Intelligent petbot and method for identifying elderly health status using it

Abstract

The present invention relates to a method for determining whether there is a health abnormality using an intelligent pet bot that can respond in a timely manner by determining the health condition of an elderly person using artificial intelligence.

Description

Technology Field

[0001] The present invention relates to a method for determining the health status of an elderly person using artificial intelligence. Background Technology

[0003] As global aging accelerates, the proportion of elderly people living alone is rapidly increasing, and consequently, the rate of lonely deaths among the elderly is rising.

[0004] Solitary death refers to the phenomenon of dying in a lonely situation due to the severance of family or social relationships; in the case of elderly people living alone, the risk of solitary death is increasing due to physical or mental problems (loneliness or depression).

[0005] Consequently, while reliance on technical equipment such as CCTVs is currently employed to prevent solitary deaths, their effectiveness is often limited due to concerns regarding privacy infringement. Therefore, there is a growing demand for monitoring technologies that can seamlessly integrate into the daily lives of the elderly without compromising privacy. Prior art literature

[0007] Korean Registered Patent No. 10-2408306: Artificial Intelligence-based Situation Monitoring and Emergency Call System The problem to be solved

[0008] The purpose of this invention is to determine the health status of the elderly using artificial intelligence. means of solving the problem

[0010] A method for determining whether there is a health abnormality using an intelligent pet bot according to one embodiment of the present invention includes the steps of receiving a plurality of thermal images of an elderly person taken from an IR camera, receiving a plurality of RGB images of an elderly person taken from an RGB camera, and inputting the plurality of thermal images and RGB images into a neural network model to determine the health status of the elderly person.

[0011] The above thermal image and RGB image include shooting time information.

[0012] The above health conditions are normal, high fever, collapse, hypothermia, abnormal behavior, prolonged inactivity, and depression.

[0013] The method includes the steps of collecting a thermal image and a training RGB image, labeling the thermal image and the training RGB image respectively, and setting the thermal image and the training RGB image as input data for the neural network model and setting the health state as output data for the neural network model to perform supervised learning on the neural network model.

[0014] When the health abnormality of the elderly person is identified, the method further includes the step of sending a warning message to an external server. Effects of the invention

[0016] The present invention has the advantage of being able to identify the health condition of the elderly through artificial intelligence and respond in a timely manner.

[0017] In addition to the effects described above, the specific effects of the present invention are described together with the specific details for implementing the invention below. Brief explanation of the drawing

[0019] FIG. 1 is a block diagram of an intelligent pet bot according to an embodiment of the present invention. FIG. 2 is a conceptual diagram illustrating the operation of a processor that detects temperature. FIG. 3 is a flowchart of a method for determining whether there is a health abnormality using an intelligent pet bot according to an embodiment of the present invention. Figure 4 is a diagram illustrating the operation of a neural network model. Figures 5 and 6 are diagrams illustrating the learning process of a neural network model. Specific details for implementing the invention

[0020] The aforementioned objectives, features, and advantages are described in detail below with reference to the attached drawings, thereby enabling those skilled in the art to easily implement the technical concept of the present invention. In describing the present invention, detailed descriptions of known technologies related to the present invention are omitted if it is determined that such descriptions would unnecessarily obscure the essence of the invention. Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the attached drawings. In the drawings, the same reference numerals are used to indicate the same or similar components.

[0021] In this specification, terms such as "first," "second," etc. are used to describe various components, but these components are not limited by these terms. These terms are used merely to distinguish one component from another, and unless specifically stated otherwise, the first component may be the second component.

[0022] Additionally, in this specification, the statement that any configuration is disposed on the "upper (or lower)" or "upper (or lower)" of a component may mean not only that any configuration is disposed in contact with the upper (or lower) surface of said component, but also that another configuration may be interposed between said component and any configuration disposed on (or below) said component.

[0023] Furthermore, where it is stated in this specification that one component is "connected," "coupled," or "connected" to another component, it should be understood that while the components may be directly connected or connected to each other, another component may be "interposed" between each component, or each component may be "connected," "coupled," or "connected" through another component.

[0024] Additionally, singular expressions used in this specification include plural expressions unless the context clearly indicates otherwise. In this application, terms such as "composed of" or "comprising" should not be interpreted as necessarily including all of the various components or steps described in the specification, and should be interpreted as meaning that some of the components or steps may not be included, or that additional components or steps may be included.

[0025] Additionally, in this specification, "A and / or B" means A, B, or A and B unless specifically stated otherwise, and "C to D" means C or more and D or less unless specifically stated otherwise.

[0027] The present invention relates to an intelligent pet bot and a method for determining the health status of an elderly person using the same. Below, the intelligent pet bot will be briefly described, and then the method for determining the health status of an elderly person using the intelligent pet bot will be described in detail.

[0028] First, referring to FIG. 1, an intelligent pet bot according to one embodiment of the present invention may include an IR camera (100), an RGB camera (200), a warning speaker (300), a GPS (400), a database (500), a communication module (600), and a processor (700). Meanwhile, the intelligent pet bot may have the shape of a dog.

[0029] However, the intelligent pet bot illustrated in FIG. 1 is according to one embodiment, and the components constituting the invention are not limited to the embodiment illustrated in FIG. 1, and some components may be added, changed, or deleted as needed.

[0030] First, the IR camera (100) can photograph an elderly person to obtain a thermal image. The thermal image may include information on the time of shooting. The RGB camera (200) can photograph an elderly person like the IR camera to obtain an RGB image. The RGB image may include information on the time of shooting.

[0031] The warning speaker (300) can emit a warning sound to alert people around it to the emergency situation when an emergency occurs. The GPS (400) can generate current location information and transmit the location information to an external server via the communication module (600). A neural network model for determining the health status of the elderly can be stored in the database (500).

[0032] The communication module (600) can transmit data generated from the IR camera (100), RGB camera (200), warning speaker (300), and GPS (400) to an external server.

[0033] The processor (700) can control the IR camera (100), RGB camera (200), warning speaker (300), GPS (400), and communication module (600).

[0034] Meanwhile, the processor (700) can control the communication module (600) to send a warning notification to an external server if the temperature in the video image captured by the IR camera (100) as shown in FIG. 2 is above a threshold value. Specifically, the processor (700) can control the communication module (600) to send a warning notification to an external server if the temperature in the video image captured by the IR camera (100) is 39 degrees or higher.

[0035] To perform the above-described operation, the processor (700) may include at least one physical element among ASICs (application specific integrated circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays), controllers, and microcontrollers.

[0036] Through this, the present invention has the advantage of being able to respond in a timely manner when an emergency situation occurs involving the elderly.

[0038] Previously, an intelligent pet bot according to one embodiment of the present invention was briefly described, and next, with reference to FIG. 3, the operation of a processor (700) for determining the health status of an elderly person will be described.

[0039] First, the processor (700) can receive multiple thermal images of an elderly person taken from an IR camera (100) (S11). Next, the processor (700) can receive multiple RGB images of an elderly person taken from an RGB camera (200) (S12). Meanwhile, as previously described, the thermal images and RGB images may include shooting time information.

[0040] Next, the processor (700) can input a plurality of thermal images and RGB images into a neural network model to determine the health status of the elderly person (S13). Specifically, referring to FIG. 4, the processor (700) can input a plurality of thermal images into a neural network model (50), and the neural network model (50) can output the health status of the elderly person. At this time, the health status may be normal, high fever, collapse, hypothermia, abnormal behavior, prolonged inactivity, and depression.

[0041] Meanwhile, referring to FIG. 5, a learning process of the neural network model (50) may be performed prior to the above-described operations. To this end, the processor (700) may collect a training image (S21), wherein the training image may be a training thermal image and a training RGB image. The training thermal image and the training RGB image may include shooting time information.

[0042] Next, the processor (700) can label the training images (S22). Specifically, the processor (700) can label the training thermal image and the training RGB image, and can label the actual values ​​corresponding to the training thermal image and the training RGB image, that is, the health status of the training thermal image and the training RGB image, according to the user's command.

[0043] Next, the processor (700) can set the training image as input data for the neural network model and the health state as output data for the neural network model (50) to perform supervised learning on the neural network model (50) in advance. Specifically, the processor (700) can set the training thermal image and the training RGB image as input data for the neural network model and the health state as output data for the neural network model to perform supervised learning on the neural network model in advance. To explain further, the processor (700) can set the training thermal image and the training RGB image as input data for the neural network model (50) and perform supervised learning on the neural network model (50) based on a training dataset in which the actual value corresponding to the input data, that is, the class regarding the health state corresponding to the training thermal image and the training RGB image, is used as output data for the neural network model (50).

[0044] Through such supervised learning, the neural network model (50) can learn the correlation between the training thermal image and the training RGB image and the health state, and after the learning is completed, it can determine the health state for the unused thermal image and RGB image as well. For example, when the processor (700) inputs a plurality of thermal images and RGB images shown in FIG. 6 into the neural network model (50), the neural network model (50) can output a health state, at which time the health state may be collapse.

[0045] Meanwhile, in the present invention, the neural network model may be a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), and a Transformer.

[0046] Next, referring again to FIG. 3, the processor (700) can send a warning message externally when an abnormal health condition of an elderly person is identified. For example, if the processor (700) identifies that an elderly person has collapsed, it can send a warning message to an external server, such as a hospital or an elderly care agency.

[0047] At this time, the processor (700) can additionally transmit current location information using GPS (400). Through this, the present invention can respond in a timely manner when an emergency situation occurs for the elderly.

[0049] Although the present invention has been described above with reference to the illustrated drawings, the present invention is not limited by the embodiments and drawings disclosed in this specification, and it is obvious that various modifications can be made by a person skilled in the art within the scope of the technical concept of the present invention. Furthermore, even if the effects of the configuration of the present invention were not explicitly described while explaining the embodiments of the present invention above, it is natural to acknowledge that the effects predictable by said configuration should also be recognized.

Claims

Claim 1 A method for determining whether there is a health abnormality using an intelligent pet bot, comprising: receiving a plurality of thermal images of an elderly person taken from an IR camera; receiving a plurality of RGB images of an elderly person taken from an RGB camera; and inputting the plurality of thermal images and RGB images into a neural network model to determine the health condition of the elderly person. Claim 2 A method for determining whether there is a health abnormality using an intelligent pet bot, wherein the thermal image and RGB image include shooting time information, in accordance with claim 1. Claim 3 A method for determining whether there is a health abnormality using an intelligent pet bot, wherein the health condition is normal, high fever, collapse, hypothermia, abnormal behavior, prolonged inactivity, and depression. Claim 4 A method for determining whether there is a health abnormality using an intelligent pet bot according to claim 1, comprising: a step of collecting a thermal image for training and a training RGB image; a step of labeling the thermal image for training and the training RGB image for training, respectively; and a step of setting the thermal image for training and the training RGB image for training as input data for the neural network model and setting the health state as output data for the neural network model to perform supervised learning on the neural network model. Claim 5 A method for determining whether there is a health abnormality using an intelligent pet bot, further comprising the step of transmitting a warning message to an external server when the health abnormality of the elderly person is determined in claim 1.

Images