WO2016140332A1

WO2016140332A1 - Monitoring device and movement detection method

Info

Publication number: WO2016140332A1
Application number: PCT/JP2016/056701
Authority: WO
Inventors: 継泰豊岡; 檜山　聡; 磯　俊樹
Original assignee: 株式会社Ｎｔｔドコモ
Priority date: 2015-03-05
Filing date: 2016-03-04
Publication date: 2016-09-09
Also published as: JPWO2016140332A1; JP6696967B2

Abstract

A first acquisition unit 201 acquires acceleration information from a sensor attached to the neck of an animal. A second acquisition unit 202 acquires individual information pertaining to the individual animal. A detection unit 203 detects that the movement of an animal is a body-shaking or scratching movement, when the change over time in the strength of acceleration expressed by the acceleration information indicates that the frequency of a peak having a peak strength equal to or greater than a first threshold is equal to or greater than a second threshold. The detection unit 203 uses values determined according to the acquired individual information for both the first threshold and the second threshold. A determination unit 204 determines whether the health of the animal is good or bad on the basis of the movement history detected by the detection unit 203. A notification unit 206 notifies a prescribed destination when the determination unit 204 determines that the health of the animal is bad.

Description

Monitoring device and operation detection method

The present invention relates to a technique for grasping the state of an animal.

The movement of a canine or feline animal scratching or shaking the body is an important indicator for conveying the state of the body. One thing that can be seen from these actions is skin disease. Animal skin is always exposed to the open air, and is susceptible to changes in the environment, such as temperature and humidity, and insects such as parasites, and thus is prone to diseases. In particular, the skin disease of dogs and cats is said to have an incidence of 20% or more, which is also a leading cause of animal hospitals, and is known as a serious problem in the field of veterinary medicine.

Dermatoses include atopic dermatitis, flea allergies, parasitic infections, food allergies, etc., but after they get worse, treatment often takes time, and prevention and early detection are very important. When these animals develop skin diseases, they are often accompanied by itching, and the frequency of performing movements such as scratching the body with the legs or shaking the body is higher than before the onset. Therefore, an increase in the frequency of these operations can be an indicator of skin disease. In addition, the frequency of these operations increases due to stress.

As described above, it is important to observe the motion of scratching the body and the motion of shaking the body because it leads to prevention / early detection of skin diseases and detection of stress states in canine or feline animals. However, in order for humans to do this, it is necessary to keep observing the movements of animals all day and night, which is a heavy burden. In addition, when shooting with a camera, there is a constraint that an animal must always be in the shooting range. Therefore, various observation methods are disclosed. For example, Patent Document 1 discloses a method in which a sensor is attached to an limb or other part of an animal to detect the behavior of the animal and know the state of the body. As another approach for knowing the state of the body, Patent Document 2 discloses a method of attaching a sensor to the tail of a pet, detecting the number of times the tail is shaken, estimating the emotion of the animal, and reading the state of the body. .

Special table 2009-517047 JP 2009-136212 A

Any of the techniques based on the above-mentioned patent documents can evaluate the state of the animal based on the behavior of the animal. However, in these techniques, it is necessary to attach a sensor to the extremity or tail of the animal. Collars are common for wearing on these animals, but it is common for owners with resistance to attach sensors or the like to parts other than the neck, and the animals themselves are often disliked. Therefore, it is difficult to attach a device such as a sensor to a part other than the neck.
Therefore, an object of the present invention is to detect an action of scratching or shaking a body with a sensor attached to the neck of an animal.

In order to achieve the above object, the present invention relates to a first acquisition unit that acquires information about acceleration from a sensor attached to the neck of an animal, and a peak intensity in a time change of acceleration represented by the information. A monitoring device is provided that includes a detection unit that detects a motion of the animal scratching or shaking based on the appearance frequency of a peak that satisfies a predetermined condition.

In a preferred aspect, the first acquisition unit acquires triaxial acceleration, and the acceleration intensity is represented by a sum of squares of the triaxial acceleration.
In a preferred aspect, the detection unit determines that the operation has been performed when an appearance frequency of a peak having an intensity equal to or higher than a reference peak intensity is equal to or higher than a reference frequency value.
In a preferred aspect, the detection unit determines that the operation has been performed when the frequency of appearance of peaks having peak intensities in a predetermined range is within the predetermined range.
In a preferred aspect, a second acquisition unit that acquires individual information of the animal is provided, and at least one of the reference peak intensity and the reference frequency value is set based on the individual information.

In a preferred embodiment, the individual information includes information on the type, sex, length, weight, eating history, exercise history, activity amount, basal metabolic rate, illness or injury history, or current illness or injury status of the animal. , Representing the physical strength or health of the animal.
In a preferred embodiment, the reference frequency value is 3 times per second.
In a preferred embodiment, the reference peak intensity is 2.0 (G ² ).

In a preferred aspect, the detection unit changes either or both of the reference peak intensity and the reference frequency value based on a result of a user evaluating whether the detection result is correct or incorrect.
In a preferred aspect, the monitoring device includes: a determination unit that determines a health state of the animal based on a history of operations detected by the detection unit; and a predetermined destination when the health state of the animal is determined to be bad And a notification unit for notifying.

In a preferred embodiment, the determination unit detects the frequency at which the operation is detected when an operation having a tendency different from the operation tendency detected when the user determines that the animal is in good health is detected. When the detected duration of the operation is equal to or greater than a threshold, when the frequency or the duration during which the duration continues to increase is equal to or greater than the threshold, or when the increase rate of the frequency or the duration is equal to or greater than the threshold In some cases, it is determined that the animal is in poor health.

In addition, the present invention provides a step of acquiring information about acceleration from a sensor attached to the neck of an animal, and an appearance frequency of a peak having an intensity equal to or higher than a reference peak intensity in a temporal change in acceleration represented by the information. And detecting the motion of the animal scratching or shaking the body.

According to the present invention, it is possible to prevent skin disease and stress, detect early, and the like by detecting the motion of scratching or shaking the body with a sensor attached to the neck of the animal.

Diagram showing the configuration of the monitoring system The figure showing the hardware constitutions of the user terminal Diagram showing hardware configuration of server device Diagram showing the hardware configuration of the sensor device The figure showing an example of a mode that the sensor apparatus was attached to the animal The figure showing the functional composition realized in the monitoring system The figure showing an example of a reception image The figure showing an example of the time change of the acceleration The figure showing an example of the time change of the square sum of the acceleration of three axes The figure showing another example of the time change of the square sum of the acceleration of three axes The figure showing another example of the time change of the square sum of the acceleration of three axes The figure showing another example of the time change of the square sum of the acceleration of three axes The figure showing another example of the time change of the square sum of the acceleration of three axes A chart showing how peaks appear in each state The figure showing an example of a correction table A figure showing an example of the relation between the scratching action and the health condition The figure showing an example of the displayed notification information The figure showing an example of the operation | movement procedure until a server apparatus transmits notification information The figure showing the example of the notification information displayed by the modification The figure showing an example of the notice information displayed by the modification A figure showing an example of a screen for evaluation The figure showing an example of the functional structure in a modification The figure showing other examples of the functional composition in a modification

[1] Embodiment FIG. 1 shows a configuration of a monitoring system 1 according to an embodiment of the present invention. The monitoring system 1 is a computer system for monitoring animals. In the monitoring system 1, for example, an animal being cared for by a user such as a dog or a cat is monitored. The monitoring system 1 includes a sensor device 10, a server device 20, and a user terminal 30, and these information processing devices are connected by a network 2. The network 2 is, for example, the Internet or a mobile communication network.

The user terminal 30 is an electronic device that the user possesses and carries, for example, a smartphone or a tablet terminal. The user terminal 30 may be a PDA (Personal Digital Assistant), a portable personal computer, a palmtop computer, a laptop computer, or the like, and may be any device used by the user. The server device 20 is a monitoring device for monitoring animals, and performs detection of animal movements, determination of health conditions, and the like. The sensor device 10 is attached to an animal and measures a physical quantity necessary for detecting a motion.

FIG. 2 shows the hardware configuration of the user terminal 30. The user terminal 30 includes a control unit 31, a storage unit 32, a communication unit 33, a display unit 34, and an operation unit 35. The control unit 31 includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and a real time clock. The CPU is stored in the ROM or the storage unit 32 using the RAM as a work area. The operation of each part is controlled by executing a program. The real time clock calculates the current date and time and notifies the CPU. The storage unit 32 is a nonvolatile memory, for example, and stores various programs and data. The communication unit 33 includes a communication circuit for performing mobile communication, and performs communication via a mobile communication network. The display unit 34 includes a display device that displays various messages and images. The operation unit 35 includes an operator for operating the user terminal 30.

FIG. 3 shows the hardware configuration of the server device 20. The server device 20 includes a control unit 21, a storage unit 22, and a communication unit 23. The server device 20 may not be configured as a single device, but may be realized by cooperation of a plurality of server devices. The control unit 21 has the same configuration as the control unit 31 and controls each unit of the server device 20. The storage unit 22 includes a storage medium such as a hard disk, and stores data necessary for the operation of the control unit 21. The communication unit 23 includes a communication circuit and performs communication via the network 2.

FIG. 4 shows the hardware configuration of the sensor device 10. The sensor device 10 includes a control unit 11, a communication unit 12, and an acceleration sensor 13. The control unit 11 has the same configuration as the control unit 31 and controls each unit of the sensor device 10. The communication unit 12 includes a communication circuit for performing mobile communication, and performs communication via a mobile communication network. The acceleration sensor 13 measures accelerations of three axes (X axis, Y axis, and Z axis) orthogonal to each other and supplies acceleration information representing the measured accelerations to the control unit 11. The control unit 11 transmits the supplied acceleration information to, for example, the server device 20 via the communication unit 12. The sensor device 10 is attached to an animal.

FIG. 5 shows an example of how the sensor device 10 is attached to an animal. In this embodiment, as shown in FIG. 5, the sensor device 10 is attached to the neck (neck portion) of the animal 3 (dog). Specifically, the sensor device 10 is attached by attaching the collar 4 with the sensor device 10 fixed to the neck of the animal 3. By being attached in this way, the acceleration sensor 13 of the sensor device 10 measures the acceleration of the neck of the animal 3.

In the monitoring system 1, the control unit of each device executes a program, whereby the function illustrated in FIG. 6 is realized in each device in cooperation with the control unit and other units.
FIG. 6 shows a functional configuration realized in the monitoring system 1. The sensor device 10 includes a measurement unit 101, and the user terminal 30 includes a display unit 301 and a reception unit 302. The server device 20 includes a first acquisition unit 201, a second acquisition unit 202, a detection unit 203, a determination unit 204, a storage unit 205, and a notification unit 206.

The measuring unit 101 measures the acceleration of the animal's neck and outputs acceleration information representing the measured acceleration. In the present embodiment, the measurement unit 101 measures triaxial acceleration at a frequency of several tens of times per second by the acceleration sensor 13, adds measurement time to the acceleration information, and outputs the acceleration information to the server device 20. . The measurement unit 101 may output acceleration information every measurement, or may output the acceleration information collectively every 10 seconds or every minute. Alternatively, it may be output when requested by the user terminal 30. The measuring unit 101 outputs individual identification information for identifying an individual animal in association with acceleration information. As the individual identification information, for example, a device ID of the sensor device 10 or a registered individual ID is used.

The first acquisition unit 201 acquires acceleration information from a sensor attached to the animal's neck. Specifically, the first acquisition unit 201 acquires acceleration information output from the measurement unit 101 as acceleration information from the acceleration sensor 13 attached to the neck of the animal 3. The first acquisition unit 201 also acquires the individual identification information associated with the acceleration information, and supplies the acquired information to the detection unit 203.

The display unit 301 displays various images.
The accepting unit 302 accepts input or selection of individual animal information. The individual information is information related to an animal individual, for example, information such as gender, length, and weight. For example, the reception unit 302 causes the display unit 301 to display a reception image for inputting and selecting individual information.
FIG. 7 shows an example of the received image. In the example of FIG. 7, a character string “Please enter / select individual information”, an input field A1 for inputting “gender”, “length”, “weight”, etc. An answer column A2 for selecting an answer to a question such as “?” Or “Is it injured?” Is displayed on the display unit 301.

The accepting unit 302 accepts the content entered in the input field A1 and the content answered in the answer field A2 as input and selection of individual information. The receiving unit 302 adds a reception time to the received individual information, and outputs the individual information and the individual identification information to the server device 20 in association with the individual identification information described above. The second acquisition unit 202 acquires the individual information output from the reception unit 302 in this way, and supplies the individual information together with the acquired individual identification information to the detection unit 203.

Based on the acceleration information acquired by the first acquisition unit 201, the detection unit 203 detects that the animal has performed an operation of scratching the head or body or an operation of shaking the head or body. The action of scratching is an action of rubbing the toes on the head or body, and the action of shaking the body is an action of shaking the head or body in small increments. The detection unit 203 detects that the animal has performed an action of scratching or shaking the body based on the peak intensity in the time change of the intensity of the acceleration represented by the acceleration information and the frequency of the peak having the peak intensity. In the present embodiment, the detection unit 203 detects these operations when the frequency of peaks having a peak intensity equal to or higher than the first threshold is equal to or higher than the second threshold. A method for determining the first threshold value and the second threshold value and a change over time in the intensity of acceleration will be described with reference to FIG.

FIG. 8 shows an example of the time change of acceleration. In FIG. 8, the vertical axis indicates acceleration (unit: G (gravity acceleration)), and the horizontal axis indicates the passage of time. Changes are represented. The detection unit 203 calculates the sum of squares of three-axis accelerations so that the peak intensities can be easily compared. By summing up the acceleration to the square, the intensity of the acceleration is expressed regardless of the direction of the acceleration (positive or negative direction, triaxial direction).

FIG. 9 shows an example of a temporal change in the sum of squares of accelerations of three axes. In this example, the vertical axis represents the sum of squares of acceleration (the unit is G ² (the square of gravitational acceleration)), and the horizontal axis represents the passage of time. A time change for one second of the intensity of the acceleration (sum of squares) based on the acceleration information is shown. In this example, seven peaks of the sum of squares of acceleration appear in a range from 5.0 (G ² ) to 25 (G ² ).

FIG. 10 shows another example of the temporal change of the sum of squares of the triaxial acceleration. In this example, the time change of the intensity of the acceleration for 1 second based on the acceleration information acquired in the state where the dog is performing the motion of shaking the body is represented. Also in this example, four peaks of the sum of squares of acceleration appear in a range from 50 (G ² ) to 2.5 × 10 ² (G ² ).

FIG. 11 shows another example of the temporal change of the sum of squares of the triaxial acceleration. In this example, the temporal change of the acceleration intensity based on the acceleration information acquired in a state where the dog is walking is shown for one second. In this example, seven peaks of the sum of squares of acceleration appear in a range smaller than 1.0 (G ² ).

FIG. 12 shows another example of the temporal change of the sum of squares of the triaxial acceleration. In this example, the time change of 1 second of the intensity | strength of the acceleration based on the acceleration information acquired in the state which the dog is performing the jumping motion is represented. In this example, one peak of the sum of squares of acceleration appears in a range from 8.0 (G ² ) to 10 (G ² ).

FIG. 13 shows another example of the temporal change of the sum of squares of the triaxial acceleration. In this example, the time change of the acceleration intensity based on the acceleration information acquired in a state where the dog is not particularly moving is expressed for one second. Also in this example, 10 peaks of the sum of squares of acceleration appear in a range smaller than 2.0 × 10 ⁻³ (G ² ). The acceleration information in the five states of scratching motion, shaking motion, jumping motion, walking motion, and no motion described above, 11 dog breeds (beagle, shiba inu, toy poodle, pug, shih tzu, miniature schnauzer, Based on the results of experiments obtained on dogs of various ages, weights, and genders (Chihuahua, Miniature Dachshund, Pomeranian, Yorkshire Terrier, Papillon) To express.

FIG. 14 is a table showing how peaks appear in each state. In the state of performing scratching operation, it appears 1.0 (G ²⁾ greater than 1.0 × 10 ^² (G ²⁾ peak of smaller peak intensity at least four times per second, performs an operation of swinging the body state in, 10 (G ²⁾ greater than 1.0 × 10 ^² (G ²⁾ peak of smaller peak intensity appeared above 4 times per second. State in a state that performs an operation, 1.0 peak of the (G ²⁾ greater than 1.0 × 10 ² (G ²⁾ is smaller than the peak intensity appears once per second or twice, which performs an operation to walk jumping Then, a peak having a peak intensity larger than 1.0 × 10 ⁻² (G ² ) and smaller than 1.0 (G ² ) appeared 2 to 6 times per second. In the state without operation, a peak with a peak intensity greater than 1.0 × 10 ⁻⁵ (G ² ) and smaller than 1.0 × 10 ⁻³ (G ² ) appeared various times per second (in other words, the number of times Was not determined).

When the peak intensities were compared, the peak intensity was extremely small in the state of no operation (less than 1.0 × 10 ⁻³ (G ² )). In addition, the peak intensity of walking action (less than 1.0 (G ² )) is smaller than the peak intensity of scratching action, swinging action and jumping action (all greater than 1.0 (G ² )). It was. Moreover, when comparing the appearance frequency of peaks (the number of peaks appearing in one second), the peak appearance frequency (1 or 2 times per second) in the jumping motion is the frequency of appearance of the peak of the body swinging motion and the jumping motion (both per second). 4 times or more). Based on the above results, the detection unit 203 uses, for example, 2.0 (G ² ) as the first threshold and the peak appearance frequency of 3 times per second as the second threshold, that is, 3 (times / second). Is used to detect a scratching action and a shaking action.

In the examples from FIG. 9 to FIG. 13, 2.0 (G ² ), which is an example of the first threshold value, is represented by a two-dot chain line. In the example of FIG. 9 (scratching motion), seven peaks greater than or equal to the first threshold appear, and in the example of FIG. 10 (motion shaking motion), four peaks greater than or equal to the first threshold appear. In the example of FIG. 11 (jumping action), only one peak that is equal to or higher than the first threshold appears. In the example of FIG. 10 (walking motion) and FIG. 12 (no motion), no peak greater than the first threshold appeared. As described above, in the case of an animal used in the above-described experiment, a scratching motion or a body swinging motion is detected by using the first threshold value and the second threshold value.

In the detection of the operation by the detection unit 203, for example, the values determined in advance based on the experimental results as described above are the first threshold (2.0 (G ² ) in this embodiment) and the second threshold (in this embodiment). 3 (times / second)). However, it is not limited to this. For example, the predetermined threshold value may be used as the reference threshold value, and the reference threshold value corrected using other information may be used as the first threshold value and the second threshold value. The other information is, for example, the individual information described above. In that case, the detection unit 203 determines the first threshold and the second threshold by correcting the reference threshold based on the individual information. The detection unit 203 includes a correction unit 207 that performs this correction. The correction unit 207 uses a correction table in which individual information is associated with a threshold correction amount in order to correct a reference threshold.

FIG. 15 shows an example of a correction table. In the example of FIG. 15, the first threshold value and the second threshold value are associated with a correction amount of “+ 10%” for the sex “male”, and both the first threshold value and the second threshold value for the sex “female” are “−10%”. Is associated with the correction amount. The body lengths of “A1 cm or more”, “less than A1 cm, A2 cm or more”, and “less than A2 cm” are associated with correction amounts of “+ 10%”, “0”, and “−10%” for both the first threshold value and the second threshold value, respectively. Yes. In addition, correction amounts of “−50%” and “0” are associated with individual information indicating whether there is a disease / injury “Yes” and “No”, respectively.

The correction unit 207 may be referred to as a reference threshold (the reference threshold of the first threshold is the reference peak intensity) with the correction amount associated with the individual information supplied from the second acquisition unit 202 in the correction table. The reference threshold value of the second threshold value may be called a reference peak appearance frequency). For example, the above-described 2.0 (G ² ) is used as the first threshold reference threshold (reference peak intensity), and 3 (times / second) is used as the second threshold reference threshold (reference peak appearance frequency). . In addition, when there are a plurality of correction amounts, the correction unit 207 multiplies those correction amounts. For example, when the individual information that the sex is male, the body length is A1 cm or more, and there is a disease / injury is acquired, the correction unit 207 sets the first threshold value to 2.0 × 1.1 × 1.1 × 0.5. = 1.21 (G ² ) and the second threshold value is corrected to 3 × 1.1 × 1.1 × 0.5 = 1.815 (times / second). The detection unit 203 uses the first threshold value and the second threshold value corrected by the correction unit 207 to detect a scratching motion or a motion of shaking the body. When the detection unit 203 detects a scratching motion or a motion of shaking the body, the detection unit 203 notifies the determination unit 204 to that effect.

The determination unit 204 determines whether the animal's health is good or bad based on the motion history detected by the detection unit 203. When the determination unit 204 is notified that an operation has been detected from the detection unit, the determination unit 204 causes the storage unit 205 to store the notification time as an operation history. The storage unit 205 stores various information such as operation history. The determination unit 204 calculates, for example, the frequency at which an operation is detected by the detection unit 203 based on the stored operation history. The determination unit 204 determines that the animal is in a good health state when the calculated frequency is equal to or lower than the threshold, and determines that the animal is in a poor health state when the frequency is equal to or higher than the threshold. The relationship between the animal's health condition and the frequency of scratching or shaking motion will be described with reference to FIG.

FIG. 16 shows an example of the relationship between the scratching action and the health condition. In this example, the vertical axis indicates the frequency of scratching operations (times / 6 hours). We measured this frequency for 17 healthy dogs and 3 dogs with skin disease. The average of this frequency was 8.6 when the dog was healthy, and this frequency when the dog had skin disease. The average frequency was 79.3 times. Thus, the frequency with which the scratching operation is performed varies greatly depending on the health condition of the animal. Similarly, it is known that the frequency of the motion of shaking the body is different between when the health condition is good and when it is bad. Therefore, the frequency of the motion of shaking the body between when the health condition is good and when it is bad is measured, and a threshold value (for example, a value in the range of 25 to 50 times) that can distinguish the frequency difference between the scratching motion and the motion of shaking the body. ) Is determined, the determination unit 204 determines whether the health condition is good or bad (whether or not the patient has skin disease in this embodiment).

In addition, the duration of the scratching and shaking motions is known to be different between when the health condition is good and when it is bad. The determination unit 204 may determine whether the health condition is good or bad by measuring the duration time and determining a threshold value that can distinguish the difference between the duration times. In this case, the determination unit 204 calculates the duration of the operation detected by the detection unit 203 based on the stored operation history. The determination unit 204 determines that the health state is good when the calculated duration is less than the threshold, and determines that the animal is in a poor health state when the duration is equal to or greater than the threshold. The determination unit 204 sets, for example, the time elapsed from the start of notification from the detection unit 203 that the above operation has been detected to the end of the notification. In addition, even if there is a case where it is not detected once or twice in the middle, it may be considered that the operation of scratching or shaking the body is continued.

Also, when the animal's health deteriorates, the above frequency and duration may continue to increase. Therefore, by determining the frequency during which the frequency or duration of both operations continues to increase between when the health condition is good and when it is bad, and by setting a threshold that can distinguish the difference between these periods, the determination unit 204 may determine whether the health condition is good or bad. In this case, the determination unit 204 determines that the health state is good when the frequency at which the operation is detected by the detection unit 203 or the period during which the duration of the operation continues to increase is less than the threshold, and the period is If it is above the threshold, it is determined that the animal is in poor health.

Also, when the animal's health condition deteriorates, the above frequency and duration may increase rapidly. Therefore, by measuring the frequency of both movements or the rate of increase in duration (increased amount per unit time) between when the health condition is good and when it is bad, and setting a threshold that can distinguish the difference between the rate of increase, The determination unit 204 may determine whether the health condition is good or bad. In this case, the determination unit 204 determines that the health state is good when the frequency at which the operation is detected by the detection unit 203 or the increase rate of the duration of the operation is less than the threshold, and the increase rate is equal to or greater than the threshold. If there is, it is determined that the animal is in poor health. The determination unit 204 notifies the notification unit 206 of the determined health status.

When the determination unit 204 determines that the animal is in a poor health state, the notification unit 206 notifies the predetermined destination to that effect. As the predetermined destination, an IP (Internet Protocol) address of the user terminal 30, an e-mail address of a registered user, an SNS (Social Networking Service) account, or the like is used. The user here includes a family veterinarian in addition to the owner and the keeper. Other than these, any destination may be used as long as it can be notified to the user. The notification unit 206 transmits information regarding the animal for which the above determination has been made and information indicating that the animal is in poor health as notification information to a predetermined destination. In this example, it transmits to the IP address of the user terminal 30.

The display unit 301 displays the notification information notified by the notification unit 206.
FIG. 17 shows an example of the displayed notification information. In this example, the display unit 301 displays a character string “There is a notification. Your pet may have skin disease. It is recommended to have a medical examination.” . By looking at the notification information, the user can know that his / her pet is in a poor health state (possibly having skin disease).

FIG. 18 shows an example of an operation procedure until the server device 20 transmits the notification information. This operation procedure is started when the sensor device 10 is attached to an animal, for example. First, the server device 20 (first acquisition unit 201) acquires acceleration information (step S11). The acceleration information acquired here may be acceleration information measured at one time point or acceleration information measured during a certain period. Next, the server device 20 determines whether or not acceleration information has been acquired for a predetermined period (step S12).

The predetermined period is, for example, a period (one second in the example of FIG. 14) in which the number of peaks necessary for detecting a scratching motion or a body shaking motion appears, the frequency of the motion used for health condition determination, For example, a period (6 hours in the example of FIG. 16) in which the detection of the number of operations necessary for calculating the duration is performed. Note that the predetermined period may be longer than these periods. Further, even when calculating the frequency of the operation, the predetermined period may be 3 hours or 2 hours, and the frequency of the operation in the period may be converted into the frequency of the operation in 6 hours.

When it is determined that the acceleration information has not been acquired for a predetermined period (NO), the server device 20 (second acquisition unit 202) returns to step S11 to perform an operation, and determines that it has been acquired (YES). If so, individual information is acquired (step S13). The operation in step S13 may be performed before steps S11 and S12 or may be omitted. Subsequently, the server device 20 (the detection unit 203 and the correction unit 207) corrects the reference threshold value according to the acquired individual information and determines the first threshold value and the second threshold value (step S14). When step S13 is omitted, the reference threshold value itself is set as the first threshold value and the second threshold value (that is, the first threshold value and the second threshold value are set as they are without correcting the reference threshold value).

The server device 20 (detection unit 203) extracts a peak whose acceleration peak intensity represented by the acquired acceleration information is not less than the first threshold (step S15), and whether the peak frequency of the extracted peak is not less than the second threshold. Is determined (step S16). The server device 20 (detection unit 203) ends this operation procedure when it is determined in step S16 that it is not equal to or greater than the second threshold (NO), and when it is determined that it is equal to or greater than the second threshold (YES) A motion of scratching or a motion of shaking the body is detected (step S17).

Subsequently, the server device 20 (determination unit 204) determines the health state of the animal based on the motion detection result (step S21). The server device 20 (determination unit 204) uses the frequency of the operation detected in the past unit time (6 hours in the example of FIG. 16) when determining the health state based on the frequency of the operation. The server device 20 (notification unit 206) determines whether or not it is determined that the health condition is bad (step S22). When it is determined that the health condition is not determined (NO), the operation procedure is terminated, and the health condition is determined. If it is determined that the state is bad (YES), notification information indicating that fact is transmitted to a predetermined destination (step S23).

In this embodiment, as described above, it is possible to detect an animal scratching motion or a body shaking motion with a sensor attached to the neck of the animal. In addition, this sensor may measure only the acceleration, and a sensor for measuring other physical quantities (such as angular velocity and light quantity) is not necessary. By detecting the motion with one type of sensor in this way, the weight of the sensor device is reduced compared to the case of using multiple types of sensors, the burden on the animal's neck is reduced, and the power consumption is reduced. The power source (battery or battery) can be prolonged by reducing the number.

In addition, the degree of animal movement varies depending on the characteristics (sex, length, etc.) and conditions (disease, injuries, etc.) of the individual animal. For example, the smaller the body length and weight, the quicker the action of scratching and shaking the body, and the action becomes smaller or gentler if there is an illness or injury. For this reason, if the first threshold value and the second threshold value are fixed as described above, even if an operation to be detected is performed, the operation may not be detected, or an erroneous detection in which an operation is excessively detected may occur. In this embodiment, the threshold values (first threshold value and second threshold value) are determined according to the individual information. Therefore, when the motion is detected by the sensor attached to the neck of the animal, compared to the case where the threshold values are fixed. In addition, false detection due to individual differences can be reduced.

In addition, in this embodiment, when it is determined that the animal's health condition is poor, the fact is notified, so that early detection and early treatment of animal diseases and injuries can be performed compared to the case where this notification is not performed. It can be carried out. In this embodiment, a value obtained by correcting the standard peak intensity of 2.0 (G ² ) according to the acquired individual information is used as the first threshold value. This value is the value of the first threshold value suitable for the detection of the scratching motion and the motion of shaking the body in the experiments described in FIGS. By using this value as a reference, even when there is no correction based on individual information, it is possible to reduce erroneous detection when detecting motion with a sensor attached to the neck of an animal.

[2] Modification The above-described embodiment is merely an example of the present invention and may be modified as follows. Moreover, you may implement embodiment and each modification shown below, combining each as needed.

[2-1] Types of animals In the examples, a dog's scratching motion or a body shaking motion was detected, but the animal that is the target of motion detection is not limited to this. Other animals in the canine family (such as foxes and raccoons), feline animals (such as cats, lions, and tigers), weasel animals (such as weasels and badgers), rabbits, and rats (Mice, hamsters, etc.) may also be targeted. In short, it is possible to attach the sensor device 10 to the neck, and if it is an animal that performs a scratching motion and a body swinging motion in the same manner as a dog, those motions are detected.

[2-2] Individual information In the embodiment, as an example of correcting a reference threshold using individual information, an example in which the gender, length, weight, and current illness or injury state of an animal are used as individual information has been described. However, it is not limited to this. As the individual information, for example, the types of animals described above (canine animals, feline animals, etc.) may be used. In addition, animal activity history such as animal eating and drinking history (meal menu), exercise history (walking frequency), and activity (walking distance and time) may be used as individual information. Further, for example, a basal metabolic rate calculated from the body weight and the amount of activity or a history of past illness or injury may be used as individual information.

The above individual information represents the size of the animal's physical strength and health. For example, males have more physical strength than females, and the longer the body length, the higher the body weight, the amount of meal, the amount of exercise, and the amount of basal metabolism, the more physical strength. In addition, the history and current state of illness and injury represent the health status of animals. If these pieces of individual information are different, the degree of animal movement (scratching movement and body shaking movement) may change as described above. Can be reduced.

In addition, animals have a lower physical strength or poorer health, and the more likely they become severe if they are ill and are not treated early. Therefore, the detection unit 203 determines the threshold value so that the above-described operation is easily detected as the physical strength is low or the health state is poor, so that the determination unit 204 can easily determine that the health state is bad. As a result, instead of being likely to be judged to be in poor health when healthy, it will be notified when the health status has deteriorated even a little, so that the physical strength is low or the health status is Bad animals can be treated earlier.

[2-3] Determination of Health Status The determination unit 204 may determine whether the health status is good or bad by a method different from the embodiment. The determination unit 204 determines that the animal is in a poor health state when, for example, an operation having a tendency different from the tendency of the operation detected when the user determines that the animal is in a good health state is detected. In this case, detection of an operation based on acceleration information acquired from an animal (an animal to which the sensor device 10 is attached) that the user has determined is in good health is performed in advance. The motion frequency and the average duration value thus detected represent the motion tendency of an animal with good health. These values calculated in advance are stored in the storage unit 22, for example.

When the determination unit 204 is notified from the detection unit 203 that an operation has been detected, if the difference between the frequency and duration of the operation and the stored average value is equal to or greater than a threshold value, It is determined that motion has been detected, and it is determined that the animal is in poor health. Note that the determination unit 204 is considered to change the value indicating the above-described movement tendency (movement tendency of an animal having a good health state) when this difference is always occurring in a range that is less than the threshold value. Therefore, this value may be updated based on the difference.

Specifically, the determination unit 204 updates the value representing the tendency of the operation by adding the average value of the differences that occur within the range below the threshold (when the health condition is good). Thus, the determination unit 204 may update the tendency of the operation detected from an animal with a good health state based on the result detected by the detection unit 203. Thereby, compared with the case where this update is not performed, even if the tendency of the operation | movement detected from an animal with good health condition changes, it can continue determining appropriately whether the health condition is good or bad.

[2-4] Animal Health Conditions Animal health conditions are not only deteriorated when suffering from skin diseases as described in the example of FIG. In addition, the state of health may be deteriorated even in an excessively stressed state, a wet state, an injured state, or an extremely cold or hot surrounding. The frequency and duration of the action detected in each state is measured, and the determination unit 204 determines whether the health state is good or bad by setting a threshold value that can distinguish between the state and the state that is not. You may judge.

[2-5] Degree of health condition The determination unit 204 may determine how bad the animal is rather than having a poor health condition. For example, in the case of the skin disease shown in FIG. 16, it is determined that the frequency of the scratching operation (times / 6 hours) is 50 or more, it is determined that the patient is suffering from a skin disease. If it is 100 or more, it is determined that the skin disease has become serious. When these determinations are made, different notification information is displayed.

FIG. 19 shows an example of notification information displayed in this modification. In FIG. 19 (a), the notification information when the determination unit 204 determines that the patient is suffering from a skin disease is “Your pet is becoming a skin disease. The character string “?” Is displayed. In FIG. 19 (b), as the notification information when the determination unit 204 determines that a skin disease has occurred, “Your pet has a skin disease. It is recommended to have a medical examination for treatment. "" Is displayed. In FIG. 19C, as the notification information when the determination unit 204 determines that the skin disease has become serious, “Your pet's skin disease has become serious. Let's receive treatment as soon as possible. "Is displayed. According to this modification, it is possible to notify the user of how much of the prevention, treatment, emergency treatment, and the like is required depending on the degree of the health condition.

[2-6] Learning of Motion Detection The user may be able to scrutinize so that the first threshold value and the second threshold value become more appropriate values. For example, the detection unit 203 changes the value of one or both of the first threshold value and the second threshold value based on the result of the user evaluating the correctness of the detection result. In this modified example, when the detection unit 203 detects a scratching motion or a motion of shaking the body, the notification unit 206 is notified of this, and the notification unit 206 notifies the user that the motion has been detected. The display unit 301 of the user terminal 30 displays the notification information thus notified.

FIG. 20 shows an example of the notification information displayed in this modification. In this example, a character string “A scratching motion of your pet or a shaking motion has been detected. Is this detection result correct?”, A manipulator image B1 representing “Yes”, and “No” Is displayed on the display unit 301, and an operation element image B3 indicating "I don't know" is displayed. When the user operates the operator image B1, the user evaluates that the detection result is correct, and when the user operates the operator image B2, the user evaluates that the detection result is incorrect. The user terminal 30 notifies the server device 20 of the evaluated result.

For example, when the ratio or number of evaluations that the detection result is incorrect in a predetermined period is equal to or greater than a threshold, the detection unit 203 detects either or both of the first threshold and the second threshold. Change it to a value that is less likely to be used (both are larger values). Thereby, compared with the case where the threshold value is not changed in the present modification example, it is possible to reduce the erroneous detection that the operation is detected even though the operation is not performed, and to improve the detection accuracy. . When the user is not looking at the pet, the user only has to operate the operator image B3. In that case, the user terminal 30 does not notify the server device 20 of the evaluation result. Thereby, it can prevent that the detection precision falls by evaluation without a user's conviction.

Since this evaluation cannot be performed unless the user is near the pet, for example, when the user terminal 30 includes a measurement unit that measures the position of the own device, the display unit 301 registers the measured position. If it is not included in the home area of the user, the notification information may not be displayed. Further, when the sensor device 10 also includes a measurement unit that measures the position of its own device, the position information measured by both the sensor device 10 and the user terminal 30 is transmitted to the server device 20, and the notification unit 206 The notification information of this modification may be transmitted only when the distance between the positions of the devices is less than the threshold value. Thereby, it is possible to prevent the user from evaluating the motion detection result without looking at the pet.

In addition, when the motion is not detected even though the pet scratches or shakes, the user may evaluate that the motion is not correctly detected. In this case, for example, when the user sees these movements of the pet, the user performs an operation of starting an evaluation program.
FIG. 21 shows an example of an evaluation screen. In this example, a character string “Do you want to notify you that your pet has performed a scratching action or a shaking action?” And an operator image B11 representing “Yes” are displayed on the display unit 301. Yes.

When the user operates the operator image B11 on this screen, the user evaluates that correct detection is not performed, and the user terminal 30 notifies the server device 20 that this evaluation has been performed. For example, when the number of evaluations that the motion detection is not correctly performed is greater than or equal to a threshold value, the detection unit 203 determines whether or not the first threshold value and the second threshold value are detected. The value is changed to a value that is easily detected (both are smaller values). As a result, compared with the case where the detection unit 203 does not change the threshold value, the situation in which the motion is not detected even though the motion or the motion of shaking is performed is improved, and the detection accuracy is improved. Can do.

[2-7] First Threshold and Second Threshold In the embodiment, an example has been described in which values determined according to the acquired individual information are used for both the first threshold and the second threshold. Not only the first threshold value and the second threshold value, but also a value determined according to the acquired individual information may be used. Even in that case, compared to the case where both threshold values are fixed, it is possible to reduce erroneous detection due to individual differences when detecting an operation with a sensor attached to the neck of the animal.

In the embodiment, the first threshold value and second threshold value, both a predetermined value based on the experiments of (first threshold value 2.0 (G ^2), the second threshold value is 3 (times / sec)) As described above, the load on the apparatus that implements the detection unit 203 is reduced as compared with the case where a value corresponding to individual information is determined. The first threshold is a value determined according to individual information, the second threshold is a predetermined value, the first threshold is a predetermined value, and the second threshold is an individual. A value determined according to information may be used.

[2-8] Detection Based on Peak Intensity and Peak Appearance Frequency The detection unit 203 may detect an operation without using the first threshold and the second threshold. For example, the value of the peak intensity in the time change of the acceleration intensity represented by the acceleration information and the value of the appearance frequency of the peak having the peak intensity obtained when the animal performs the motion of scratching or shaking the body are predetermined. The range of values obtained by substituting into the above formula is confirmed by experiment. The detection unit 203 detects that the animal has performed an action of scratching or shaking the body when the value obtained from the acquired acceleration information is included in the range confirmed by the experiment. In addition to this, if the correlation between the peak intensity and the appearance frequency of the peak when the animal performs a motion of scratching or shaking the body can be found, the acceleration information for reproducing the correlation can be obtained. If acquired, the detection unit 203 may detect the operation.

[2-9] Notification unit The notification unit 206 notifies that the animal is in a poor health state, but is not limited thereto. For example, the notification unit 206 may notify that it is determined that the animal's health condition is good, or may notify that a motion of scratching or shaking is detected.

[2-10] Notification information In the embodiment, the notification information is displayed on the display unit 301. However, the present invention is not limited to this. If the user terminal 30 has a voice output function, it may be output by voice. Further, if the user terminal 30 has a vibration function, the user terminal 30 may be vibrated to notify that there is a notification. It is desirable that the user terminal 30 operates so that the user is aware as soon as possible that the animal is in poor health.

[2-11] Configuration of Device for Realizing Each Function Functions corresponding to the respective units shown in FIG. 6 may be realized by a device different from the embodiment.
FIG. 22 shows an example of a functional configuration in this modification. In this example, each function of the detection unit 203 and the like realized by the server device 20 is realized by the user terminal 30a. In this case, the user terminal 30a functions as a monitoring device for monitoring animals. The user terminal 30a acquires acceleration information transmitted from the sensor device 10 through, for example, Bluetooth (registered trademark) or wireless LAN (Local Area Network) communication. In the example of FIG. 22, for example, every time the user terminal 30 a can communicate with the sensor device 10, the operation is detected and the health condition is determined. Thereby, since the health state of the animal is determined every time the user approaches the animal to which the sensor device 10 is attached, it is possible to prevent the user from noticing that the health state of the animal in front of him is bad. Can do.

FIG. 23 shows another example of the functional configuration in this modification. In this example, the sensor device 10b realizes functions of the detection unit 203 and the like realized by the server device 20 and functions of the reception unit 302 and the like realized by the user terminal 30. In this case, the sensor device 10b functions as a monitoring device for monitoring animals. According to the example of FIG. 23, not only the owner of the user terminal or the owner of the animal, but anyone who can see the display unit 301 of the sensor device 10 b can notice that the animal is in a poor health state. it can. In addition, when the server apparatus 20 detects an operation | movement and the determination of a healthy state like an Example, it can notify that the health condition of an animal is bad also to the user of whereabouts. In addition to the above, for example, another device may perform motion detection and health status determination, or another device may receive individual information and display notification information. As described above, each unit illustrated in FIG. 6 and the like may be realized by any device configuration.

[2-12] Category of Invention In addition to the monitoring device (sensor device, server device, and user terminal) described above, the present invention is not limited to the sensor device and user terminal described in the embodiments, and other devices that realize the above-described functional groups. It can also be understood as each device such as an animal monitoring system including these devices.
In short, the present invention includes an acquisition unit that acquires information about acceleration from a sensor attached to the neck of an animal, and the appearance of a peak that satisfies a predetermined condition for peak intensity in the time change of acceleration represented by the information. An apparatus is provided that includes a detection unit that detects a motion of the animal scratching or shaking the body based on frequency.
In addition, the present invention provides a step of acquiring information about acceleration from a sensor attached to the neck of an animal, and an appearance frequency of a peak having an intensity equal to or higher than a reference peak intensity in a temporal change in acceleration represented by the information. And a method for monitoring an animal, and a program for causing a computer to execute the method, comprising: detecting a motion of the animal scratching or shaking the body.
This program may be provided in the form of a recording medium such as an optical disk in which it is stored, or may be provided in the form of being downloaded to a computer via a network such as the Internet, installed and made available for use. May be.

DESCRIPTION OF SYMBOLS 1 ... Monitoring system, 2 ... Network, 4 ... Collar, 10 ... Sensor apparatus, 20 ... Server apparatus, 30 ... User terminal, 11, 21, 31 ... Control part, 12, 23, 33 ... Communication part, 13 ... Acceleration sensor , 22, 32 ... storage unit, 34 ... display unit, 35 ... operation unit, 101 ... measurement unit, 201 ... first acquisition unit, 202 ... second acquisition unit, 203 ... detection unit, 204 ... determination unit 204 ... storage unit 205 ... notification unit, 207 ... correction unit, 301 ... reception unit, 302 ... display unit

Claims

A first acquisition unit for acquiring information about acceleration from a sensor attached to the neck of the animal;
A monitoring device comprising: a detection unit that detects a motion of the animal scratching or shaking based on an appearance frequency of a peak that satisfies a predetermined condition for peak intensity in a time change of acceleration represented by the information.
The first acquisition unit acquires triaxial acceleration,
The monitoring apparatus according to claim 1, wherein the intensity of the acceleration is represented by a sum of squares of the accelerations of the three axes.
The monitoring device according to claim 1, wherein the detection unit determines that the operation has been performed when an appearance frequency of a peak having an intensity equal to or higher than a reference peak intensity is equal to or higher than a reference frequency value.
The monitoring device according to claim 1, wherein the detection unit determines that the operation has been performed when the frequency of appearance of a peak having a peak intensity in a predetermined range is within the predetermined range.
A second acquisition unit for acquiring individual information of the animal;
The monitoring apparatus according to claim 3, wherein at least one of the reference peak intensity and the reference frequency value is set based on the individual information.
The individual information includes information on the animal's type, sex, length, weight, eating and drinking history, exercise history, activity, basal metabolism, illness or injury history, or current illness or injury status. The monitoring device according to claim 5, which represents physical strength or a health condition.
The monitoring apparatus according to claim 3, wherein the reference frequency value is 3 times per second.
The monitoring apparatus according to claim 3, wherein the reference peak intensity is 2.0 (G 2 ).
The monitoring device according to claim 3, wherein the detection unit changes one or both of the reference peak intensity and the reference frequency value based on a result of a user evaluating whether the detection result is correct or incorrect.
A determination unit that determines a health state of the animal based on a history of operations detected by the detection unit;
The monitoring apparatus according to claim 1, further comprising a notification unit that notifies a predetermined destination when it is determined that the animal is in a poor health state.
The determination unit detects the frequency at which the operation is detected or the detected frequency when an operation having a tendency different from the tendency of the operation detected when the user determines that the animal is in good health When the duration of the operation is greater than or equal to a threshold, if the frequency or the duration during which the duration continues to increase is greater than or equal to the threshold, or if the increase rate of the frequency or duration is greater than or equal to the threshold, The monitoring device according to claim 10, wherein the animal is determined to be in a poor health state.
Obtaining information about acceleration from a sensor attached to the neck of the animal;
Detecting the motion of the animal scratching or shaking the body based on the appearance frequency of a peak that satisfies a predetermined condition for peak intensity in the time change of acceleration represented by the information.