Method and system for determining risk level based on abnormal recumbency

Abstract

According to an aspect of the present invention, a method for determining a risk level according to abnormal recumbency of a target subject is provided, the method comprising the steps of: acquiring information related to movement of a target subject; generating information related to a recumbency behavior on the basis of the acquired information related to movement; and determining information related to a risk level according to abnormal recumbency on the basis of the generated information related to the recumbency behavior.

Description

Method and system for determining risk according to abnormal transverse curvature

[0001] The present invention relates to a method and system for determining risk according to an abnormal transverse angle.

[0002] Abnormal lateral rolling, or lateral rolling, refers to a situation in which a cow is unable to get up after lateral rolling. This situation can pose a serious health risk to the cow. The severity of the problem is particularly acute when lateral rolling occurs at night while the operator (manager) is asleep, as prompt response is impossible. Therefore, without continuous monitoring of the cow's movements and health during the night, it becomes difficult to detect and respond promptly to injuries or illnesses resulting from lateral rolling.

[0003] Cows that remain in a lateral position for extended periods can suffer from rumen damage, circulatory problems, muscle and tissue damage, and even death. This causes economic losses for farm operators and negatively impacts cow welfare. Furthermore, accidents occurring at night can delay response times, potentially increasing the scale of the damage.

[0004] To address these issues, a 24-hour detection system capable of monitoring cattle in real time, even during the night, is essential. This allows for rapid detection of abnormal lateral movements and appropriate action, protecting cattle health and improving farm operational efficiency.

[0005] Accordingly, the inventor(s) of the present invention propose a monitoring technology that can effectively detect sideways accidents that frequently occur, especially at night, and quickly warn users, thereby contributing to farm management and accident prevention.

[0006] The purpose of the present invention is to solve all of the problems of the above-mentioned prior art.

[0007] In addition, the present invention has another purpose of obtaining information related to the movement of a target object, generating information related to a lateral movement behavior based on the information related to the obtained movement, and determining information related to the risk of an abnormal lateral movement based on the information related to the generated lateral movement behavior.

[0008] In addition, another object of the present invention is to detect abnormal transverse movements by sensing the movement of a target object and analyzing the pattern of transverse and recumbent movements, and to determine the level of risk accordingly, and to maximize the efficiency of detecting abnormal transverse movements by providing different risk calculation algorithms for each time zone.

[0009] A representative configuration of the present invention to achieve the above purpose is as follows.

[0010] According to one aspect of the present invention, a method is provided, comprising: a step of obtaining information related to movement of a target object; a step of generating information related to a lateral movement behavior based on the information related to the obtained movement; and a step of determining information related to a risk level according to an abnormal lateral movement based on the information related to the generated lateral movement behavior.

[0011] According to another aspect of the present invention, a system is provided, including a movement information acquisition unit that acquires information related to the movement of a target object, a lateral movement information generation unit that generates information related to a lateral movement behavior based on the information related to the acquired movement, and a risk determination unit that determines information related to a risk according to an abnormal lateral movement based on the information related to the generated lateral movement behavior.

[0012] In addition, a non-transitory computer-readable recording medium recording another method for implementing the present invention, another system, and a computer program for executing the method are further provided.

[0013] According to the present invention, information related to the movement of a target object can be acquired, information related to a lateral movement can be generated based on the acquired information related to the movement, and information related to the risk of an abnormal lateral movement can be determined based on the generated information related to the lateral movement.

[0014] In addition, according to the present invention, by sensing the movement of a target object and analyzing the pattern of the lateral and recumbent behavior, an abnormal lateral movement is detected, the risk level is determined accordingly, and a risk level calculation algorithm that changes by time zone is provided, thereby maximizing the efficiency of abnormal lateral movement detection.

[0015] FIG. 1 is a diagram schematically illustrating the configuration of an entire system for determining the risk level according to an abnormal transverse curvature of a target object according to one embodiment of the present invention.

[0016] FIG. 2 is a drawing showing in detail the internal configuration of a risk determination system (200) according to one embodiment of the present invention.

[0017] FIG. 3 is a diagram exemplarily showing a process of detecting an abnormal horizontal axis and notifying a user of the same through a risk determination algorithm that changes according to a time zone according to one embodiment of the present invention.

[0018] <Explanation of symbols>

[0019] 100: Communications network

[0020] 200: Risk Determination System

[0021] 210: Movement information acquisition unit

[0022] 220: Horizontal information generation unit

[0023] 230: Risk Determination Unit

[0024] 240: Notification Information Decision Unit

[0025] 250: Communications Department

[0026] 260: Control unit

[0027] 300: Device

[0028] The following detailed description of the present invention refers to the accompanying drawings, which illustrate specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present invention. It should be understood that the various embodiments of the present invention, while different from each other, are not necessarily mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be modified and implemented from one embodiment to another without departing from the spirit and scope of the present invention. Furthermore, it should be understood that the positions or arrangements of individual components within each embodiment may also be modified without departing from the spirit and scope of the present invention. Accordingly, the following detailed description is not to be taken in a limiting sense, and the scope of the present invention is to be construed to encompass the scope of the claims and all equivalents thereof. Like reference numerals in the drawings represent the same or similar elements throughout the several aspects.

[0029] Hereinafter, various preferred embodiments of the present invention will be described in detail with reference to the attached drawings so that a person having ordinary skill in the art to which the present invention pertains can easily practice the present invention.

[0030] In this specification, the term "lateral lying" may refer to a posture in which a subject lies on his or her side. Specifically, in the lateral lying posture, the subject lies with the torso parallel to the floor, and the limbs may be extended to the side. The lateral lying posture may be a natural resting posture, or it may be caused as an abnormal symptom due to various abnormal conditions such as disease, injury (e.g., dislocation, etc.), difficult childbirth (e.g., dystocia, etc.), stress, poisoning, digestive problems (e.g., digestive diseases such as bloating, etc.), and nervous system problems (e.g., paralysis and brain damage, etc.).

[0031] In this specification, the term "abnormal transverse curvature" refers to any type of transverse curvature other than normal transverse curvature, and may refer to abnormal transverse curvature caused by various abnormal conditions as described above. Meanwhile, the term "abnormal transverse curvature" has the same meaning as the term "transverse curvature accident," and thus may be used interchangeably.

[0032] In this specification, the term "prone" refers to a movement that includes a state in which a subject's stomach and chest are pressed against the ground, and may refer to a movement included in the process of attempting to stand up after lying face down. Specifically, a subject in a face down state can stand up through a movement process that includes a prone action (prone state) as follows: (1) face down state (a state in which the subject is lying on its side), (2) transition process (a process in which the subject changes its center of gravity and moves to a prone state, in which the subject changes its posture by tilting the body or moving the legs so that the stomach and chest touch the ground, and in this process, the subject's head and neck are raised and an attempt is made to transfer its weight to the forelegs), (3) prone state (the subject's body is supported by the stomach and chest, and a stable posture is maintained in preparation for standing up), and (4) standing up (the subject completely stands up from a prone state using the legs).

[0033] Therefore, by measuring the pattern of the lying down behavior and prone behavior, it is possible to determine whether the target individual escapes or fails to escape from the lying down state after the lying down state. That is, by sensing the number and interval of the lying down behavior of the target individual after the lying down state, it is possible to determine whether the target individual escapes the lying down state and successfully stands up (i.e., the number of lying down behaviors after the lying down state is low, and the behavior of the target individual moving in a specific direction after the lying down behavior is sensed, etc.) or fails to stand up (i.e., the number of lying down behaviors after the lying down state is high, or the number of lying down behaviors is high and then the interval between the lying down behaviors gradually increases until eventually the lying down behavior is no longer sensed, etc.). In conclusion, if there is an attempt to lie down after the lying down state but fails to stand up (i.e., continues to be in the lying down state), it can be determined as an abnormal lying down state or a lying down accident.

[0034] Composition of the entire system

[0035] FIG. 1 is a diagram schematically illustrating the configuration of an entire system for determining the risk level according to an abnormal transverse curvature of a target object according to one embodiment of the present invention.

[0036] As illustrated in FIG. 1, the entire system according to one embodiment of the present invention may include a communication network (100), a risk determination system (200), and a device (300).

[0037] First, the communication network (100) according to one embodiment of the present invention can be configured regardless of the communication mode such as wired communication or wireless communication, and can be configured with various communication networks such as a local area network (LAN), a metropolitan area network (MAN), and a wide area network (WAN). Preferably, the communication network (100) referred to herein may be the well-known Internet or the World Wide Web (WWW). However, the communication network (100) is not necessarily limited thereto, and may include at least a portion of a well-known wired or wireless data communication network, a well-known telephone network, or a well-known wired or wireless television communication network.

[0038] For example, the communication network (100) may be a wireless data communication network that implements conventional communication methods such as WiFi communication, WiFi-Direct communication, Long Term Evolution (LTE) communication, 5G communication, Bluetooth communication (including Bluetooth Low Energy (BLE) communication), infrared communication, ultrasonic communication, etc., at least in part. As another example, the communication network (100) may be an optical communication network that implements conventional communication methods such as LiFi (Light Fidelity), etc., at least in part.

[0039] Next, the risk determination system (200) according to one embodiment of the present invention can perform a function of acquiring information related to the movement of a target object, generating information related to a lateral motion based on the acquired information related to the movement, and determining information related to a risk according to an abnormal lateral motion based on the generated information related to the lateral motion.

[0040] The configuration and function of the risk determination system (200) according to the present invention will be described in detail below.

[0041] Next, a device (300) according to one embodiment of the present invention is a digital device that includes a function for communicating after being connected to a risk determination system (200), and any digital device having a memory means, a microprocessor, and a computing capability, such as a smart phone, a tablet, a smart watch, a smart band, smart glasses, a desktop computer, a notebook computer, a workstation, a PDA, a web pad, a mobile phone, etc., can be adopted as the device (300) according to the present invention.

[0042] In particular, the device (300) may include an application (not shown) that supports the user to receive services such as information on the occurrence of a sideways accident and the risk of the accident from the risk determination system (200). Such an application may be downloaded from the risk determination system (200) or an external application distribution server (not shown). Meanwhile, the characteristics of such an application may be generally similar to the movement information acquisition unit (210), sideways information generation unit (220), risk determination unit (230), notification information determination unit (240), communication unit (250), and control unit (260) of the risk determination system (200), which will be described later. Here, at least a part of the application may be replaced with a hardware device or firmware device that can perform functions substantially the same as or equivalent to it, as necessary.

[0043] Composition of the risk assessment system

[0044] Below, the internal configuration and functions of each component of the risk determination system (200) that performs important functions for implementing the present invention will be examined.

[0045] FIG. 2 is a drawing showing in detail the internal configuration of a risk determination system (200) according to one embodiment of the present invention.

[0046] As illustrated in FIG. 2, a risk determination system (200) according to an embodiment of the present invention may include a movement information acquisition unit (210), a lateral information generation unit (220), a risk determination unit (230), a notification information determination unit (240), a communication unit (250), and a control unit (260). According to an embodiment of the present invention, at least some of the movement information acquisition unit (210), the lateral information generation unit (220), the risk determination unit (230), the notification information determination unit (240), the communication unit (250), and the control unit (260) may be program modules that communicate with an external system (not shown). These program modules may be included in the risk determination system (200) in the form of an operating system, an application program module, or other program modules, and may be physically stored in various known memory devices. In addition, these program modules may also be stored in a remote memory device capable of communicating with the risk determination system (200). Meanwhile, these program modules include, but are not limited to, routines, subroutines, programs, objects, components, data structures, etc. that perform specific tasks or execute specific abstract data types, as described later in accordance with the present invention.

[0047] Meanwhile, although the risk determination system (200) has been described as above, this description is exemplary, and it is obvious to those skilled in the art that at least some of the components or functions of the risk determination system (200) may be realized within a device (300) or a server (not shown) or included within an external system (not shown) as needed.

[0048] First, the movement information acquisition unit (210) according to one embodiment of the present invention can perform a function of acquiring information related to the movement of a target object.

[0049] According to one embodiment of the present invention, the target object may refer to an animal or livestock used in agriculture or livestock farming. Specifically, the target object may refer to a ruminant, and more specifically, may be a cow, sheep, goat, deer, or water buffalo, and most specifically, may be a cow (e.g., a cow raised in a barn). However, the target objects listed above are merely examples, and any type of animal exhibiting lateral lounging behavior may be included as a target object without limitation.

[0050] Information related to movement according to one embodiment of the present invention may refer to all types of information regarding the movement or posture of a target object. Specifically, the movement of a target object according to one embodiment of the present invention may refer to the movement behavior of the target object in the forward, backward, left, right, up, and down directions. Meanwhile, such information related to movement should be understood as a concept that includes not only the movement behavior of the target object in a specific direction, but also the actions of the target object moving each part of its body. For example, in a situation where a target object stands in place and then sits down, or a situation where a target object sits and then transitions to a sideways posture, even if the target object does not move in a specific direction, the movement of the body in the up and down directions when sitting or the body leaning to one side (left or right) when transitioning to a sideways posture may all be included in the information related to movement according to one embodiment of the present invention.

[0051] According to one embodiment of the present invention, the direction of movement may be divided into up, down, left, right, front, and back directions with the target object as the center and displayed. The up direction may be defined as the spine direction (upward) of the target object, the down direction may be defined as the belly direction (downward) of the target object, the left direction may be defined as the left side of the target object (the side where the left ear, the left foreleg, and the left hind leg are located), the right direction may be defined as the right side of the target object (the side where the right ear, the right foreleg, and the right hind leg are located), the forward direction may be defined as the head direction (forward) of the target object, and the back direction may be defined as the buttocks or tail direction (backward) of the target object.

[0052] Continuing, information related to movement according to one embodiment of the present invention may refer to coordinate values ​​of a target object or a sensor capable of detecting movement attached to the target object and the degree of change in the coordinate values ​​(e.g., speed and acceleration, etc.). The above-described coordinates may be calculated with the upper and lower directions as the z-axis, the left and right directions as the x-axis, and the front and rear directions as the y-axis based on the target object. However, the description of the above-described coordinates and axes is merely exemplary and may be changed as much as it is consistent with the purpose of the present invention.

[0053] According to one embodiment of the present invention, movement information of a target object can be obtained through (1) a wearable device-based sensing method and (2) a non-invasive sensing method.

[0054] A wearable device-based sensing method according to one embodiment of the present invention is a method of measuring movement by attaching a specific device to the body of a target object, and may mean, for example, a method of sensing movement of a target object using a wearable device including an accelerometer, gyroscope, GPS sensor, IMU sensor, or RFID tag mounted on the body of an animal.

[0055] For example, a device for sensing movement information of a target object according to one embodiment of the present invention is a necklace-type wearable device that can be attached to the neck of a target object to sense and collect movement-related information, and may be a movement detection sensor including at least one of an accelerometer, a gyroscope, and a GPS.

[0056] A non-invasive sensing method according to one embodiment of the present invention is a method of measuring the movement of a target object externally instead of mounting a physical device on the body of the target object, and may mean a method of sensing the movement of a target object using, for example, video monitoring, LiDAR, a thermal camera, a pressure sensor (which measures movement through pressure applied by the target object to the ground or a structure), a vibration sensor (which measures movement through vibration of the target object's footsteps), or an ultrasonic sensor.

[0057] Specifically, information related to movement according to one embodiment of the present invention may be information related to acceleration in the up, down, left, and right directions.

[0058] That is, information related to movement can be information in the up, down, left, right, forward, and backward directions, excluding the forward and backward directions.

[0059] Information related to acceleration according to one embodiment of the present invention is data collected through an acceleration sensor, and may mean the rate of change of velocity per unit time in each direction.

[0060] That is, information related to movement according to one embodiment of the present invention may be the rate of change in velocity per unit time of a target object (or a wearable device attached to the target object) in each of the up, down, left, and right directions.

[0061] For example, (1) information related to left and right movement may refer to acceleration that occurs when the cow turns its head left and right or moves left and right, and (2) information related to up and down movement may refer to acceleration that occurs in a downward direction, such as when the target object goes from standing to lying down, and acceleration that occurs in an upward direction, such as when the target object goes from lying to prone or standing.

[0062] Specifically, information related to acceleration may be an acceleration value and a degree of change in the acceleration value.

[0063] The change in acceleration value according to one embodiment of the present invention may refer to the degree of change in acceleration value measured separately during a predetermined time interval. For example, if (1) the case where the acceleration value in the first section is 5 and the acceleration value in the second section which is temporally later than the first time section is compared with (2) the case where the acceleration value in the first section is 5 and the acceleration value in the second section which is temporally later than the first time section is compared, the degree of change in acceleration value in the case of (1) described above is greater.

[0064] Specifically, the degree of change in the acceleration value can be calculated based on the average and variance of the acceleration value over at least one time interval.

[0065] That is, the degree of change in the acceleration value described above can mean the degree of change in acceleration values ​​for one or more time intervals measured based on at least one time interval. This degree of change can mean how much the acceleration values ​​of one or more time intervals described above are spread out with respect to the average value, and specifically, it can be measured by calculating the variance of the acceleration value(s) for one or more time intervals. That is, if the variance value is large, it can be determined that the change in the acceleration value is large and the movement of the target object is large, and if the variance value is small, it can be determined that the change in the acceleration value is small and the movement of the target object is small or at a standstill. For example, if the variance of the acceleration value is small in a specific time interval, it can be determined that the cow is sitting or lying down in the specific time interval, and if the variance of the acceleration value is large in the specific time interval, it can be determined that the cow is sitting and then standing up, or lying down and then prone (attempting to stand up) in the specific time interval.

[0066] For example, if a specific lateral roll is a normal lateral roll, a stable state is maintained like a lateral roll and then easily succeeds in prone roll or standing up. In this case, the acceleration value will maintain a state with small dispersion (i.e., a stable state) and then the dispersion of the acceleration value will increase at one time (i.e., successfully stands up with just one prone roll). On the other hand, in the case of an abnormal lateral roll, a stable state is maintained until multiple prone roll attempts occur (i.e., a situation where the prone roll attempts continue to fail), or the interval between prone roll attempts gradually increases (i.e., the target subject becomes tired and eventually fails to prone roll attempts), etc., a specific behavioral pattern will appear in which the target subject fails to prone roll or stand up. Even in these cases, the specific behavioral pattern can be identified through the dispersion of the acceleration value.

[0067] Sensing or judging movement through the degree of change in these acceleration values ​​may be accomplished using a specific algorithm, or may be accomplished through an artificial intelligence model that can sense or judge movement by analyzing the degree of change or change pattern of the acceleration value.

[0068] Meanwhile, the reference time interval for calculating the aforementioned acceleration values ​​can be changed as needed. For example, if the time interval is set to 1 minute, speed and acceleration values ​​are calculated based on 1 minute, and information related to the movement of the target object can be determined based on the degree of change in the multiple calculated acceleration values. However, during risky times (e.g., nighttime), this time interval can be set shorter (e.g., 30 seconds) to allow for more stringent monitoring of the target object.

[0069] Next, the transverse information generation unit (220) according to one embodiment of the present invention can perform a function of generating information related to a transverse motion based on information related to the acquired movement.

[0070] Information related to a lateral movement behavior according to one embodiment of the present invention may mean all information on a behavior or posture analyzed as a lateral movement behavior among the results of analyzing the behavior or posture of a target object based on information related to movement.

[0071] Specifically, information related to a lateral movement according to one embodiment of the present invention may include characteristics of a lateral movement and characteristics of a prone movement.

[0072] The characteristics of the lateral movement behavior according to one embodiment of the present invention should be understood to encompass all information regarding the lateral movement behavior of the target object, but specifically, may be at least one of the number of lateral movements and the duration of the lateral movement behavior.

[0073] The number of lateral movements described above may refer to the time over which the target object's movements were measured, or the number of lateral movements over a given period of time. In other words, a high number of lateral movements may mean that the target object frequently engages in lateral movements, but this does not necessarily mean that the lateral movements last a long time.

[0074] The aforementioned duration of the lateral movement may refer to the duration of a single lateral movement. In other words, a long lateral movement duration may mean that the subject is continuing the lateral movement for a long time, but it may not necessarily mean that the number of lateral movements is high.

[0075] The characteristics of the prone behavior according to one embodiment of the present invention should be understood to encompass all information about the prone behavior of the target object, but specifically, the characteristics of the prone behavior may be at least one of the number of prone behaviors after the transverse behavior and the time interval between the prone behaviors after the transverse behavior.

[0076] According to one embodiment of the present invention, the number of prone behaviors after the lying-down behavior may refer to the number of prone behaviors that the target individual has performed in an attempt to stand up from a lying-down state, and specifically, may refer to the number of prone behaviors when the subject has performed the lying-down behavior in a lying-down state but failed to stand up and has repeated the lying-down behavior. For example, if the number of prone behaviors performed in a lying-down state is less than a threshold value, it can be determined that the subject has successfully stood up normally, and thus the lying-down state is a normal lying state, whereas if the number of prone behaviors performed in a lying-down state is more than a threshold value, it can be determined that the subject has not successfully stood up and continues to be in a lying-down state, and thus the lying-down state is an abnormal lying state.

[0077] The time interval between the prone behavior after the lying-down behavior according to one embodiment of the present invention may mean the time interval between the prone behaviors when the target object attempts to stand up from the lying-down state by performing the prone behavior more than twice, and specifically, may mean the time interval between multiple prone behaviors when the target object performs the prone behavior from the lying-down state but fails to stand up and repeats the prone behavior.

[0078] That is, the risk determination system (200) according to one embodiment of the present invention can determine whether the lateral movement behavior of a target object is normal or whether the lateral movement behavior of the target object corresponds to an abnormal lateral movement (i.e., the risk of the lateral movement behavior) by applying a predetermined standard based on the pattern (combined pattern) of the lateral movement behavior and the recumbent movement behavior.

[0079] Next, the risk determination unit (230) according to one embodiment of the present invention can perform a function of determining information related to the risk according to an abnormal lateral movement based on information related to the generated lateral movement behavior.

[0080] Information related to the risk of abnormal lateral movement according to one embodiment of the present invention may include the probability that the lateral movement behavior of the target object corresponds to an abnormal lateral movement (i.e., the probability that a lateral movement accident occurred in the target object).

[0081] The probability of the above-mentioned abnormal side rolling is the abnormal side rolling probability finally calculated based on information related to the above-mentioned side rolling behavior, and specifically, (1) based on the fact that the risk of a side rolling accident is high when a prone behavior is repeated after a side rolling behavior, it can be determined in a manner that the probability of a side rolling accident occurring is high in proportion to at least one of the number of side rolling behaviors, the number of prone behaviors, the frequency of the prone behavior, the frequency of the prone behavior, and the duration of the prone behavior, or (2) by setting a standard for a normal side rolling and determining that the probability of an abnormal side rolling is high in proportion to the degree of difference compared to the standard.

[0082] For example, we can assume that the subject performed the first prone behavior 30 seconds after the prone behavior, the second prone behavior 1 minute after the prone behavior, and the third prone behavior 5 minutes after the prone behavior. In this situation, the probability of corresponding to an abnormal lateral lying down according to an embodiment of the present invention can be calculated by inputting the frequency of the prone behavior (e.g., 3 times in 5 minutes) into a predetermined formula in the manner of (1) described above to calculate the probability of corresponding to an abnormal lateral lying down, and comparing it with the standard of normal lateral lying down (e.g., the standard that the interval between repeated prone behaviors thereafter is relatively constant in the case of normal lateral lying down) in the manner of (2) described above to derive the difference (i.e., the time interval between the initial prone behaviors was short, but the time interval between subsequent prone behaviors increased (i.e., the target individual attempted to stand up, failed to stand up, and gradually became tired), so that it is different from the example of the above-described normal lateral lying down standard), and calculating the probability of corresponding to an abnormal lateral lying down based on this.

[0083] To elaborate on the case (1) described above, the frequency of lateral movement and the time of lateral movement are each multiplied by different coefficients (these coefficients may vary depending on the environment of the livestock shed or farm where the target object is located), and the accident index is calculated by adding the multiplied values ​​together, and the probability of an abnormal lateral movement can be calculated to be high in proportion to the accident index.

[0084] Determining information related to the risk of abnormal transverse rotation based on information related to transverse rotation behavior generated according to one embodiment of the present invention may mean that, if there are many features among the features of transverse rotation behavior and the features of the prone motion behavior included in the information related to transverse rotation behavior that have a positive (+) correlation with the occurrence of abnormal transverse rotation, the risk is determined to be high based on these, and if there are many features that have a negative (-) correlation with the occurrence of abnormal transverse rotation, the risk is determined to be low based on these.

[0085] Meanwhile, risk determination based on the aforementioned positive (+) and negative (-) correlation features can be performed using general algorithms or artificial intelligence. However, the description of risk determination described above is merely exemplary and may be modified as long as it suits the purpose of the invention.

[0086] Meanwhile, the information related to the risk described above may include a risk level or risk stage calculated based on the probability that the target object's lateral movement behavior corresponds to an abnormal lateral movement.

[0087] The risk level according to one embodiment of the present invention may mean a risk level divided into two or more stages, with stage 1 being the lowest risk level and the risk level increasing as the stage increases.

[0088] For example, the risk level can be divided into the following three levels. Level 1 is a low-risk level where the sideways roll lasts less than 10 minutes and there are 1 or 2 attempts to lie down after the sideways roll, and there is a high possibility that the sideways roll was successful. Level 2 is a high-risk level where the sideways roll lasts 10 to 20 minutes and there are 3 or 4 attempts to lie down after the sideways roll, and there is a relatively low possibility that the sideways roll was successful. Level 3 is a level where the sideways roll lasts more than 20 minutes and there are 5 or more attempts to lie down (i.e., there were many attempts to lie down after the sideways roll but were unable to get up) or there were no attempts to lie down at all (i.e., the patient was unable to get up at all after the sideways roll), and this may be the level where there is the highest possibility that a sideways roll accident has occurred.

[0089] However, the risk levels described above are merely examples, and the number of levels, the criteria for distinguishing each level, and the criteria for calculating the risk level may be changed as long as it is consistent with the purpose of the invention.

[0090] Specifically, the risk determination unit (230) according to one embodiment of the present invention may determine that the risk is higher as the number of times the sideways movement is performed increases, the risk is higher as the duration of the sideways movement is longer, the risk is higher as the number of times the sideways movement is performed after the sideways movement is greater, and the risk is higher as the time interval between the sideways movement and the sideways movement is narrower.

[0091] That is, the risk determination unit (230) according to one embodiment of the present invention can determine the risk based on at least one of the characteristics of the lateral movement behavior and the characteristics of the prone movement behavior, and as described above, can determine the risk based only on the characteristics of the lateral movement behavior and the characteristics of the prone movement behavior that have a positive (+) correlation with the occurrence of an abnormal lateral movement.

[0092] Continuing, the risk determination unit (230) according to one embodiment of the present invention can determine information related to the risk based more on the characteristics of the target object.

[0093] Specifically, the risk determination unit (230) according to one embodiment of the present invention determining information related to risk based more on the characteristics of the target entity may mean calculating the risk by taking more individual characteristics of the target entity into account. For example, if the target entity is relatively older than other entities, the risk calculation standard may be changed by taking into account the individual characteristics of the entity, such as not determining an abnormal lateral movement even if the duration of the lateral movement is relatively long, considering that the activity of the entity decreases relatively as age increases.

[0094] Specifically, the characteristics of the target object according to one embodiment of the present invention may include at least one of a unique behavioral pattern of the target object and a health status of the target object.

[0095] According to one embodiment of the present invention, a characteristic behavior pattern of a target object is a behavior pattern in a normal state that can be identified by averaging the target object's usual behavioral patterns, for example, if a specific target object has a relatively longer duration of sideways rolling compared to other objects even in normal times when there is no sideways rolling accident, the standard for sideways rolling duration can be made longer when determining whether or not the specific target object is in an abnormal sideways rolling state or at a high risk level by taking this into consideration.

[0096] The health status of the subject according to one embodiment of the present invention should be interpreted to include all physical characteristics or conditions of the subject. Specifically, the above-mentioned physical characteristics may be characteristics that mainly affect the lying down behavior or the prone behavior, and more specifically, may be body weight (obesity level), pregnancy status, trauma, disease, etc. For example, if the subject is an individual who is generally healthy but has a higher than average obesity level, even a normal lying down may last for a long time, and therefore, when determining whether or not a lying down is abnormal or the risk level, this may be taken into consideration, such as by making the lying down duration longer among the criteria that can be determined as an abnormal lying down.

[0097] The risk determination system (200) according to one embodiment of the present invention may further include a notification information determination unit (240).

[0098] The notification information determination unit (240) according to one embodiment of the present invention can perform a function of determining information related to user notification based on information related to risk.

[0099] According to one embodiment of the present invention, a user includes all subjects who use the risk determination system (200), and specifically, the user may be a livestock farmer or livestock farm manager who uses the risk determination system (200).

[0100] Information related to a user notification according to one embodiment of the present invention may include a risk determined by a risk determination unit (230), basis data used to determine the aforementioned risk (e.g., information related to a lateral movement behavior), a risk value or risk level (stage), information on a target object for which the risk was calculated (e.g., the location of the target object, the number (location) of the livestock shed where the target object is located, etc.).

[0101] Continuing, in addition to the risk level itself described above, information related to user notifications may also include measures to deal with sideways accidents (e.g., providing a message such as "There is a high possibility that a sideways accident has occurred in barn 10, so immediately prepare lifting equipment and go to that barn").

[0102] The method for providing user notifications described above may vary depending on the risk level or level. For example, if the risk level or level is low, notifications may be provided via an app alarm or SMS. As the risk level or level increases, notifications may be provided via a more easily accessible method, such as a phone call.

[0103] A user notification according to one embodiment of the present invention can be provided in real time in conjunction with a risk determination system (200), thereby enabling the user to quickly respond to a sideways accident and take necessary measures.

[0104] Continuing, the criteria for determining information related to risk by the risk determination unit (230) according to one embodiment of the present invention and the criteria for determining information related to the user notification by the notification information determination unit (240) according to one embodiment of the present invention may be set differently depending on the time zone.

[0105] Specifically, a time zone in which a user can directly (visually) determine an abnormal transverse curvature of a target object (i.e., a non-risk time zone) and a time zone in which a user cannot (i.e., a risk time zone) can be distinguished, and the criteria for determining information related to risk by the risk determination unit (230) and the criteria for determining information related to user notification by the notification information determination unit (240) can be set differently for each distinguished time zone.

[0106] For example, during the daytime, since it is a time when it is easy for users to directly observe the target object, even if a sideways accident occurs, it is likely that users will discover it and respond to it directly, so even if the sideways accident occurs, it may not be determined that a sideways accident has occurred even if the sideways accident time is relatively long. On the other hand, during the nighttime, although the sideways behavior of the target object frequently occurs, it is a time when it is difficult for users to directly observe the target object, so even if the target object shows a sideways accident time that is the same as or relatively long than the daytime, it may be determined that a sideways accident has occurred.

[0107] As another example, even if the risk assessment criteria apply equally to daytime and nighttime, the notification requirements and method can be set differently for each time zone. For example, if the risk assessment is determined to be the same, users can be notified of risk-related information during the daytime through a means like text messaging, but at night, users can be notified through a more easily accessible method like phone calls. Thus, the criteria for determining user notification information can vary depending on the time zone.

[0108] As described above, the risk determination system (200), risk determination unit (230), or notification information determination unit (240) according to one embodiment of the present invention can save resources required for monitoring the target object by varying the risk determination criteria, risk-related information, and user notification criteria (method) for each time zone, and can also detect sideways accidents occurring during times when it is difficult for the user to directly intervene, thereby maximizing the efficiency of livestock house management.

[0109] Next, the communication unit (250) according to one embodiment of the present invention can perform a function that enables data transmission and reception from / to the movement information acquisition unit (210), the horizontal information generation unit (220), the risk determination unit (230), and the notification information determination unit (240).

[0110] Finally, the control unit (260) according to one embodiment of the present invention can perform a function of controlling the flow of data between the movement information acquisition unit (210), the lateral information generation unit (220), the risk determination unit (230), the notification information determination unit (240), and the communication unit (250). That is, the control unit (260) according to one embodiment of the present invention can control the flow of data from / to the outside of the risk determination system (200) or the flow of data between each component of the risk determination system (200), thereby controlling the movement information acquisition unit (210), the lateral information generation unit (220), the risk determination unit (230), the notification information determination unit (240), and the communication unit (250) to perform their own functions.

[0111] Example

[0112] Referring to FIG. 3, the process of determining the risk of a target object by the risk determination system (200) of the present invention is described as follows. First, data is collected from a sensor that senses the movement of the target object (410), and features can be extracted therefrom (420). The extracted features can be input into an artificial intelligence model (an artificial intelligence model trained to infer and output whether there is a sideways roll using the movement data of the target object as an input value) so that the artificial intelligence model can determine whether there is a sideways roll (430). Meanwhile, since the sideways roll may be a normal sideways roll, the process of first determining whether there is a sideways roll (430) and then determining whether there is an abnormal sideways roll (sideways roll accident) (440) can be performed. The process of determining whether there is an abnormal sideways roll (440) can be determined by applying different criteria (or different artificial intelligence models) for each time period. That is, in non-dangerous times, the presence or absence of a sideways turn can be determined using relatively less stringent risk determination criteria (441), whereas in dangerous times, the presence or absence of a sideways turn can be determined using more stringent risk determination criteria (442). In addition, in the step of determining whether or not an abnormal sideways turn has occurred (440), if an abnormal sideways turn is determined, relevant information or a warning can be notified to the user (450).

[0113] Meanwhile, the above embodiment described using FIG. 3 is only one example of various ways in which the risk determination system (200) of the present invention operates or is used, and it is obvious that the contents included in the embodiment may be changed as needed.

[0114] The embodiments of the present invention described above may be implemented in the form of program commands that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program commands, data files, data structures, etc., either singly or in combination. The program commands recorded on the computer-readable recording medium may be specially designed and configured for the present invention or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specifically configured to store and execute program commands, such as ROMs, RAMs, and flash memories. Examples of program commands include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc. Hardware devices may be changed into one or more software modules to perform processing according to the present invention, and vice versa.

[0115] Although the present invention has been described above with specific details such as specific components and limited examples and drawings, these are provided only to help a more general understanding of the present invention, and the present invention is not limited to the above examples, and those with ordinary knowledge in the technical field to which the present invention pertains can make various modifications and changes based on this description.

[0116] Therefore, the idea of ​​the present invention should not be limited to the embodiments described above, and not only the scope of the patent claims described below but also all scopes equivalent to or equivalently modified from the scope of the patent claims are considered to fall within the scope of the idea of ​​the present invention.

Claims

1. A method for determining the risk according to the abnormal transverse curvature of the target object, A step of acquiring information related to the movement of the target object; A step of generating information related to lateral movement based on information related to the above-mentioned acquired movement, and A step of determining information related to the risk according to an abnormal transverse motion based on information related to the generated transverse motion. method.

2. In paragraph 1, Information related to the above movement is information related to acceleration in the up, down, left and right directions. method.

3. In paragraph 2, The information related to the above acceleration is the acceleration value and the degree of change in the acceleration value. method.

4. In paragraph 3, The degree of change in the above acceleration value is calculated based on the average and variance of the acceleration value over at least one time interval. method.

5. In paragraph 1, Information related to the above transverse behavior includes the characteristics of the transverse behavior and the characteristics of the prone behavior. method.

6. In paragraph 5, The above characteristics of the horizontal motion are at least one of the number of horizontal motions and the duration of the horizontal motion, The above-mentioned characteristics of the prone behavior are at least one of the number of prone behaviors after the transverse behavior and the time interval between the prone behaviors after the transverse behavior. method.

7. In paragraph 6, At the stage of determining information related to the above risk, The higher the number of times the above-mentioned horizontal motion is performed, the higher the risk is determined, and the longer the duration of the above-mentioned horizontal motion is, the higher the risk is determined. The higher the number of times the prone behavior occurs after the above-mentioned transverse behavior, the higher the risk is determined, and the shorter the time interval between the prone behavior and the transverse behavior, the higher the risk is determined. method.

8. In paragraph 1, In the step of determining information related to the above risk, information related to the risk is determined based more on the characteristics of the target object. method.

9. In paragraph 8, The characteristics of the above target object include at least one of the target object's unique behavioral pattern and the target object's health status. method.

10. In paragraph 1, Further comprising a step of determining information related to user notification based on information related to the determined risk level. method.

11. In paragraph 10, The criteria for determining information related to the above risk and the criteria for determining information related to the above user notification may be set differently depending on the time zone. method.

12. A non-transitory computer-readable recording medium recording a computer program for executing the method according to paragraph 1.

13. A system for determining the risk level according to the abnormal transverse curvature of the target object, A movement information acquisition unit that acquires information related to the movement of a target object; A transverse information generation unit that generates information related to a transverse motion based on information related to the above-mentioned acquired movement, and A risk determination unit that determines information related to the risk according to an abnormal lateral movement based on information related to the generated lateral movement behavior. System.

14. In paragraph 13, Information related to the above movement is information related to acceleration in the up, down, left and right directions. System.

15. In paragraph 14, The information related to the above acceleration is the acceleration value and the degree of change in the acceleration value. System.

16. In paragraph 15, The degree of change in the above acceleration value is calculated based on the average and variance of the acceleration value over at least one time interval. System.

17. In paragraph 13, Information related to the above transverse behavior includes the characteristics of the transverse behavior and the characteristics of the prone behavior. System.

18. In paragraph 17, The above characteristics of the horizontal motion are at least one of the number of horizontal motions and the duration of the horizontal motion, The above-mentioned characteristics of the prone behavior are at least one of the number of prone behaviors after the transverse behavior and the time interval between the prone behaviors after the transverse behavior. System.

19. In paragraph 18, The above risk determination unit is, The higher the number of times the above-mentioned horizontal motion is performed, the higher the risk is determined, and the longer the duration of the above-mentioned horizontal motion is, the higher the risk is determined. The higher the number of times the prone behavior occurs after the above-mentioned transverse behavior, the higher the risk is determined, and the shorter the time interval between the prone behavior and the transverse behavior, the higher the risk is determined. System.

20. In paragraph 13, The above risk determination unit determines information related to risk based more on the characteristics of the target object. System.

21. In paragraph 20, The characteristics of the above target object include at least one of the target object's unique behavioral pattern and the target object's health status. System.

22. In paragraph 13, Further comprising a notification information determination unit that determines information related to user notification based on information related to the determined risk level. System.

23. In paragraph 22, The criteria for determining information related to the above risk and the criteria for determining information related to the above user notification may be set differently depending on the time zone. System.

Images