range defined by an angle of view equivalent to the field of vision of an average healthy person).

[0147] Communication I / F 44 is connected to network 54. Communication I / F 44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F 44 and 26 is performed in a secure state.

[0148] Figure 4 An example of the main functions of the data processing device 12 and the smart glasses 214 is shown. Figure 4 As shown, in the data processing device 12, specific processing is performed by the processor 28. The memory 32 stores a specific processing program 56.

[0149] The processor 28 reads a specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is implemented by the processor 28 operating as a specific processing unit 290 based on the specific processing program 56 executed on the RAM 30.

[0150] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. The emotion inference function using the emotion-specific model 59 (emotion-specific function) includes inferring and predicting the user's emotions, performing various inferences and predictions related to the user's emotions, but is not limited to this example. Furthermore, emotion inference and prediction also include, for example, emotion analysis (analysis).

[0151] In the smart glasses 214, specific processing is performed by the processor 46. A specific processing program 60 is stored in the memory 50. The processor 46 reads the specific processing program 60 from the memory 50 and executes the read specific processing program 60 on the RAM 48. Specific processing is implemented by the processor 46 operating as a control unit 46A based on the specific processing program 60 executed on the RAM 48. Furthermore, the smart glasses 214 may also have the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and use these models to perform the same processing as the specific processing unit 290.

[0152] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. In addition, the data processing device 12 may be a server device or a user-owned terminal device (e.g., a mobile phone, robot, home appliance, etc.).

[0153] The specific processing unit 290 sends 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 voice input representing the user's input to the specific processing result. The control unit 46A sends the voice data representing the user's input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0154] Data generation model 58 is a so-called generative AI. An example of data generation model 58 includes generative AIs such as ChatGPT. Data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing instructions is input to data generation model 58, along with inference data such as speech data representing speech, text data representing text, and image data representing images (e.g., data from still images or moving images). Data generation model 58 infers the inference data based on the instructions shown in the prompt and outputs the inference result in one or more data forms such as speech data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. Specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. Data generation model 58 can also be a fine-tuned model to output inference results from prompts without instructions; in this case, data generation model 58 can output inference results from prompts without instructions. The data processing device 12, etc., includes various data generation models 58, which include AI other than generative AI. These AIs include, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and are capable of various processing methods, but are not limited to these examples. Furthermore, AI can also be an AI agent. Additionally, when the processing described above is performed by AI, this processing may be partially or entirely performed by AI, but is not limited to these examples. Moreover, processing performed by AI including generative AI can be replaced by rule-based processing, and vice versa.

[0155] The data processing system 210 of the second embodiment performs the same processing as the data processing system 10 of the first embodiment. The processing performed by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it can also be executed jointly by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or external devices, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or external devices.

[0156] Each of the aforementioned elements, including the acquisition unit, detection unit, editing unit, and report generation unit, can be implemented, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the acquisition unit can acquire images from the security camera via the camera 42 of the smart glasses 214 or the communication I / F 26 of the data processing device 12. The detection unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, which analyzes the images from the security camera and identifies individuals engaging in abnormal behavior. The editing unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, which extracts only the portion containing the moment of theft or suspicious behavior. The report generation unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, which records in detail the behavior of the detected suspicious individuals and compiles it into a report. The correspondence between each unit and the device or control unit is not limited to the above examples and can be modified in various ways.

[0157] Third Implementation Method

[0158] Figure 5 An example of the configuration of the data processing system 310 according to the third embodiment is shown.

[0159] like Figure 5 As shown, the data processing system 310 includes a data processing device 12 and a head-mounted terminal 314. An example of the data processing device 12 is a server.

[0160] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. An example of the network 54 includes a WAN and / or LAN, etc.

[0161] The head-mounted terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0162] Microphone 238 receives user commands by receiving the user's voice. Microphone 238 captures the user's voice, converts the captured sound into speech data, and outputs it to processor 46. Speaker 240 outputs sound according to commands from processor 46.

[0163] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, used to capture the user's surroundings (e.g., the shooting range defined by an angle of view equivalent to the field of vision of an average healthy person).

[0164] Communication I / F 44 is connected to network 54. Communication I / F 44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F 44 and 26 is performed in a secure state.

[0165] Figure 6 An example of the main functions of the data processing device 12 and the head-mounted terminal 314 is shown. Figure 6 As shown, in the data processing device 12, specific processing is performed by the processor 28. The memory 32 stores a specific processing program 56.

[0166] The processor 28 reads a specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is implemented by the processor 28 operating as a specific processing unit 290 based on the specific processing program 56 executed on the RAM 30.

[0167] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. The emotion inference function using the emotion-specific model 59 (emotion-specific function) includes inferring and predicting the user's emotions, performing various inferences and predictions related to the user's emotions, but is not limited to this example. Furthermore, emotion inference and prediction also include, for example, emotion analysis (analysis).

[0168] In the head-mounted terminal 314, specific processing is performed by the processor 46. A specific program 60 is stored in the memory 50. The processor 46 reads the specific program 60 from the memory 50 and executes the read specific program 60 on the RAM 48. Specific processing is implemented by the processor 46 operating as a control unit 46A based on the specific program 60 executed on the RAM 48. Furthermore, the head-mounted terminal 314 may also have the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and use these models to perform the same processing as the specific processing unit 290.

[0169] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. In addition, the data processing device 12 may be a server device or a user-owned terminal device (e.g., a mobile phone, robot, home appliance, etc.).

[0170] The specific processing unit 290 sends the result of the specific processing to the head-mounted terminal 314. In the head-mounted 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 voice representing the user's input to the specific processing result. The control unit 46A sends the voice data representing the user's input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0171] Data generation model 58 is a so-called generative AI. An example of data generation model 58 includes generative AIs such as ChatGPT. Data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing instructions is input to data generation model 58, along with inference data such as speech data representing speech, text data representing text, and image data representing images (e.g., data from still images or moving images). Data generation model 58 infers the inference data based on the instructions shown in the prompt and outputs the inference result in one or more data forms such as speech data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. Specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. Data generation model 58 can also be a fine-tuned model to output inference results from prompts without instructions; in this case, data generation model 58 can output inference results from prompts without instructions. The data processing device 12, etc., includes various data generation models 58, which include AI other than generative AI. These AIs include, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and are capable of various processing methods, but are not limited to these examples. Furthermore, AI can also be an AI agent. Additionally, when the processing described above is performed by AI, this processing may be partially or entirely performed by AI, but is not limited to these examples. Moreover, processing performed by AI including generative AI can be replaced by rule-based processing, and vice versa.

[0172] The data processing system 310 of the third embodiment performs the same processing as the data processing system 10 of the first embodiment. The processing performed by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the head-mounted terminal 314, but it can also be executed jointly by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the head-mounted terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the head-mounted terminal 314 or external devices, and the head-mounted terminal 314 acquires or collects information required for processing from the data processing device 12 or external devices.

[0173] Each of the aforementioned elements, including the acquisition unit, detection unit, editing unit, and report generation unit, can be implemented, for example, in at least one of the head-mounted terminal 314 and the data processing device 12. For example, the acquisition unit can acquire images from the security camera via the camera 42 of the head-mounted terminal 314 or the communication I / F 26 of the data processing device 12. The detection unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, which analyzes the images from the security camera and identifies individuals engaging in abnormal behavior. The editing unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, which extracts only the portion containing the moment of theft or suspicious behavior. The report generation unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, which records in detail the behavior of the detected suspicious individuals and compiles it into a report. The correspondence between each unit and the device or control unit is not limited to the above examples and can be modified in various ways.

[0174] Fourth Implementation Method

[0175] Figure 7 An example of the configuration of the data processing system 410 according to the fourth embodiment is shown.

[0176] like Figure 7 As shown, 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.

[0177] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. An example of the network 54 includes a WAN and / or LAN, etc.

[0178] Robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control object 443. Computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, and control object 443 are also connected to the bus 52.

[0179] Microphone 238 receives user commands by receiving the user's voice. Microphone 238 captures the user's voice, converts the captured sound into speech data, and outputs it to processor 46. Speaker 240 outputs sound according to commands from processor 46.

[0180] The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, used to photograph the user's surroundings (e.g., the shooting range defined by an angle of view equivalent to the field of vision of an average healthy person).

[0181] Communication I / F 44 is connected to network 54. Communication I / F 44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F 44 and 26 is performed in a secure state.

[0182] The controlled object 443 includes a display device, LEDs for the eyes, and motors for driving the arms, hands, and feet. The posture and movements of the robot 414 are controlled by controlling the motors for the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. In addition, facial expressions of the robot 414 can also be expressed by controlling the illumination state of the LEDs for the robot 414's eyes.

[0183] Figure 8 An example of the main functions of the data processing device 12 and the robot 414 is shown. For example... Figure 8 As shown, in the data processing device 12, specific processing is performed by the processor 28. The memory 32 stores a specific processing program 56.

[0184] The processor 28 reads a specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is implemented by the processor 28 operating as a specific processing unit 290 based on the specific processing program 56 executed on the RAM 30.

[0185] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. The emotion inference function using the emotion-specific model 59 (emotion-specific function) includes inferring and predicting the user's emotions, performing various inferences and predictions related to the user's emotions, but is not limited to this example. Furthermore, emotion inference and prediction also include, for example, emotion analysis (analysis).

[0186] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in memory 50. Processor 46 reads the specific program 60 from memory 50 and executes the read specific program 60 on RAM 48. Specific processing is achieved by processor 46 acting as control unit 46A based on the specific program 60 executed on RAM 48. Furthermore, robot 414 may also have the same data generation model and emotion-specific model as data generation model 58 and emotion-specific model 59, and use these models to perform the same processing as specific processing unit 290.

[0187] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. In addition, the data processing device 12 may be a server device or a user-owned terminal device (e.g., a mobile phone, robot, home appliance, etc.).

[0188] The specific processing unit 290 sends 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 voice representing the user's input regarding the result of the specific processing. The control unit 46A sends the voice data representing the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0189] Data generation model 58 is a so-called generative AI. An example of data generation model 58 includes generative AIs such as ChatGPT. Data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing instructions is input to data generation model 58, along with inference data such as speech data representing speech, text data representing text, and image data representing images (e.g., data from still images or moving images). Data generation model 58 infers the inference data based on the instructions shown in the prompt and outputs the inference result in one or more data forms such as speech data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. Specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. Data generation model 58 can also be a fine-tuned model to output inference results from prompts without instructions; in this case, data generation model 58 can output inference results from prompts without instructions. The data processing device 12, etc., includes various data generation models 58, which include AI other than generative AI. These AIs include, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and are capable of various processing methods, but are not limited to these examples. Furthermore, AI can also be an AI agent. Additionally, when the processing described above is performed by AI, this processing may be partially or entirely performed by AI, but is not limited to these examples. Moreover, processing performed by AI including generative AI can be replaced by rule-based processing, and vice versa.

[0190] The data processing system 410 of the fourth embodiment performs the same processing as the data processing system 10 of the first embodiment. The processing performed by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it can also be executed jointly by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or external devices, and the robot 414 acquires or collects information required for processing from the data processing device 12 or external devices.

[0191] Each of the aforementioned elements, including the acquisition unit, detection unit, editing unit, and report generation unit, can be implemented, for example, in at least one of the robot 414 and the data processing device 12. For example, the acquisition unit can acquire images from the security camera via the robot 414's camera 42 or the data processing device 12's communication I / F 26. The detection unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, which analyzes the images from the security camera and identifies individuals engaging in abnormal behavior. The editing unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, which extracts only the portion containing the moment of theft or suspicious behavior. The report generation unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, which records in detail the behavior of the detected suspicious individuals and compiles it into a report. The correspondence between each unit and the device or control unit is not limited to the above examples and can be modified in various ways.

[0192] Furthermore, the emotion-specific model 59, acting as an emotion engine, can determine the user's emotion based on a specific mapping. Specifically, the emotion-specific model 59 can determine the user's emotion based on an emotion graph that serves as a specific mapping (see...). Figure 9 The robot's emotions can be determined by the emotion-specific model 59. In addition, the emotion-specific model 59 can also determine the robot's emotions in the same way, and the specific processing unit 290 can also perform specific processing using the robot's emotions.

[0193] Figure 9 This is a diagram representing an emotion map 400 that maps various emotions. In the emotion map 400, emotions are arranged radially from the center in concentric circles. The closer to the center of the concentric circles, the more primitive the emotion is. Further out on the concentric circles, emotions are arranged representing states or actions arising from mood. Emotion is a concept that includes both feelings and mental states. To the left of the concentric circles, emotions generated by reactions occurring in the brain are arranged roughly. To the right of the concentric circles, emotions guided by situational judgments are arranged roughly. Above and below the concentric circles, emotions generated by reactions occurring in the brain and guided by situational judgments are arranged roughly. Furthermore, the emotion of "pleasure" is arranged above the concentric circles, and the emotion of "unpleasantness" is arranged below. Thus, in the emotion map 400, various emotions are mapped according to the structure of emotion generation, while easily generated emotions are mapped nearby.

[0194] These emotions are distributed at the 3 o'clock position on the Emotion Chart 400, and usually fluctuate between peace and unease. In the right half of the Emotion Chart 400, because situational awareness is more dominant than internal feelings, it gives a sense of calm.

[0195] The inner side of the emotion diagram 400 represents the mind, and the outer side of the emotion diagram 400 represents actions. Therefore, the further you go to the outer side of the emotion diagram 400, the more the emotion can be seen (manifested in actions).

[0196] Here, human emotions are based on a balance of various factors such as posture and blood sugar levels. When these balances deviate from the ideal, it indicates unhappiness; when they approach the ideal, it indicates pleasure. In robots, cars, and motorcycles, emotions can also be created based on a balance of factors such as posture and remaining battery power. When these balances deviate from the ideal, it indicates unhappiness; when they approach the ideal, it indicates pleasure. Emotion maps can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Speech Emotion Recognition and Brain Physiological Signal Analysis Systems for Emotion, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). In the left half of the emotion map, emotions belonging to the "Reaction" domain, where sensation is dominant, are arranged. Furthermore, in the right half of the emotion map, emotions belonging to the "Situation" domain, where situational cognition is dominant, are arranged.

[0197] The emotion map defines two types of emotions that promote learning. One is a negative emotion located near the middle of "repentance" or "reflection" on the situation side. That is, when the robot experiences negative emotions such as "I never want to feel this way again" or "I never want to be scolded again." The other is a positive emotion located near "desire" on the response side. That is, when the robot experiences positive feelings such as "wanting more" or "wanting to know more."

[0198] The emotion-specific model 59 feeds user input into a pre-learned neural network to obtain emotion values ​​representing each emotion shown in the emotion graph 400, and determines the user's emotion. This neural network is pre-learned based on multiple learning data sets that combine user input with emotion values ​​representing each emotion shown in the emotion graph 400. Furthermore, this neural network is learned to... Figure 10 As shown in sentiment graph 900, nearby sentiment values ​​are similar to each other. Figure 10 Examples show how emotions such as "peace of mind," "stability," and "reassurance" can be associated with similar emotional values.

[0199] In the above embodiments, a specific processing is described by a single computer 22, but the technology disclosed herein is not limited to this, and distributed processing by multiple computers, including computer 22, is also possible.

[0200] In the above embodiments, an example of storing a specific processing program 56 in memory 32 is illustrated, but the technology disclosed herein is not limited thereto. For example, the specific processing program 56 may also be stored in a portable computer-readable non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 performs specific processing according to the specific processing program 56.

[0201] Alternatively, the specific processing program 56 can be stored in a storage device such as a server connected to the data processing device 12 via a network 54, and the specific processing program 56 can be downloaded and installed into the computer 22 upon request from the data processing device 12.

[0202] Furthermore, it is not necessary to store the entire specific process 56 in a storage device such as a server connected to the data processing device 12 via the network 54, nor is it necessary to store the entire specific process 56 in the memory 32; a portion of the specific process 56 may also be stored.

[0203] As a hardware resource for performing specific processing, various processors can be used. For example, a CPU is a general-purpose processor that functions as a hardware resource for performing specific processing by executing software, i.e., programs. Additionally, a dedicated circuit can be listed as a processor; it is a processor with a circuit structure specifically designed for performing specific processing, such as a FPGA (Field-Programmable Gate Array), PLD (Programmable Logic Device), or ASIC (Application Specific Integrated Circuit). Every processor has built-in or connected memory, and every processor executes specific processing by using that memory.

[0204] The hardware resources for performing a specific process can consist of one of these various processors, or a combination of two or more processors of the same or different types (e.g., a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Furthermore, the hardware resources for performing a specific process can also be a single processor.

[0205] As an example of a single processor, the first type consists of a combination of one or more CPUs and software, which functions as a hardware resource to perform specific processing. The second type uses a processor, such as a System-on-a-chip (SoC), which implements the entire system functionality, including multiple hardware resources for performing specific processing, using a single IC chip. In this case, the specific processing is implemented using one or more of the aforementioned processors that serve as hardware resources.

[0206] Furthermore, as the hardware architecture of these various processors, more specifically, circuits combining semiconductor elements and other circuit components can be used. Moreover, the specific process described above is merely an example. Therefore, it goes without saying that, without departing from the main point, unnecessary steps can be removed, new steps can be added, or the processing order can be changed.

[0207] Furthermore, although the above examples have been described in terms of first to fourth embodiments, some or all of these embodiments can be combined. Additionally, the smart device 14, smart glasses 214, head-mounted terminal 314, and robot 414 are just examples and can be combined separately, or other devices may be used. Furthermore, although the above examples have been described in terms of morphological example 1 and morphological example 2, these can also be combined.

[0208] The foregoing descriptions and illustrations are detailed explanations of the parts covered by this disclosure and are merely one example of this disclosure. For instance, the descriptions of the above-described structure, function, role, and effect are just one example of the structure, function, role, and effect of the parts covered by this disclosure. Therefore, it goes without saying that, without departing from the spirit of this disclosure, unnecessary parts can be deleted, new elements can be added, or replacements can be made to the foregoing descriptions and illustrations. Furthermore, to avoid confusion and facilitate understanding of the parts covered by this disclosure, explanations of technical common sense that does not require special explanation for implementing this disclosure have been omitted from the foregoing descriptions and illustrations.

[0209] All documents, patent applications and technical standards described in this specification are incorporated herein by reference as if they were specifically and individually described as incorporated by reference.

[0210] [Postscript 1]

[0211] A system characterized in that,

[0212] It includes: a data acquisition unit for acquiring images from security cameras;

[0213] The detection unit is used to analyze the images acquired by the acquisition unit and to detect suspicious persons;

[0214] The editing unit is used to edit only the required portions of suspicious persons detected by the detection unit.

[0215] The report generation department is used to generate reports based on the images edited by the editing department.

[0216] [Postscript 2]

[0217] The system as described in Appendix 1 is characterized in that,

[0218] The detection unit analyzes the images from the security camera and identifies individuals engaging in abnormal behavior.

[0219] [Postscript 3]

[0220] The system as described in Appendix 1 is characterized in that,

[0221] The editing unit only edits the required portion from the image detected by the detection unit.

[0222] [Postscript 4]

[0223] The system as described in Appendix 1 is characterized in that,

[0224] The report generation department generates reports based on images edited by the editing department.

[0225] [Postscript 5]

[0226] The system as described in Appendix 1 is characterized in that,

[0227] The acquisition unit collects images from multiple security cameras.

[0228] [Postscript 6]

[0229] The system as described in Appendix 1 is characterized in that,

[0230] The detection department detects behaviors such as picking up goods and immediately putting them back, or moving around the store abnormally.

[0231] [Postscript 7]

[0232] The system as described in Appendix 1 is characterized in that,

[0233] The acquisition unit infers the user's emotions and adjusts the timing of image acquisition by the anti-theft camera based on the inferred user emotions.

[0234] [Postscript 8]

[0235] The system as described in Appendix 1 is characterized in that,

[0236] The acquisition unit dynamically adjusts the installation position of the anti-theft camera to achieve optimal image acquisition.

[0237] [Postscript 9]

[0238] The system as described in Appendix 1 is characterized in that,

[0239] The acquisition unit changes its acquisition method according to specific time periods or days of the week when acquiring images.

[0240] [Postscript 10]

[0241] The system as described in Appendix 1 is characterized in that,

[0242] The acquisition unit infers the user's emotions and determines the priority of acquiring images based on the inferred user emotions.

[0243] [Postscript 11]

[0244] The system as described in Appendix 1 is characterized in that,

[0245] The acquisition unit adjusts the acquisition method according to weather or lighting conditions during image acquisition.

[0246] [Postscript 12]

[0247] The system as described in Appendix 1 is characterized in that,

[0248] When acquiring images, the acquisition unit analyzes the crowding situation inside the store and selects the optimal acquisition method.

[0249] [Postscript 13]

[0250] The system as described in Appendix 1 is characterized in that,

[0251] The detection unit infers the user's emotions and adjusts the detection criteria for abnormal behavior based on the inferred user emotions.

[0252] [Postscript 14]

[0253] The system as described in Appendix 1 is characterized in that,

[0254] During the detection process, the detection unit optimizes the detection algorithm based on past theft data.

[0255] [Postscript 15]

[0256] The system as described in Appendix 1 is characterized in that,

[0257] During the detection process, the detection unit identifies specific abnormal behaviors based on the attribute information of the person.

[0258] [Postscript 16]

[0259] The system as described in Appendix 1 is characterized in that,

[0260] The detection unit infers the user's emotions and adjusts the display method of the detection results based on the inferred user emotions.

[0261] [Postscript 17]

[0262] The system as described in Appendix 1 is characterized in that,

[0263] During the inspection, the detection department identifies specific abnormal behaviors based on the store's layout information.

[0264] [Postscript 18]

[0265] The system as described in Appendix 1 is characterized in that,

[0266] During detection, the detection unit coordinates with other anti-theft systems to exhibit specific abnormal behaviors.

[0267] [Postscript 19]

[0268] The system as described in Appendix 1 is characterized in that,

[0269] The editing department infers the user's emotions and adjusts the editing range based on the inferred user emotions.

[0270] [Postscript 20]

[0271] The system as described in Appendix 1 is characterized in that,

[0272] During editing, the editing unit optimizes the image quality to extract the desired portion.

[0273] [Postscript 21]

[0274] The system as described in Appendix 1 is characterized in that,

[0275] The editing unit integrates images from multiple cameras for optimal editing during the editing process.

[0276] [Postscript 22]

[0277] The system as described in Appendix 1 is characterized in that,

[0278] The editing unit infers the user's emotions and adjusts the display method of the edited images based on the inferred user emotions.

[0279] [Postscript 23]

[0280] The system as described in Appendix 1 is characterized in that,

[0281] During editing, the editing unit adjusts the timeline of the image to extract the optimal portion.

[0282] [Postscript 24]

[0283] The system as described in Appendix 1 is characterized in that,

[0284] During editing, the editing unit analyzes the audio data of the video to extract the desired portion.

[0285] [Postscript 25]

[0286] The system as described in Appendix 1 is characterized in that,

[0287] The report generation unit infers the user's emotions and adjusts the report content based on the inferred user emotions.

[0288] [Postscript 26]

[0289] The system as described in Appendix 1 is characterized in that,

[0290] When generating a report, the report generation department selects the optimal report format based on previous report data.

[0291] [Postscript 27]

[0292] The system as described in Appendix 1 is characterized in that,

[0293] The report generation department automatically adds image metadata when generating a report.

[0294] [Postscript 28]

[0295] The system as described in Appendix 1 is characterized in that,

[0296] The report generation unit infers the user's emotions and determines the priority of the report based on the inferred user emotions.

[0297] [Postscript 29]

[0298] The system as described in Appendix 1 is characterized in that,

[0299] The report generation department integrates data from other anti-theft systems when generating reports.

[0300] [Postscript 30]

[0301] The system as described in Appendix 1 is characterized in that,

[0302] When generating a report, the report generation department selects the report sending method.

Claims

1. A system, characterized in that, include: The acquisition unit is used to acquire images from security cameras; The detection unit is used to analyze the images acquired by the acquisition unit and to detect suspicious persons; The editing unit is used to edit only the required portions of suspicious persons detected by the detection unit. The report generation department is used to generate reports based on the images edited by the editing department.

2. The system as described in claim 1, characterized in that, The detection unit analyzes the images from the security camera and identifies individuals engaging in abnormal behavior.

3. The system as described in claim 1, characterized in that, The editing unit only edits the required portion from the image detected by the detection unit.

4. The system as described in claim 1, characterized in that, The report generation department generates reports based on images edited by the editing department.

5. The system as described in claim 1, characterized in that, The acquisition unit collects images from multiple security cameras.

6. The system as described in claim 1, characterized in that, The detection department detects behaviors such as picking up goods and immediately putting them back, or moving around the store abnormally.

7. The system as described in claim 1, characterized in that, The acquisition unit infers the user's emotions and adjusts the timing of image acquisition by the anti-theft camera based on the inferred user emotions.

8. The system as described in claim 1, characterized in that, The acquisition unit dynamically adjusts the installation position of the anti-theft camera to achieve optimal image acquisition.

Images