System

Abstract

A system is provided.SOLUTION: The system includes a video acquisition means for acquiring real-time video data of an animal, a data analysis means including a generation AI model for analyzing the acquired video data, a collation means for collating a result analyzed by the data analysis means with case data of the animal and determining necessity of a visit, and a notification means for notifying a user of a result determined by the collation means.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Medical expenses for animals tend to be expensive, and there is a strong demand from owners to reduce medical expenses by taking them to the vet early. However, because animals cannot speak and cannot directly communicate their physical condition, it is currently difficult for owners to determine the appropriate timing for a visit. Furthermore, because animal symptoms often appear as subtle changes, many owners often miss them. To solve this problem, there is a need for a system that can analyze real-time video data of animals and compare it with case data to quickly and accurately determine the need for visits to the vet. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means. It provides a video acquisition means for acquiring real-time video data of an animal and a data analysis means including a generative AI model for analyzing the acquired video data. It also includes a comparison means for comparing the results of the analysis by the data analysis means with the animal's case data and determining the need for hospital visits. Furthermore, by incorporating a notification means for notifying the user of the results determined by the comparison means, the user can grasp the animal's condition early and visit the hospital at the appropriate time. This system can prevent the animal's condition from becoming severe and reduce medical costs. Furthermore, by adding a function to provide information about veterinary clinics when it is determined that hospital visits are highly necessary, and an information sharing means for automatically sending the video data and analysis results to the veterinary clinic, it can also support prompt and accurate medical treatment.

[0006] "Animal" refers to a living creature kept as a pet by an owner that may require medical treatment.

[0007] "Real-time video data" refers to video data of animals that is being acquired in real time, and refers to live broadcast data with almost no time delay.

[0008] "Image capture means" refers to the entire device, including the camera and its accessories, for capturing real-time image data of an animal.

[0009] A "generative AI model" is an artificial intelligence model used to analyze captured video data, particularly a model that utilizes deep learning or machine learning.

[0010] "Data analysis means" refers to a series of processes that analyze video data using a generative AI model to detect abnormal behavior or symptoms.

[0011] "Case data" refers to a database that accumulates detailed data on the health status of animals and past cases, and is used to compare with the analysis results.

[0012] The "collation means" refers to a means for comparing the results obtained by the data analysis means with case data and evaluating and determining the need for outpatient visits.

[0013] "Necessity of medical visits" refers to the criteria for determining whether an animal needs to be visited a veterinary hospital based on its health condition.

[0014] "Notification means" refers to the means of conveying the judgment results to the user as information, and includes communication means such as smartphone apps, SMS, and email.

[0015] "Veterinary hospital" means a medical institution that provides medical care for animals and is a place where such animals can receive the best possible medical care.

[0016] "Information sharing means" refers to the means by which analysis results and video data are automatically sent to veterinary hospitals to be used for medical treatment. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention is a system that acquires and analyzes real-time video data of animals, compares it with case data, determines the need for hospital visits, and notifies the user. This system mainly includes video acquisition means, data analysis means, comparison means, notification means, and, if necessary, information sharing means.

[0039] Video acquisition method

[0040] The device (pet camera) continuously captures real-time video data of the animal. The camera tracks the animal's movements and saves the data in a buffer every 5 seconds. Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet.

[0041] Data Analysis Methods

[0042] The server stores the received video data in the cloud. The server then analyzes the video data using a generative AI model (e.g., a deep learning model). The generative AI model extracts the animal's behavior and movements as features and detects abnormal behavior or symptoms. For example, if an animal is detected to be frequently licking its front paws, this can be recognized as an early symptom of inflammation.

[0043] Matching method

[0044] The server compares the data analysis results with a database of previously collected animal cases. Through the comparison, known conditions that may match the analysis data are identified. Based on the comparison results, the need for a hospital visit is assessed. The assessment is made in categories such as "no abnormality," "mild abnormality," and "severe abnormality."

[0045] Notification means

[0046] The server notifies the user of the results of the comparison. Notifications are sent via a dedicated app, SMS, or email. For example, if a "severe abnormality" is detected, the server will inform the user that an immediate visit to the veterinary clinic is necessary and provide information about the nearest veterinary clinic.

[0047] Information sharing means

[0048] The server has the function to automatically send analysis results and video data to veterinary clinics when necessary. In this case, the user's consent is obtained before the data is sent. After obtaining the user's consent, the server securely transmits this data to the veterinary clinic. The veterinary clinic can refer to this data at the first consultation, enabling faster and more accurate diagnosis.

[0049] Specific examples

[0050] The pet camera captures real-time footage of the pet and sends it to a server. On the server side, a generative AI model analyzes the footage and detects behaviors such as the animal frequently licking its front paws. This analysis result is compared with a case database and determines that the animal may be in the early stages of dermatitis.

[0051] Based on this result, the server sends a notification to the user's app saying, "A visit to the vet is necessary. Please go to a nearby veterinary clinic." At the same time, it also provides information about the nearest veterinary clinic.

[0052] If necessary, with the user's consent, the analysis results and video data will be sent to the veterinary clinic, which can then use this information to conduct an examination and provide the owner with the appropriate medical treatment promptly.

[0053] This system allows owners to quickly understand their pet's health condition and schedule timely visits to the hospital, which is expected to prevent pets from becoming seriously ill and reduce medical costs.

[0054] The processing flow will be explained below.

[0055] Step 1: Acquiring and transmitting video data

[0056] Device (Pet Camera):

[0057] The camera captures real-time footage of your pet.

[0058] Video data is saved in a buffer every 5 seconds.

[0059] Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet.

[0060] Step 2: Receiving and saving video data

[0061] server:

[0062] Receives video data sent from the terminal.

[0063] The received video data is stored in a database in chronological order.

[0064] Step 3: Analyzing the video data

[0065] server:

[0066] Loads saved video data.

[0067] Video data is analyzed using a generative AI model (deep learning model).

[0068] Extracts features of animal movements and behaviors to detect abnormal behaviors and symptoms.

[0069] For example, detecting whether an animal is frequently licking its front paws.

[0070] Step 4: Matching with case data

[0071] server:

[0072] The analysis results are compared with a case database.

[0073] Based on the comparison results, the need for outpatient treatment is evaluated and determined.

[0074] The evaluation is made in the categories of "no abnormality," "mild abnormality," and "severe abnormality."

[0075] Step 5: Notify users

[0076] server:

[0077] The result determined by the collation means is notified to the user.

[0078] Notifications will be sent via a dedicated app, SMS, or email.

[0079] If it is determined that a visit to the veterinary clinic is necessary, information about the nearest veterinary clinic will also be provided.

[0080] Step 6: Share information with hospitals

[0081] server:

[0082] Prepare to send analysis results and video data to the veterinary clinic, if necessary.

[0083] Obtain user consent before sending data.

[0084] Once the user's consent is obtained, the analysis results and video data are sent to the veterinary hospital.

[0085] The veterinary clinic confirms receipt of the data and sends a confirmation notice to the user.

[0086] Example 1

[0087] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0088] Today's busy pet owners find it difficult to constantly monitor their pets' health, so they need prompt medical treatment through early detection of abnormalities. Even if you discover abnormal behavior in your pet, it is often difficult to determine whether it is a problem that warrants a visit to the veterinary hospital. Furthermore, if you are unable to properly determine the need for a visit to the veterinary hospital, you may end up spending excessive medical expenses or, conversely, it may be too late.

[0089] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0090] In this invention, the server includes a means for acquiring real-time video data of the animal, a means for transmitting the acquired video data via the Internet, and a means for storing the transmitted video data in the cloud, thereby enabling the user to remotely monitor the health condition of their pet, quickly detect abnormalities, and take the pet to the vet at the appropriate time.

[0091] "Animal" refers to living creatures such as pets and livestock, and specifically includes dogs and cats kept within the home.

[0092] "Real-time video data" refers to data that captures the current state of an animal as video sequentially and can be displayed without delay.

[0093] "Image acquisition means" refers to a system or device that has the function of acquiring images of animals in real time using a device such as a camera.

[0094] The "means for transmitting via the Internet" is a function for transmitting the acquired video data to another device or server via an Internet line.

[0095] "Means for storing on the cloud" refers to the function of storing acquired video data in a cloud storage service via the Internet.

[0096] A "generative AI model" refers to an algorithm that uses machine learning or deep learning techniques to analyze data and detect specific patterns or anomalies.

[0097] "Data analysis means" refers to a system or software that has the function of analyzing video data stored on the cloud and evaluating the behavior and condition of animals.

[0098] The "collation means" is a system or device that has the function of comparing the analyzed data with existing case data and determining the type and degree of abnormality.

[0099] "Notification means" refers to the means for informing the user of the results of the analysis and matching, and may include a dedicated app, SMS, or email.

[0100] An "information sharing means" is a system or device that has the function of transmitting analysis results and video data to a third-party institution such as a veterinary clinic with the user's consent.

[0101] The present invention provides a system that acquires and analyzes real-time video data of an animal, compares it with case data, determines the need for a hospital visit, and notifies the user. This system includes a video acquisition unit, a data analysis unit, a comparison unit, a notification unit, and an information sharing unit. An example of each unit is described in detail below.

[0102] Video acquisition method

[0103] The device (pet camera) continuously captures real-time video data of animals. When the device's built-in camera detects animal movement, it automatically starts recording and saves the video data in a buffer every 5 seconds. Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet. Specifically, the data is compressed in JPEG format, and the Wi-Fi module sends the compressed data to the server.

[0104] Data Analysis Methods

[0105] The server stores the received video data in the cloud. At this time, the server's storage system writes the data to cloud storage. The server then analyzes the video data using a generative AI model (e.g., a deep learning model). The generative AI model uses libraries such as TENSORFLOW (registered trademark) to extract animal behavior and movements as features and detect abnormal behavior and symptoms. Specifically, a Python script analyzes the animal's movements and behavior.

[0106] Matching method

[0107] The server compares the data analysis results with a database of pre-collected animal cases. An SQL database query on the server collates the analysis results and identifies matching symptoms. The comparison identifies known symptoms that the analysis data may match and assesses the need for a medical visit. The assessment is made in categories such as "no abnormality," "mild abnormality," or "severe abnormality."

[0108] Notification means

[0109] The server notifies the user of the results of the collation process. Notifications are sent via a dedicated app, SMS, or email. The server's notification system references the user's contact information and sends a notification message. For example, if the pet is judged to have a "severe abnormality," the server will inform the user that they need to visit a veterinarian immediately and provide information about the nearest veterinary clinic.

[0110] Information sharing means

[0111] The server has the ability to automatically send analysis results and video data to veterinary clinics when necessary. In this case, the user's consent is obtained before the data is sent, and a confirmation screen is displayed in the dedicated app. If the user selects "Agree," the consent information is stored on the server. The server then sends the data to the veterinary clinic's system using a secure communication protocol (e.g., HTTPS).

[0112] Specific examples

[0113] The pet camera captures real-time footage of the pet and sends it to a server. On the server side, a generative AI model analyzes the footage and detects behaviors such as the animal frequently licking its front paws. This analysis result is compared with a case database and determines that the animal may be in the early stages of dermatitis.

[0114] Based on these results, the server sends a notification to the user via a dedicated app saying, "A visit to the veterinary clinic is necessary. Please go to a nearby veterinary clinic." At the same time, it also provides information about the nearest veterinary clinic. If necessary, with the user's consent, it sends the analysis results and video data to the veterinary clinic. The veterinary clinic can then use this information to conduct an examination and provide the owner with the appropriate medical treatment promptly.

[0115] In this way, the system of the present invention allows users to quickly understand the health condition of their pets and realize timely visits to the hospital, which is expected to prevent the pet's condition from becoming serious and reduce medical costs.

[0116] Prompt Sentence Examples

[0117] "Please explain the design of the generative AI model that analyzes real-time video data of pets and detects abnormal behavior. Please also explain in detail how the results are notified to the user."

[0118] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0119] Step 1:

[0120] The device (pet camera) captures real-time video data of the animal. When the camera detects animal movement, it stores the video data in a buffer every 5 seconds.

[0121] Input: Detect animal movement.

[0122] Output: Video data is stored in a buffer every 5 seconds.

[0123] How it works: When the device's built-in sensor detects animal movement, the camera starts recording, and the recorded footage is saved to a local buffer every 5 seconds.

[0124] Step 2:

[0125] The device compresses the video data in the buffer every 10 minutes and sends it to a server via the Internet.

[0126] Input: 10 minutes of accumulated video data.

[0127] Output: The compressed video data is sent to the server.

[0128] How it works: The device's built-in compressor compresses the video data into JPEG format, and then the Wi-Fi module sends the compressed data to the server.

[0129] Step 3:

[0130] The server stores the received video data on the cloud.

[0131] Input: Compressed video data.

[0132] Output: Video data saved in cloud storage.

[0133] Specific operation: The server's storage system decodes the received data and writes it to cloud storage.

[0134] Step 4:

[0135] The server uses a generative AI model to analyze the stored video data.

[0136] Input: Video data stored in cloud storage.

[0137] Output: Analysis results (detection of animal behavior patterns and abnormal behavior).

[0138] How it works: A Python script runs on the server and uses libraries such as TensorFlow to execute a deep learning model, analyzing each frame of video data, extracting features, and detecting abnormal behavior.

[0139] Step 5:

[0140] The server compares the results of the data analysis with a database of animal cases.

[0141] Input: Analysis results.

[0142] Output: Matching results with case data and judgment results.

[0143] What happens: A SQL database query is run on the server to match the analysis data against a database of cases and identify matching symptoms.

[0144] Step 6:

[0145] The server evaluates the need for hospital visits based on the collation results.

[0146] Input: Case data matching results and judgment results.

[0147] Output: Assessment of need for hospital visit ("No abnormality", "Mild abnormality", "Severe abnormality").

[0148] Specific operation: The evaluation algorithm performs a rule-based evaluation based on the matching results and classifies them into the appropriate category.

[0149] Step 7:

[0150] The server notifies the user of the evaluation results.

[0151] Input: Assessment results of need for medical visit.

[0152] Output: A notification message to the user.

[0153] What it does: The server's notification system looks up the user's contact information and sends notification messages via a dedicated app, SMS, or email.

[0154] Step 8:

[0155] The server obtains the user's consent to send the analysis results and video data to the veterinary clinic as needed.

[0156] Input: User consent.

[0157] Output: The consent information is saved on the server.

[0158] Specific operation: A confirmation screen is displayed in the dedicated app, and if the user selects "Agree," the consent information is recorded on the server.

[0159] Step 9:

[0160] After obtaining the user's consent, the server sends the analysis results and video data to the veterinary clinic.

[0161] Input: User consent, analysis results, and video data.

[0162] Output: Send data to veterinary clinic.

[0163] What happens: The server sends the data to the veterinary clinic's system using a secure communication protocol (e.g., HTTPS).

[0164] This detailed processing step allows for real-time monitoring of the animal's health and rapid response.

[0165] (Application example 1)

[0166] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0167] The management of goods in logistics centers is extensive and complex, and is dependent on human resources, which can lead to reduced efficiency. Furthermore, when goods are misplaced or damaged, it takes time to discover the problem, making it difficult to quickly resolve the issue. To improve this situation, a system is needed that can quickly detect and notify abnormalities in goods.

[0168] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0169] In this invention, the server includes an image acquisition means for acquiring real-time image data of the items, a data analysis means including a generative AI model for analyzing the acquired image data, a comparison means for comparing the results of the analysis by the data analysis means with the item status data to determine whether or not an abnormality exists, and a notification means for notifying a manager of the results determined by the comparison means. This improves the efficiency of item management within the logistics center, making it possible to quickly detect abnormalities such as misplacement or damage and immediately notify the manager.

[0170] "Goods" is a general term for products, lumber, equipment, consumables, etc. that are subject to management at logistics centers, etc.

[0171] "Real-time video data" refers to video data that provides instant visual information on the current status of an item.

[0172] "Video acquisition means" refers to a device or method that uses a camera or sensor to collect real-time video data.

[0173] A "generative AI model" is an artificial intelligence model used to analyze video data, and specifically utilizes technologies such as deep learning.

[0174] "Data analysis means" refers to a device or method that uses a generative AI model to analyze acquired video data and extract abnormalities and features.

[0175] "Condition data" refers to data that includes reference information such as the correct placement of an item, its proper condition, and whether or not it is damaged.

[0176] The "comparison means" is a device or method that compares the features extracted by the data analysis means with the status data to determine whether or not there is an abnormality.

[0177] "Notification means" refers to a system or method for notifying the user or administrator of the judgment result, and specifically includes email, application notification, etc.

[0178] "Information sharing means" refers to a device or method for sharing analysis results and video data with relevant parties such as administrators after an abnormality is detected.

[0179] The present invention relates to a system for real-time management and abnormality detection of goods in a logistics center.

[0180] Video acquisition method

[0181] In this system, real-time video data of goods is first captured by cameras installed within the logistics center. The cameras monitor a wide area of ​​the logistics center and continuously collect video data. The video data is stored in a buffer at regular intervals, compressed as necessary, and sent to a server via the Internet.

[0182] Data Analysis Methods

[0183] The server stores the acquired video data on the cloud. A generative AI model is installed in the server and analyzes the video data. Specifically, the generative AI model (e.g., a deep learning model) extracts the location and condition of the item as features and detects whether or not there is an abnormality. For example, if an item is not in its designated location or if damage is observed, it is detected as an abnormality.

[0184] Matching method

[0185] The analyzed data is collated with pre-registered item status data. The server compares the analysis results with the status data to determine whether there are any abnormalities. If the collation results indicate an abnormality, the server immediately takes action based on that information.

[0186] Notification means

[0187] The phone server immediately notifies the administrator of the results of the verification process via email, SMS, or a dedicated app. For example, if damage or misplacement of an item is detected, the administrator will be notified that immediate correction is required and suggestions on how to address the issue will be provided.

[0188] Information sharing means

[0189] If necessary, the server can automatically transmit analysis results and video data to other management systems or personnel, ensuring secure transmission and processing according to pre-defined protocols.

[0190] Specific examples

[0191] For example, a camera captures images of items being arranged in their designated locations in a logistics center and sends the captured image to a server. On the server side, a generative AI model analyzes the video and detects if an item is in an abnormal position. Based on the analysis results, the server sends a notification to the administrator via a dedicated app saying, "The item is not in its designated location. Please check immediately." If necessary, the video data and analysis results can also be sent to other administrators or systems based on user settings.

[0192] Prompt Sentence Examples

[0193] The system analyzes surveillance camera footage to check whether items are scattered around the logistics center and notifies the user if any abnormalities are detected.

[0194] This invention realizes more efficient item management in logistics centers and enables rapid detection and response of abnormalities, thereby improving the operational efficiency of the entire logistics center and enabling early resolution of problems.

[0195] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0196] Step 1:

[0197] The camera device captures real-time video data of items in the logistics center.

[0198] Input: Image data of the item

[0199] Output: Buffered video data

[0200] How it works: Cameras are installed throughout the logistics center, capturing images periodically and temporarily storing them in a buffer. The data in the buffer is then periodically sent to a server.

[0201] Step 2:

[0202] The server receives the transmitted video data from the buffer.

[0203] Input: Video data sent from the camera device

[0204] Output: Video data stored on the cloud

[0205] Specific operation: The server receives video data sent from the camera at regular intervals and stores it in cloud storage, ensuring continuous data acquisition.

[0206] Step 3:

[0207] The server analyzes the video data using the generated AI model.

[0208] Input: Video data stored in the cloud

[0209] Output: Analysis results (item features and abnormality determination)

[0210] Specific operation: A generative AI model (e.g., a deep learning model) installed on the server extracts information about the condition and placement of items as features from the stored video data, and analyzes them to detect abnormal conditions.

[0211] Step 4:

[0212] The server compares the analysis results with the item's condition data.

[0213] Input: Analyzed features, state database

[0214] Output: Abnormality judgment result

[0215] Specific operation: The server compares the analyzed features with a pre-registered condition database to determine whether the item is normal or abnormal. If it is determined to be abnormal, it also generates detailed information about the abnormality.

[0216] Step 5:

[0217] The server notifies the administrator of the abnormality determination result.

[0218] Input: Abnormality detection result, administrator contact information

[0219] Output: Send notification message

[0220] Specific operation: Based on the result of the abnormality judgment, the server will send a message to the administrator using the configured notification method (email, SMS, dedicated app). The message will include the details of the abnormality and how to respond.

[0221] Step 6:

[0222] The server shares the analysis results and video data with other management systems and personnel.

[0223] Input: User settings, abnormality detection results, video data

[0224] Output: Shared analysis results and video data

[0225] Specific operation: If necessary, the server will share the analysis results and related video data with other management systems and personnel, securely according to pre-defined protocols.

[0226] These processing steps enable efficient real-time management of goods and abnormality detection in a logistics center.

[0227] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0228] The present invention combines a system that acquires and analyzes real-time video data of animals, compares it with case data to determine the need for hospital visits, and notifies the user, with an emotion engine that recognizes the user's emotions. This system mainly includes video acquisition means, data analysis means, comparison means, notification means, emotion engine, and, if necessary, information sharing means.

[0229] Video acquisition method

[0230] The device (pet camera) continuously captures real-time video data of the animal. The camera tracks the animal's movements and saves the data in a buffer every 5 seconds. Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet.

[0231] Data Analysis Methods

[0232] The server stores the received video data in the cloud. The server then analyzes the video data using a generative AI model (e.g., a deep learning model). The generative AI model extracts the animal's behavior and movements as features and detects abnormal behavior or symptoms. For example, if an animal is detected to be frequently licking its front paws, this can be recognized as an early symptom of inflammation.

[0233] Matching method

[0234] The server compares the data analysis results with a database of previously collected animal cases. Through the comparison, known conditions that may match the analysis data are identified. Based on the comparison results, the need for a hospital visit is assessed. The assessment is made in categories such as "no abnormality," "mild abnormality," and "severe abnormality."

[0235] Notification means

[0236] The server notifies the user of the results of the comparison. Notifications are sent via a dedicated app, SMS, or email. For example, if a "severe abnormality" is detected, the server will inform the user that an immediate visit to the veterinary clinic is necessary and provide information about the nearest veterinary clinic.

[0237] Emotion Engine

[0238] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine evaluates the user's emotional state when a notification is sent via the notification means to notify the user of a visit. If the engine determines that the user is feeling stressed, it adds a message or advice to the notification to ease the user's feelings. In addition, if necessary, the emotion data is sent to the veterinary clinic, helping the clinic to provide medical care that takes the user's emotional state into consideration.

[0239] Information sharing means

[0240] The server has the function to automatically send analysis results and video data to veterinary clinics when necessary. In this case, the user's consent is obtained before the data is sent. After obtaining the user's consent, the server securely transmits this data to the veterinary clinic. The veterinary clinic can refer to this data at the first consultation, enabling faster and more accurate diagnosis.

[0241] Specific examples

[0242] The pet camera captures real-time footage of the pet and sends it to a server. On the server side, a generative AI model analyzes the footage and detects behaviors such as the animal frequently licking its front paws. The results of this analysis are compared with a case database, and a high probability of early-stage dermatitis is determined.

[0243] Based on this result, the server sends a notification to the user's app saying, "A visit to the vet is necessary. Please go to a nearby veterinary clinic." At the same time, it also provides information about the nearest veterinary clinic.

[0244] Furthermore, if the emotion engine evaluates the user's emotions and determines that the pet is feeling stressed, the notification will include a message such as, "Do not panic. Take action. Get a proper diagnosis at a nearby veterinary clinic."

[0245] If necessary, with the user's consent, the analysis results and video data will be sent to the veterinary clinic. The veterinary clinic can then use this information to conduct an examination and provide the owner with appropriate medical treatment promptly. The user's emotional data is also shared, allowing them to respond in a way that takes into account the user's psychological state.

[0246] This system allows owners to quickly understand their pet's health condition and schedule timely visits to the hospital. This is expected to prevent pets from becoming seriously ill and reduce medical costs. It also enables notifications and treatment that take the user's emotions into consideration, reducing the mental burden on owners.

[0247] The processing flow will be explained below.

[0248] Step 1: Acquiring and transmitting video data

[0249] Device (Pet Camera):

[0250] The camera captures real-time footage of your pet.

[0251] Video data is saved in a buffer every 5 seconds.

[0252] Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet.

[0253] Step 2: Receiving and saving video data

[0254] server:

[0255] Receives video data sent from the terminal.

[0256] The received video data is stored in a database in chronological order.

[0257] Step 3: Analyzing the video data

[0258] server:

[0259] Loads saved video data.

[0260] Video data is analyzed using a generative AI model (deep learning model).

[0261] Extracts features of animal movements and behaviors to detect abnormal behaviors and symptoms.

[0262] For example, the behavior of an animal frequently licking its front paws is detected.

[0263] Step 4: Matching with case data

[0264] server:

[0265] The analysis results are compared with a case database.

[0266] Based on the comparison results, the need for outpatient treatment is evaluated and determined.

[0267] The evaluation is made in the categories of "no abnormality," "mild abnormality," and "severe abnormality."

[0268] Step 5: Notify users

[0269] server:

[0270] The result determined by the collation means is notified to the user.

[0271] Notifications will be sent via a dedicated app, SMS, or email.

[0272] If it is determined that a visit to the veterinary clinic is necessary, information about the nearest veterinary clinic will also be provided.

[0273] Step 6: Evaluate your emotions

[0274] server:

[0275] An emotion engine is used to assess the user's emotional state when a notification means notifies the user of a hospital visit.

[0276] If the emotion engine determines that the user is feeling stressed, the notification will include a message or advice to ease the user's feelings.

[0277] Step 7: Share information with hospitals

[0278] server:

[0279] Prepare to send analysis results and video data to the veterinary clinic, if necessary.

[0280] Obtain user consent before sending data.

[0281] Once the user's consent is obtained, the analysis results and video data are sent to the veterinary hospital.

[0282] The veterinary clinic confirms receipt of the data and sends a confirmation notice to the user.

[0283] Example 2

[0284] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0285] Pet owners face challenges in properly monitoring their pets' health and detecting abnormalities early. Even if they obtain information about their pet's health, it can be difficult to determine when to share that information with a veterinary clinic. Furthermore, there is a lack of systems that support pet owners in correctly understanding their pet's health information and responding appropriately without stress. Furthermore, there is a need for an efficient means of sharing information so that veterinary clinics can understand their pet's health status before an examination.

[0286] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0287] In this invention, the server includes a terminal that acquires real-time video data of the animal, a server that includes a generative AI model for analyzing the acquired video data, a server that compares the results of the analysis by the generative AI model with previously collected case data and determines the need for a veterinary visit, a server that notifies the user of the results determined by the comparison means, a server that includes an emotion recognition engine that evaluates the user's emotional state and adds a message that takes the user's emotions into consideration depending on the content of the notification, and an information sharing means that automatically transmits the analysis results and video data to a veterinary clinic as needed. This allows for quick and accurate monitoring of the pet's health condition, allowing owners to make timely decisions about when to visit the veterinary clinic. Furthermore, it reduces the psychological burden on owners and enables efficient information sharing with veterinary clinics.

[0288] "Real-time animal video data" refers to video data that records the current behavior and status of pets and other animals.

[0289] A "terminal" is a device that includes a camera and sensors for acquiring real-time video data of animals.

[0290] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to analyze and classify acquired video data.

[0291] A "server" is a central control unit that analyzes data, stores results, and notifies users and other systems.

[0292] "Data analysis" is the process of extracting features from the acquired video data and detecting abnormal behavior or symptoms.

[0293] "Matching" is the process of comparing analysis results with previously collected case data to identify possible matching symptoms.

[0294] "Notification" is a means of communication to inform the user of the results of analysis and matching.

[0295] The "emotion recognition engine" is a program that evaluates the user's emotional state and adds an appropriate message depending on the notification content.

[0296] The "information sharing means" refers to a communication device or method for transmitting analysis results and video data to a third party such as a veterinary clinic as needed.

[0297] "Necessity of medical visits" refers to the degree to which a pet's health condition is deemed to require a visit to a veterinary hospital.

[0298] MODE FOR CARRYING OUT THE INVENTION

[0299] System Configuration

[0300] This invention is a system that acquires real-time video data of animals, analyzes it, and compares it with case data to determine the need for medical treatment and notify the user. This system has three main components: a terminal (pet camera), a server, and a user.

[0301] Device (Pet Camera)

[0302] The terminal is a device that includes a camera to capture real-time video data of the animal. The camera on the terminal tracks the animal's movements and stores the data in a buffer every 5 seconds. The video data in the buffer is compressed every 10 minutes and sent to a server via the Internet. The hardware used is a commercially available high-performance pet camera, and it is possible to use, for example, H.264 video compression technology.

[0303] server

[0304] The server stores the received video data in the cloud and analyzes the data using a generative AI model. The software used is the deep learning frameworks TensorFlow and PyTorch. The generative AI model extracts the animal's behavior and movements as features and detects abnormal behavior or symptoms. For example, if an animal is detected to be frequently licking its front paws, it will recognize this as an early symptom of inflammation.

[0305] Data analysis

[0306] The server then compares the analysis results with previously collected case data to identify potential matching symptoms. This involves using an SQL database to match the analysis results' features with known symptoms in the case database. Based on the results, the server assesses whether the patient needs to visit the hospital, categorizing them as "no abnormality," "mild abnormality," or "severe abnormality."

[0307] Notification means

[0308] The server notifies the user of the evaluation results. Specifically, it notifies the user via a dedicated application, SMS, or email. For example, if the result is a "severe abnormality," the user will be notified that "immediate medical attention is required." Information about the nearest veterinary clinic will also be provided.

[0309] Emotion Recognition Engine

[0310] The server also includes an emotion recognition engine that recognizes the user's emotions. This engine evaluates the user's emotional state when a hospital visit notification is sent via the notification means. Emotion recognition can utilize the Sentiment Analysis API. If it is determined that the user is feeling stressed, a message such as "Don't panic, take action" is added to the notification.

[0311] Information sharing means

[0312] The server has an information sharing mechanism that automatically sends analysis results and video data to veterinary clinics as needed. This mechanism sends data encrypted using SSL / TLS with the user's consent. Veterinary clinics can then make a quick and accurate diagnosis based on the received data.

[0313] user

[0314] Through this system, users can keep track of their pet's health in real time. For example, if their pet is frequently licking its front paws, the system will notify the user, "Your pet needs medical attention. Please go to a nearby veterinary clinic." Furthermore, if the emotion recognition engine detects stress in the user, a message such as "Don't panic, act accordingly" will be added to the notification.

[0315] Specific examples

[0316] The pet camera captures real-time footage of the pet and sends it to a server. On the server side, a generative AI model analyzes the footage and detects behaviors such as the animal frequently licking its front paws. The results of this analysis are compared with a case database, and a high probability of early-stage dermatitis is determined.

[0317] Based on these results, the server sends a notification to the user via a dedicated app saying, "A visit to the vet is necessary. Please go to a nearby veterinary clinic." At the same time, it also provides information about the nearest veterinary clinic. Furthermore, if the emotion engine evaluates the user's emotions and determines that the user is feeling stressed, the notification will include a message such as, "Do not panic. Take action. Get a proper diagnosis at a nearby veterinary clinic."

[0318] If necessary, with the user's consent, the analysis results and video data are sent to the veterinary hospital. The veterinary hospital can use this information to conduct an examination and provide the owner with appropriate medical treatment promptly. In addition, the user's emotional data is also shared, allowing for responses that take into account the user's psychological state. This system allows owners to quickly understand their pet's health condition and ensure appropriate visits to the vet. This is expected to prevent pets from becoming seriously ill and reduce medical costs. It also enables notifications and treatment that take the user's emotions into consideration, which has the effect of reducing the mental burden on owners.

[0319] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0320] Step 1:

[0321] The terminal (pet camera) acquires real-time video data of the animal. As input, it has the video data from the camera. The camera tracks the animal's movements and saves the video data in a buffer every 5 seconds. This allows the video data of the animal's behavior and status to be accumulated in the buffer.

[0322] Step 2:

[0323] The terminal compresses the video data in the buffer every 10 minutes and sends it to the server via the Internet. The input here is the raw video data stored in the buffer. The data is compressed using H.264 video compression technology, and the compressed video data is sent to the server as the output.

[0324] Step 3:

[0325] The server stores the received compressed video data in the cloud. The input is the compressed video data sent from the terminal. The server stores the data using a cloud storage service (e.g., Amazon S3 or Google (registered trademark) Cloud Storage), and the output is the data stored in the cloud.

[0326] Step 4:

[0327] The server analyzes video data stored on the cloud using a generative AI model. The input is the stored video data. The generative AI model uses TensorFlow and PyTorch to extract features representing the animal's behavior and state, and detects abnormal behavior and symptoms. The output is the analysis results. For example, if the model detects that an animal is frequently licking its front paws, it will identify this as an early symptom of inflammation.

[0328] Step 5:

[0329] The server compares the analysis results obtained by the generative AI model with previously collected case data. The inputs are the analysis results and the case database. An SQL database is used to match the features of the analysis results with known symptoms in the case database. The output identifies symptoms that may match the analysis results.

[0330] Step 6:

[0331] The server evaluates the need for outpatient care based on the analysis results and the comparison results of the case data. The input is the comparison results. The need for outpatient care is evaluated in categories such as "no abnormality," "mild abnormality," and "severe abnormality." The output is the evaluation result regarding the need for outpatient care.

[0332] Step 7:

[0333] The server notifies the user of the assessment results regarding the need for medical attention. The inputs are the assessment results and the user's contact information. The notification is sent via a dedicated app, SMS, or email, and conveys a message to the user such as "An immediate medical visit is required." The output is a notification sent to the user.

[0334] Step 8:

[0335] The server uses an emotion recognition engine to evaluate the user's emotional state. The input is the notification content and the user's reaction data. The emotion recognition engine (e.g., Sentiment Analysis API) is used to evaluate the user's emotion, and the output is whether the user is feeling stressed. If necessary, a message such as "Don't panic, take action" is added to the notification content.

[0336] Step 9:

[0337] The server sends the analysis results and video data to the veterinary hospital as needed. The input is the analysis results and the user's consent. The data is encrypted using SSL / TLS and sent securely to the veterinary hospital. The output is the data sent to the veterinary hospital. The veterinary hospital can use this data as a reference to make a quick and accurate diagnosis.

[0338] (Application example 2)

[0339] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0340] Conventional pet monitoring systems often overlooked abnormal behavior or symptoms because they did not provide a means to regularly check an animal's behavior. This meant that opportunities for early and appropriate medical treatment could be missed, making them insufficient for protecting a pet's health. Furthermore, even if a user noticed something unusual about their pet, there were few ways to quickly obtain appropriate advice or information, and the system was unable to respond to the user's emotions. Furthermore, there was no function to display advertisements linked to the pet's health status, making it difficult to access health care products and information.

[0341] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an optical device that acquires real-time video data of the animal, an information processing device including a generative AI model for analyzing the acquired video data, a comparison means that compares the results of the analysis by the information processing device with the animal's case data and determines the need for medical treatment, a display device that notifies the user of the results determined by the comparison means, and a promotion means that displays advertisements related to the pet's health condition and behavior. This makes it possible to monitor the pet's health condition in real time and promptly notify the user if an abnormality is detected. In addition, displaying advertisements for products and services related to the pet's health condition makes it easier for the user to access appropriate care products and medical services. It is also possible to display messages that take the user's emotions into consideration, thereby reducing the psychological burden on the owner.

[0342] "Optical devices" is a general term for cameras and sensor devices used to acquire real-time video data of animals.

[0343] An "information processing device" is a computer device equipped with a generative AI model for analyzing acquired video data.

[0344] The "comparison means" is a function for comparing the results of analysis by the information processing device with the animal's case data and determining the need for hospital visits.

[0345] A "display device" is a screen or mobile device that notifies the user of the results determined by the comparison means.

[0346] "Promotional tools" are features for displaying advertisements related to pet health and behavior.

[0347] "Data sharing means" is a function that automatically transmits video data and analysis results to veterinary medical facilities.

[0348] This invention provides a system that acquires real-time video data of pets, analyzes it using a generative AI model to detect abnormal behavior and symptoms, notifies the user based on the data, and displays advertisements linked to the pet's health status.

[0349] The server uses optical devices, such as IP cameras and smart cameras, to capture real-time video data of animals, tracking pet movements every five seconds and compressing the video data and sending it to the cloud every ten minutes.

[0350] The server analyzes the captured video data using a generative AI model in the cloud. A deep learning model, for example, is used as the generative AI model, extracting animal behavior and movements as features and identifying abnormal behavior and symptoms. Machine learning libraries such as TensorFlow are used for this analysis.

[0351] The results of the video data analysis are collated with a database of animal cases collected in advance. An algorithm is used to compare the analysis results with the case database and determine whether or not a visit to the hospital is necessary. This results in an assessment into categories such as "no abnormalities," "mild abnormalities," or "severe abnormalities."

[0352] The server notifies the user of the results of the collation process via a dedicated app, SMS, or email. For example, if a "severe abnormality" is detected, the server will send a message urging the user to visit a veterinarian immediately, along with information about the nearest veterinary clinic.

[0353] As a promotional tool, users will be shown advertisements related to their pet's health. For example, if a pet is detected licking its paws frequently, advertisements for skin care products or veterinary clinics will be displayed. The app also has an emotion engine that recognizes the user's emotions, and if the user is feeling stressed, a comforting message will be added to the notification.

[0354] As a specific example, a pet camera captures video of a pet in real time and sends it to a server. A generative AI model on the server analyzes the video and detects behaviors such as the animal frequently licking its front paws. This analysis result is compared with a case database, and if early symptoms of dermatitis are determined, a notification is sent to the user's smartphone saying, "A visit to the nearest veterinary clinic is required. Please go to a nearby veterinary clinic." At the same time, an emotion engine evaluates the user's emotions and adds a comforting message such as, "Don't panic. Please go to a nearby veterinary clinic and receive a proper diagnosis."

[0355] An example of a prompt is as follows:

[0356] "Real-time video data of animals is acquired and analyzed with a generative AI model to detect abnormal behavior. The analysis results are compared with case data to determine the need for medical attention and notify the user. The system evaluates the user's emotions to add appropriate messages and display pet-related advertisements."

[0357] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0358] Step 1:

[0359] The server receives video data from optical devices (such as IP cameras) in real time. The input is the video signal from the optical device, and the output is the temporarily stored video data. Specifically, the IP camera tracks the animal's movements and stores the video data in a buffer every 5 seconds.

[0360] Step 2:

[0361] The server compresses the video data in the buffer every 10 minutes and sends it to the cloud. The input is the temporarily stored video data, and the output is the compressed video data. Specifically, the video data is compressed in H.264 format or similar and uploaded to the cloud server via the Internet.

[0362] Step 3:

[0363] The server analyzes the received video data using a generative AI model (e.g., a deep learning model) in the cloud. The input is compressed video data, and the output is analyzed feature data. Specifically, it uses machine learning libraries such as TensorFlow to extract features based on the animal's behavior and movements, and identifies abnormal behavior and symptoms.

[0364] Step 4:

[0365] The server compares the analysis results with the case database. The input is the analyzed feature data, and the output is the comparison result. Specifically, it matches the analysis results with known symptoms stored in the case database and evaluates the need for hospital visits.

[0366] Step 5:

[0367] The server sends a notification to the user based on the matching results. The input is the matching result, and the output is a notification message to the user. Specifically, it sends a notification such as "You need to visit the hospital" to the user's smartphone or email. If the user is feeling stressed, it also adds a comforting message based on the evaluation by the emotion engine.

[0368] Step 6:

[0369] The server displays advertisements related to the pet's health condition and behavior. The input is the analysis results, and the output is advertisement display information. Specifically, advertisements that match the symptoms and behaviors exhibited by the pet (for example, information about pet skin care products or veterinary clinics) are displayed on the user's smartphone.

[0370] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0371] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0372] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0373] [Second embodiment]

[0374] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0375] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0376] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0377] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0378] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0379] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0380] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0381] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0382] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0383] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0384] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0385] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0386] The present invention is a system that acquires and analyzes real-time video data of animals, compares it with case data, determines the need for hospital visits, and notifies the user. This system mainly includes video acquisition means, data analysis means, comparison means, notification means, and, if necessary, information sharing means.

[0387] Video acquisition method

[0388] The device (pet camera) continuously captures real-time video data of the animal. The camera tracks the animal's movements and saves the data in a buffer every 5 seconds. Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet.

[0389] Data Analysis Methods

[0390] The server stores the received video data in the cloud. The server then analyzes the video data using a generative AI model (e.g., a deep learning model). The generative AI model extracts the animal's behavior and movements as features and detects abnormal behavior or symptoms. For example, if an animal is detected to be frequently licking its front paws, this can be recognized as an early symptom of inflammation.

[0391] Matching method

[0392] The server compares the data analysis results with a database of previously collected animal cases. Through the comparison, known conditions that may match the analysis data are identified. Based on the comparison results, the need for a hospital visit is assessed. The assessment is made in categories such as "no abnormality," "mild abnormality," and "severe abnormality."

[0393] Notification means

[0394] The server notifies the user of the results of the comparison. Notifications are sent via a dedicated app, SMS, or email. For example, if a "severe abnormality" is detected, the server will inform the user that an immediate visit to the veterinary clinic is necessary and provide information about the nearest veterinary clinic.

[0395] Information sharing means

[0396] The server has the function to automatically send analysis results and video data to veterinary clinics when necessary. In this case, the user's consent is obtained before the data is sent. After obtaining the user's consent, the server securely transmits this data to the veterinary clinic. The veterinary clinic can refer to this data at the first consultation, enabling faster and more accurate diagnosis.

[0397] Specific examples

[0398] The pet camera captures real-time footage of the pet and sends it to a server. On the server side, a generative AI model analyzes the footage and detects behaviors such as the animal frequently licking its front paws. This analysis result is compared with a case database and determines that the animal may be in the early stages of dermatitis.

[0399] Based on this result, the server sends a notification to the user's app saying, "A visit to the vet is necessary. Please go to a nearby veterinary clinic." At the same time, it also provides information about the nearest veterinary clinic.

[0400] If necessary, with the user's consent, the analysis results and video data will be sent to the veterinary clinic, which can then use this information to conduct an examination and provide the owner with the appropriate medical treatment promptly.

[0401] This system allows owners to quickly understand their pet's health condition and schedule timely visits to the hospital, which is expected to prevent pets from becoming seriously ill and reduce medical costs.

[0402] The processing flow will be explained below.

[0403] Step 1: Acquiring and transmitting video data

[0404] Device (Pet Camera):

[0405] The camera captures real-time footage of your pet.

[0406] Video data is saved in a buffer every 5 seconds.

[0407] Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet.

[0408] Step 2: Receiving and saving video data

[0409] server:

[0410] Receives video data sent from the terminal.

[0411] The received video data is stored in a database in chronological order.

[0412] Step 3: Analyzing the video data

[0413] server:

[0414] Loads saved video data.

[0415] Video data is analyzed using a generative AI model (deep learning model).

[0416] Extracts features of animal movements and behaviors to detect abnormal behaviors and symptoms.

[0417] For example, detecting whether an animal is frequently licking its front paws.

[0418] Step 4: Matching with case data

[0419] server:

[0420] The analysis results are compared with a case database.

[0421] Based on the comparison results, the need for outpatient treatment is evaluated and determined.

[0422] The evaluation is made in the categories of "no abnormality," "mild abnormality," and "severe abnormality."

[0423] Step 5: Notify users

[0424] server:

[0425] The result determined by the collation means is notified to the user.

[0426] Notifications will be sent via a dedicated app, SMS, or email.

[0427] If it is determined that a visit to the veterinary clinic is necessary, information about the nearest veterinary clinic will also be provided.

[0428] Step 6: Share information with hospitals

[0429] server:

[0430] Prepare to send analysis results and video data to the veterinary clinic, if necessary.

[0431] Obtain user consent before sending data.

[0432] Once the user's consent is obtained, the analysis results and video data are sent to the veterinary hospital.

[0433] The veterinary clinic confirms receipt of the data and sends a confirmation notice to the user.

[0434] Example 1

[0435] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0436] Today's busy pet owners find it difficult to constantly monitor their pets' health, so they need prompt medical treatment through early detection of abnormalities. Even if you discover abnormal behavior in your pet, it is often difficult to determine whether it is a problem that warrants a visit to the veterinary hospital. Furthermore, if you are unable to properly determine the need for a visit to the veterinary hospital, you may end up spending excessive medical expenses or, conversely, it may be too late.

[0437] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0438] In this invention, the server includes a means for acquiring real-time video data of the animal, a means for transmitting the acquired video data via the Internet, and a means for storing the transmitted video data in the cloud, thereby enabling the user to remotely monitor the health condition of their pet, quickly detect abnormalities, and take the pet to the vet at the appropriate time.

[0439] "Animal" refers to living creatures such as pets and livestock, and specifically includes dogs and cats kept within the home.

[0440] "Real-time video data" refers to data that captures the current state of an animal as video sequentially and can be displayed without delay.

[0441] "Image acquisition means" refers to a system or device that has the function of acquiring images of animals in real time using a device such as a camera.

[0442] The "means for transmitting via the Internet" is a function for transmitting the acquired video data to another device or server via an Internet line.

[0443] "Means for storing on the cloud" refers to the function of storing acquired video data in a cloud storage service via the Internet.

[0444] A "generative AI model" refers to an algorithm that uses machine learning or deep learning techniques to analyze data and detect specific patterns or anomalies.

[0445] "Data analysis means" refers to a system or software that has the function of analyzing video data stored on the cloud and evaluating the behavior and condition of animals.

[0446] The "collation means" is a system or device that has the function of comparing the analyzed data with existing case data and determining the type and degree of abnormality.

[0447] "Notification means" refers to the means for informing the user of the results of the analysis and matching, and may include a dedicated app, SMS, or email.

[0448] An "information sharing means" is a system or device that has the function of transmitting analysis results and video data to a third-party institution such as a veterinary clinic with the user's consent.

[0449] The present invention provides a system that acquires and analyzes real-time video data of an animal, compares it with case data, determines the need for a hospital visit, and notifies the user. This system includes a video acquisition unit, a data analysis unit, a comparison unit, a notification unit, and an information sharing unit. An example of each unit is described in detail below.

[0450] Video acquisition method

[0451] The device (pet camera) continuously captures real-time video data of animals. When the device's built-in camera detects animal movement, it automatically starts recording and saves the video data in a buffer every 5 seconds. Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet. Specifically, the data is compressed in JPEG format, and the Wi-Fi module sends the compressed data to the server.

[0452] Data Analysis Methods

[0453] The server stores the received video data in the cloud. At this time, the server's storage system writes the data to cloud storage. The server then analyzes the video data using a generative AI model (e.g., a deep learning model). The generative AI model uses libraries such as TensorFlow to extract animal behavior and movements as features and detect abnormal behavior and symptoms. Specifically, a Python script analyzes the animal's movements and behavior.

[0454] Matching method

[0455] The server compares the data analysis results with a database of pre-collected animal cases. An SQL database query on the server collates the analysis results and identifies matching symptoms. The comparison identifies known symptoms that the analysis data may match and assesses the need for a medical visit. The assessment is made in categories such as "no abnormality," "mild abnormality," or "severe abnormality."

[0456] Notification means

[0457] The server notifies the user of the results of the collation process. Notifications are sent via a dedicated app, SMS, or email. The server's notification system references the user's contact information and sends a notification message. For example, if the pet is judged to have a "severe abnormality," the server will inform the user that they need to visit a veterinarian immediately and provide information about the nearest veterinary clinic.

[0458] Information sharing means

[0459] The server has the ability to automatically send analysis results and video data to veterinary clinics when necessary. In this case, the user's consent is obtained before the data is sent, and a confirmation screen is displayed in the dedicated app. If the user selects "Agree," the consent information is stored on the server. The server then sends the data to the veterinary clinic's system using a secure communication protocol (e.g., HTTPS).

[0460] Specific examples

[0461] The pet camera captures real-time footage of the pet and sends it to a server. On the server side, a generative AI model analyzes the footage and detects behaviors such as the animal frequently licking its front paws. This analysis result is compared with a case database and determines that the animal may be in the early stages of dermatitis.

[0462] Based on these results, the server sends a notification to the user via a dedicated app saying, "A visit to the veterinary clinic is necessary. Please go to a nearby veterinary clinic." At the same time, it also provides information about the nearest veterinary clinic. If necessary, with the user's consent, it sends the analysis results and video data to the veterinary clinic. The veterinary clinic can then use this information to conduct an examination and provide the owner with the appropriate medical treatment promptly.

[0463] In this way, the system of the present invention allows users to quickly understand the health condition of their pets and realize timely visits to the hospital, which is expected to prevent the pet's condition from becoming serious and reduce medical costs.

[0464] Prompt Sentence Examples

[0465] "Please explain the design of the generative AI model that analyzes real-time video data of pets and detects abnormal behavior. Please also explain in detail how the results are notified to the user."

[0466] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0467] Step 1:

[0468] The device (pet camera) captures real-time video data of the animal. When the camera detects animal movement, it stores the video data in a buffer every 5 seconds.

[0469] Input: Detect animal movement.

[0470] Output: Video data is stored in a buffer every 5 seconds.

[0471] How it works: When the device's built-in sensor detects animal movement, the camera starts recording, and the recorded footage is saved to a local buffer every 5 seconds.

[0472] Step 2:

[0473] The device compresses the video data in the buffer every 10 minutes and sends it to a server via the Internet.

[0474] Input: 10 minutes of accumulated video data.

[0475] Output: The compressed video data is sent to the server.

[0476] How it works: The device's built-in compressor compresses the video data into JPEG format, and then the Wi-Fi module sends the compressed data to the server.

[0477] Step 3:

[0478] The server stores the received video data on the cloud.

[0479] Input: Compressed video data.

[0480] Output: Video data saved in cloud storage.

[0481] Specific operation: The server's storage system decodes the received data and writes it to cloud storage.

[0482] Step 4:

[0483] The server uses a generative AI model to analyze the stored video data.

[0484] Input: Video data stored in cloud storage.

[0485] Output: Analysis results (detection of animal behavior patterns and abnormal behavior).

[0486] How it works: A Python script runs on the server and uses libraries such as TensorFlow to execute a deep learning model, analyzing each frame of video data, extracting features, and detecting abnormal behavior.

[0487] Step 5:

[0488] The server compares the results of the data analysis with a database of animal cases.

[0489] Input: Analysis results.

[0490] Output: Matching results with case data and judgment results.

[0491] What happens: A SQL database query is run on the server to match the analysis data against a database of cases and identify matching symptoms.

[0492] Step 6:

[0493] The server evaluates the need for hospital visits based on the collation results.

[0494] Input: Case data matching results and judgment results.

[0495] Output: Assessment of need for hospital visit ("No abnormality", "Mild abnormality", "Severe abnormality").

[0496] Specific operation: The evaluation algorithm performs a rule-based evaluation based on the matching results and classifies them into the appropriate category.

[0497] Step 7:

[0498] The server notifies the user of the evaluation results.

[0499] Input: Assessment results of need for medical visit.

[0500] Output: A notification message to the user.

[0501] What it does: The server's notification system looks up the user's contact information and sends notification messages via a dedicated app, SMS, or email.

[0502] Step 8:

[0503] The server obtains the user's consent to send the analysis results and video data to the veterinary clinic as needed.

[0504] Input: User consent.

[0505] Output: The consent information is saved on the server.

[0506] Specific operation: A confirmation screen is displayed in the dedicated app, and if the user selects "Agree," the consent information is recorded on the server.

[0507] Step 9:

[0508] After obtaining the user's consent, the server sends the analysis results and video data to the veterinary clinic.

[0509] Input: User consent, analysis results, and video data.

[0510] Output: Send data to veterinary clinic.

[0511] What happens: The server sends the data to the veterinary clinic's system using a secure communication protocol (e.g., HTTPS).

[0512] This detailed processing step allows for real-time monitoring of the animal's health and rapid response.

[0513] (Application example 1)

[0514] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0515] The management of goods in logistics centers is extensive and complex, and is dependent on human resources, which can lead to reduced efficiency. Furthermore, when goods are misplaced or damaged, it takes time to discover the problem, making it difficult to quickly resolve the issue. To improve this situation, a system is needed that can quickly detect and notify abnormalities in goods.

[0516] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0517] In this invention, the server includes an image acquisition means for acquiring real-time image data of the items, a data analysis means including a generative AI model for analyzing the acquired image data, a comparison means for comparing the results of the analysis by the data analysis means with the item status data to determine whether or not an abnormality exists, and a notification means for notifying a manager of the results determined by the comparison means. This improves the efficiency of item management within the logistics center, making it possible to quickly detect abnormalities such as misplacement or damage and immediately notify the manager.

[0518] "Goods" is a general term for products, lumber, equipment, consumables, etc. that are subject to management at logistics centers, etc.

[0519] "Real-time video data" refers to video data that provides instant visual information on the current status of an item.

[0520] "Video acquisition means" refers to a device or method that uses a camera or sensor to collect real-time video data.

[0521] A "generative AI model" is an artificial intelligence model used to analyze video data, and specifically utilizes technologies such as deep learning.

[0522] "Data analysis means" refers to a device or method that uses a generative AI model to analyze acquired video data and extract abnormalities and features.

[0523] "Condition data" refers to data that includes reference information such as the correct placement of an item, its proper condition, and whether or not it is damaged.

[0524] The "comparison means" is a device or method that compares the features extracted by the data analysis means with the status data to determine whether or not there is an abnormality.

[0525] "Notification means" refers to a system or method for notifying the user or administrator of the judgment result, and specifically includes email, application notification, etc.

[0526] "Information sharing means" refers to a device or method for sharing analysis results and video data with relevant parties such as administrators after an abnormality is detected.

[0527] The present invention relates to a system for real-time management and abnormality detection of goods in a logistics center.

[0528] Video acquisition method

[0529] In this system, real-time video data of goods is first captured by cameras installed within the logistics center. The cameras monitor a wide area of ​​the logistics center and continuously collect video data. The video data is stored in a buffer at regular intervals, compressed as necessary, and sent to a server via the Internet.

[0530] Data Analysis Methods

[0531] The server stores the acquired video data on the cloud. A generative AI model is installed in the server and analyzes the video data. Specifically, the generative AI model (e.g., a deep learning model) extracts the location and condition of the item as features and detects whether or not there is an abnormality. For example, if an item is not in its designated location or if damage is observed, it is detected as an abnormality.

[0532] Matching method

[0533] The analyzed data is collated with pre-registered item status data. The server compares the analysis results with the status data to determine whether there are any abnormalities. If the collation results indicate an abnormality, the server immediately takes action based on that information.

[0534] Notification means

[0535] The phone server immediately notifies the administrator of the results of the verification process via email, SMS, or a dedicated app. For example, if damage or misplacement of an item is detected, the administrator will be notified that immediate correction is required and suggestions on how to address the issue will be provided.

[0536] Information sharing means

[0537] If necessary, the server can automatically transmit analysis results and video data to other management systems or personnel, ensuring secure transmission and processing according to pre-defined protocols.

[0538] Specific examples

[0539] For example, a camera captures images of items being arranged in their designated locations in a logistics center and sends the captured image to a server. On the server side, a generative AI model analyzes the video and detects if an item is in an abnormal position. Based on the analysis results, the server sends a notification to the administrator via a dedicated app saying, "The item is not in its designated location. Please check immediately." If necessary, the video data and analysis results can also be sent to other administrators or systems based on user settings.

[0540] Prompt Sentence Examples

[0541] The system analyzes surveillance camera footage to check whether items are scattered around the logistics center and notifies the user if any abnormalities are detected.

[0542] This invention realizes more efficient item management in logistics centers and enables rapid detection and response of abnormalities, thereby improving the operational efficiency of the entire logistics center and enabling early resolution of problems.

[0543] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0544] Step 1:

[0545] The camera device captures real-time video data of items in the logistics center.

[0546] Input: Image data of the item

[0547] Output: Buffered video data

[0548] How it works: Cameras are installed throughout the logistics center, capturing images periodically and temporarily storing them in a buffer. The data in the buffer is then periodically sent to a server.

[0549] Step 2:

[0550] The server receives the transmitted video data from the buffer.

[0551] Input: Video data sent from the camera device

[0552] Output: Video data stored on the cloud

[0553] Specific operation: The server receives video data sent from the camera at regular intervals and stores it in cloud storage, ensuring continuous data acquisition.

[0554] Step 3:

[0555] The server analyzes the video data using the generated AI model.

[0556] Input: Video data stored in the cloud

[0557] Output: Analysis results (item features and abnormality determination)

[0558] Specific operation: A generative AI model (e.g., a deep learning model) installed on the server extracts information about the condition and placement of items as features from the stored video data, and analyzes them to detect abnormal conditions.

[0559] Step 4:

[0560] The server compares the analysis results with the item's condition data.

[0561] Input: Analyzed features, state database

[0562] Output: Abnormality judgment result

[0563] Specific operation: The server compares the analyzed features with a pre-registered condition database to determine whether the item is normal or abnormal. If it is determined to be abnormal, it also generates detailed information about the abnormality.

[0564] Step 5:

[0565] The server notifies the administrator of the abnormality determination result.

[0566] Input: Abnormality detection result, administrator contact information

[0567] Output: Send notification message

[0568] Specific operation: Based on the result of the abnormality judgment, the server will send a message to the administrator using the configured notification method (email, SMS, dedicated app). The message will include the details of the abnormality and how to respond.

[0569] Step 6:

[0570] The server shares the analysis results and video data with other management systems and personnel.

[0571] Input: User settings, abnormality detection results, video data

[0572] Output: Shared analysis results and video data

[0573] Specific operation: If necessary, the server will share the analysis results and related video data with other management systems and personnel, securely according to pre-defined protocols.

[0574] These processing steps enable efficient real-time management of goods and abnormality detection in a logistics center.

[0575] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0576] The present invention combines a system that acquires and analyzes real-time video data of animals, compares it with case data to determine the need for hospital visits, and notifies the user, with an emotion engine that recognizes the user's emotions. This system mainly includes video acquisition means, data analysis means, comparison means, notification means, emotion engine, and, if necessary, information sharing means.

[0577] Video acquisition method

[0578] The device (pet camera) continuously captures real-time video data of the animal. The camera tracks the animal's movements and saves the data in a buffer every 5 seconds. Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet.

[0579] Data Analysis Methods

[0580] The server stores the received video data in the cloud. The server then analyzes the video data using a generative AI model (e.g., a deep learning model). The generative AI model extracts the animal's behavior and movements as features and detects abnormal behavior or symptoms. For example, if an animal is detected to be frequently licking its front paws, this can be recognized as an early symptom of inflammation.

[0581] Matching method

[0582] The server compares the data analysis results with a database of previously collected animal cases. Through the comparison, known conditions that may match the analysis data are identified. Based on the comparison results, the need for a hospital visit is assessed. The assessment is made in categories such as "no abnormality," "mild abnormality," and "severe abnormality."

[0583] Notification means

[0584] The server notifies the user of the results of the comparison. Notifications are sent via a dedicated app, SMS, or email. For example, if a "severe abnormality" is detected, the server will inform the user that an immediate visit to the veterinary clinic is necessary and provide information about the nearest veterinary clinic.

[0585] Emotion Engine

[0586] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine evaluates the user's emotional state when a notification is sent via the notification means to notify the user of a visit. If the engine determines that the user is feeling stressed, it adds a message or advice to the notification to ease the user's feelings. In addition, if necessary, the emotion data is sent to the veterinary clinic, helping the clinic to provide medical care that takes the user's emotional state into consideration.

[0587] Information sharing means

[0588] The server has the function to automatically send analysis results and video data to veterinary clinics when necessary. In this case, the user's consent is obtained before the data is sent. After obtaining the user's consent, the server securely transmits this data to the veterinary clinic. The veterinary clinic can refer to this data at the first consultation, enabling faster and more accurate diagnosis.

[0589] Specific examples

[0590] The pet camera captures real-time footage of the pet and sends it to a server. On the server side, a generative AI model analyzes the footage and detects behaviors such as the animal frequently licking its front paws. The results of this analysis are compared with a case database, and a high probability of early-stage dermatitis is determined.

[0591] Based on this result, the server sends a notification to the user's app saying, "A visit to the vet is necessary. Please go to a nearby veterinary clinic." At the same time, it also provides information about the nearest veterinary clinic.

[0592] Furthermore, if the emotion engine evaluates the user's emotions and determines that the pet is feeling stressed, the notification will include a message such as, "Do not panic. Take action. Get a proper diagnosis at a nearby veterinary clinic."

[0593] If necessary, with the user's consent, the analysis results and video data will be sent to the veterinary clinic. The veterinary clinic can then use this information to conduct an examination and provide the owner with appropriate medical treatment promptly. The user's emotional data is also shared, allowing them to respond in a way that takes into account the user's psychological state.

[0594] This system allows owners to quickly understand their pet's health condition and schedule timely visits to the hospital. This is expected to prevent pets from becoming seriously ill and reduce medical costs. It also enables notifications and treatment that take the user's emotions into consideration, reducing the mental burden on owners.

[0595] The processing flow will be explained below.

[0596] Step 1: Acquiring and transmitting video data

[0597] Device (Pet Camera):

[0598] The camera captures real-time footage of your pet.

[0599] Video data is saved in a buffer every 5 seconds.

[0600] Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet.

[0601] Step 2: Receiving and saving video data

[0602] server:

[0603] Receives video data sent from the terminal.

[0604] The received video data is stored in a database in chronological order.

[0605] Step 3: Analyzing the video data

[0606] server:

[0607] Loads saved video data.

[0608] Video data is analyzed using a generative AI model (deep learning model).

[0609] Extracts features of animal movements and behaviors to detect abnormal behaviors and symptoms.

[0610] For example, the behavior of an animal frequently licking its front paws is detected.

[0611] Step 4: Matching with case data

[0612] server:

[0613] The analysis results are compared with a case database.

[0614] Based on the comparison results, the need for outpatient treatment is evaluated and determined.

[0615] The evaluation is made in the categories of "no abnormality," "mild abnormality," and "severe abnormality."

[0616] Step 5: Notify users

[0617] server:

[0618] The result determined by the collation means is notified to the user.

[0619] Notifications will be sent via a dedicated app, SMS, or email.

[0620] If it is determined that a visit to the veterinary clinic is necessary, information about the nearest veterinary clinic will also be provided.

[0621] Step 6: Evaluate your emotions

[0622] server:

[0623] An emotion engine is used to assess the user's emotional state when a notification means notifies the user of a hospital visit.

[0624] If the emotion engine determines that the user is feeling stressed, the notification will include a message or advice to ease the user's feelings.

[0625] Step 7: Share information with hospitals

[0626] server:

[0627] Prepare to send analysis results and video data to the veterinary clinic, if necessary.

[0628] Obtain user consent before sending data.

[0629] Once the user's consent is obtained, the analysis results and video data are sent to the veterinary hospital.

[0630] The veterinary clinic confirms receipt of the data and sends a confirmation notice to the user.

[0631] Example 2

[0632] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0633] Pet owners face challenges in properly monitoring their pets' health and detecting abnormalities early. Even if they obtain information about their pet's health, it can be difficult to determine when to share that information with a veterinary clinic. Furthermore, there is a lack of systems that support pet owners in correctly understanding their pet's health information and responding appropriately without stress. Furthermore, there is a need for an efficient means of sharing information so that veterinary clinics can understand their pet's health status before an examination.

[0634] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0635] In this invention, the server includes a terminal that acquires real-time video data of the animal, a server that includes a generative AI model for analyzing the acquired video data, a server that compares the results of the analysis by the generative AI model with previously collected case data and determines the need for a veterinary visit, a server that notifies the user of the results determined by the comparison means, a server that includes an emotion recognition engine that evaluates the user's emotional state and adds a message that takes the user's emotions into consideration depending on the content of the notification, and an information sharing means that automatically transmits the analysis results and video data to a veterinary clinic as needed. This allows for quick and accurate monitoring of the pet's health condition, allowing owners to make timely decisions about when to visit the veterinary clinic. Furthermore, it reduces the psychological burden on owners and enables efficient information sharing with veterinary clinics.

[0636] "Real-time animal video data" refers to video data that records the current behavior and status of pets and other animals.

[0637] A "terminal" is a device that includes a camera and sensors for acquiring real-time video data of animals.

[0638] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to analyze and classify acquired video data.

[0639] A "server" is a central control unit that analyzes data, stores results, and notifies users and other systems.

[0640] "Data analysis" is the process of extracting features from the acquired video data and detecting abnormal behavior or symptoms.

[0641] "Matching" is the process of comparing analysis results with previously collected case data to identify possible matching symptoms.

[0642] "Notification" is a means of communication to inform the user of the results of analysis and matching.

[0643] The "emotion recognition engine" is a program that evaluates the user's emotional state and adds an appropriate message depending on the notification content.

[0644] The "information sharing means" refers to a communication device or method for transmitting analysis results and video data to a third party such as a veterinary clinic as needed.

[0645] "Necessity of medical visits" refers to the degree to which a pet's health condition is deemed to require a visit to a veterinary hospital.

[0646] MODE FOR CARRYING OUT THE INVENTION

[0647] System Configuration

[0648] This invention is a system that acquires real-time video data of animals, analyzes it, and compares it with case data to determine the need for medical treatment and notify the user. This system has three main components: a terminal (pet camera), a server, and a user.

[0649] Device (Pet Camera)

[0650] The terminal is a device that includes a camera to capture real-time video data of the animal. The camera on the terminal tracks the animal's movements and stores the data in a buffer every 5 seconds. The video data in the buffer is compressed every 10 minutes and sent to a server via the Internet. The hardware used is a commercially available high-performance pet camera, and it is possible to use, for example, H.264 video compression technology.

[0651] server

[0652] The server stores the received video data in the cloud and analyzes the data using a generative AI model. The software used is the deep learning frameworks TensorFlow and PyTorch. The generative AI model extracts the animal's behavior and movements as features and detects abnormal behavior or symptoms. For example, if an animal is detected to be frequently licking its front paws, it will recognize this as an early symptom of inflammation.

[0653] Data analysis

[0654] The server then compares the analysis results with previously collected case data to identify potential matching symptoms. This involves using an SQL database to match the analysis results' features with known symptoms in the case database. Based on the results, the server assesses whether the patient needs to visit the hospital, categorizing them as "no abnormality," "mild abnormality," or "severe abnormality."

[0655] Notification means

[0656] The server notifies the user of the evaluation results. Specifically, it notifies the user via a dedicated application, SMS, or email. For example, if the result is a "severe abnormality," the user will be notified that "immediate medical attention is required." Information about the nearest veterinary clinic will also be provided.

[0657] Emotion Recognition Engine

[0658] The server also includes an emotion recognition engine that recognizes the user's emotions. This engine evaluates the user's emotional state when a hospital visit notification is sent via the notification means. Emotion recognition can utilize the Sentiment Analysis API. If it is determined that the user is feeling stressed, a message such as "Don't panic, take action" is added to the notification.

[0659] Information sharing means

[0660] The server has an information sharing mechanism that automatically sends analysis results and video data to veterinary clinics as needed. This mechanism sends data encrypted using SSL / TLS with the user's consent. Veterinary clinics can then make a quick and accurate diagnosis based on the received data.

[0661] user

[0662] Through this system, users can keep track of their pet's health in real time. For example, if their pet is frequently licking its front paws, the system will notify the user, "Your pet needs medical attention. Please go to a nearby veterinary clinic." Furthermore, if the emotion recognition engine detects stress in the user, a message such as "Don't panic, act accordingly" will be added to the notification.

[0663] Specific examples

[0664] The pet camera captures real-time footage of the pet and sends it to a server. On the server side, a generative AI model analyzes the footage and detects behaviors such as the animal frequently licking its front paws. The results of this analysis are compared with a case database, and a high probability of early-stage dermatitis is determined.

[0665] Based on these results, the server sends a notification to the user via a dedicated app saying, "A visit to the vet is necessary. Please go to a nearby veterinary clinic." At the same time, it also provides information about the nearest veterinary clinic. Furthermore, if the emotion engine evaluates the user's emotions and determines that the user is feeling stressed, the notification will include a message such as, "Do not panic. Take action. Get a proper diagnosis at a nearby veterinary clinic."

[0666] If necessary, with the user's consent, the analysis results and video data are sent to the veterinary hospital. The veterinary hospital can use this information to conduct an examination and provide the owner with appropriate medical treatment promptly. In addition, the user's emotional data is also shared, allowing for responses that take into account the user's psychological state. This system allows owners to quickly understand their pet's health condition and ensure appropriate visits to the vet. This is expected to prevent pets from becoming seriously ill and reduce medical costs. It also enables notifications and treatment that take the user's emotions into consideration, which has the effect of reducing the mental burden on owners.

[0667] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0668] Step 1:

[0669] The terminal (pet camera) acquires real-time video data of the animal. As input, it has the video data from the camera. The camera tracks the animal's movements and saves the video data in a buffer every 5 seconds. This allows the video data of the animal's behavior and status to be accumulated in the buffer.

[0670] Step 2:

[0671] The terminal compresses the video data in the buffer every 10 minutes and sends it to the server via the Internet. The input here is the raw video data stored in the buffer. The data is compressed using H.264 video compression technology, and the compressed video data is sent to the server as the output.

[0672] Step 3:

[0673] The server stores the received compressed video data in the cloud. The input is the compressed video data sent from the device. The server stores the data using a cloud storage service (e.g., Amazon S3 or Google Cloud Storage), and the output is the data stored in the cloud.

[0674] Step 4:

[0675] The server analyzes video data stored on the cloud using a generative AI model. The input is the stored video data. The generative AI model uses TensorFlow and PyTorch to extract features representing the animal's behavior and state, and detects abnormal behavior and symptoms. The output is the analysis results. For example, if the model detects that an animal is frequently licking its front paws, it will identify this as an early symptom of inflammation.

[0676] Step 5:

[0677] The server compares the analysis results obtained by the generative AI model with previously collected case data. The inputs are the analysis results and the case database. An SQL database is used to match the features of the analysis results with known symptoms in the case database. The output identifies symptoms that may match the analysis results.

[0678] Step 6:

[0679] The server evaluates the need for outpatient care based on the analysis results and the comparison results of the case data. The input is the comparison results. The need for outpatient care is evaluated in categories such as "no abnormality," "mild abnormality," and "severe abnormality." The output is the evaluation result regarding the need for outpatient care.

[0680] Step 7:

[0681] The server notifies the user of the assessment results regarding the need for medical attention. The inputs are the assessment results and the user's contact information. The notification is sent via a dedicated app, SMS, or email, and conveys a message to the user such as "An immediate medical visit is required." The output is a notification sent to the user.

[0682] Step 8:

[0683] The server uses an emotion recognition engine to evaluate the user's emotional state. The input is the notification content and the user's reaction data. The emotion recognition engine (e.g., Sentiment Analysis API) is used to evaluate the user's emotion, and the output is whether the user is feeling stressed. If necessary, a message such as "Don't panic, take action" is added to the notification content.

[0684] Step 9:

[0685] The server sends the analysis results and video data to the veterinary hospital as needed. The input is the analysis results and the user's consent. The data is encrypted using SSL / TLS and sent securely to the veterinary hospital. The output is the data sent to the veterinary hospital. The veterinary hospital can use this data as a reference to make a quick and accurate diagnosis.

[0686] (Application example 2)

[0687] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0688] Conventional pet monitoring systems often overlooked abnormal behavior or symptoms because they did not provide a means to regularly check an animal's behavior. This meant that opportunities for early and appropriate medical treatment could be missed, making them insufficient for protecting a pet's health. Furthermore, even if a user noticed something unusual about their pet, there were few ways to quickly obtain appropriate advice or information, and the system was unable to respond to the user's emotions. Furthermore, there was no function to display advertisements linked to the pet's health status, making it difficult to access health care products and information.

[0689] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an optical device that acquires real-time video data of the animal, an information processing device including a generative AI model for analyzing the acquired video data, a comparison means that compares the results of the analysis by the information processing device with the animal's case data and determines the need for medical treatment, a display device that notifies the user of the results determined by the comparison means, and a promotion means that displays advertisements related to the pet's health condition and behavior. This makes it possible to monitor the pet's health condition in real time and promptly notify the user if an abnormality is detected. In addition, displaying advertisements for products and services related to the pet's health condition makes it easier for the user to access appropriate care products and medical services. It is also possible to display messages that take the user's emotions into consideration, thereby reducing the psychological burden on the owner.

[0690] "Optical devices" is a general term for cameras and sensor devices used to acquire real-time video data of animals.

[0691] An "information processing device" is a computer device equipped with a generative AI model for analyzing acquired video data.

[0692] The "comparison means" is a function for comparing the results of analysis by the information processing device with the animal's case data and determining the need for hospital visits.

[0693] A "display device" is a screen or mobile device that notifies the user of the results determined by the comparison means.

[0694] "Promotional tools" are features for displaying advertisements related to pet health and behavior.

[0695] "Data sharing means" is a function that automatically transmits video data and analysis results to veterinary medical facilities.

[0696] This invention provides a system that acquires real-time video data of pets, analyzes it using a generative AI model to detect abnormal behavior and symptoms, notifies the user based on the data, and displays advertisements linked to the pet's health status.

[0697] The server uses optical devices, such as IP cameras and smart cameras, to capture real-time video data of animals, tracking pet movements every five seconds and compressing the video data and sending it to the cloud every ten minutes.

[0698] The server analyzes the captured video data using a generative AI model in the cloud. A deep learning model, for example, is used as the generative AI model, extracting animal behavior and movements as features and identifying abnormal behavior and symptoms. Machine learning libraries such as TensorFlow are used for this analysis.

[0699] The results of the video data analysis are collated with a database of animal cases collected in advance. An algorithm is used to compare the analysis results with the case database and determine whether or not a visit to the hospital is necessary. This results in an assessment into categories such as "no abnormalities," "mild abnormalities," or "severe abnormalities."

[0700] The server notifies the user of the results of the collation process via a dedicated app, SMS, or email. For example, if a "severe abnormality" is detected, the server will send a message urging the user to visit a veterinarian immediately, along with information about the nearest veterinary clinic.

[0701] As a promotional tool, users will be shown advertisements related to their pet's health. For example, if a pet is detected licking its paws frequently, advertisements for skin care products or veterinary clinics will be displayed. The app also has an emotion engine that recognizes the user's emotions, and if the user is feeling stressed, a comforting message will be added to the notification.

[0702] As a specific example, a pet camera captures video of a pet in real time and sends it to a server. A generative AI model on the server analyzes the video and detects behaviors such as the animal frequently licking its front paws. This analysis result is compared with a case database, and if early symptoms of dermatitis are determined, a notification is sent to the user's smartphone saying, "A visit to the nearest veterinary clinic is required. Please go to a nearby veterinary clinic." At the same time, an emotion engine evaluates the user's emotions and adds a comforting message such as, "Don't panic. Please go to a nearby veterinary clinic and receive a proper diagnosis."

[0703] An example of a prompt is as follows:

[0704] "Real-time video data of animals is acquired and analyzed with a generative AI model to detect abnormal behavior. The analysis results are compared with case data to determine the need for medical attention and notify the user. The system evaluates the user's emotions to add appropriate messages and display pet-related advertisements."

[0705] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0706] Step 1:

[0707] The server receives video data from optical devices (such as IP cameras) in real time. The input is the video signal from the optical device, and the output is the temporarily stored video data. Specifically, the IP camera tracks the animal's movements and stores the video data in a buffer every 5 seconds.

[0708] Step 2:

[0709] The server compresses the video data in the buffer every 10 minutes and sends it to the cloud. The input is the temporarily stored video data, and the output is the compressed video data. Specifically, the video data is compressed in H.264 format or similar and uploaded to the cloud server via the Internet.

[0710] Step 3:

[0711] The server analyzes the received video data using a generative AI model (e.g., a deep learning model) in the cloud. The input is compressed video data, and the output is analyzed feature data. Specifically, it uses machine learning libraries such as TensorFlow to extract features based on the animal's behavior and movements, and identifies abnormal behavior and symptoms.

[0712] Step 4:

[0713] The server compares the analysis results with the case database. The input is the analyzed feature data, and the output is the comparison result. Specifically, it matches the analysis results with known symptoms stored in the case database and evaluates the need for hospital visits.

[0714] Step 5:

[0715] The server sends a notification to the user based on the matching results. The input is the matching result, and the output is a notification message to the user. Specifically, it sends a notification such as "You need to visit the hospital" to the user's smartphone or email. If the user is feeling stressed, it also adds a comforting message based on the evaluation by the emotion engine.

[0716] Step 6:

[0717] The server displays advertisements related to the pet's health condition and behavior. The input is the analysis results, and the output is advertisement display information. Specifically, advertisements that match the symptoms and behaviors exhibited by the pet (for example, information about pet skin care products or veterinary clinics) are displayed on the user's smartphone.

[0718] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0719] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0720] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0721] [Third embodiment]

[0722] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0723] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0724] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0725] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0726] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0727] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0728] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0729] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0730] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0731] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0732] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0733] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0734] The present invention is a system that acquires and analyzes real-time video data of animals, compares it with case data, determines the need for hospital visits, and notifies the user. This system mainly includes video acquisition means, data analysis means, comparison means, notification means, and, if necessary, information sharing means.

[0735] Video acquisition method

[0736] The device (pet camera) continuously captures real-time video data of the animal. The camera tracks the animal's movements and saves the data in a buffer every 5 seconds. Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet.

[0737] Data Analysis Methods

[0738] The server stores the received video data in the cloud. The server then analyzes the video data using a generative AI model (e.g., a deep learning model). The generative AI model extracts the animal's behavior and movements as features and detects abnormal behavior or symptoms. For example, if an animal is detected to be frequently licking its front paws, this can be recognized as an early symptom of inflammation.

[0739] Matching method

[0740] The server compares the data analysis results with a database of previously collected animal cases. Through the comparison, known conditions that may match the analysis data are identified. Based on the comparison results, the need for a hospital visit is assessed. The assessment is made in categories such as "no abnormality," "mild abnormality," and "severe abnormality."

[0741] Notification means

[0742] The server notifies the user of the results of the comparison. Notifications are sent via a dedicated app, SMS, or email. For example, if a "severe abnormality" is detected, the server will inform the user that an immediate visit to the veterinary clinic is necessary and provide information about the nearest veterinary clinic.

[0743] Information sharing means

[0744] The server has the function to automatically send analysis results and video data to veterinary clinics when necessary. In this case, the user's consent is obtained before the data is sent. After obtaining the user's consent, the server securely transmits this data to the veterinary clinic. The veterinary clinic can refer to this data at the first consultation, enabling faster and more accurate diagnosis.

[0745] Specific examples

[0746] The pet camera captures real-time footage of the pet and sends it to a server. On the server side, a generative AI model analyzes the footage and detects behaviors such as the animal frequently licking its front paws. This analysis result is compared with a case database and determines that the animal may be in the early stages of dermatitis.

[0747] Based on this result, the server sends a notification to the user's app saying, "A visit to the vet is necessary. Please go to a nearby veterinary clinic." At the same time, it also provides information about the nearest veterinary clinic.

[0748] If necessary, with the user's consent, the analysis results and video data will be sent to the veterinary clinic, which can then use this information to conduct an examination and provide the owner with the appropriate medical treatment promptly.

[0749] This system allows owners to quickly understand their pet's health condition and schedule timely visits to the hospital, which is expected to prevent pets from becoming seriously ill and reduce medical costs.

[0750] The processing flow will be explained below.

[0751] Step 1: Acquiring and transmitting video data

[0752] Device (Pet Camera):

[0753] The camera captures real-time footage of your pet.

[0754] Video data is saved in a buffer every 5 seconds.

[0755] Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet.

[0756] Step 2: Receiving and saving video data

[0757] server:

[0758] Receives video data sent from the terminal.

[0759] The received video data is stored in a database in chronological order.

[0760] Step 3: Analyzing the video data

[0761] server:

[0762] Loads saved video data.

[0763] Video data is analyzed using a generative AI model (deep learning model).

[0764] Extracts features of animal movements and behaviors to detect abnormal behaviors and symptoms.

[0765] For example, detecting whether an animal is frequently licking its front paws.

[0766] Step 4: Matching with case data

[0767] server:

[0768] The analysis results are compared with a case database.

[0769] Based on the comparison results, the need for outpatient treatment is evaluated and determined.

[0770] The evaluation is made in the categories of "no abnormality," "mild abnormality," and "severe abnormality."

[0771] Step 5: Notify users

[0772] server:

[0773] The result determined by the collation means is notified to the user.

[0774] Notifications will be sent via a dedicated app, SMS, or email.

[0775] If it is determined that a visit to the veterinary clinic is necessary, information about the nearest veterinary clinic will also be provided.

[0776] Step 6: Share information with hospitals

[0777] server:

[0778] Prepare to send analysis results and video data to the veterinary clinic, if necessary.

[0779] Obtain user consent before sending data.

[0780] Once the user's consent is obtained, the analysis results and video data are sent to the veterinary hospital.

[0781] The veterinary clinic confirms receipt of the data and sends a confirmation notice to the user.

[0782] Example 1

[0783] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0784] Today's busy pet owners find it difficult to constantly monitor their pets' health, so they need prompt medical treatment through early detection of abnormalities. Even if you discover abnormal behavior in your pet, it is often difficult to determine whether it is a problem that warrants a visit to the veterinary hospital. Furthermore, if you are unable to properly determine the need for a visit to the veterinary hospital, you may end up spending excessive medical expenses or, conversely, it may be too late.

[0785] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0786] In this invention, the server includes a means for acquiring real-time video data of the animal, a means for transmitting the acquired video data via the Internet, and a means for storing the transmitted video data in the cloud, thereby enabling the user to remotely monitor the health condition of their pet, quickly detect abnormalities, and take the pet to the vet at the appropriate time.

[0787] "Animal" refers to living creatures such as pets and livestock, and specifically includes dogs and cats kept within the home.

[0788] "Real-time video data" refers to data that captures the current state of an animal as video sequentially and can be displayed without delay.

[0789] "Image acquisition means" refers to a system or device that has the function of acquiring images of animals in real time using a device such as a camera.

[0790] The "means for transmitting via the Internet" is a function for transmitting the acquired video data to another device or server via an Internet line.

[0791] "Means for storing on the cloud" refers to the function of storing acquired video data in a cloud storage service via the Internet.

[0792] A "generative AI model" refers to an algorithm that uses machine learning or deep learning techniques to analyze data and detect specific patterns or anomalies.

[0793] "Data analysis means" refers to a system or software that has the function of analyzing video data stored on the cloud and evaluating the behavior and condition of animals.

[0794] The "collation means" is a system or device that has the function of comparing the analyzed data with existing case data and determining the type and degree of abnormality.

[0795] "Notification means" refers to the means for informing the user of the results of the analysis and matching, and may include a dedicated app, SMS, or email.

[0796] An "information sharing means" is a system or device that has the function of transmitting analysis results and video data to a third-party institution such as a veterinary clinic with the user's consent.

[0797] The present invention provides a system that acquires and analyzes real-time video data of an animal, compares it with case data, determines the need for a hospital visit, and notifies the user. This system includes a video acquisition unit, a data analysis unit, a comparison unit, a notification unit, and an information sharing unit. An example of each unit is described in detail below.

[0798] Video acquisition method

[0799] The device (pet camera) continuously captures real-time video data of animals. When the device's built-in camera detects animal movement, it automatically starts recording and saves the video data in a buffer every 5 seconds. Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet. Specifically, the data is compressed in JPEG format, and the Wi-Fi module sends the compressed data to the server.

[0800] Data Analysis Methods

[0801] The server stores the received video data in the cloud. At this time, the server's storage system writes the data to cloud storage. The server then analyzes the video data using a generative AI model (e.g., a deep learning model). The generative AI model uses libraries such as TensorFlow to extract animal behavior and movements as features and detect abnormal behavior and symptoms. Specifically, a Python script analyzes the animal's movements and behavior.

[0802] Matching method

[0803] The server compares the data analysis results with a database of pre-collected animal cases. An SQL database query on the server collates the analysis results and identifies matching symptoms. The comparison identifies known symptoms that the analysis data may match and assesses the need for a medical visit. The assessment is made in categories such as "no abnormality," "mild abnormality," or "severe abnormality."

[0804] Notification means

[0805] The server notifies the user of the results of the collation process. Notifications are sent via a dedicated app, SMS, or email. The server's notification system references the user's contact information and sends a notification message. For example, if the pet is judged to have a "severe abnormality," the server will inform the user that they need to visit a veterinarian immediately and provide information about the nearest veterinary clinic.

[0806] Information sharing means

[0807] The server has the ability to automatically send analysis results and video data to veterinary clinics when necessary. In this case, the user's consent is obtained before the data is sent, and a confirmation screen is displayed in the dedicated app. If the user selects "Agree," the consent information is stored on the server. The server then sends the data to the veterinary clinic's system using a secure communication protocol (e.g., HTTPS).

[0808] Specific examples

[0809] The pet camera captures real-time footage of the pet and sends it to a server. On the server side, a generative AI model analyzes the footage and detects behaviors such as the animal frequently licking its front paws. This analysis result is compared with a case database and determines that the animal may be in the early stages of dermatitis.

[0810] Based on these results, the server sends a notification to the user via a dedicated app saying, "A visit to the veterinary clinic is necessary. Please go to a nearby veterinary clinic." At the same time, it also provides information about the nearest veterinary clinic. If necessary, with the user's consent, it sends the analysis results and video data to the veterinary clinic. The veterinary clinic can then use this information to conduct an examination and provide the owner with the appropriate medical treatment promptly.

[0811] In this way, the system of the present invention allows users to quickly understand the health condition of their pets and realize timely visits to the hospital, which is expected to prevent the pet's condition from becoming serious and reduce medical costs.

[0812] Prompt Sentence Examples

[0813] "Please explain the design of the generative AI model that analyzes real-time video data of pets and detects abnormal behavior. Please also explain in detail how the results are notified to the user."

[0814] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0815] Step 1:

[0816] The device (pet camera) captures real-time video data of the animal. When the camera detects animal movement, it stores the video data in a buffer every 5 seconds.

[0817] Input: Detect animal movement.

[0818] Output: Video data is stored in a buffer every 5 seconds.

[0819] How it works: When the device's built-in sensor detects animal movement, the camera starts recording, and the recorded footage is saved to a local buffer every 5 seconds.

[0820] Step 2:

[0821] The device compresses the video data in the buffer every 10 minutes and sends it to a server via the Internet.

[0822] Input: 10 minutes of accumulated video data.

[0823] Output: The compressed video data is sent to the server.

[0824] How it works: The device's built-in compressor compresses the video data into JPEG format, and then the Wi-Fi module sends the compressed data to the server.

[0825] Step 3:

[0826] The server stores the received video data on the cloud.

[0827] Input: Compressed video data.

[0828] Output: Video data saved in cloud storage.

[0829] Specific operation: The server's storage system decodes the received data and writes it to cloud storage.

[0830] Step 4:

[0831] The server uses a generative AI model to analyze the stored video data.

[0832] Input: Video data stored in cloud storage.

[0833] Output: Analysis results (detection of animal behavior patterns and abnormal behavior).

[0834] How it works: A Python script runs on the server and uses libraries such as TensorFlow to execute a deep learning model, analyzing each frame of video data, extracting features, and detecting abnormal behavior.

[0835] Step 5:

[0836] The server compares the results of the data analysis with a database of animal cases.

[0837] Input: Analysis results.

[0838] Output: Matching results with case data and judgment results.

[0839] What happens: A SQL database query is run on the server to match the analysis data against a database of cases and identify matching symptoms.

[0840] Step 6:

[0841] The server evaluates the need for hospital visits based on the collation results.

[0842] Input: Case data matching results and judgment results.

[0843] Output: Assessment of need for hospital visit ("No abnormality", "Mild abnormality", "Severe abnormality").

[0844] Specific operation: The evaluation algorithm performs a rule-based evaluation based on the matching results and classifies them into the appropriate category.

[0845] Step 7:

[0846] The server notifies the user of the evaluation results.

[0847] Input: Assessment results of need for medical visit.

[0848] Output: A notification message to the user.

[0849] What it does: The server's notification system looks up the user's contact information and sends notification messages via a dedicated app, SMS, or email.

[0850] Step 8:

[0851] The server obtains the user's consent to send the analysis results and video data to the veterinary clinic as needed.

[0852] Input: User consent.

[0853] Output: The consent information is saved on the server.

[0854] Specific operation: A confirmation screen is displayed in the dedicated app, and if the user selects "Agree," the consent information is recorded on the server.

[0855] Step 9:

[0856] After obtaining the user's consent, the server sends the analysis results and video data to the veterinary clinic.

[0857] Input: User consent, analysis results, and video data.

[0858] Output: Send data to veterinary clinic.

[0859] What happens: The server sends the data to the veterinary clinic's system using a secure communication protocol (e.g., HTTPS).

[0860] This detailed processing step allows for real-time monitoring of the animal's health and rapid response.

[0861] (Application example 1)

[0862] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0863] The management of goods in logistics centers is extensive and complex, and is dependent on human resources, which can lead to reduced efficiency. Furthermore, when goods are misplaced or damaged, it takes time to discover the problem, making it difficult to quickly resolve the issue. To improve this situation, a system is needed that can quickly detect and notify abnormalities in goods.

[0864] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0865] In this invention, the server includes an image acquisition means for acquiring real-time image data of the items, a data analysis means including a generative AI model for analyzing the acquired image data, a comparison means for comparing the results of the analysis by the data analysis means with the item status data to determine whether or not an abnormality exists, and a notification means for notifying a manager of the results determined by the comparison means. This improves the efficiency of item management within the logistics center, making it possible to quickly detect abnormalities such as misplacement or damage and immediately notify the manager.

[0866] "Goods" is a general term for products, lumber, equipment, consumables, etc. that are subject to management at logistics centers, etc.

[0867] "Real-time video data" refers to video data that provides instant visual information on the current status of an item.

[0868] "Video acquisition means" refers to a device or method that uses a camera or sensor to collect real-time video data.

[0869] A "generative AI model" is an artificial intelligence model used to analyze video data, and specifically utilizes technologies such as deep learning.

[0870] "Data analysis means" refers to a device or method that uses a generative AI model to analyze acquired video data and extract abnormalities and features.

[0871] "Condition data" refers to data that includes reference information such as the correct placement of an item, its proper condition, and whether or not it is damaged.

[0872] The "comparison means" is a device or method that compares the features extracted by the data analysis means with the status data to determine whether or not there is an abnormality.

[0873] "Notification means" refers to a system or method for notifying the user or administrator of the judgment result, and specifically includes email, application notification, etc.

[0874] "Information sharing means" refers to a device or method for sharing analysis results and video data with relevant parties such as administrators after an abnormality is detected.

[0875] The present invention relates to a system for real-time management and abnormality detection of goods in a logistics center.

[0876] Video acquisition method

[0877] In this system, real-time video data of goods is first captured by cameras installed within the logistics center. The cameras monitor a wide area of ​​the logistics center and continuously collect video data. The video data is stored in a buffer at regular intervals, compressed as necessary, and sent to a server via the Internet.

[0878] Data Analysis Methods

[0879] The server stores the acquired video data on the cloud. A generative AI model is installed in the server and analyzes the video data. Specifically, the generative AI model (e.g., a deep learning model) extracts the location and condition of the item as features and detects whether or not there is an abnormality. For example, if an item is not in its designated location or if damage is observed, it is detected as an abnormality.

[0880] Matching method

[0881] The analyzed data is collated with pre-registered item status data. The server compares the analysis results with the status data to determine whether there are any abnormalities. If the collation results indicate an abnormality, the server immediately takes action based on that information.

[0882] Notification means

[0883] The phone server immediately notifies the administrator of the results of the verification process via email, SMS, or a dedicated app. For example, if damage or misplacement of an item is detected, the administrator will be notified that immediate correction is required and suggestions on how to address the issue will be provided.

[0884] Information sharing means

[0885] If necessary, the server can automatically transmit analysis results and video data to other management systems or personnel, ensuring secure transmission and processing according to pre-defined protocols.

[0886] Specific examples

[0887] For example, a camera captures images of items being arranged in their designated locations in a logistics center and sends the captured image to a server. On the server side, a generative AI model analyzes the video and detects if an item is in an abnormal position. Based on the analysis results, the server sends a notification to the administrator via a dedicated app saying, "The item is not in its designated location. Please check immediately." If necessary, the video data and analysis results can also be sent to other administrators or systems based on user settings.

[0888] Prompt Sentence Examples

[0889] The system analyzes surveillance camera footage to check whether items are scattered around the logistics center and notifies the user if any abnormalities are detected.

[0890] This invention realizes more efficient item management in logistics centers and enables rapid detection and response of abnormalities, thereby improving the operational efficiency of the entire logistics center and enabling early resolution of problems.

[0891] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0892] Step 1:

[0893] The camera device captures real-time video data of items in the logistics center.

[0894] Input: Image data of the item

[0895] Output: Buffered video data

[0896] How it works: Cameras are installed throughout the logistics center, capturing images periodically and temporarily storing them in a buffer. The data in the buffer is then periodically sent to a server.

[0897] Step 2:

[0898] The server receives the transmitted video data from the buffer.

[0899] Input: Video data sent from the camera device

[0900] Output: Video data stored on the cloud

[0901] Specific operation: The server receives video data sent from the camera at regular intervals and stores it in cloud storage, ensuring continuous data acquisition.

[0902] Step 3:

[0903] The server analyzes the video data using the generated AI model.

[0904] Input: Video data stored in the cloud

[0905] Output: Analysis results (item features and abnormality determination)

[0906] Specific operation: A generative AI model (e.g., a deep learning model) installed on the server extracts information about the condition and placement of items as features from the stored video data, and analyzes them to detect abnormal conditions.

[0907] Step 4:

[0908] The server compares the analysis results with the item's condition data.

[0909] Input: Analyzed features, state database

[0910] Output: Abnormality judgment result

[0911] Specific operation: The server compares the analyzed features with a pre-registered condition database to determine whether the item is normal or abnormal. If it is determined to be abnormal, it also generates detailed information about the abnormality.

[0912] Step 5:

[0913] The server notifies the administrator of the abnormality determination result.

[0914] Input: Abnormality detection result, administrator contact information

[0915] Output: Send notification message

[0916] Specific operation: Based on the result of the abnormality judgment, the server will send a message to the administrator using the configured notification method (email, SMS, dedicated app). The message will include the details of the abnormality and how to respond.

[0917] Step 6:

[0918] The server shares the analysis results and video data with other management systems and personnel.

[0919] Input: User settings, abnormality detection results, video data

[0920] Output: Shared analysis results and video data

[0921] Specific operation: If necessary, the server will share the analysis results and related video data with other management systems and personnel, securely according to pre-defined protocols.

[0922] These processing steps enable efficient real-time management of goods and abnormality detection in a logistics center.

[0923] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0924] The present invention combines a system that acquires and analyzes real-time video data of animals, compares it with case data to determine the need for hospital visits, and notifies the user, with an emotion engine that recognizes the user's emotions. This system mainly includes video acquisition means, data analysis means, comparison means, notification means, emotion engine, and, if necessary, information sharing means.

[0925] Video acquisition method

[0926] The device (pet camera) continuously captures real-time video data of the animal. The camera tracks the animal's movements and saves the data in a buffer every 5 seconds. Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet.

[0927] Data Analysis Methods

[0928] The server stores the received video data in the cloud. The server then analyzes the video data using a generative AI model (e.g., a deep learning model). The generative AI model extracts the animal's behavior and movements as features and detects abnormal behavior or symptoms. For example, if an animal is detected to be frequently licking its front paws, this can be recognized as an early symptom of inflammation.

[0929] Matching method

[0930] The server compares the data analysis results with a database of previously collected animal cases. Through the comparison, known conditions that may match the analysis data are identified. Based on the comparison results, the need for a hospital visit is assessed. The assessment is made in categories such as "no abnormality," "mild abnormality," and "severe abnormality."

[0931] Notification means

[0932] The server notifies the user of the results of the comparison. Notifications are sent via a dedicated app, SMS, or email. For example, if a "severe abnormality" is detected, the server will inform the user that an immediate visit to the veterinary clinic is necessary and provide information about the nearest veterinary clinic.

[0933] Emotion Engine

[0934] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine evaluates the user's emotional state when a notification is sent via the notification means to notify the user of a visit. If the engine determines that the user is feeling stressed, it adds a message or advice to the notification to ease the user's feelings. In addition, if necessary, the emotion data is sent to the veterinary clinic, helping the clinic to provide medical care that takes the user's emotional state into consideration.

[0935] Information sharing means

[0936] The server has the function to automatically send analysis results and video data to veterinary clinics when necessary. In this case, the user's consent is obtained before the data is sent. After obtaining the user's consent, the server securely transmits this data to the veterinary clinic. The veterinary clinic can refer to this data at the first consultation, enabling faster and more accurate diagnosis.

[0937] Specific examples

[0938] The pet camera captures real-time footage of the pet and sends it to a server. On the server side, a generative AI model analyzes the footage and detects behaviors such as the animal frequently licking its front paws. The results of this analysis are compared with a case database, and a high probability of early-stage dermatitis is determined.

[0939] Based on this result, the server sends a notification to the user's app saying, "A visit to the vet is necessary. Please go to a nearby veterinary clinic." At the same time, it also provides information about the nearest veterinary clinic.

[0940] Furthermore, if the emotion engine evaluates the user's emotions and determines that the pet is feeling stressed, the notification will include a message such as, "Do not panic. Take action. Get a proper diagnosis at a nearby veterinary clinic."

[0941] If necessary, with the user's consent, the analysis results and video data will be sent to the veterinary clinic. The veterinary clinic can then use this information to conduct an examination and provide the owner with appropriate medical treatment promptly. The user's emotional data is also shared, allowing them to respond in a way that takes into account the user's psychological state.

[0942] This system allows owners to quickly understand their pet's health condition and schedule timely visits to the hospital. This is expected to prevent pets from becoming seriously ill and reduce medical costs. It also enables notifications and treatment that take the user's emotions into consideration, reducing the mental burden on owners.

[0943] The processing flow will be explained below.

[0944] Step 1: Acquiring and transmitting video data

[0945] Device (Pet Camera):

[0946] The camera captures real-time footage of your pet.

[0947] Video data is saved in a buffer every 5 seconds.

[0948] Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet.

[0949] Step 2: Receiving and saving video data

[0950] server:

[0951] Receives video data sent from the terminal.

[0952] The received video data is stored in a database in chronological order.

[0953] Step 3: Analyzing the video data

[0954] server:

[0955] Loads saved video data.

[0956] Video data is analyzed using a generative AI model (deep learning model).

[0957] Extracts features of animal movements and behaviors to detect abnormal behaviors and symptoms.

[0958] For example, the behavior of an animal frequently licking its front paws is detected.

[0959] Step 4: Matching with case data

[0960] server:

[0961] The analysis results are compared with a case database.

[0962] Based on the comparison results, the need for outpatient treatment is evaluated and determined.

[0963] The evaluation is made in the categories of "no abnormality," "mild abnormality," and "severe abnormality."

[0964] Step 5: Notify users

[0965] server:

[0966] The result determined by the collation means is notified to the user.

[0967] Notifications will be sent via a dedicated app, SMS, or email.

[0968] If it is determined that a visit to the veterinary clinic is necessary, information about the nearest veterinary clinic will also be provided.

[0969] Step 6: Evaluate your emotions

[0970] server:

[0971] An emotion engine is used to assess the user's emotional state when a notification means notifies the user of a hospital visit.

[0972] If the emotion engine determines that the user is feeling stressed, the notification will include a message or advice to ease the user's feelings.

[0973] Step 7: Share information with hospitals

[0974] server:

[0975] Prepare to send analysis results and video data to the veterinary clinic, if necessary.

[0976] Obtain user consent before sending data.

[0977] Once the user's consent is obtained, the analysis results and video data are sent to the veterinary hospital.

[0978] The veterinary clinic confirms receipt of the data and sends a confirmation notice to the user.

[0979] Example 2

[0980] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0981] Pet owners face challenges in properly monitoring their pets' health and detecting abnormalities early. Even if they obtain information about their pet's health, it can be difficult to determine when to share that information with a veterinary clinic. Furthermore, there is a lack of systems that support pet owners in correctly understanding their pet's health information and responding appropriately without stress. Furthermore, there is a need for an efficient means of sharing information so that veterinary clinics can understand their pet's health status before an examination.

[0982] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0983] In this invention, the server includes a terminal that acquires real-time video data of the animal, a server that includes a generative AI model for analyzing the acquired video data, a server that compares the results of the analysis by the generative AI model with previously collected case data and determines the need for a veterinary visit, a server that notifies the user of the results determined by the comparison means, a server that includes an emotion recognition engine that evaluates the user's emotional state and adds a message that takes the user's emotions into consideration depending on the content of the notification, and an information sharing means that automatically transmits the analysis results and video data to a veterinary clinic as needed. This allows for quick and accurate monitoring of the pet's health condition, allowing owners to make timely decisions about when to visit the veterinary clinic. Furthermore, it reduces the psychological burden on owners and enables efficient information sharing with veterinary clinics.

[0984] "Real-time animal video data" refers to video data that records the current behavior and status of pets and other animals.

[0985] A "terminal" is a device that includes a camera and sensors for acquiring real-time video data of animals.

[0986] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to analyze and classify acquired video data.

[0987] A "server" is a central control unit that analyzes data, stores results, and notifies users and other systems.

[0988] "Data analysis" is the process of extracting features from the acquired video data and detecting abnormal behavior or symptoms.

[0989] "Matching" is the process of comparing analysis results with previously collected case data to identify possible matching symptoms.

[0990] "Notification" is a means of communication to inform the user of the results of analysis and matching.

[0991] The "emotion recognition engine" is a program that evaluates the user's emotional state and adds an appropriate message depending on the notification content.

[0992] The "information sharing means" refers to a communication device or method for transmitting analysis results and video data to a third party such as a veterinary clinic as needed.

[0993] "Necessity of medical visits" refers to the degree to which a pet's health condition is deemed to require a visit to a veterinary hospital.

[0994] MODE FOR CARRYING OUT THE INVENTION

[0995] System Configuration

[0996] This invention is a system that acquires real-time video data of animals, analyzes it, and compares it with case data to determine the need for medical treatment and notify the user. This system has three main components: a terminal (pet camera), a server, and a user.

[0997] Device (Pet Camera)

[0998] The terminal is a device that includes a camera to capture real-time video data of the animal. The camera on the terminal tracks the animal's movements and stores the data in a buffer every 5 seconds. The video data in the buffer is compressed every 10 minutes and sent to a server via the Internet. The hardware used is a commercially available high-performance pet camera, and it is possible to use, for example, H.264 video compression technology.

[0999] server

[1000] The server stores the received video data in the cloud and analyzes the data using a generative AI model. The software used is the deep learning frameworks TensorFlow and PyTorch. The generative AI model extracts the animal's behavior and movements as features and detects abnormal behavior or symptoms. For example, if an animal is detected to be frequently licking its front paws, it will recognize this as an early symptom of inflammation.

[1001] Data analysis

[1002] The server then compares the analysis results with previously collected case data to identify potential matching symptoms. This involves using an SQL database to match the analysis results' features with known symptoms in the case database. Based on the results, the server assesses whether the patient needs to visit the hospital, categorizing them as "no abnormality," "mild abnormality," or "severe abnormality."

[1003] Notification means

[1004] The server notifies the user of the evaluation results. Specifically, it notifies the user via a dedicated application, SMS, or email. For example, if the result is a "severe abnormality," the user will be notified that "immediate medical attention is required." Information about the nearest veterinary clinic will also be provided.

[1005] Emotion Recognition Engine

[1006] The server also includes an emotion recognition engine that recognizes the user's emotions. This engine evaluates the user's emotional state when a hospital visit notification is sent via the notification means. Emotion recognition can utilize the Sentiment Analysis API. If it is determined that the user is feeling stressed, a message such as "Don't panic, take action" is added to the notification.

[1007] Information sharing means

[1008] The server has an information sharing mechanism that automatically sends analysis results and video data to veterinary clinics as needed. This mechanism sends data encrypted using SSL / TLS with the user's consent. Veterinary clinics can then make a quick and accurate diagnosis based on the received data.

[1009] user

[1010] Through this system, users can keep track of their pet's health in real time. For example, if their pet is frequently licking its front paws, the system will notify the user, "Your pet needs medical attention. Please go to a nearby veterinary clinic." Furthermore, if the emotion recognition engine detects stress in the user, a message such as "Don't panic, act accordingly" will be added to the notification.

[1011] Specific examples

[1012] The pet camera captures real-time footage of the pet and sends it to a server. On the server side, a generative AI model analyzes the footage and detects behaviors such as the animal frequently licking its front paws. The results of this analysis are compared with a case database, and a high probability of early-stage dermatitis is determined.

[1013] Based on these results, the server sends a notification to the user via a dedicated app saying, "A visit to the vet is necessary. Please go to a nearby veterinary clinic." At the same time, it also provides information about the nearest veterinary clinic. Furthermore, if the emotion engine evaluates the user's emotions and determines that the user is feeling stressed, the notification will include a message such as, "Do not panic. Take action. Get a proper diagnosis at a nearby veterinary clinic."

[1014] If necessary, with the user's consent, the analysis results and video data are sent to the veterinary hospital. The veterinary hospital can use this information to conduct an examination and provide the owner with appropriate medical treatment promptly. In addition, the user's emotional data is also shared, allowing for responses that take into account the user's psychological state. This system allows owners to quickly understand their pet's health condition and ensure appropriate visits to the vet. This is expected to prevent pets from becoming seriously ill and reduce medical costs. It also enables notifications and treatment that take the user's emotions into consideration, which has the effect of reducing the mental burden on owners.

[1015] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1016] Step 1:

[1017] The terminal (pet camera) acquires real-time video data of the animal. As input, it has the video data from the camera. The camera tracks the animal's movements and saves the video data in a buffer every 5 seconds. This allows the video data of the animal's behavior and status to be accumulated in the buffer.

[1018] Step 2:

[1019] The terminal compresses the video data in the buffer every 10 minutes and sends it to the server via the Internet. The input here is the raw video data stored in the buffer. The data is compressed using H.264 video compression technology, and the compressed video data is sent to the server as the output.

[1020] Step 3:

[1021] The server stores the received compressed video data in the cloud. The input is the compressed video data sent from the device. The server stores the data using a cloud storage service (e.g., Amazon S3 or Google Cloud Storage), and the output is the data stored in the cloud.

[1022] Step 4:

[1023] The server analyzes video data stored on the cloud using a generative AI model. The input is the stored video data. The generative AI model uses TensorFlow and PyTorch to extract features representing the animal's behavior and state, and detects abnormal behavior and symptoms. The output is the analysis results. For example, if the model detects that an animal is frequently licking its front paws, it will identify this as an early symptom of inflammation.

[1024] Step 5:

[1025] The server compares the analysis results obtained by the generative AI model with previously collected case data. The inputs are the analysis results and the case database. An SQL database is used to match the features of the analysis results with known symptoms in the case database. The output identifies symptoms that may match the analysis results.

[1026] Step 6:

[1027] The server evaluates the need for outpatient care based on the analysis results and the comparison results of the case data. The input is the comparison results. The need for outpatient care is evaluated in categories such as "no abnormality," "mild abnormality," and "severe abnormality." The output is the evaluation result regarding the need for outpatient care.

[1028] Step 7:

[1029] The server notifies the user of the assessment results regarding the need for medical attention. The inputs are the assessment results and the user's contact information. The notification is sent via a dedicated app, SMS, or email, and conveys a message to the user such as "An immediate medical visit is required." The output is a notification sent to the user.

[1030] Step 8:

[1031] The server uses an emotion recognition engine to evaluate the user's emotional state. The input is the notification content and the user's reaction data. The emotion recognition engine (e.g., Sentiment Analysis API) is used to evaluate the user's emotion, and the output is whether the user is feeling stressed. If necessary, a message such as "Don't panic, take action" is added to the notification content.

[1032] Step 9:

[1033] The server sends the analysis results and video data to the veterinary hospital as needed. The input is the analysis results and the user's consent. The data is encrypted using SSL / TLS and sent securely to the veterinary hospital. The output is the data sent to the veterinary hospital. The veterinary hospital can use this data as a reference to make a quick and accurate diagnosis.

[1034] (Application example 2)

[1035] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1036] Conventional pet monitoring systems often overlooked abnormal behavior or symptoms because they did not provide a means to regularly check an animal's behavior. This meant that opportunities for early and appropriate medical treatment could be missed, making them insufficient for protecting a pet's health. Furthermore, even if a user noticed something unusual about their pet, there were few ways to quickly obtain appropriate advice or information, and the system was unable to respond to the user's emotions. Furthermore, there was no function to display advertisements linked to the pet's health status, making it difficult to access health care products and information.

[1037] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an optical device that acquires real-time video data of the animal, an information processing device including a generative AI model for analyzing the acquired video data, a comparison means that compares the results of the analysis by the information processing device with the animal's case data and determines the need for medical treatment, a display device that notifies the user of the results determined by the comparison means, and a promotion means that displays advertisements related to the pet's health condition and behavior. This makes it possible to monitor the pet's health condition in real time and promptly notify the user if an abnormality is detected. In addition, displaying advertisements for products and services related to the pet's health condition makes it easier for the user to access appropriate care products and medical services. It is also possible to display messages that take the user's emotions into consideration, thereby reducing the psychological burden on the owner.

[1038] "Optical devices" is a general term for cameras and sensor devices used to acquire real-time video data of animals.

[1039] An "information processing device" is a computer device equipped with a generative AI model for analyzing acquired video data.

[1040] The "comparison means" is a function for comparing the results of analysis by the information processing device with the animal's case data and determining the need for hospital visits.

[1041] A "display device" is a screen or mobile device that notifies the user of the results determined by the comparison means.

[1042] "Promotional tools" are features for displaying advertisements related to pet health and behavior.

[1043] "Data sharing means" is a function that automatically transmits video data and analysis results to veterinary medical facilities.

[1044] This invention provides a system that acquires real-time video data of pets, analyzes it using a generative AI model to detect abnormal behavior and symptoms, notifies the user based on the data, and displays advertisements linked to the pet's health status.

[1045] The server uses optical devices, such as IP cameras and smart cameras, to capture real-time video data of animals, tracking pet movements every five seconds and compressing the video data and sending it to the cloud every ten minutes.

[1046] The server analyzes the captured video data using a generative AI model in the cloud. A deep learning model, for example, is used as the generative AI model, extracting animal behavior and movements as features and identifying abnormal behavior and symptoms. Machine learning libraries such as TensorFlow are used for this analysis.

[1047] The results of the video data analysis are collated with a database of animal cases collected in advance. An algorithm is used to compare the analysis results with the case database and determine whether or not a visit to the hospital is necessary. This results in an assessment into categories such as "no abnormalities," "mild abnormalities," or "severe abnormalities."

[1048] The server notifies the user of the results of the collation process via a dedicated app, SMS, or email. For example, if a "severe abnormality" is detected, the server will send a message urging the user to visit a veterinarian immediately, along with information about the nearest veterinary clinic.

[1049] As a promotional tool, users will be shown advertisements related to their pet's health. For example, if a pet is detected licking its paws frequently, advertisements for skin care products or veterinary clinics will be displayed. The app also has an emotion engine that recognizes the user's emotions, and if the user is feeling stressed, a comforting message will be added to the notification.

[1050] As a specific example, a pet camera captures video of a pet in real time and sends it to a server. A generative AI model on the server analyzes the video and detects behaviors such as the animal frequently licking its front paws. This analysis result is compared with a case database, and if early symptoms of dermatitis are determined, a notification is sent to the user's smartphone saying, "A visit to the nearest veterinary clinic is required. Please go to a nearby veterinary clinic." At the same time, an emotion engine evaluates the user's emotions and adds a comforting message such as, "Don't panic. Please go to a nearby veterinary clinic and receive a proper diagnosis."

[1051] An example of a prompt is as follows:

[1052] "Real-time video data of animals is acquired and analyzed with a generative AI model to detect abnormal behavior. The analysis results are compared with case data to determine the need for medical attention and notify the user. The system evaluates the user's emotions to add appropriate messages and display pet-related advertisements."

[1053] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1054] Step 1:

[1055] The server receives video data from optical devices (such as IP cameras) in real time. The input is the video signal from the optical device, and the output is the temporarily stored video data. Specifically, the IP camera tracks the animal's movements and stores the video data in a buffer every 5 seconds.

[1056] Step 2:

[1057] The server compresses the video data in the buffer every 10 minutes and sends it to the cloud. The input is the temporarily stored video data, and the output is the compressed video data. Specifically, the video data is compressed in H.264 format or similar and uploaded to the cloud server via the Internet.

[1058] Step 3:

[1059] The server analyzes the received video data using a generative AI model (e.g., a deep learning model) in the cloud. The input is compressed video data, and the output is analyzed feature data. Specifically, it uses machine learning libraries such as TensorFlow to extract features based on the animal's behavior and movements, and identifies abnormal behavior and symptoms.

[1060] Step 4:

[1061] The server compares the analysis results with the case database. The input is the analyzed feature data, and the output is the comparison result. Specifically, it matches the analysis results with known symptoms stored in the case database and evaluates the need for hospital visits.

[1062] Step 5:

[1063] The server sends a notification to the user based on the matching results. The input is the matching result, and the output is a notification message to the user. Specifically, it sends a notification such as "You need to visit the hospital" to the user's smartphone or email. If the user is feeling stressed, it also adds a comforting message based on the evaluation by the emotion engine.

[1064] Step 6:

[1065] The server displays advertisements related to the pet's health condition and behavior. The input is the analysis results, and the output is advertisement display information. Specifically, advertisements that match the symptoms and behaviors exhibited by the pet (for example, information about pet skin care products or veterinary clinics) are displayed on the user's smartphone.

[1066] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1067] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1068] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1069] [Fourth embodiment]

[1070] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1071] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1072] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1073] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1074] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1075] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1076] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1077] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1078] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1079] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1080] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1081] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1082] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1083] The present invention is a system that acquires and analyzes real-time video data of animals, compares it with case data, determines the need for hospital visits, and notifies the user. This system mainly includes video acquisition means, data analysis means, comparison means, notification means, and, if necessary, information sharing means.

[1084] Video acquisition method

[1085] The device (pet camera) continuously captures real-time video data of the animal. The camera tracks the animal's movements and saves the data in a buffer every 5 seconds. Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet.

[1086] Data Analysis Methods

[1087] The server stores the received video data in the cloud. The server then analyzes the video data using a generative AI model (e.g., a deep learning model). The generative AI model extracts the animal's behavior and movements as features and detects abnormal behavior or symptoms. For example, if an animal is detected to be frequently licking its front paws, this can be recognized as an early symptom of inflammation.

[1088] Matching method

[1089] The server compares the data analysis results with a database of previously collected animal cases. Through the comparison, known conditions that may match the analysis data are identified. Based on the comparison results, the need for a hospital visit is assessed. The assessment is made in categories such as "no abnormality," "mild abnormality," and "severe abnormality."

[1090] Notification means

[1091] The server notifies the user of the results of the comparison. Notifications are sent via a dedicated app, SMS, or email. For example, if a "severe abnormality" is detected, the server will inform the user that an immediate visit to the veterinary clinic is necessary and provide information about the nearest veterinary clinic.

[1092] Information sharing means

[1093] The server has the function to automatically send analysis results and video data to veterinary clinics when necessary. In this case, the user's consent is obtained before the data is sent. After obtaining the user's consent, the server securely transmits this data to the veterinary clinic. The veterinary clinic can refer to this data at the first consultation, enabling faster and more accurate diagnosis.

[1094] Specific examples

[1095] The pet camera captures real-time footage of the pet and sends it to a server. On the server side, a generative AI model analyzes the footage and detects behaviors such as the animal frequently licking its front paws. This analysis result is compared with a case database and determines that the animal may be in the early stages of dermatitis.

[1096] Based on this result, the server sends a notification to the user's app saying, "A visit to the vet is necessary. Please go to a nearby veterinary clinic." At the same time, it also provides information about the nearest veterinary clinic.

[1097] If necessary, with the user's consent, the analysis results and video data will be sent to the veterinary clinic, which can then use this information to conduct an examination and provide the owner with the appropriate medical treatment promptly.

[1098] This system allows owners to quickly understand their pet's health condition and schedule timely visits to the hospital, which is expected to prevent pets from becoming seriously ill and reduce medical costs.

[1099] The processing flow will be explained below.

[1100] Step 1: Acquiring and transmitting video data

[1101] Device (Pet Camera):

[1102] The camera captures real-time footage of your pet.

[1103] Video data is saved in a buffer every 5 seconds.

[1104] Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet.

[1105] Step 2: Receiving and saving video data

[1106] server:

[1107] Receives video data sent from the terminal.

[1108] The received video data is stored in a database in chronological order.

[1109] Step 3: Analyzing the video data

[1110] server:

[1111] Loads saved video data.

[1112] Video data is analyzed using a generative AI model (deep learning model).

[1113] Extracts features of animal movements and behaviors to detect abnormal behaviors and symptoms.

[1114] For example, detecting whether an animal is frequently licking its front paws.

[1115] Step 4: Matching with case data

[1116] server:

[1117] The analysis results are compared with a case database.

[1118] Based on the comparison results, the need for outpatient treatment is evaluated and determined.

[1119] The evaluation is made in the categories of "no abnormality," "mild abnormality," and "severe abnormality."

[1120] Step 5: Notify users

[1121] server:

[1122] The result determined by the collation means is notified to the user.

[1123] Notifications will be sent via a dedicated app, SMS, or email.

[1124] If it is determined that a visit to the veterinary clinic is necessary, information about the nearest veterinary clinic will also be provided.

[1125] Step 6: Share information with hospitals

[1126] server:

[1127] Prepare to send analysis results and video data to the veterinary clinic, if necessary.

[1128] Obtain user consent before sending data.

[1129] Once the user's consent is obtained, the analysis results and video data are sent to the veterinary hospital.

[1130] The veterinary clinic confirms receipt of the data and sends a confirmation notice to the user.

[1131] Example 1

[1132] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1133] Today's busy pet owners find it difficult to constantly monitor their pets' health, so they need prompt medical treatment through early detection of abnormalities. Even if you discover abnormal behavior in your pet, it is often difficult to determine whether it is a problem that warrants a visit to the veterinary hospital. Furthermore, if you are unable to properly determine the need for a visit to the veterinary hospital, you may end up spending excessive medical expenses or, conversely, it may be too late.

[1134] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1135] In this invention, the server includes a means for acquiring real-time video data of the animal, a means for transmitting the acquired video data via the Internet, and a means for storing the transmitted video data in the cloud, thereby enabling the user to remotely monitor the health condition of their pet, quickly detect abnormalities, and take the pet to the vet at the appropriate time.

[1136] "Animal" refers to living creatures such as pets and livestock, and specifically includes dogs and cats kept within the home.

[1137] "Real-time video data" refers to data that captures the current state of an animal as video sequentially and can be displayed without delay.

[1138] "Image acquisition means" refers to a system or device that has the function of acquiring images of animals in real time using a device such as a camera.

[1139] The "means for transmitting via the Internet" is a function for transmitting the acquired video data to another device or server via an Internet line.

[1140] "Means for storing on the cloud" refers to the function of storing acquired video data in a cloud storage service via the Internet.

[1141] A "generative AI model" refers to an algorithm that uses machine learning or deep learning techniques to analyze data and detect specific patterns or anomalies.

[1142] "Data analysis means" refers to a system or software that has the function of analyzing video data stored on the cloud and evaluating the behavior and condition of animals.

[1143] The "collation means" is a system or device that has the function of comparing the analyzed data with existing case data and determining the type and degree of abnormality.

[1144] "Notification means" refers to the means for informing the user of the results of the analysis and matching, and may include a dedicated app, SMS, or email.

[1145] An "information sharing means" is a system or device that has the function of transmitting analysis results and video data to a third-party institution such as a veterinary clinic with the user's consent.

[1146] The present invention provides a system that acquires and analyzes real-time video data of an animal, compares it with case data, determines the need for a hospital visit, and notifies the user. This system includes a video acquisition unit, a data analysis unit, a comparison unit, a notification unit, and an information sharing unit. An example of each unit is described in detail below.

[1147] Video acquisition method

[1148] The device (pet camera) continuously captures real-time video data of animals. When the device's built-in camera detects animal movement, it automatically starts recording and saves the video data in a buffer every 5 seconds. Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet. Specifically, the data is compressed in JPEG format, and the Wi-Fi module sends the compressed data to the server.

[1149] Data Analysis Methods

[1150] The server stores the received video data in the cloud. At this time, the server's storage system writes the data to cloud storage. The server then analyzes the video data using a generative AI model (e.g., a deep learning model). The generative AI model uses libraries such as TensorFlow to extract animal behavior and movements as features and detect abnormal behavior and symptoms. Specifically, a Python script analyzes the animal's movements and behavior.

[1151] Matching method

[1152] The server compares the data analysis results with a database of pre-collected animal cases. An SQL database query on the server collates the analysis results and identifies matching symptoms. The comparison identifies known symptoms that the analysis data may match and assesses the need for a medical visit. The assessment is made in categories such as "no abnormality," "mild abnormality," or "severe abnormality."

[1153] Notification means

[1154] The server notifies the user of the results of the collation process. Notifications are sent via a dedicated app, SMS, or email. The server's notification system references the user's contact information and sends a notification message. For example, if the pet is judged to have a "severe abnormality," the server will inform the user that they need to visit a veterinarian immediately and provide information about the nearest veterinary clinic.

[1155] Information sharing means

[1156] The server has the ability to automatically send analysis results and video data to veterinary clinics when necessary. In this case, the user's consent is obtained before the data is sent, and a confirmation screen is displayed in the dedicated app. If the user selects "Agree," the consent information is stored on the server. The server then sends the data to the veterinary clinic's system using a secure communication protocol (e.g., HTTPS).

[1157] Specific examples

[1158] The pet camera captures real-time footage of the pet and sends it to a server. On the server side, a generative AI model analyzes the footage and detects behaviors such as the animal frequently licking its front paws. This analysis result is compared with a case database and determines that the animal may be in the early stages of dermatitis.

[1159] Based on these results, the server sends a notification to the user via a dedicated app saying, "A visit to the veterinary clinic is necessary. Please go to a nearby veterinary clinic." At the same time, it also provides information about the nearest veterinary clinic. If necessary, with the user's consent, it sends the analysis results and video data to the veterinary clinic. The veterinary clinic can then use this information to conduct an examination and provide the owner with the appropriate medical treatment promptly.

[1160] In this way, the system of the present invention allows users to quickly understand the health condition of their pets and realize timely visits to the hospital, which is expected to prevent the pet's condition from becoming serious and reduce medical costs.

[1161] Prompt Sentence Examples

[1162] "Please explain the design of the generative AI model that analyzes real-time video data of pets and detects abnormal behavior. Please also explain in detail how the results are notified to the user."

[1163] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1164] Step 1:

[1165] The device (pet camera) captures real-time video data of the animal. When the camera detects animal movement, it stores the video data in a buffer every 5 seconds.

[1166] Input: Detect animal movement.

[1167] Output: Video data is stored in a buffer every 5 seconds.

[1168] How it works: When the device's built-in sensor detects animal movement, the camera starts recording, and the recorded footage is saved to a local buffer every 5 seconds.

[1169] Step 2:

[1170] The device compresses the video data in the buffer every 10 minutes and sends it to a server via the Internet.

[1171] Input: 10 minutes of accumulated video data.

[1172] Output: The compressed video data is sent to the server.

[1173] How it works: The device's built-in compressor compresses the video data into JPEG format, and then the Wi-Fi module sends the compressed data to the server.

[1174] Step 3:

[1175] The server stores the received video data on the cloud.

[1176] Input: Compressed video data.

[1177] Output: Video data saved in cloud storage.

[1178] Specific operation: The server's storage system decodes the received data and writes it to cloud storage.

[1179] Step 4:

[1180] The server uses a generative AI model to analyze the stored video data.

[1181] Input: Video data stored in cloud storage.

[1182] Output: Analysis results (detection of animal behavior patterns and abnormal behavior).

[1183] How it works: A Python script runs on the server and uses libraries such as TensorFlow to execute a deep learning model, analyzing each frame of video data, extracting features, and detecting abnormal behavior.

[1184] Step 5:

[1185] The server compares the results of the data analysis with a database of animal cases.

[1186] Input: Analysis results.

[1187] Output: Matching results with case data and judgment results.

[1188] What happens: A SQL database query is run on the server to match the analysis data against a database of cases and identify matching symptoms.

[1189] Step 6:

[1190] The server evaluates the need for hospital visits based on the collation results.

[1191] Input: Case data matching results and judgment results.

[1192] Output: Assessment of need for hospital visit ("No abnormality", "Mild abnormality", "Severe abnormality").

[1193] Specific operation: The evaluation algorithm performs a rule-based evaluation based on the matching results and classifies them into the appropriate category.

[1194] Step 7:

[1195] The server notifies the user of the evaluation results.

[1196] Input: Assessment results of need for medical visit.

[1197] Output: A notification message to the user.

[1198] What it does: The server's notification system looks up the user's contact information and sends notification messages via a dedicated app, SMS, or email.

[1199] Step 8:

[1200] The server obtains the user's consent to send the analysis results and video data to the veterinary clinic as needed.

[1201] Input: User consent.

[1202] Output: The consent information is saved on the server.

[1203] Specific operation: A confirmation screen is displayed in the dedicated app, and if the user selects "Agree," the consent information is recorded on the server.

[1204] Step 9:

[1205] After obtaining the user's consent, the server sends the analysis results and video data to the veterinary clinic.

[1206] Input: User consent, analysis results, and video data.

[1207] Output: Send data to veterinary clinic.

[1208] What happens: The server sends the data to the veterinary clinic's system using a secure communication protocol (e.g., HTTPS).

[1209] This detailed processing step allows for real-time monitoring of the animal's health and rapid response.

[1210] (Application example 1)

[1211] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1212] The management of goods in logistics centers is extensive and complex, and is dependent on human resources, which can lead to reduced efficiency. Furthermore, when goods are misplaced or damaged, it takes time to discover the problem, making it difficult to quickly resolve the issue. To improve this situation, a system is needed that can quickly detect and notify abnormalities in goods.

[1213] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1214] In this invention, the server includes an image acquisition means for acquiring real-time image data of the items, a data analysis means including a generative AI model for analyzing the acquired image data, a comparison means for comparing the results of the analysis by the data analysis means with the item status data to determine whether or not an abnormality exists, and a notification means for notifying a manager of the results determined by the comparison means. This improves the efficiency of item management within the logistics center, making it possible to quickly detect abnormalities such as misplacement or damage and immediately notify the manager.

[1215] "Goods" is a general term for products, lumber, equipment, consumables, etc. that are subject to management at logistics centers, etc.

[1216] "Real-time video data" refers to video data that provides instant visual information on the current status of an item.

[1217] "Video acquisition means" refers to a device or method that uses a camera or sensor to collect real-time video data.

[1218] A "generative AI model" is an artificial intelligence model used to analyze video data, and specifically utilizes technologies such as deep learning.

[1219] "Data analysis means" refers to a device or method that uses a generative AI model to analyze acquired video data and extract abnormalities and features.

[1220] "Condition data" refers to data that includes reference information such as the correct placement of an item, its proper condition, and whether or not it is damaged.

[1221] The "comparison means" is a device or method that compares the features extracted by the data analysis means with the status data to determine whether or not there is an abnormality.

[1222] "Notification means" refers to a system or method for notifying the user or administrator of the judgment result, and specifically includes email, application notification, etc.

[1223] "Information sharing means" refers to a device or method for sharing analysis results and video data with relevant parties such as administrators after an abnormality is detected.

[1224] The present invention relates to a system for real-time management and abnormality detection of goods in a logistics center.

[1225] Video acquisition method

[1226] In this system, real-time video data of goods is first captured by cameras installed within the logistics center. The cameras monitor a wide area of ​​the logistics center and continuously collect video data. The video data is stored in a buffer at regular intervals, compressed as necessary, and sent to a server via the Internet.

[1227] Data Analysis Methods

[1228] The server stores the acquired video data on the cloud. A generative AI model is installed in the server and analyzes the video data. Specifically, the generative AI model (e.g., a deep learning model) extracts the location and condition of the item as features and detects whether or not there is an abnormality. For example, if an item is not in its designated location or if damage is observed, it is detected as an abnormality.

[1229] Matching method

[1230] The analyzed data is collated with pre-registered item status data. The server compares the analysis results with the status data to determine whether there are any abnormalities. If the collation results indicate an abnormality, the server immediately takes action based on that information.

[1231] Notification means

[1232] The phone server immediately notifies the administrator of the results of the verification process via email, SMS, or a dedicated app. For example, if damage or misplacement of an item is detected, the administrator will be notified that immediate correction is required and suggestions on how to address the issue will be provided.

[1233] Information sharing means

[1234] If necessary, the server can automatically transmit analysis results and video data to other management systems or personnel, ensuring secure transmission and processing according to pre-defined protocols.

[1235] Specific examples

[1236] For example, a camera captures images of items being arranged in their designated locations in a logistics center and sends the captured image to a server. On the server side, a generative AI model analyzes the video and detects if an item is in an abnormal position. Based on the analysis results, the server sends a notification to the administrator via a dedicated app saying, "The item is not in its designated location. Please check immediately." If necessary, the video data and analysis results can also be sent to other administrators or systems based on user settings.

[1237] Prompt Sentence Examples

[1238] The system analyzes surveillance camera footage to check whether items are scattered around the logistics center and notifies the user if any abnormalities are detected.

[1239] This invention realizes more efficient item management in logistics centers and enables rapid detection and response of abnormalities, thereby improving the operational efficiency of the entire logistics center and enabling early resolution of problems.

[1240] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1241] Step 1:

[1242] The camera device captures real-time video data of items in the logistics center.

[1243] Input: Image data of the item

[1244] Output: Buffered video data

[1245] How it works: Cameras are installed throughout the logistics center, capturing images periodically and temporarily storing them in a buffer. The data in the buffer is then periodically sent to a server.

[1246] Step 2:

[1247] The server receives the transmitted video data from the buffer.

[1248] Input: Video data sent from the camera device

[1249] Output: Video data stored on the cloud

[1250] Specific operation: The server receives video data sent from the camera at regular intervals and stores it in cloud storage, ensuring continuous data acquisition.

[1251] Step 3:

[1252] The server analyzes the video data using the generated AI model.

[1253] Input: Video data stored in the cloud

[1254] Output: Analysis results (item features and abnormality determination)

[1255] Specific operation: A generative AI model (e.g., a deep learning model) installed on the server extracts information about the condition and placement of items as features from the stored video data, and analyzes them to detect abnormal conditions.

[1256] Step 4:

[1257] The server compares the analysis results with the item's condition data.

[1258] Input: Analyzed features, state database

[1259] Output: Abnormality judgment result

[1260] Specific operation: The server compares the analyzed features with a pre-registered condition database to determine whether the item is normal or abnormal. If it is determined to be abnormal, it also generates detailed information about the abnormality.

[1261] Step 5:

[1262] The server notifies the administrator of the abnormality determination result.

[1263] Input: Abnormality detection result, administrator contact information

[1264] Output: Send notification message

[1265] Specific operation: Based on the result of the abnormality judgment, the server will send a message to the administrator using the configured notification method (email, SMS, dedicated app). The message will include the details of the abnormality and how to respond.

[1266] Step 6:

[1267] The server shares the analysis results and video data with other management systems and personnel.

[1268] Input: User settings, abnormality detection results, video data

[1269] Output: Shared analysis results and video data

[1270] Specific operation: If necessary, the server will share the analysis results and related video data with other management systems and personnel, securely according to pre-defined protocols.

[1271] These processing steps enable efficient real-time management of goods and abnormality detection in a logistics center.

[1272] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1273] The present invention combines a system that acquires and analyzes real-time video data of animals, compares it with case data to determine the need for hospital visits, and notifies the user, with an emotion engine that recognizes the user's emotions. This system mainly includes video acquisition means, data analysis means, comparison means, notification means, emotion engine, and, if necessary, information sharing means.

[1274] Video acquisition method

[1275] The device (pet camera) continuously captures real-time video data of the animal. The camera tracks the animal's movements and saves the data in a buffer every 5 seconds. Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet.

[1276] Data Analysis Methods

[1277] The server stores the received video data in the cloud. The server then analyzes the video data using a generative AI model (e.g., a deep learning model). The generative AI model extracts the animal's behavior and movements as features and detects abnormal behavior or symptoms. For example, if an animal is detected to be frequently licking its front paws, this can be recognized as an early symptom of inflammation.

[1278] Matching method

[1279] The server compares the data analysis results with a database of previously collected animal cases. Through the comparison, known conditions that may match the analysis data are identified. Based on the comparison results, the need for a hospital visit is assessed. The assessment is made in categories such as "no abnormality," "mild abnormality," and "severe abnormality."

[1280] Notification means

[1281] The server notifies the user of the results of the comparison. Notifications are sent via a dedicated app, SMS, or email. For example, if a "severe abnormality" is detected, the server will inform the user that an immediate visit to the veterinary clinic is necessary and provide information about the nearest veterinary clinic.

[1282] Emotion Engine

[1283] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine evaluates the user's emotional state when a notification is sent via the notification means to notify the user of a visit. If the engine determines that the user is feeling stressed, it adds a message or advice to the notification to ease the user's feelings. In addition, if necessary, the emotion data is sent to the veterinary clinic, helping the clinic to provide medical care that takes the user's emotional state into consideration.

[1284] Information sharing means

[1285] The server has the function to automatically send analysis results and video data to veterinary clinics when necessary. In this case, the user's consent is obtained before the data is sent. After obtaining the user's consent, the server securely transmits this data to the veterinary clinic. The veterinary clinic can refer to this data at the first consultation, enabling faster and more accurate diagnosis.

[1286] Specific examples

[1287] The pet camera captures real-time footage of the pet and sends it to a server. On the server side, a generative AI model analyzes the footage and detects behaviors such as the animal frequently licking its front paws. The results of this analysis are compared with a case database, and a high probability of early-stage dermatitis is determined.

[1288] Based on this result, the server sends a notification to the user's app saying, "A visit to the vet is necessary. Please go to a nearby veterinary clinic." At the same time, it also provides information about the nearest veterinary clinic.

[1289] Furthermore, if the emotion engine evaluates the user's emotions and determines that the pet is feeling stressed, the notification will include a message such as, "Do not panic. Take action. Get a proper diagnosis at a nearby veterinary clinic."

[1290] If necessary, with the user's consent, the analysis results and video data will be sent to the veterinary clinic. The veterinary clinic can then use this information to conduct an examination and provide the owner with appropriate medical treatment promptly. The user's emotional data is also shared, allowing them to respond in a way that takes into account the user's psychological state.

[1291] This system allows owners to quickly understand their pet's health condition and schedule timely visits to the hospital. This is expected to prevent pets from becoming seriously ill and reduce medical costs. It also enables notifications and treatment that take the user's emotions into consideration, reducing the mental burden on owners.

[1292] The processing flow will be explained below.

[1293] Step 1: Acquiring and transmitting video data

[1294] Device (Pet Camera):

[1295] The camera captures real-time footage of your pet.

[1296] Video data is saved in a buffer every 5 seconds.

[1297] Every 10 minutes, the video data in the buffer is compressed and sent to a server via the Internet.

[1298] Step 2: Receiving and saving video data

[1299] server:

[1300] Receives video data sent from the terminal.

[1301] The received video data is stored in a database in chronological order.

[1302] Step 3: Analyzing the video data

[1303] server:

[1304] Loads saved video data.

[1305] Video data is analyzed using a generative AI model (deep learning model).

[1306] Extracts features of animal movements and behaviors to detect abnormal behaviors and symptoms.

[1307] For example, the behavior of an animal frequently licking its front paws is detected.

[1308] Step 4: Matching with case data

[1309] server:

[1310] The analysis results are compared with a case database.

[1311] Based on the comparison results, the need for outpatient treatment is evaluated and determined.

[1312] The evaluation is made in the categories of "no abnormality," "mild abnormality," and "severe abnormality."

[1313] Step 5: Notify users

[1314] server:

[1315] The result determined by the collation means is notified to the user.

[1316] Notifications will be sent via a dedicated app, SMS, or email.

[1317] If it is determined that a visit to the veterinary clinic is necessary, information about the nearest veterinary clinic will also be provided.

[1318] Step 6: Evaluate your emotions

[1319] server:

[1320] An emotion engine is used to assess the user's emotional state when a notification means notifies the user of a hospital visit.

[1321] If the emotion engine determines that the user is feeling stressed, the notification will include a message or advice to ease the user's feelings.

[1322] Step 7: Share information with hospitals

[1323] server:

[1324] Prepare to send analysis results and video data to the veterinary clinic, if necessary.

[1325] Obtain user consent before sending data.

[1326] Once the user's consent is obtained, the analysis results and video data are sent to the veterinary hospital.

[1327] The veterinary clinic confirms receipt of the data and sends a confirmation notice to the user.

[1328] Example 2

[1329] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1330] Pet owners face challenges in properly monitoring their pets' health and detecting abnormalities early. Even if they obtain information about their pet's health, it can be difficult to determine when to share that information with a veterinary clinic. Furthermore, there is a lack of systems that support pet owners in correctly understanding their pet's health information and responding appropriately without stress. Furthermore, there is a need for an efficient means of sharing information so that veterinary clinics can understand their pet's health status before an examination.

[1331] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1332] In this invention, the server includes a terminal that acquires real-time video data of the animal, a server that includes a generative AI model for analyzing the acquired video data, a server that compares the results of the analysis by the generative AI model with previously collected case data and determines the need for a veterinary visit, a server that notifies the user of the results determined by the comparison means, a server that includes an emotion recognition engine that evaluates the user's emotional state and adds a message that takes the user's emotions into consideration depending on the content of the notification, and an information sharing means that automatically transmits the analysis results and video data to a veterinary clinic as needed. This allows for quick and accurate monitoring of the pet's health condition, allowing owners to make timely decisions about when to visit the veterinary clinic. Furthermore, it reduces the psychological burden on owners and enables efficient information sharing with veterinary clinics.

[1333] "Real-time animal video data" refers to video data that records the current behavior and status of pets and other animals.

[1334] A "terminal" is a device that includes a camera and sensors for acquiring real-time video data of animals.

[1335] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to analyze and classify acquired video data.

[1336] A "server" is a central control unit that analyzes data, stores results, and notifies users and other systems.

[1337] "Data analysis" is the process of extracting features from the acquired video data and detecting abnormal behavior or symptoms.

[1338] "Matching" is the process of comparing analysis results with previously collected case data to identify possible matching symptoms.

[1339] "Notification" is a means of communication to inform the user of the results of analysis and matching.

[1340] The "emotion recognition engine" is a program that evaluates the user's emotional state and adds an appropriate message depending on the notification content.

[1341] The "information sharing means" refers to a communication device or method for transmitting analysis results and video data to a third party such as a veterinary clinic as needed.

[1342] "Necessity of medical visits" refers to the degree to which a pet's health condition is deemed to require a visit to a veterinary hospital.

[1343] MODE FOR CARRYING OUT THE INVENTION

[1344] System Configuration

[1345] This invention is a system that acquires real-time video data of animals, analyzes it, and compares it with case data to determine the need for medical treatment and notify the user. This system has three main components: a terminal (pet camera), a server, and a user.

[1346] Device (Pet Camera)

[1347] The terminal is a device that includes a camera to capture real-time video data of the animal. The camera on the terminal tracks the animal's movements and stores the data in a buffer every 5 seconds. The video data in the buffer is compressed every 10 minutes and sent to a server via the Internet. The hardware used is a commercially available high-performance pet camera, and it is possible to use, for example, H.264 video compression technology.

[1348] server

[1349] The server stores the received video data in the cloud and analyzes the data using a generative AI model. The software used is the deep learning frameworks TensorFlow and PyTorch. The generative AI model extracts the animal's behavior and movements as features and detects abnormal behavior or symptoms. For example, if an animal is detected to be frequently licking its front paws, it will recognize this as an early symptom of inflammation.

[1350] Data analysis

[1351] The server then compares the analysis results with previously collected case data to identify potential matching symptoms. This involves using an SQL database to match the analysis results' features with known symptoms in the case database. Based on the results, the server assesses whether the patient needs to visit the hospital, categorizing them as "no abnormality," "mild abnormality," or "severe abnormality."

[1352] Notification means

[1353] The server notifies the user of the evaluation results. Specifically, it notifies the user via a dedicated application, SMS, or email. For example, if the result is a "severe abnormality," the user will be notified that "immediate medical attention is required." Information about the nearest veterinary clinic will also be provided.

[1354] Emotion Recognition Engine

[1355] The server also includes an emotion recognition engine that recognizes the user's emotions. This engine evaluates the user's emotional state when a hospital visit notification is sent via the notification means. Emotion recognition can utilize the Sentiment Analysis API. If it is determined that the user is feeling stressed, a message such as "Don't panic, take action" is added to the notification.

[1356] Information sharing means

[1357] The server has an information sharing mechanism that automatically sends analysis results and video data to veterinary clinics as needed. This mechanism sends data encrypted using SSL / TLS with the user's consent. Veterinary clinics can then make a quick and accurate diagnosis based on the received data.

[1358] user

[1359] Through this system, users can keep track of their pet's health in real time. For example, if their pet is frequently licking its front paws, the system will notify the user, "Your pet needs medical attention. Please go to a nearby veterinary clinic." Furthermore, if the emotion recognition engine detects stress in the user, a message such as "Don't panic, act accordingly" will be added to the notification.

[1360] Specific examples

[1361] The pet camera captures real-time footage of the pet and sends it to a server. On the server side, a generative AI model analyzes the footage and detects behaviors such as the animal frequently licking its front paws. The results of this analysis are compared with a case database, and a high probability of early-stage dermatitis is determined.

[1362] Based on these results, the server sends a notification to the user via a dedicated app saying, "A visit to the vet is necessary. Please go to a nearby veterinary clinic." At the same time, it also provides information about the nearest veterinary clinic. Furthermore, if the emotion engine evaluates the user's emotions and determines that the user is feeling stressed, the notification will include a message such as, "Do not panic. Take action. Get a proper diagnosis at a nearby veterinary clinic."

[1363] If necessary, with the user's consent, the analysis results and video data are sent to the veterinary hospital. The veterinary hospital can use this information to conduct an examination and provide the owner with appropriate medical treatment promptly. In addition, the user's emotional data is also shared, allowing for responses that take into account the user's psychological state. This system allows owners to quickly understand their pet's health condition and ensure appropriate visits to the vet. This is expected to prevent pets from becoming seriously ill and reduce medical costs. It also enables notifications and treatment that take the user's emotions into consideration, which has the effect of reducing the mental burden on owners.

[1364] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1365] Step 1:

[1366] The terminal (pet camera) acquires real-time video data of the animal. As input, it has the video data from the camera. The camera tracks the animal's movements and saves the video data in a buffer every 5 seconds. This allows the video data of the animal's behavior and status to be accumulated in the buffer.

[1367] Step 2:

[1368] The terminal compresses the video data in the buffer every 10 minutes and sends it to the server via the Internet. The input here is the raw video data stored in the buffer. The data is compressed using H.264 video compression technology, and the compressed video data is sent to the server as the output.

[1369] Step 3:

[1370] The server stores the received compressed video data in the cloud. The input is the compressed video data sent from the device. The server stores the data using a cloud storage service (e.g., Amazon S3 or Google Cloud Storage), and the output is the data stored in the cloud.

[1371] Step 4:

[1372] The server analyzes video data stored on the cloud using a generative AI model. The input is the stored video data. The generative AI model uses TensorFlow and PyTorch to extract features representing the animal's behavior and state, and detects abnormal behavior and symptoms. The output is the analysis results. For example, if the model detects that an animal is frequently licking its front paws, it will identify this as an early symptom of inflammation.

[1373] Step 5:

[1374] The server compares the analysis results obtained by the generative AI model with previously collected case data. The inputs are the analysis results and the case database. An SQL database is used to match the features of the analysis results with known symptoms in the case database. The output identifies symptoms that may match the analysis results.

[1375] Step 6:

[1376] The server evaluates the need for outpatient care based on the analysis results and the comparison results of the case data. The input is the comparison results. The need for outpatient care is evaluated in categories such as "no abnormality," "mild abnormality," and "severe abnormality." The output is the evaluation result regarding the need for outpatient care.

[1377] Step 7:

[1378] The server notifies the user of the assessment results regarding the need for medical attention. The inputs are the assessment results and the user's contact information. The notification is sent via a dedicated app, SMS, or email, and conveys a message to the user such as "An immediate medical visit is required." The output is a notification sent to the user.

[1379] Step 8:

[1380] The server uses an emotion recognition engine to evaluate the user's emotional state. The input is the notification content and the user's reaction data. The emotion recognition engine (e.g., Sentiment Analysis API) is used to evaluate the user's emotion, and the output is whether the user is feeling stressed. If necessary, a message such as "Don't panic, take action" is added to the notification content.

[1381] Step 9:

[1382] The server sends the analysis results and video data to the veterinary hospital as needed. The input is the analysis results and the user's consent. The data is encrypted using SSL / TLS and sent securely to the veterinary hospital. The output is the data sent to the veterinary hospital. The veterinary hospital can use this data as a reference to make a quick and accurate diagnosis.

[1383] (Application example 2)

[1384] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1385] Conventional pet monitoring systems often overlooked abnormal behavior or symptoms because they did not provide a means to regularly check an animal's behavior. This meant that opportunities for early and appropriate medical treatment could be missed, making them insufficient for protecting a pet's health. Furthermore, even if a user noticed something unusual about their pet, there were few ways to quickly obtain appropriate advice or information, and the system was unable to respond to the user's emotions. Furthermore, there was no function to display advertisements linked to the pet's health status, making it difficult to access health care products and information.

[1386] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an optical device that acquires real-time video data of the animal, an information processing device including a generative AI model for analyzing the acquired video data, a comparison means that compares the results of the analysis by the information processing device with the animal's case data and determines the need for medical treatment, a display device that notifies the user of the results determined by the comparison means, and a promotion means that displays advertisements related to the pet's health condition and behavior. This makes it possible to monitor the pet's health condition in real time and promptly notify the user if an abnormality is detected. In addition, displaying advertisements for products and services related to the pet's health condition makes it easier for the user to access appropriate care products and medical services. It is also possible to display messages that take the user's emotions into consideration, thereby reducing the psychological burden on the owner.

[1387] "Optical devices" is a general term for cameras and sensor devices used to acquire real-time video data of animals.

[1388] An "information processing device" is a computer device equipped with a generative AI model for analyzing acquired video data.

[1389] The "comparison means" is a function for comparing the results of analysis by the information processing device with the animal's case data and determining the need for hospital visits.

[1390] A "display device" is a screen or mobile device that notifies the user of the results determined by the comparison means.

[1391] "Promotional tools" are features for displaying advertisements related to pet health and behavior.

[1392] "Data sharing means" is a function that automatically transmits video data and analysis results to veterinary medical facilities.

[1393] This invention provides a system that acquires real-time video data of pets, analyzes it using a generative AI model to detect abnormal behavior and symptoms, notifies the user based on the data, and displays advertisements linked to the pet's health status.

[1394] The server uses optical devices, such as IP cameras and smart cameras, to capture real-time video data of animals, tracking pet movements every five seconds and compressing the video data and sending it to the cloud every ten minutes.

[1395] The server analyzes the captured video data using a generative AI model in the cloud. A deep learning model, for example, is used as the generative AI model, extracting animal behavior and movements as features and identifying abnormal behavior and symptoms. Machine learning libraries such as TensorFlow are used for this analysis.

[1396] The results of the video data analysis are collated with a database of animal cases collected in advance. An algorithm is used to compare the analysis results with the case database and determine whether or not a visit to the hospital is necessary. This results in an assessment into categories such as "no abnormalities," "mild abnormalities," or "severe abnormalities."

[1397] The server notifies the user of the results of the collation process via a dedicated app, SMS, or email. For example, if a "severe abnormality" is detected, the server will send a message urging the user to visit a veterinarian immediately, along with information about the nearest veterinary clinic.

[1398] As a promotional tool, users will be shown advertisements related to their pet's health. For example, if a pet is detected licking its paws frequently, advertisements for skin care products or veterinary clinics will be displayed. The app also has an emotion engine that recognizes the user's emotions, and if the user is feeling stressed, a comforting message will be added to the notification.

[1399] As a specific example, a pet camera captures video of a pet in real time and sends it to a server. A generative AI model on the server analyzes the video and detects behaviors such as the animal frequently licking its front paws. This analysis result is compared with a case database, and if early symptoms of dermatitis are determined, a notification is sent to the user's smartphone saying, "A visit to the nearest veterinary clinic is required. Please go to a nearby veterinary clinic." At the same time, an emotion engine evaluates the user's emotions and adds a comforting message such as, "Don't panic. Please go to a nearby veterinary clinic and receive a proper diagnosis."

[1400] An example of a prompt is as follows:

[1401] "Real-time video data of animals is acquired and analyzed with a generative AI model to detect abnormal behavior. The analysis results are compared with case data to determine the need for medical attention and notify the user. The system evaluates the user's emotions to add appropriate messages and display pet-related advertisements."

[1402] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1403] Step 1:

[1404] The server receives video data from optical devices (such as IP cameras) in real time. The input is the video signal from the optical device, and the output is the temporarily stored video data. Specifically, the IP camera tracks the animal's movements and stores the video data in a buffer every 5 seconds.

[1405] Step 2:

[1406] The server compresses the video data in the buffer every 10 minutes and sends it to the cloud. The input is the temporarily stored video data, and the output is the compressed video data. Specifically, the video data is compressed in H.264 format or similar and uploaded to the cloud server via the Internet.

[1407] Step 3:

[1408] The server analyzes the received video data using a generative AI model (e.g., a deep learning model) in the cloud. The input is compressed video data, and the output is analyzed feature data. Specifically, it uses machine learning libraries such as TensorFlow to extract features based on the animal's behavior and movements, and identifies abnormal behavior and symptoms.

[1409] Step 4:

[1410] The server compares the analysis results with the case database. The input is the analyzed feature data, and the output is the comparison result. Specifically, it matches the analysis results with known symptoms stored in the case database and evaluates the need for hospital visits.

[1411] Step 5:

[1412] The server sends a notification to the user based on the matching results. The input is the matching result, and the output is a notification message to the user. Specifically, it sends a notification such as "You need to visit the hospital" to the user's smartphone or email. If the user is feeling stressed, it also adds a comforting message based on the evaluation by the emotion engine.

[1413] Step 6:

[1414] The server displays advertisements related to the pet's health condition and behavior. The input is the analysis results, and the output is advertisement display information. Specifically, advertisements that match the symptoms and behaviors exhibited by the pet (for example, information about pet skin care products or veterinary clinics) are displayed on the user's smartphone.

[1415] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1416] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1417] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1418] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1419] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1420] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1421] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1422] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1423] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1424] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1425] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1426] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1427] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1428] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1429] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1430] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1431] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1432] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1433] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1434] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1435] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1436] The following is further disclosed regarding the above embodiment.

[1437] (Claim 1)

[1438] an image acquisition means for acquiring real-time image data of an animal;

[1439] a data analysis means including a generative AI model for analyzing the acquired video data;

[1440] a comparison means for comparing the results of the analysis by the data analysis means with case data of the animal to determine the need for hospital visits;

[1441] a notification means for notifying a user of the result determined by the comparison means;

[1442] A system including:

[1443] (Claim 2)

[1444] 2. The system according to claim 1, further comprising a function of providing information about veterinary clinics when the checking means determines that a visit to a veterinary clinic is highly necessary.

[1445] (Claim 3)

[1446] 2. The system according to claim 1, further comprising an information sharing means for automatically transmitting the video data and the analysis results to a veterinary clinic.

[1447] "Example 1"

[1448] (Claim 1)

[1449] an image acquisition means for acquiring real-time image data of an animal;

[1450] means for transmitting the acquired video data over the Internet;

[1451] A means for storing the transmitted video data on the cloud;

[1452] a data analysis means including a generative AI model for analyzing the stored video data;

[1453] a comparison means for comparing the results of the analysis by the data analysis means with case data of the animal to determine the need for hospital visits;

[1454] a notification means for notifying a user of the result determined by the comparison means;

[1455] A system including:

[1456] (Claim 2)

[1457] 2. The system according to claim 1, further comprising a function of providing information about veterinary clinics when it is determined that a visit to a veterinary clinic is highly necessary.

[1458] (Claim 3)

[1459] 10. The system of claim 1, further comprising an information sharing means for automatically transmitting the video data and analysis results to a veterinary clinic.

[1460] "Application Example 1"

[1461] (Claim 1)

[1462] an image acquisition means for acquiring real-time image data of an item;

[1463] a data analysis means including a generative AI model for analyzing the acquired video data;

[1464] a comparison means for comparing the results of the analysis by the data analysis means with the item status data to determine whether or not an abnormality exists;

[1465] a notification means for notifying an administrator of the result determined by the comparison means;

[1466] A system including:

[1467] (Claim 2)

[1468] 2. The system according to claim 1, further comprising a function of notifying an administrator when an abnormality in an item is detected.

[1469] (Claim 3)

[1470] 2. The system according to claim 1, further comprising an information sharing means for automatically transmitting the video data and analysis results to an administrator when an abnormality is detected.

[1471] "Example 2: Combining Emotion Engines"

[1472] (Claim 1)

[1473] A terminal that acquires real-time video data of animals;

[1474] a server including a generative AI model for analyzing the acquired video data;

[1475] A server that compares the results of the analysis by the generative AI model with pre-collected case data and determines the need for outpatient visits;

[1476] a means for notifying a user of the result determined by the matching means;

[1477] a server including an emotion recognition engine that evaluates the emotional state of a user and adds a message that takes the user's emotion into consideration according to the notification content;

[1478] a server including an information sharing means for automatically transmitting analysis results and video data to a veterinary clinic as needed;

[1479] A system including:

[1480] (Claim 2)

[1481] 10. The system of claim 1, further comprising a function for providing information about veterinary clinics.

[1482] (Claim 3)

[1483] 10. The system of claim 1, further comprising a function for automatically transmitting the video data and analysis results to a veterinary clinic.

[1484] "Application example 2 when combining emotion engines"

[1485] (Claim 1)

[1486] an optical device for acquiring real-time video data of animals;

[1487] an information processing device including a generative AI model for analyzing acquired video data;

[1488] a comparison means for comparing the results of the analysis by the information processing device with case data of the animal to determine the need for hospital visits;

[1489] a display device that notifies a user of the result determined by the comparison means;

[1490] promotional vehicles that display advertisements related to pet health and behavior;

[1491] A system including:

[1492] (Claim 2)

[1493] 2. The system according to claim 1, further comprising a function of providing information about veterinary medical facilities when the comparison means determines that the need for hospital visits is high.

[1494] (Claim 3)

[1495] 10. The system of claim 1, further comprising a data sharing means for automatically transmitting the video data and analysis results to the veterinary facility. [Explanation of symbols]

[1496] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. an image acquisition means for acquiring real-time image data of an animal; a data analysis means including a generative AI model for analyzing the acquired video data; a comparison means for comparing the results of the analysis by the data analysis means with case data of the animal to determine the need for hospital visits; a notification means for notifying a user of the result determined by the comparison means; A system including:

2. 2. The system according to claim 1, further comprising a function of providing information about veterinary clinics when the checking means determines that a visit to a veterinary clinic is highly necessary.

3. 2. The system according to claim 1, further comprising an information sharing means for automatically transmitting the video data and the analysis results to a veterinary clinic.

Images