JP2022036278A - server - Google Patents

Abstract

PROBLEM TO BE SOLVED: To suitably control power consumption of a device for pet.

SOLUTION: There is provided a server for controlling a device for pet includes a measurement data acquisition unit for acquiring measurement data of a pet, an action information generation unit for generating action information of the pet on the basis of the measurement data, and a switching control unit for switching the power state of the device for pet on the basis of the action information. According to the present invention, power consumption of the device for pet can be suitably controlled.

SELECTED DRAWING: Figure 2

COPYRIGHT: (C)2022,JPO&INPIT

Description

Application for application of Article 30, Paragraph 2 of the Patent Act May 19, 2nd year Reiwa Published on official Twitter account of RABO Co., Ltd.

Patent Law Article 30, Paragraph 2 Application Applicable September 24, 1st year of Reiwa Published via the company's website of RABO Co., Ltd.

The present invention relates to a server for controlling a pet device.

In recent years, awareness of pet health management has increased.

Patent Document 1 describes a management server that determines and outputs the composition of components contained in the food provided to the pet animal based on the information obtained from the sensor attached to the pet animal.

Japanese Unexamined Patent Publication No. 2020-5534

However, in order to implement the above-mentioned services for pets, wearable devices to be worn on pets and IoT devices such as toilets and feeders are required, and battery life becomes an issue.

Therefore, one object of the present invention is to provide a server for appropriately controlling the power consumption of a pet device.

According to the present invention, a server that controls a pet device, a measurement data acquisition unit that acquires pet acceleration data, and an action information generation unit that generates pet behavior information based on the acceleration data. , A server including a switching control unit for switching the power mode of the pet device based on the behavior information can be obtained.

According to the present invention, it is possible to provide a server that appropriately controls the power consumption of a pet device.

It is a figure which shows the structural example of the system by embodiment of this invention. It is a conceptual diagram explaining the sensing of the animal in the house by embodiment of this invention. It is a figure which shows the hardware configuration example of the server by embodiment of this invention. It is a figure which shows the software configuration example of the server by embodiment of this invention. It is a configuration example of the measurement data acquisition unit and the measurement data storage unit according to the embodiment of the present invention. It is a configuration example of the animal information generation unit and the animal information storage unit according to the embodiment of the present invention. It is explanatory drawing about the flow of the analysis of the behavior type by embodiment of this invention. It is a figure explaining the input data analysis by embodiment of this invention. It is explanatory drawing of the Embodiment of this invention. It is a figure explaining the method of measuring the food intake by embodiment of this invention. It is a figure explaining the method of measuring the excretion amount by embodiment of this invention. It is a figure explaining the method of measuring the body weight by embodiment of this invention. It is a figure explaining the method of measuring the food intake by embodiment of this invention. It is a figure explaining the individual identification method by embodiment of this invention. It is a figure which showed the flow of the process by embodiment of this invention. It is a figure which shows the software configuration example of the server by embodiment of this invention.

The contents of the embodiments of the present invention will be described in a list. The present invention has the following configurations.
[Item 1]
A server that controls pet devices
The measurement data acquisition unit that acquires the measurement data of pets,
A behavior information generation unit that generates behavior information of the pet based on the measurement data,
A switching control unit that switches the power state of the pet device based on the behavior information,
Server with.
[Item 2]
The measurement data includes acceleration data.
The server according to item 1, wherein the behavior information generation unit generates behavior information based on the acceleration data.
[Item 3]
When the switching control unit detects behavioral information indicating sleep, the switching control unit
The server according to item 1 or 2, wherein the power state is switched to the power saving state.
[Item 4]
When the switching control unit further detects behavioral information other than sleep, the switching control unit further
The server according to item 3, wherein the power state is switched from the power saving state.
[Item 5]
The switching control unit further determines that the feeding time of the automatic feeder is based on the feeding time of the automatic feeder.
The server according to item 3 or 4, wherein the power state is switched from the power saving state.
[Item 6]
A server that controls pet devices
A judgment unit that determines the user's home status,
A switching control unit that switches the power state of the pet device based on the determination result,
A server.
[Item 7]
When the determination unit determines that the user has returned home,
The server according to item 6, wherein the switching control unit switches the power state to a power saving state.

<Details of the embodiment>
Hereinafter, embodiments of the present invention will be described with reference to the drawings.

<Overview>
The system according to the embodiment of the present invention includes a wearable device having a built-in acceleration sensor attached to a pet, a weighing scale device having a weight sensor for monitoring various weights such as weight, excretion, and food, a pet camera, and automatic feeding. Regarding power control of pet devices such as vessels. As shown in FIG. 1, the system of the present invention includes a server 1 and a pet sensor 5, a weight sensor 8, a communication terminal 2, and a user terminal 3 connected to the server 1 via a network such as the Internet. FIG. 1 shows one pet sensor 5 each for convenience of explanation.
, The weight sensor 8, the communication terminal 2, and the user terminal 3 are shown, but each of a plurality of terminals can be connected to the network of this system. In addition to the weighing device equipped with the weight sensor, other pet devices such as an automatic feeder and a pet camera may be connected to the network.

The pet sensor 5 to be attached to the pet may be, for example, an acceleration sensor, a temperature sensor, or the like. The weight sensor 8 measures the weight of the pet, and the excrement of the pet (feces,
There are those that measure urine), those that measure pet food (food, water), etc., which may be installed in beds, toilets, tableware itself, or on a table on which they are placed.

The data acquired by each sensor is transmitted to the server 1 via the communication terminal 2. The server 1 monitors the condition of the pet by analyzing the obtained data, detects changes in the health condition, and provides necessary information to the user.

The server 1 can provide the service to the user terminal 3 via the application. The user terminal 3 downloads an application from the server 1 or another server, executes this application, and accesses the server 1 via web page browsing software such as a browser to send and receive information to and from the server 1. You can do it again
It will be possible to receive services.

The communication terminal 2 can acquire each data by performing short-range wireless communication with the weight sensor 8 and the pet sensor 5 mounted on an animal, for example, a cat 6. More specifically, first, as shown in FIG. 2, a collar-shaped (or pendant-shaped) wearable device is attached to an animal 6 such as a cat. The wearable device contains an accelerometer and / or a temperature sensor. The weight sensor 8 and the pet sensor 5 BLUETOOT the data.
Through short-range wireless communication such as H (registered trademark) LAW ENERGY (BLE), the data is transmitted to the receiving device 7 installed in the same house, and the receiving device 7 transfers the data to the communication terminal 2 such as a router, and the communication terminal. 2 transmits data to the server 1 via the network. The weight sensor 8 and the pet sensor 5 use BLUETOOTH (registered trademark) LAWEN for data.
It may be transmitted directly to the user terminal 3 through short-range wireless communication such as ERGY (BLE). Here, as an example, the receiving device 7 can be equipped with a Linux (registered trademark) -based operation system, and can also be equipped with various sensors such as a temperature sensor for measuring the temperature. However, it may of course be one that does not have an OS, such as an embedded chipset.

The pet sensor 5 is, for example, an acceleration sensor. The accelerometer 5 has, as shown in FIG. 2,
It is a sensor that detects accelerations in three axis directions (x-axis, y-axis, and z-axis directions) that are orthogonal to each other, and is built in a collar attached to the neck of a cat. As shown in FIG. 2, the front-back direction of the cat is defined as the X direction, the left-right direction is defined as the Y direction, and the vertical direction is defined as the Z direction, and a collar is attached to the cat so that acceleration signals in each direction can be detected according to the movement of the cat. .. The type of sensor is not limited to this, and any sensing device that can acquire information on the movement of the cat, such as a gyro sensor and a motion sensor, can be adopted.

Pet devices such as wearable devices and weigh scale devices include a control mechanism that controls the power state based on the instruction information received from the server. For example, in the case of a wearable device, the power state can be changed by making the sampling rate changeable to a plurality of values (Hz). In addition, it is possible to take a sleep state by stopping an arbitrary function so as to suppress power consumption.

The user terminal 3 may be a general-purpose computer such as a workstation or a personal computer, or may be a smartphone, a tablet, a mobile terminal, another information terminal, or the like.

<Hardware configuration>
The server 1 and the user terminal 3 according to the present embodiment have the following hardware configurations. The following configuration is an example, and may have other configurations.

The server 1 is connected to a database (not shown) and constitutes a part of the system. The server 1 may be a general-purpose computer such as a workstation or a personal computer, or may be logically realized by cloud computing.

As shown in FIG. 3, the server 1 has at least a control unit 10, a memory 11, and a storage 12.
, Transmission / reception unit 13, input / output unit 14, and the like, which are electrically connected to each other through the bus 15.

The control unit 10 controls the operation of the entire server 1 and controls the transmission and reception of data between each element.
It is an arithmetic unit that performs information processing and the like necessary for execution of applications and authentication processing. For example, the control unit 10 is a CPU (Central Processing Unit).
Each information processing is performed by executing a program or the like stored in the storage 12 and expanded in the memory 11.

The memory 11 is a DRAM (Dynamic Random Access Memory).
) And other volatile storage devices, as well as flash memory and HDD (Hard D).
Includes auxiliary storage configured with a non-volatile storage device such as iscDrive). Memory 1
Reference numeral 1 is used as a work area or the like of the processor 10, and also stores a BIOS (Basic Input / Output System) executed when the server 1 is started, various setting information, and the like.

The storage 12 stores various programs such as application programs. A database (not shown) storing data used for each process may be built in the storage 12.

The transmission / reception unit 13 connects the server 1 to the network. The transmission / reception unit 13 is set to Blu.
It may be provided with a short-range communication interface of echoth (registered trademark) and BLE (Bluetooth Low Energy).

The input / output unit 14 is an information input device such as a keyboard and a mouse, and an output device such as a display.

The bus 15 is commonly connected to each of the above elements and transmits, for example, an address signal, a data signal, and various control signals.

<First Embodiment>
In the first embodiment, the power state can be controlled based on the behavior of the pet.

FIG. 4 is a diagram showing an example of software configuration of the server 1 in the system of the present invention. The server 1 can include a measurement data acquisition unit 21, an animal information generation unit 22, a switching control unit 23, a measurement data storage unit 31, an animal information storage unit 32, and a user information storage unit 33.

The measurement data acquisition unit 21, the animal information generation unit 22, and the switching control unit 23 are realized by the control unit 10 included in the server reading the program stored in the storage 12 into the memory 11 and executing the measurement data. The storage unit 31, the animal information storage unit 32, and the user information storage unit 33 are realized as a part of the storage area provided by at least one of the memory 11 and the storage 12.

The measurement data acquisition unit 21 acquires data related to the state of the animal from various measurement data acquisition means. As shown in FIG. 5, the measurement data acquisition unit 21 may include a behavior measurement data acquisition unit 211, a weight data acquisition unit 212, and an environmental data acquisition unit 213. Data on the condition of an animal includes data on the behavior, activity, physical condition, and surrounding environment of the animal. The measurement data acquisition means referred to here includes a device for acquiring data such as a pet sensor 5 such as an acceleration sensor, a weight sensor 8, and a camera. Further, various data acquired by the measurement data acquisition unit 21 are stored in the measurement data storage unit 31. As shown in FIG. 5, the measurement data storage unit 31 may include a behavior measurement data storage unit 311, a weight data storage unit 312, and an environmental data storage unit 313, and the data acquired from the corresponding measurement data acquisition units 21 may be included. Will be stored. Measurement data acquisition unit 21
In addition to these data, the measurement data storage unit 31 may include an acquisition unit and a storage unit for acquiring other data such as animal body temperature data and image data.

The behavior measurement data acquisition unit 211 receives the behavior measurement data detected by the pet sensor 5 and transmitted via the communication terminal 2 via the transmission / reception unit 13 of the server 1. The received behavior measurement data is stored in the behavior measurement data storage unit 311. Alternatively, it can be stored in the storage built in the analysis server 9 shown in FIG. The behavior measurement data is acceleration data when the pet sensor 5 is an acceleration sensor. In addition, other data such as image data and infrared data that can grasp the behavior of the pet may be used.

The pet sensor 5 is, for example, an acceleration sensor. The accelerometer 5 has, as shown in FIG. 2,
It is a sensor that detects accelerations in three axis directions (x-axis, y-axis, z-axis directions) that are orthogonal to each other, and is built in a collar worn on the neck of an animal such as a cat. As shown in FIG. 2, the front-back direction of the animal is defined as the X direction, the left-right direction is defined as the Y direction, and the vertical direction is defined as the Z direction, and a collar is attached to the animal so that acceleration signals in each direction can be detected according to the movement of the animal. .. The type of sensor is not limited to this, and any sensing device that can acquire information on the movement of animals, such as a gyro sensor and a motion sensor, can be adopted.

The weight data acquisition unit 212 acquires weight data from the weight measuring means. The weight measuring means is
There is no particular limitation as long as it is a device equipped with a weight sensor 8 and capable of measuring the amount of food, excretion, and body weight. Depending on the application, it is preferable to have a shape (for example, a board type) on which pet items such as toilets, tableware, and water bowls can be placed. The weight measuring means and the server 1 are connected by a communication network. Weight data is preferably acquired in chronological order. The acquired weight data is stored in the weight data storage unit 312 together with the time information. The weight data storage unit 312 stores the weight data acquired by the weight data acquisition unit 212 for each weight measuring means. The weight data is preferably time series data stored together with the time data.

The environmental data acquisition unit 213 acquires environmental data in which animals are bred. For example, temperature data, room temperature data, humidity data, etc. are acquired from thermometers and hygrometers installed indoors and outdoors. You may also obtain data on the climate of the area where the animals are located on the Internet. Further, the environmental data acquisition unit 213 acquires information on the disaster. Information on disasters is information on the occurrence of earthquakes, fires, floods, tsunamis, lightning strikes, tornadoes, and the like. Information on disasters may be acquired from various sensors installed indoors and outdoors, or disaster information provided on the Internet may be acquired, and the method is not particularly limited. The acquired environmental data is stored in the environmental data storage unit 313.

The animal information generation unit 22 generates animal information regarding the activity of the animal to be measured by analyzing various measurement data. That is, "animal information" is obtained by generating meaningful information (weight of a specific measurement target, number of times of a specific action, time, etc.) from measurement data which is raw data.
Is. As shown in FIG. 6, the animal information generation unit 22 can include a behavior information generation unit 221, a weight information generation unit 222, and the like. Further, the data related to the animal generated by the animal information generation unit 22 is stored in the animal information storage unit 32. The animal information storage unit 32 is a behavior information storage unit 3.
21, the weight information storage unit 322 may be included.

The behavior information generation unit 221 generates animal behavior data based on the received behavior measurement data in cooperation with the analysis server 9 (or by a single process in the behavior information generation unit 221).

Here, the behavior information is exercise data, sleep data, stored in the behavior information storage unit 321.
Includes meal data, toilet data, location data, etc. More specifically, as exercise data,
Aggregate data such as the presence or absence of exercise and how much activity you are doing in a day with time, as sleep data, aggregate data such as the presence or absence of sleep and how much sleep you are doing in a day with time, as dietary data Aggregate data such as how many times and when you ate a meal with the presence or absence of eating behavior and time, aggregated data such as how many times you drank water and when you drank with water intake behavior and time, and toilet data of defecation behavior Aggregated data such as how many times and when urination was performed with the presence or absence and time, and aggregated data such as how many times and when urination was performed with time and presence of urination behavior. In addition, the position data includes the direction in which the patient moved, the position in which the patient was located, and other data such as the time and number of grooming times. In short, it may be information such as the time and number of actions that can be given a specific label. Further, although not shown, the body temperature of the animal at the time of measurement may be measured.

Hereinafter, the flow of generating behavioral information when acceleration data is used as measurement data will be described. First, the behavior information generation unit 221 confirms the measurement data detected by the behavior measurement data acquisition unit 21. Subsequently, the action information generation unit 221 determines the action type based on the measurement data. The behavior type determination method can be realized by some known behavior analysis methods,
For example, acceleration data (Gx, Gy, Gz) in the xyz axis direction obtained from the acceleration sensor 5.
Using the wavelet transform, the signal with vibration is decomposed into period and amplitude for each time, the periodicity of the signal at each time is recognized as an action spectrum, and the action registered in advance according to the similarity of the spectra. Behaviors can be classified by comparing them with elements.

If there is no information on the behavioral element registered in advance, it can be recognized as a new behavioral element and provided to a veterinarian, for example, as data indicating the abnormal behavior described later. Alternatively, for example, the acceleration data obtained from the acceleration sensor 5 is Fourier transformed, and the average value or peak value of the frequency component calculated along the time axis is set to the same or different animal behavior type (exercise, sleep, meal). , Toilet, etc.) to identify the behavior by comparing with the known frequency, and to obtain characteristic waveforms and spectral values based on the frequency component calculated by performing the fast Fourier transform (FFT) of the acceleration component. Behavior can be identified by extracting and comparing with known characteristic waveforms or spectral values corresponding to the same or different animal behavior types (exercise, sleep, diet, toilet, etc.). In addition, the behavior type can be estimated by grasping the posture of the animal from the postures (θx, θy, θz) in each axial direction calculated by the acceleration sensor 5.

When the action type is determined, the action information generation unit 221 generates the data indicating the action type as the action information together with the date and time when the measurement data is measured (or the date and time when the measurement data is received, the date and time when the action information is generated).

Here, the flow of analysis of behavior types will be further described with reference to FIG. 7. The acceleration data 101 acquired from the acceleration sensor 5 is subjected to data preprocessing 102 so as to be the spectral data obtained by the above-mentioned wavelet transform or the component data obtained by the Fourier transform or the like. The data thus preprocessed is subsequently scored 103 by the binary model group. The binary model according to the present embodiment is comparatively analyzed with a model of activity that can be concretely expressed (interpreted) such as a WALK model, a RUN model, an EAT model, and a STAY model, and is specified among the preprocessed data 102. Score which action the part can be inferred to be. For example, as shown in FIG. 8, the accuracy is scored by analyzing the input data in each model. In the illustrated example, "walking" is 9
1. "Run" is 62, "Eat" is 21, "Stop" is 8, and the highest score is 91 for "Walk". Therefore, the scoring result by the binary model group is "Walk". are categorized.

Then, returning to FIG. 7, scoring 104 by the multi-valued model group is performed. In the scoring by the multi-valued model group according to the present embodiment, when the results obtained by the binary-valued model are in competition, which binary model group should be prioritized based on machine learning. judge. For example, in the example shown in FIG. 8, "walking" is 91 and "running" is 62, and the evaluation score of "running" is relatively high. In this case, it is determined which binary model should be prioritized in this case from the combination of the input data to the past binary model group and the determination result. As described above, in the present embodiment, the accuracy of the data is improved by further evaluating the results of the binary model group specialized in the determination of each behavior by the multi-value model group.

Returning to FIG. 7, the determined action is further corrected based on the rule base. For example, during a judgment section such as "eat" or "sleep" that often continues for a certain period of time due to the behavior of the cat.
If the binary model determines a behavior that is unlikely to occur suddenly, such as "running," or if it cannot be determined, the prediction result of the binary model in this section is rejected, and the correction is estimated to be another behavior according to the rules. I do. When the correction is completed, the action label 106 registered in advance for the action is given. In the above, it was explained that the scoring 103 by the binary model is followed by the scoring 104 by the multivalued model, but the scoring by the submodel (binary model) is performed after the scoring 104 by the multivalued model. You may try to do it.

In the present embodiment, in particular, in order to deal with individual differences of each animal and individual factors due to the environment, feedback 107 from the user is received. Specifically, as shown in FIG. 9, the current behavior is recorded (manually) while observing the animals under its control. By associating the recording with the data of the accelerometer, it is possible to collect teacher data by visual inspection or the like. The feedback data 108 thus obtained is
It is accumulated and used to improve the accuracy of the binary model group.

The behavior information generated as described above is stored in the behavior information storage unit 321. Behavior information is
It is preferably time series data stored together with time data. Even when image data other than acceleration data is used as the measurement data, the behavior of the pet is analyzed by an appropriately known method and behavior information is generated.

The weight information generation unit 222 analyzes the weight data acquired by the weight data acquisition unit 212, and the weight information generation unit 222 analyzes the weight data.
Calculate various measurement targets (body weight, food volume, water intake, defecation volume, urination volume, etc.). The weight information generation unit 222 includes a weight calculation unit. The weight calculation unit analyzes the weight data acquired by the weight data acquisition unit 212 and outputs the weight information of the target measurement target. When the weight acquisition means can set a plurality of measurement modes, the weight calculation unit calculates the weight according to the set measurement modes. The measurement mode defines at least a measurement target as described below, and may be set by the user, or may be automatically set by recognizing an item mounted on the weight measuring means.
An example of the weight calculation method for each measurement mode is shown below.

<Meal amount / water intake / weight measurement mode>
FIG. 10 shows an example of measuring the amount of food, the amount of water intake, and the body weight. When an animal rests on a weighing instrument to eat or drink water, the time-series weight data behaves, for example, as in FIG. The difference ΔW1 between the weight before the animal is placed on the weight measuring means and the weight when the animal is placed can be regarded as the weight of the animal. In addition, the difference ΔW2 between the weight before the animal gets on the weight measuring means and the weight when the animal finishes eating and drinking and gets off is the amount of decrease in food or water, that is, the intake. It can be seen as the amount of food and water intake. If the weight data is blurred due to the movement of the animal while the animal is on the weight measuring means, use the average value or the weight data when the animal has stopped moving for a certain period of time, etc. The optimum value may be adopted as appropriate.

<Excretion / weight measurement mode>
FIG. 11 shows an example of measuring the amount of excretion and body weight. When an animal enters a toilet above a weighing instrument to defecate or urinate, time-series weight data behaves, for example, as shown in FIG. Difference between the weight when the animal enters the toilet and the weight when the animal leaves the toilet ΔW3
Can be seen as the weight of an animal. The weight is the weight before the animal entered the toilet,
The difference from the weight immediately after entering the toilet may be adopted. Further, the difference ΔW4 between the weight before the animal enters the toilet and the weight after the animal leaves the toilet can be regarded as the excretion amount. If the weight data is blurred due to the movement of the animal while the animal is in the toilet, it is optimal to use the average value or the weight data when the animal has stopped moving for a certain period of time. It is good to adopt the value.

<Weight measurement mode>
FIG. 12 shows an example of measuring body weight. When an animal sits on a bed or the like on a weight measuring means to sleep or relax in the bed, the time-series weight data behaves as shown in FIG. 14, for example. The difference ΔW5 between the weight when the animal enters the bed and the weight when the animal leaves the bed can be regarded as the weight of the animal.

As described above, the weight calculation unit can estimate the weight of various measurement targets from the change of the weight data in the time series. The type of measurement target and its calculation method are not limited to those described above, and can be set arbitrarily.

The weight information generation unit 222 may further include a weight information evaluation unit. The weight information evaluation department
The accuracy of the weight information is evaluated by comparing the weight information calculated by the weight calculation unit with the behavior data. The weight information evaluation unit refers to the behavior data from the behavior information storage unit 321 at the time (t1 to t2) when the weight information of the measurement target is acquired, and whether the behavior of the pet at that time matches the measurement target of the weight information. To confirm. For example, when measuring in the meal amount measurement mode,
When the weight data fluctuates, the amount of change in the weight data is judged as "meal amount" as described above, but as shown in FIG. 13, the behavior data in that time zone (t1 to t2) indicates "meal". Therefore, it can be determined that the weight information is likely to be the amount of food. On the other hand, when the behavior data in that time zone is not "meal" (for example, "playing"), it is determined that the weight information may not indicate the amount of food. In this way, the weight information evaluation unit determines that the weight information is probable when the behavior data in the same time zone as the weight information matches the weight information, and when the behavior data does not match, the weight information is used. It can be tagged or deleted as uncertain data.

The weight information generation unit 222 may further include a weight type identification unit. The weight type identification part is
If the behavioral data can distinguish between eating rice and drinking water, or defecation and urination, the weight information calculated by the weight calculation unit. Can be specified more specifically. For example, in the food / water intake / weight measurement mode, when both the tableware and the water bowl are placed on the weight measuring means, ΔW2 indicates the total of the food amount and / or the water intake. Here, if the behavioral data in t1 to t2 indicate "meal", it can be determined that ΔW2 is the amount of food. Similarly, in the excretion / weight measurement mode, ΔW4 indicates the total of defecation volume, urination volume, or both, but the behavior data in the time zone when the weight data was acquired was “defecation”. In this case, ΔW4 can be determined to be the amount of defecation. In this way, the weight type specifying unit can more specifically specify the measurement target of the weight information from the behavior data in the same time zone.

The weight information generation unit 222 may further include an individual identification unit. The individual identification unit can determine which individual the weight information calculated by the weight calculation unit is based on in the case of a multi-headed animal. In the case of multi-headed animals, it is usually difficult to identify which individual is on one weighing means. The individual identification unit refers to the behavior data of each individual in the time zone (t1 to t2) when the weight data of the measurement target is acquired, and identifies the individual to which the weight information should be associated. In the example shown in FIG. 14, it is determined from the behavior data of the individual A and the individual B in t1 to t2 that the weight data acquired by the weight measuring means is that of the individual A who was eating. In this way, the individual identification unit can select an individual showing behavioral data that matches each weight information and add the individual information to the weight information.

Further, the individual may be identified from the waveform such as the acceleration data obtained from the sensor of each individual. It is known that even if the behavior is the same, each individual has a unique characteristic of the waveform. Individuals can be identified by comparing the characteristics of the behavioral waveform data in the time zone in which the weight data of the measurement target is acquired with the waveform of each behavior registered in advance.

For individual identification, various methods may be adopted in addition to the above-mentioned methods. For example, it may be performed by analyzing an image obtained by an image acquisition means capable of taking a weight measuring means. A moving image is taken over time by an image acquisition means such as a video camera, and an individual on the weight measuring means is identified by image recognition. The individual identification unit can identify an individual to which the weight information should be associated from the image data at the time when the weight data of the measurement target is acquired.

The individual identification unit may identify an individual near the weight measuring means by the strength of the radio wave intensity such as BLUETOOTH (registered trademark) LAW ENERGY (BLE) for data including individual information from a pet's collar or the like. A BEL receiving means can be provided at or near the weighing means to recognize an individual closer to the weight measuring means.

The individual identification unit may identify an individual by body weight. The individual can be identified by registering the body weight of the individual in advance and referring to the registered body weight when the body weight is calculated in each measurement mode.

As described above, the individual identification unit can identify an individual by a plurality of methods, but one or more of them can be adopted, and individual identification may be performed by combining a plurality of methods.

The weight information generated by the weight information generation unit 222 is stored in the weight information storage unit 322. For example, the measurement target and the weight of the measurement target (eg, the amount of food) may be stored for each measurement date and time. In addition to this, in the case of a multi-headed animal, information on an individual name and an individual ID may be included.

The user information storage unit 33 manages the basic information of the user (owner) and the basic information of the animal raised by the user. The basic information of the user includes information such as gender, age, occupation, and address. Basic information on animals raised by users includes name, type (dog, cat, etc.), breed, age, gender, place of residence, breeding environment (outdoor, indoor), genetic information, presence or absence of multi-headed breeding, health information, etc. ..
Examples of health information include hospital visit history and medical history. Information on multiple animals can be registered for one user. In addition, the basic information of these users and the basic information of animals are
For example, it is managed in association with the user ID given to the user. It is also possible to assign an ID to an animal.

The switching control unit 23 switches the power state of the pet device. As one embodiment, the switching control unit 23 can switch the power state based on the change in the behavior information of the pet. For example, by setting the action information and the power state in advance in association with each other, it is possible to determine whether to switch the power state when a predetermined action information is detected. As an example, as the behavior information of the first category, normal behaviors such as walking, playing, eating, excreting, grooming, and relaxing are registered. Further, as the behavior information of the second category, the behavior that does not cause any problem even if the power control of the pet device such as sleep is set to the power saving state is registered.
Further, as the behavior information of the third category, abnormal behaviors such as convulsions and vomiting that require higher accuracy of data acquisition than usual are registered. Then, when the behavior information of the first category is detected, the first power state is detected, and when the behavior information of the second category is detected, the second power state and the behavior information of the third category are detected. In this case, the power state of the pet device corresponding to each category can be set so that the third power state is set. The above-mentioned first to third action categorization and the power state switching setting based on the categorization are not limited to these examples, and 4
It may be set to one or more, or two or less. Further, the actions to be registered in each action category are not limited to the above examples, and can be appropriately set by the server administrator or the user.

With such a setting, the switching control unit 23 switches the power control from the first power state to the second power state when, for example, the pet's behavior information changes from "grooming" to "sleep". Control your pet device. Further, when the pet wakes up from "sleep" and starts "walking", the pet device is controlled so as to switch the power control from the second power state to the third power state.

Here, switching the power state of the pet device includes changing the power consumption, for example, in the case of a wearable device, changing the sampling rate. If it is an accelerometer, it is possible to save power by setting a sampling rate lower than the normal sampling rate. As described above, the sampling rate in the first to third states can be set in advance. For example, when the sampling rate of the accelerometer is switched as described above, it can be set to 2 Hz in the second power state, 10 Hz in the first power state, 32 Hz in the third power state, etc., but it is a specific numerical value. Can be selected as appropriate. The power control method is not limited to this, and the predetermined function is OF.
It suffices if it is possible to switch to a different power consumption state, such as setting it to F or putting the power supply into a sleep state. When setting the first to third power states as described above, it is possible to set so that the power consumption increases and the sampling rate increases in the order of 3>1> 2. can.

As a preferred embodiment, the switching control unit 23 can switch the power state according to the behavior information generated by the animal information generation unit 22 analyzing the acceleration data. For example, when the animal information generation unit 22 detects the "sleep" behavior, the switching control unit 23 transmits an instruction to switch the first power state to the second power state to the pet device. Upon receiving the instruction information, the pet device performs switching to a predetermined power saving state such as lowering the sampling rate.

Further, when the animal information generation unit 22 detects the behavior of the first or third category after instructing to set the second power state based on the "sleep" behavior, the switching control unit 23 may perform the switching control unit 23. An instruction to switch the power state to the first power state or the third power state is transmitted to the pet device. Upon receiving the instruction information, the pet device performs switching to a predetermined power state such as increasing the sampling rate. By controlling in this way, when the pet wakes up from sleep and starts other behaviors other than sleep such as walking, running, and playing, the power state can be quickly switched, which hinders the acquisition of normal behavior data. There is no effect. In addition, the sleep of pets is irregular and usually difficult to predict, but by detecting sleep based on the behavior classification, it is possible to accurately grasp the state of the pet and perform accurate power control.

The switching control unit 23 may switch the power state based on information other than the action information based on the acceleration data. For example, the behavior information of the pet may be acquired by analyzing the image data obtained by capturing the state of the pet with a camera. When using image data, the power state may be switched based on various actions in the same manner as described above. That is, for example, when it is determined from the image data that the person is sleeping, the power saving state (second power state) is switched to, and when behavior other than sleep is observed, the normal state (first power state) is set. Can be done. Any method can be adopted as the analysis method for grasping the behavior from the image data.

Further, the switching control unit 23 may switch the power state according to the activation of a specific device such as an automatic feeder. For example, in an automatic feeder, food is automatically supplied to the tableware, but pets often notice the sound and smell of food being supplied to the tableware even when sleeping. By utilizing this habit, it is possible to acquire preset food supply time information in the automatic feeder and switch the power state when the time is reached.
Further, when the user who is the owner operates the automatic feeder remotely, the remote controlled information can be acquired and the power state can be switched. Further, a camera, a predetermined sensor, or the like may be installed in the automatic feeder to detect that the feed has been supplied and switch the power state. When the behavior of the second category such as sleep is detected and controlled to the second power state, the power state is switched from the second power state to the first power state based on the operation of the automatic feeder. As a result, it may be possible to switch the power state without a time lag.

FIG. 15 is an operation flow of the server 1 according to the embodiment of the present invention.

The measurement data acquisition unit 21 acquires acceleration data (S301). Animal information generation unit 22
Generates behavioral information by analyzing acceleration data (S302). The switching control unit 23 determines whether or not there is a predetermined behavior change set in advance (S303). That is, it classifies which of the preset action categories the generated action information belongs to, and when a change to a different action category is detected (S303 = Yes), an instruction to switch the power state to a predetermined state is given. Generate and send to the pet device (S304). The process returns to step S301 again, and the detection of the behavioral change and the switching of the power state are repeated. Although the case where the acceleration data is used as the measurement data is described here, other data such as image data and infrared data may be adopted as the measurement data as long as the behavior information can be generated.

According to the first embodiment, the power state of the pet device can be switched according to the behavior of the pet. For example, while the pet is sleeping, the sampling rate of the wearable device can be lowered, and the pet device such as the weigh scale device can be in a power saving state, so that the battery life can be improved.

<Second embodiment>
In the second embodiment, the power state is controlled based on the going out / returning home of the user who is the owner.

FIG. 16 is an example of software configuration of the server 1 in this embodiment. The server 1 is different from the first embodiment in that it further includes a determination unit 24, but is the same in other respects.

In the second embodiment, the determination unit 24 determines whether the user goes out or returns home, and the switching control unit 23 switches the power state based on the determination result. For example, when the user goes out, the detection accuracy may be lowered as the first power state in order to improve the detection accuracy of the pet wearable device, and when the user is at home, the detection accuracy may be lowered as the second power state. The switching of the power state is not limited to this, and the first power state may be set when the user is at home and the second power state may be set when the user goes out. The first and second power states referred to here are states in which the power consumption of the second power state is lower than that of the first power state, as in the first embodiment. For example, in the case of a wearable device, the sampling rate of the second power state is lower than that of the first power state.

The determination unit 24 determines whether the user goes out / returns home. For example, the determination unit 24 may determine whether to go out / return home by registering the user's normal outing time and return time. That is, when going out at 8 am on weekdays and returning home at 19:00 on weekdays, it can be determined to be "going out" at 8 am on weekdays and "returning home" at 19:00 on weekdays. The time to go out and the time to return home may be registered multiple times in a day, or may be changed for each day of the week. In addition, if it is known in advance that the user will go out and return home at a different time than usual, the user may enter these times each time.

Further, the determination unit 24 may determine whether the user goes out / returns home by interlocking with an external application for schedule management. The application for schedule management is not particularly limited, but any application may be used as long as it can register information such as time and place for the user's business. The determination unit acquires the user's schedule information from the schedule management application. Then, it is possible to determine whether to go out / return home based on the event included in the schedule information. For example, "going out" may be determined at the start time of the first event in the day included in the schedule, and "returning home" may be determined at the end time of the last event. Further, in consideration of the travel time, "going out" may be set before the predetermined time of the start time of the event, and "returning home" may be set after the predetermined time of the end time of the event. The travel time may be calculated according to the distance between the location of the event and the home. Further, it may be determined whether or not the event requires going out based on the information such as the location and contents of the event registered in the schedule management application. That is, if the place is "home", it can be determined that the event does not go out. The determination unit 24 may learn the relationship between the past event information and the presence / absence of going out, the going out time / returning time, and the like by any method such as machine learning, and may estimate the going out time / returning time from the schedule information.

Further, the determination unit 24 may determine whether the user goes out or returns home based on the image data acquired by the camera. For example, if the user is not detected in the image data of a predetermined place in the house for a predetermined time or more, it is determined that the user has gone out, and if the user is detected in the image data, the user returns home. It may be determined that it has been done. Any method can be used to detect the user from the image data.

Further, the determination unit 24 may determine whether the user goes out / returns home in conjunction with the smart lock system at the entrance. The determination unit 24 acquires information about the lock from the smart lock system. For example, when the information that the lock is locked is acquired, it can be determined as "going out", and when the information that the lock is released and the information is acquired is acquired, it can be determined as "returning home".

The determination unit 24 may determine the user's going out / returning home by adopting a plurality of methods among the means described above. For example, the condition that the time is normal for going out / returning home may be determined together with the information acquired from the smart lock system. In addition to these methods, the determination unit 24 can adopt a method capable of determining whether the user is going out / returning home. When the user goes out and returns home, he / she may input through the user terminal 3. The determination unit 24
The determination result is transmitted to the switching control unit 23. The switching control unit 23 generates control information for the pet device based on the determination result.

According to the second embodiment, it is possible to determine whether the user goes out / return home and control the power state of the pet device. For example, a wearable device for grasping the behavior of a pet may improve the data acquisition accuracy particularly when the user goes out.

The embodiments described above are merely examples for facilitating the understanding of the present invention, and are not intended to limit the interpretation of the present invention. It goes without saying that the present invention can be modified and improved without departing from the spirit thereof, and the present invention includes its equivalents.

1 Server 2 Communication terminal 3 User terminal 5 Pet sensor 8 Weight sensor

Claims (7)

A server that controls pet devices
The measurement data acquisition unit that acquires the measurement data of pets,
A behavior information generation unit that generates behavior information of the pet based on the measurement data,
A switching control unit that switches the power state of the pet device based on the behavior information,
Server with. The measurement data includes acceleration data.
The server according to claim 1, wherein the behavior information generation unit generates behavior information based on the acceleration data. When the switching control unit detects behavioral information indicating sleep, the switching control unit
The server according to claim 1 or 2, wherein the power state is switched to a power saving state. When the switching control unit further detects behavioral information other than sleep, the switching control unit further
The server according to claim 3, wherein the power state is switched from the power saving state. The switching control unit further determines that the feeding time of the automatic feeder is based on the feeding time of the automatic feeder.
The server according to claim 3 or 4, wherein the power state is switched from the power saving state. A server that controls pet devices
A judgment unit that determines the user's home status,
A switching control unit that switches the power state of the pet device based on the determination result,
A server. When the determination unit determines that the user has returned home,
The server according to claim 6, wherein the switching control unit switches the power state to a power saving state.

Images