KR102328981B1 - System for providing pet information sharing service using harness camera - Google Patents

Abstract

Provided is a system for providing companion animal information sharing service using a harness camera. The system comprises: a harness camera that is installed or provided opposite the face of a companion animal to photograph the face of the companion animal, is fixed and supported on a harness worn on part or the entire body of the companion animal, and outputs image data of the face of the companion animal; a user terminal that uploads the image data received from the harness camera in real time through wireless or wired communications, and outputs result data based on an analysis result of the image data; and a sharing service providing server that includes a registration unit that maps and registers the user terminal and the harness camera from the user terminal, an extraction unit that pre-processes and then extracts a facial region or body region, which is an object included in the image data received from the harness camera via the user terminal, a storage unit that labels and maps a tag to the facial region or the body region and stores the tag, a reception unit that transmits the labeled tag to the user terminal to receive feedback, and a sharing unit that shares the image data and the tag corresponding to the facial region or the body region if the feedback is positive.

Description

Companion animal information sharing service using harness camera {SYSTEM FOR PROVIDING PET INFORMATION SHARING SERVICE USING HARNESS CAMERA}

The present invention relates to a system for providing information sharing service for companion animals using a harness camera, and provides a platform for building and sharing big data as research data by installing a harness camera to photograph the face or body of a companion animal and sharing it.

The number of companion animals in Korea is increasing due to the development of social awareness of companion animals and changes in household types. Accordingly, as interest in high-quality parenting methods and health care for companion animals increases, related industries including companion animal feed, medicines, daily necessities, and medical services are also growing rapidly and growing to about KRW 6 trillion as of 2020. did. Countries such as the United States, United Kingdom, Germany, France, and Japan, which have a high proportion of households raising companion animals, have been conducting various research and data management on companion animal health, and medical products and service industries are also developing. Recently, systems and mobile apps have been developed in the UK and Japan, such as personalized medical services for humans, that frequently check the behavior and health of companion animals and provide solutions based on the examination data. In addition, healthcare service products that measure the play and exercise of companion animals and provide information by comparing them with the same breed were launched in the US and Austria.

At this time, a method for observing companion animals and automatically managing them from a remote location has been researched and developed. In No. 0041185 (published on April 22, 2019), companion animals can be monitored in real time while they are away or can talk, and the recorded voice of the guardian can be heard. A camera module for monitoring the status of companion animals in a mobile communication terminal, an audio module for conversation between the guardian and companion animals, a food tank that stores food, and food from the food tank so that they can be thrown so that they can play. The composition of the extraction means to extract and move it to the launch pad, detects the companion animal so that the companion animal can accurately understand the situation of the companion animal, detects the weight of the companion animal that has entered the accommodation space, and shoots the accommodation space. A configuration capable of controlling and regulating illumination, temperature, and feed supply by sensing the body temperature of a companion animal entering the accommodation space and providing lighting to the accommodation space is disclosed.

However, in order to visually check the condition of the companion animal, most of the above-described configuration is a product to which a fixed CCTV is applied, and a number of CCTVs are required to view each room or a method of limiting the range of motion of the companion animal is used. Among them, products that can be remotely controlled by using a smartphone as a keypad have been commercialized, but products that automatically track the target by recognizing the characteristics or specific behavioral patterns of companion animals have not been commercialized yet. In addition, since the object detection system is generally configured to detect an object through a difference operation on an image frame or to detect the heat of a human body using an infrared sensor, it is difficult to detect a specific object. Accordingly, in a situation where data for behavioral research of companion animals is absolutely insufficient compared to other countries, it is possible to prepare a basis for research by collecting images that can provide a basis for visual analysis of companion animals while having mobility. Research and development of a platform that exists is required.

An embodiment of the present invention collects facial data and body data of a companion animal using a harness camera fixed in a direction opposite to the face or body so that the face or body of the companion animal can be photographed to be used by researchers or research institutes. However, the pre-processing and labeling process necessary for building big data can be handled by the companion who knows his or her companion animal best, or the accuracy of the pre-processing and labeling process can be increased by giving a review or feedback, and the researcher or research institute Companion using a harness camera can increase the participation of users who are companion animals by paying the usage fee for data and body data as feed or snacks analyzed according to the characteristics of companion animals, and ultimately develop the field of companion animal behavior research. A method for providing an animal information sharing service may be provided. However, the technical task to be achieved by the present embodiment is not limited to the technical task as described above, and other technical tasks may exist.

As a technical means for achieving the above-described technical problem, an embodiment of the present invention is installed or provided to face in the face direction to photograph the face of the companion animal, and is fixed through a harness filled in part or all of the body of the companion animal. and a harness camera that outputs image data of a companion animal's face, uploads image data received from the harness camera in real time through wireless or wired communication, and outputs result data based on the analysis result of the image data A registration unit that maps and registers a user terminal and a harness camera from a user terminal and a user terminal, an extractor that extracts the face region or body region, which is an object included in the image data received from the harness camera via the user terminal, after preprocessing, the facial region Alternatively, a storage unit that labels and maps a tag to a body region and stores it, a receiver that transmits the labeled tag to a user terminal to receive feedback, and when the feedback is positive feedback, image data corresponding to the face region or body region and and a sharing service providing server including a sharing unit for sharing tags.

According to any one of the above-described problem solving means of the present invention, facial data and body data of a companion animal are collected using a harness camera fixed to a direction opposite to the face or body so that the face or body of the companion animal can be photographed. Share it for use by researchers or research institutes, but allow a companion who knows your companion animal best to handle the pre-processing and labeling process necessary for building big data, or to increase the accuracy of the pre-processing and labeling process by giving a review or feedback, By paying the usage fee for facial data and body data by researchers or research institutes as feeds or snacks analyzed according to the characteristics of companion animals, it is possible to increase the participation of users who are companion animals, and ultimately achieve development in the field of companion animal behavior research. .

1 is a view for explaining a system for providing a companion animal information sharing service using a harness camera according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a shared service providing server included in the system of FIG. 1 .
3 and 4 are diagrams for explaining an embodiment in which a companion animal information sharing service using a harness camera according to an embodiment of the present invention is implemented.
5 is an operation flowchart illustrating a method of providing a companion animal information sharing service using a harness camera according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement them. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is "connected" with another part, this includes not only the case of being "directly connected" but also the case of being "electrically connected" with another element interposed therebetween. . Also, when a part "includes" a component, it means that other components may be further included, rather than excluding other components, unless otherwise stated, and one or more other features However, it is to be understood that the existence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded in advance.

The terms "about", "substantially", etc. to the extent used throughout the specification are used in a sense at or close to the numerical value when the manufacturing and material tolerances inherent in the stated meaning are presented, and serve to enhance the understanding of the present invention. To help, precise or absolute figures are used to prevent unfair use by unscrupulous infringers of the stated disclosure. As used throughout the specification of the present invention, the term “step for (to)” or “step for” does not mean “step for”.

In this specification, a "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. In addition, one unit may be implemented using two or more hardware, and two or more units may be implemented by one hardware. Meanwhile, '~ unit' is not limited to software or hardware, and '~ unit' may be configured to be in an addressable storage medium or may be configured to reproduce one or more processors. Thus, as an example, '~' refers to components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. The functions provided in the components and '~ units' may be combined into a smaller number of components and '~ units' or further separated into additional components and '~ units'. In addition, components and '~ units' may be implemented to play one or more CPUs in a device or secure multimedia card.

In this specification, some of the operations or functions described as being performed by the terminal, apparatus, or device may be performed instead of in a server connected to the terminal, apparatus, or device. Similarly, some of the operations or functions described as being performed by the server may also be performed in a terminal, apparatus, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal means mapping or matching the terminal's unique number or personal identification information, which is the identification data of the terminal. can be interpreted as

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

1 is a view for explaining a system for providing a companion animal information sharing service using a harness camera according to an embodiment of the present invention. Referring to FIG. 1 , a system 1 for providing a companion animal information sharing service using a harness camera includes at least one user terminal 100 , a sharing service providing server 300 , at least one harness camera 400 , and at least one of the research institute server 500 may be included. However, since the companion animal information sharing service providing system 1 using the harness camera of FIG. 1 is only an embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1 .

In this case, each component of FIG. 1 is generally connected through a network 200 . For example, as shown in FIG. 1 , at least one user terminal 100 may be connected to the shared service providing server 300 through the network 200 . In addition, the shared service providing server 300 may be connected to at least one user terminal 100 , at least one harness camera 400 , and at least one research institute server 500 through the network 200 . In addition, at least one harness camera 400 may be connected to the shared service providing server 300 through the network 200 . In addition, the at least one research institute server 500 may be connected to at least one user terminal 100 , the shared service providing server 300 , and at least one harness camera 400 through the network 200 .

Here, the network refers to a connection structure in which information exchange is possible between each node, such as a plurality of terminals and servers, and an example of such a network includes a local area network (LAN), a wide area network (WAN: Wide Area Network), the Internet (WWW: World Wide Web), wired and wireless data communication networks, telephone networks, wired and wireless television networks, and the like. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), 5th Generation Partnership Project (5GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), Wi-Fi (Wi-Fi) , Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth (Bluetooth) network, NFC ( Near-Field Communication) networks, satellite broadcast networks, analog broadcast networks, Digital Multimedia Broadcasting (DMB) networks, and the like are included, but are not limited thereto.

In the following, the term at least one is defined as a term including the singular and the plural, and even if at least one term does not exist, each element may exist in the singular or plural, and may mean the singular or plural. it will be self-evident In addition, that each component is provided in singular or plural may be changed according to embodiments.

Before describing each component of the present invention, the reason why the work of each component is distributed will be first described. The contents described below will not be repeatedly described while describing the configuration to be described later.

In one embodiment of the present invention, the image data uploaded via the user terminal 100 is first classified by the sharing service providing server 300 and the tag is labeled, and then whether it is correct is transmitted to the user terminal 100 again. to confirm and receive confirmation, and allow only the confirmed video data to build an artificial intelligence algorithm with the training dataset and test dataset, or share and sell to the research institute server 500 that wants to build big data or conduct research. make it possible

Of course, labeling can be done mechanically or by manual labor, but a companion who has been with a pet for a long time can't understand what they are talking about, but even if they see their expression, hear a barking or cry, or just a glance, they can see what they want or what they want. Sometimes you know what you're talking about. Although there are similarities for each animal, it can be different depending on the characteristics of each species or individual companion animal, so manual or automatic labeling at a research institute or by people who have never raised the companion animal in batches may be inaccurate. The dataset can cause misfortune to start training artificial intelligence algorithms. It is self-evident that if the input data is not accurate, neither the trained result nor the artificial intelligence algorithm being modeled will be accurate.

Accordingly, the user terminal 100 may select whether or not a tag is appropriate for the result labeled by the shared service providing server 300 . Of course, it would be ideal to label all tags in the user terminal 100 from the beginning, but since this becomes a "task" for the user who is a customer, there is a possibility that the service of the present invention will not be used. Therefore, in one embodiment of the present invention, after pre-processing in the shared service providing server 300, and after labeling based on the existing data, the platform is configured so that the user, who is a human, has to confirm this, even though it is correct, to obtain accurate information. and so that users do not feel annoyed.

For reference, in order to model an AI algorithm, raw data is collected, and after preprocessing, a labeling operation is performed to attach a “tag” to identify what the raw data (image data) means. After that, [image data-tag] is entered into the artificial intelligence algorithm as a training dataset and a test dataset, and the artificial intelligence algorithm that has been trained (learning) and tested is subsequently trained when similar image data is input as a query. By outputting "tag", what the corresponding image data means is output. The following components will be described based on the above-described mechanism.

At least one user terminal 100 is a harness camera 400 when a companion animal is registered and the harness camera 400 is purchased using a web page, an app page, a program or an application related to the companion animal information sharing service using the harness camera. ) and a terminal that registers information of its companion animal. In addition, the user terminal 100 may be a user terminal that checks whether a tag labeled by the shared service providing server 300 or the research institute server 500 is correct. In addition, the user terminal 100 may receive the state of the companion animal to be shared in real time, or may be a terminal that receives information interpreting the state of the companion animal from the sharing service providing server 300 , and the user terminal 100 Based on the capacity, type, number, etc. of the uploaded or confirmed tag, you receive points as a reward from the sharing service providing server 300 It may be a terminal.

Here, the at least one user terminal 100 may be implemented as a computer that can access a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser, a desktop, and a laptop. In this case, the at least one user terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one user terminal 100, for example, as a wireless communication device that guarantees portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W-Code Division Multiple Access), Wibro(Wireless Broadband Internet) ) terminal, a smart phone, a smart pad, a tablet PC, etc. may include all kinds of handheld-based wireless communication devices.

The sharing service providing server 300 may be a server that provides a companion animal information sharing service web page, an app page, a program, or an application using a harness camera. Then, the shared service providing server 300 collects at least one companion animal facial or body data, and sends it to the user terminal 100 whether the labeled tag is correct before making a training dataset and a test dataset after pre-processing and labeling. It may be a server that receives the confirmation. If there is no confirmation of the user terminal 100, the labeled tag may be used as it is. And, the shared service providing server 300 may share the training dataset and the test dataset with at least one research institute server 500, or it may be a server that builds big data by itself to model an artificial intelligence algorithm. . In addition, the shared service providing server 300 maps the user terminal 100 and the harness camera 400 when the harness camera 400 is purchased from the user terminal 100 or when the harness camera 400 is registered. It may be a server that stores it. Then, the shared service providing server 300 receives the facial or body data photographed from the harness camera 400 in real time, analyzes it, and informs the user terminal 100 if there is an abnormal behavior, and the analyzed state In some cases, it may be a server that controls at least one payroll device (not shown) or controls at least one device (not shown) linked to a home network.

Here, the shared service providing server 300 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser, a desktop, and a laptop.

The at least one harness camera 400 directly transmits image data obtained by photographing the face of a companion animal using a companion animal information sharing service related web page, app page, program or application using the harness camera to the sharing service providing server 300 . Or it may be an indirect uploading device. In this case, the harness camera 400 may further include a multi-camera (not shown), and the multi-camera may be a camera that captures the body of the companion animal instead of the face. In addition, the harness camera 400 may be a camera fixed to a harness, that is, a string capable of tying a lead string while wrapping the body of the companion animal. In addition, the harness camera 400 may be a camera that uploads image data to the shared service providing server 300 through a home network built in the home or using the user terminal 100 as an AP unless a long-distance communication module is built-in. have.

Here, the at least one harness camera 400 may be implemented as a computer that can connect to a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser, a desktop, and a laptop. In this case, the at least one harness camera 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. The at least one harness camera 400 is, for example, a wireless communication device that ensures portability and mobility, including navigation, Personal Communication System (PCS), Global System for Mobile communications (GSM), Personal Digital Cellular (PDC), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W-Code Division Multiple Access), Wibro(Wireless Broadband Internet) ) terminal, a smart phone, a smart pad, a tablet PC, etc. may include all kinds of handheld-based wireless communication devices.

At least one research institute server 500 uses a companion animal information sharing service-related web page, an app page, a program, or an application using a harness camera or a companion animal data set without using the comprehensive management service server 300 It may be a server of a research institution that is shared or purchased from. At this time, the comprehensive management service providing server 300 can analyze or estimate the behavior or disease of the companion animal of the user terminal 100 based on the proposition or theory obtained after the research in the research institution server 500, and comprehensive management The service providing server 300 may transmit to the user terminal 100 .

Here, the at least one research institute server 500 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser, a desktop, and a laptop. In this case, the at least one research institute server 500 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one research institute server 500, for example, as a wireless communication device that guarantees portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular) , PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband) Internet) terminals, smartphones, smart pads, tablet PCs, etc. may include all types of handheld-based wireless communication devices.

2 is a block diagram for explaining a shared service providing server included in the system of FIG. 1, and FIGS. 3 and 4 are an implementation of a companion animal information sharing service using a harness camera according to an embodiment of the present invention. It is a drawing for explaining an embodiment.

Referring to FIG. 2 , the shared service providing server 300 includes a registration unit 310 , an extracting unit 320 , a storage unit 330 , a receiving unit 340 , a sharing unit 350 , a point unit 360 , and a recommendation. It may include a unit 370 and a big data conversion unit 380 .

At least one user terminal 100, at least one harness camera 400, and at least one research When transmitting a companion animal information sharing service application, program, app page, web page, etc. using a harness camera to the institution server 500 , at least one user terminal 100 , at least one harness camera 400 , and at least One research institute server 500 may install or open a companion animal information sharing service application using a harness camera, a program, an app page, a web page, and the like. In addition, the service program may be driven in at least one user terminal 100 , at least one harness camera 400 , and at least one research institute server 500 using a script executed in a web browser. Here, the web browser is a program that enables the use of a web (WWW: World Wide Web) service, and refers to a program that receives and displays hypertext written in HTML (Hyper Text Mark-up Language), for example, Netscape. , Explorer, Chrome, and the like. In addition, the application means an application on the terminal, for example, includes an app (App) executed in a mobile terminal (smartphone).

Referring to FIG. 2 , the registration unit 310 may register the mapping between the user terminal 100 and the harness camera 400 from the user terminal 100 . The user terminal 100 may upload the image data received from the harness camera 400 in real time through wireless or wired communication, and output result data based on the analysis result of the image data. The harness camera 400 is installed or provided to face in the face direction to photograph the face of the companion animal, is fixed and supported through a harness filled in part or all of the body of the companion animal, and image data obtained by photographing the face of the companion animal can be printed out.

The extractor 320 may extract the facial region or body region, which is an object included in the image data received from the harness camera 400 via the user terminal 100 , after pre-processing. In this case, YOLO can be used because YOLO can set a boundary box, that is, a bounding box, and recognize and analyze an object inside it in real time. Of course, various methods other than YOLO may be used.

The storage unit 330 may label and map the tag to the face region or the body region and store the label. At this time, in order to label a tag on a face region or a body region, specifically, in order to allow a “machine” rather than a “human” to process the labeling itself, an artificial intelligence algorithm for the corresponding labeling is separately required. For this, human observation and selection process are required initially. That is, for later artificial intelligence modeling, it can be defined as artificial intelligence algorithm modeling for labeling.

Through observation, 12 behaviors showing the highest frequency among multiple behaviors can be selected. The selected behavior may be, for example, Lying, Sitting, Standing, Shivering, Shaking, Barking, Eating, Drinking, Jumping, Slow-walking, Walking, Running, but is not limited thereto. For example, in order to determine a diseased dog, images and behavioral classification of a diseased dog may be required, and this may be added. In order to classify the behavior, first, the behavior of the dog can be classified and tagged using the Segmentation Tool. By analyzing the collected video images, it is possible to manually tag the dog's behavior and the beginning and the end according to the selected 12 behaviors.

In order to increase the accuracy of the behavior classification, the behavior data of the tagged dog can be classified using the SVM algorithm. The classified data can be used for machine learning and performance evaluation using the 5 fold-verication method. A plurality of tests can be performed by dividing the entire data into data to be used for learning and data to be used for testing. The emotion classification part allows various experts to manually select the emotions that appear in the dog at the beginning. The selected emotion may be selected as, for example, Pain, Hunger, Fear, Lonely, Enjoy, or Comofort, but does not exclude increase, transformation or deletion. A veterinarian or a dog behavior expert directly observes the dog's behavior and compares the selected 12 behaviors with 6 emotions.

After the classification and definition by humans is completed in this way, the artificial intelligence model can be configured to perform labeling by analyzing and predicting the dog's emotions according to the dog's behavior data. It can consist of a dog behavior video obtained through data collection, a manual tag graph using a segmentation tool, an expected tagging graph according to machine learning and performance evaluation, and six emotion graphs of dogs. For emotions according to each action, an average value of the prediction result can be obtained to create an emotion table, and emotions for other actions can be predicted on the time axis. When identification-monitoring-tracking-behavioral recognition-emotion recognition is completed in this way, these data can be stored for each user and used as input data of the storage unit 330 , and furthermore, the user can be informed. Accordingly, it is possible to understand in more detail abnormal behaviors or emotions that the user has not been able to properly grasp due to the small amount of time spent with the companion animal, and the storage unit 330 can automatically acquire input data.

The receiver 340 may receive feedback by transmitting the labeled tag to the user terminal 100 . For example, if a companion animal called “Jindol” is howling in video A, and the storage unit 330 labels the tag as “loneliness”, the receiver 340 transmits it to the user terminal 100, It is to be confirmed whether the scene is the scene where Jindol is currently lonely. Of course, since the user of the user terminal 100 is not his/her own business, he/she may not answer them one by one. In this case, the tag, which is a result of labeling based on the expert opinion described above, may be used as it is.

The sharing unit 350 may share the tag with image data corresponding to the face region or the body region when the feedback is positive feedback. The at least one research institute server 500 may construct big data by sharing image data and tags corresponding to the face region or the body region. In other words, research institutes need data to study animal behavior, disease, or abnormal symptoms, but there are not enough data for research in Korea. Research has not been able to keep up with the scale of the developed industry, and as if reflecting Korea's high floor area ratio, most Korean companion animals live in apartments or collective buildings. These collective buildings show different characteristics from those grown in foreign yards, and the damage caused is also different. This is because the barking behavior of a dog is not a problem behavior in a place where the distance between houses is wide, but in Korea where it is not, it becomes a reason for complaints or disputes. Accordingly, in order to study the characteristics of dogs and other companion animals living in "Korea", data on companion animals currently living in Korea are needed. To this end, an embodiment of the present invention collects image data of companion animals from Korean users in order to understand the characteristics of companion animals in Korea and distributes the labeled dataset to research institutions or researchers for free or for a fee. will do

The point unit 360 may accumulate points corresponding to compensation to the user terminal 100 based on the feedback rate and the capacity of the image data transmitted from the user terminal 100 . In this case, the compensation may be proportional to the capacity photographed and uploaded by the user terminal 100 , or may be based on the type and number of actually meaningful tags and image data. For example, if you filmed 6 hours and the puppy was sleeping all 6 hours, it would be difficult to label meaningful tags. In other words, although the amount of image data is large, it is difficult to say that meaningful image data for learning has been extracted. Accordingly, compensation may be provided based on the type or capacity. In this case, it is possible to cover the ever-increasing cost of managing pets with points, and if you use points to buy feed or snacks or if feed or treats are provided as compensation for free, the user pays for the cost of caring for pets. can ease the burden.

The recommendation unit 370 may extract at least one companion animal product and recommend it to the user terminal 100 based on a result of analyzing the companion animal, which is an object in the image data transmitted from the user terminal 100 . At this time, since the labeled tag has been verified, the corresponding tag can be used. For example, the recommendation unit 370 lists at least one product including at least one disease tag and at least one product tag selected from the user terminal 100, or at least one product whose similarity between tags exceeds a preset similarity. can be extracted. For example, if the tags selected by the user are A, B, and C, and the "A" feed sold by the seller includes all of A, B, and C, you can extract the "A" feed, but when the tag becomes complicated There may not be a product that reflects all of the user-selected characteristics, i.e., tags. In this case, the most similar tag should be selected. Since the vectorized tag exists as described above, the similarity can be measured by the Euclidean distance or the cosine similarity, and products can be extracted and listed in the order of the highest similarity. have. At this time, since the Euclidean distance and the cosine similarity are the same as those of the known technology, they will not be described in detail.

At this time, the degree of similarity between each keyword or tag (product keyword (OR tag) vs. question or answer keyword (OR tag)) is different by expressing the word as a vector and expressing the weight between the words as the Euclidean distance and cosine similarity. Even if used, positive feedback can be provided when referring to the same term. In addition, in order to extract words by morphological analysis of the described user text and to provide automatic feedback based on the frequency of occurrence of words, or to overcome the limitations of morpheme analysis, conceptual information of words is extracted and used to measure similarity. A method of reflecting or reflecting a syntactic relationship between words and a semantic relationship may be used. In addition, the method of applying syntactic semantic analysis to the sentences of the answer and using the resulting syntax and case semantic information, or comparing the syntactic semantic tree resulting from the syntactic semantic analysis, and using a comparator to compare the syntactic semantic tree are also used. can be

When the feedback is positive feedback, the big data conversion unit 380 may construct big data as a dataset by mapping image data corresponding to the face region or the body region and tags. If there is no feedback from the user terminal 100 or the training dataset is insufficient or further learning is required, a bot such as a web crawler may be used to collect raw data. Here, the bot may be a web macro bot, but is not limited thereto. A macro program is a software that automatically programs and processes simple/repetitive tasks. Simple tasks using a computer are usually performed manually by inputting tasks such as keyboard and mouse input values and input sequence in advance to automatically and repeatedly execute them. used to increase the efficiency of Automating simple/repetitive tasks using a macro program is necessary for efficient business processing, and the macro program can be configured in a way that automates permitted commands.

In this case, the dataset may include companion animal information including the species, age, disease, weight, and height of the companion animal included in the image data input from the user terminal 100 . In addition, the big data conversion unit 380 parallelly and distributedly stores raw data including companion animal information, image data, and tags that have received positive feedback collected from the user terminal 100, and stores it in the stored raw data. Refining the included unstructured data, structured data and semi-structured data, performing preprocessing including classification as meta data, and data mining the preprocessed data. analysis can be performed.

In addition, the big data conversion unit 380 collects the companion animal's medical record data (Electronic Medical Record) and the ANICOM code, which is a diagnostic code, from at least one veterinary hospital terminal to generate learning data, and uses a random forest. Thus, when a symptom is input as a query, a diagnosis code is output and a report can be made as an expected disease. If the above-described sharing unit 350 collects and classifies abnormal behavior or disease symptoms based on the image, the big data conversion unit 380 classifies and learns the disease based on the disease code and symptom text data, and then new symptoms are generated. When inputted, the disease code is extracted.

The big data conversion unit 380 may first collect scattered data between hospitals in order to build a diagnosis assistance model, and integrate and classify data format preprocessing tasks such as matching different data formats and codes between hospitals and symptoms and diagnostic codes. can do the job. A model for diagnostic classification may be built based on a random forest model. The random forest model is built to output a list of diagnosis names with a high probability of inputting personal information, symptoms, and test results of companion animals. The construction process of the random forest model is divided into three parts. The first is the ANICOM code integration process, the second is the preprocessing and integration of companion animal EMR confirmation data, and the third is the random forest learning process.

Since a lot of medical record data (EMR, Electronic Medical Record) is essential for diagnostic accuracy to be used in an actual veterinary hospital, it is necessary to collect a large amount of data from as many animal hospitals as possible. However, the attribute name of the medical record data is different for each hospital, and above all, the current situation is that different codes are used for each veterinary hospital because there is no unified diagnosis name category. There is a problem of discrepancy between the test result values for the same test item. In order to solve these data integration problems, the data attribute matching operation, the coding process of using the Japanese ANICOM code to modify 22 diagnostic codes, and the preprocessing of discretizing and mutually calibrating the test result values for each equipment work is required

One of the important tasks in the data integration process is to unify different diagnosis names for each hospital. Unfortunately, there is no integrated companion animal diagnosis code in Korea yet. For this reason, the diagnosis name can be coded using the ANICOM code, which is a disease code that has already been verified and is used in Japan. The code classifies disease names into major and minor categories. There are 16 major categories, and each major category has a sub-category diagnosis name, which is a total of 303. Here, the sub-categories can be reduced to 291 except for the case of exotic animals. The major category consists of digestive, circulatory, respiratory, and urinary organs. For example, in the digestive major category, it is subdivided into sub-categories such as gastritis, enteritis, vomiting, and diarrhea. The final diagnostic classification can be set to a total of 22 diagnostic classes by adding 12 major categories and 10 frequent diseases (out of 291 diseases that occur mainly in companion animals) except for the 8, 9, and 11 major categories with a small number of data. . This is because the number of collected data is not sufficient to build a diagnostic classification model in the small classification dimension (291 classes). It can be added to a large category. Because frequent disease is a disease belonging to an existing large category, it can be removed from the corresponding large category so that it does not overlap.

Second, it is the pre-processing and integration process of companion animal EMR confirmation data. Even if the same symptoms and diagnoses are collected from veterinary hospitals, the preprocessing process is essential before data integration because all veterinary hospitals do not use the same symptom name and test item name. The basic pet's breed, age, and gender information can be used as it is. The pre-processing process consists of a total of three steps: ① symptom coding, ② integration of standard names of test items, and ③ grading of test results. In the case of symptom attributes, opinions input by veterinarians during examination are mostly in text form, so they can be categorized and, like diagnostic attributes, can be standardized into a total of 80 symptom categories through validation by a veterinarian. Another difficulty in integrating the collected data is the properties of the test equipment (the total number of equipment is 9 blood test equipment and 14 chemical test equipment) used in veterinary hospitals (name of item in EMR, range of test results) etc.) may not be the same. In order to match the test names of the same type of test equipment, the process of integrating them into 64 standard test names can be further processed after being verified by a veterinarian. In addition, in order to integrate the measurement result values of the same type of inspection equipment that have different inspection values due to different manufacturers, it can be reset based on the normal range of each inspection equipment.

The third stage is the random forest learning stage. Assuming that the companion animal diagnostic classification model provides diagnostic information with high probability among 22 diagnostic classes based on 147 predictive factors, in theory of machine learning, the input dimension of 147 for the number of 6,500 data sets is quite high. In addition, due to the nature of the medical field, the user's interpretability for inference results is also an important factor in model selection. In consideration of this point, a random forest model can be adopted, because the random forest model has slightly different properties due to randomness in order to handle high-dimensional data, and the predictions of each tree are non-correlated. In addition, we randomize to deal with noise caused by various predictors.

The random forest is an evolution of the existing classification regression tree. Classification regression tree is a technique for judging the influence on variables by maximizing the nonlinearity and interaction of explanatory variables or predictors. A branch is created for explanatory variables according to importance criteria, and judgments are made about response variables at leaf nodes. At this time, the top 5 classes (diagnostic classification names) with high probability in the leaf node are presented to the user. Rather than presenting only one diagnosis out of 22 diagnostic categories for an input with 147 attributes, the method of providing the top 5 diagnostic categories with the highest probability out of 22 classes with the probability of the corresponding category is better than the method of presenting only one diagnosis among 22 diagnostic categories. Due to the nature of the primary veterinary hospital that diagnoses, the effectiveness of the diagnostic assistance system can be doubled. Of course, it will be obvious that a disease can be derived or a diagnosis name for a symptom can be derived by various methods other than the above-described method, and it is not limited to the listed ones and is not excluded for reasons not listed.

Hereinafter, an operation process according to the configuration of the shared service providing server of FIG. 2 will be described in detail with reference to FIGS. 3 and 4 as an example. However, it will be apparent that the embodiment is only one of various embodiments of the present invention and is not limited thereto.

Referring to FIG. 3 , (a) the shared service providing server 300 registers companion animal information from the user terminal 100 and interlocks the harness camera 400 . And, (b) the shared service providing server 300 identifies the object in the uploaded image data, identifies the current behavioral state and emotional state through facial recognition of the object, and then labels the tag. Then, image data and the tag are transmitted to the user terminal 100 to confirm whether the tag is properly labeled. In addition, (c) after constructing the collected behaviors or emotional states of various companion animals of various users as a dataset, the shared service providing server 300 provides the at least one research institution server 500 for free or for a fee. distribution, and (d) a compensation process of distributing a portion of the proceeds of the sale price to the user terminal 100 or providing free feed, etc. is performed.

Referring to FIG. 4 , (a) the shared service providing server 300 collects information about a disease, disease, or health condition of a companion animal from the user terminal 100, and collects it separately along with image data and tags. Big data may be built together using EMR data, or rewards such as snacks or toys may be provided to the user terminal 100 that has provided this information. (b) The user terminal 100 may exchange this reward for snacks or feed, or use it for a discount. (c) In this way, when behavior-emotions, etc. are learned or analysis of abnormal behavior is completed, the shared service providing server 300 analyzes the image collected in real time with the harness camera 400 and uses it to analyze the image collected by the user terminal 100 ), and when the user terminal 100 outputs a preset voice or uses the user terminal 100 and a real-time voice channel to hear the user's voice from the harness camera 400 or the home network is established, the artificial intelligence speaker (not shown) and so on.

The matters not described for the method of providing the companion animal information sharing service using the harness camera of FIGS. 2 to 4 are the same as those described above for the method of providing the companion animal information sharing service using the harness camera through FIG. 1 or Since it can be easily inferred from the described content, the following description will be omitted.

5 is a diagram illustrating a process in which data is transmitted/received between components included in the system for providing a companion animal information sharing service using the harness camera of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of a process in which data is transmitted and received between each component will be described with reference to FIG. 5, but the present application is not limited to such an embodiment, and the example shown in FIG. 5 according to the various embodiments described above will be described. It is apparent to those skilled in the art that the data transmission/reception process may be changed.

Referring to FIG. 5 , the shared service providing server maps and registers a user terminal and a harness camera from a user terminal (S5100), and a facial area or body that is an object included in image data received from the harness camera via the user terminal. The region is extracted after pre-processing (S5200).

In addition, the shared service providing server labels and maps the tag to the facial region or the body region and stores it (S5300), and transmits the labeled tag to the user terminal to receive feedback (S5400).

Finally, when the feedback is positive feedback, the shared service providing server shares the tag with image data corresponding to the face region or body region ( S5500 ).

The order between the above-described steps (S5100 to S5500) is only an example, and is not limited thereto. That is, the order between the above-described steps ( S5100 to S5500 ) may be mutually changed, and some of these steps may be simultaneously executed or deleted.

The matters not described with respect to the method for providing the companion animal information sharing service using the harness camera of FIG. 5 are the same as those described above for the method for providing the companion animal information sharing service using the harness camera through FIGS. 1 to 4, or Since it can be easily inferred from the described content, the following description will be omitted.

The method for providing a companion animal information sharing service using a harness camera according to an embodiment described with reference to FIG. 5 is also in the form of a recording medium including instructions executable by a computer, such as an application or program module executed by a computer. can be implemented. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, computer-readable media may include any computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

In the method of providing a companion animal information sharing service using a harness camera according to an embodiment of the present invention described above, an application basically installed in a terminal (which may include a program included in a platform or an operating system basically installed in the terminal) may be executed by the application store server, an application or an application (ie, a program) directly installed in the master terminal through an application providing server such as a web server related to the application or the corresponding service by the user. In this sense, the method for providing a companion animal information sharing service using a harness camera according to an embodiment of the present invention described above is implemented as an application (ie, a program) installed basically in a terminal or directly installed by a user, and is It may be recorded on a computer-readable recording medium.

The above description of the present invention is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and likewise components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

Claims (7)

A harness camera that is installed or provided to face in the face direction so as to photograph the face of the companion animal, is fixed and supported through a harness filled in part or all of the body of the companion animal, and outputs image data of the face of the companion animal ;
a user terminal for uploading the image data received from the harness camera in real time through wireless or wired communication, and outputting result data based on the analysis result of the image data; and
a registration unit for mapping and registering the user terminal and the harness camera from the user terminal; A storage unit for labeling, mapping, and storing tags on a face region or body region, a receiver unit for transmitting the labeled tag to the user terminal to receive feedback, and if the feedback is positive feedback, the facial region or body region a sharing service providing server including a sharing unit for sharing image data corresponding to and the tag;
Companion animal information sharing service providing system using a harness camera that includes.
The method of claim 1,
Companion animal information sharing service providing system using the harness camera,
at least one research institute server configured to construct big data by sharing the tag and image data corresponding to the face region or body region;
Companion animal information sharing service providing system using a harness camera, characterized in that it further comprises.
The method of claim 1,
The shared service providing server,
a point unit for accumulating points corresponding to compensation to the user terminal based on the capacity and feedback rate of the image data transmitted from the user terminal;
Companion animal information sharing service providing system using a harness camera, characterized in that it further comprises.
The method of claim 1,
The shared service providing server,
a recommendation unit that extracts at least one companion animal product based on a result of analyzing the companion animal, which is an object in the image data transmitted from the user terminal, and recommends it to the user terminal;
Companion animal information sharing service providing system using a harness camera, characterized in that it further comprises.
The method of claim 1,
The shared service providing server,
a big data conversion unit for constructing big data as a dataset by mapping the tag with the image data corresponding to the face region or body region when the feedback is positive feedback;
Companion animal information sharing service providing system using a harness camera, characterized in that it further comprises.
6. The method of claim 5,
The dataset is a harness camera comprising companion animal information including species, age, disease, weight and height of companion animals included in the image data input from the user terminal. Companion animal information sharing service providing system using
6. The method of claim 5,
The big data conversion unit,
Companion animal information collected from the user terminal, image data, and raw data including tags receiving positive feedback are stored in parallel and distributed, and unstructured data and structured data included in the stored raw data are stored. ) Refining data and semi-structured data, performing pre-processing including classification as metadata, and analyzing the pre-processed data including data mining. Companion animal information sharing service providing system using

Images