TW202023366A - Action sensing system based on learning algorithm and method thereof - Google Patents

Abstract

An action sensing system for a pet has a sensing device, a sensing signal acquiring unit and an action posture processing unit. In a determination mode, the action posture processing unit selects corresponding one among established multiple action posture reference data according to an action name, a wearing status information which the sensing device is worn by the pet and a pet body information, the sensing signal acquiring unit acquiring obtains at least one action sensing signal sensed by the sensing device, and the action posture processing unit compares an action posture data generated based upon the at least action sensing signal to the selected action posture reference data, so as to determine whether a action posture of the pet is correct or not.

Description

Motion sensing system and method for pets

The present invention relates to a motion sensing technology for pets, in particular to a pet's motion for pets whose sensing device can be worn in any posture in any wearing position and wearing manner without affecting the result of their motion posture interpretation Sensing system and its method.

In today's society, many families have pets, such as cats, dogs, minks, parrots or lizards. With the advancement of animal protection concepts and technology, many owners will pay attention to the health of their pets, and even spend time and money to train their pets to perform specific actions to increase their talents, and to interact with their pets so that their pets will also be satisfied. Not easy to be melancholy.

In the prior art, the wearable device for pets that has been proposed is described as follows. The Republic of China TW M511836 patent proposes a wearable medical and health care device for pets. The wearable medical health care device for pets can be worn around the body of the pet and fixed on the back of the pet. The wearable medical and health care device for pets also has a radiation heating layer, and the radiation heating layer is used to emit infrared radiation or far-infrared radiation to irradiate the pet's back and hip joints. In this way, the joints, bones and muscles of pets can be treated through infrared radiation or far-infrared radiation, so as to solve the problem that pets are generally active and do not want to sit (or lie down) in a specific place for treatment.

The Republic of China TW M527577 patent provides a wearable sensing device that can be worn by people or pets and has a positioning device to locate the user or pet wearing it, thereby preventing the user or pet from getting lost. It can be seen from the above that the ROC TW M511836 patent only provides a wearable device for pets with medical functions, while the ROC TW M527577 patent only provides a universal wearable device with positioning function. Therefore, the prior art does not provide a Wearable devices and motion sensing systems that sense pets' movements.

In addition, although the prior art provides wearable devices that can be worn by people and sense motion data, the wearing position and the way of wearing these wearable devices are fixed, and when the posture of the user is different, the interpretation may not be correct Whether the user's gesture is correct. Therefore, the aforementioned wearable devices with sensing motion postures cannot be directly applied to pets of different postures.

For example, the Republic of China TW I491379 patent proposes a wearable dynamic sensing device that can be worn on the user's limbs to detect the dynamic physiological signals of the user's limbs. The wearable dynamic sensing device includes a sensing module, a transmission module, and a stabilization module, and is mainly used for joint bending posture correction or rehabilitation. In other words, the wearable dynamic sensing device must be worn on the user's limbs, and does not have an adaptive design for any wearing position and wearing mode.

To take another example, the ROC TW M537280 patent proposes a fall detection system, which includes a wearable device and a processor useful for users to wear. The wearable device is equipped with an inertial sensor for detecting user motion data. The Republic of China TW M537280 No. 5 patent mainly measures normal movement posture data through a wearable posture dynamic sensing device, and stores the data in a database to compare normal and abnormal data to determine whether a fall or not. Therefore, the ROC TW M537280 patent also fails to mention the adaptable design of arbitrary wearing positions and wearing methods.

In summary, the prior art does not provide a motion sensing system that can sense pets' motions, and also does not provide a sensing device for pets that can be worn in any posture in any manner and/or wearing position. Motion sensing system.

Therefore, in order to overcome the shortcomings of the prior art, embodiments of the present invention provide a motion sensing system and method for pets. Even if the sensing devices in the motion sensing system for pets are worn on pets of different postures in different wearing modes and/or wearing positions, the motion sensing system for pets and the method thereof can still be correct Interpret the pet's movement and posture. To put it simply, the motion sensing system for pets and the method thereof enable the sensing device to be worn on the pet to have an adaptive design of any wearing position, any wearing manner, and any pet posture.

Based on at least one of the foregoing objectives, an embodiment of the present invention provides a motion sensing device worn on a pet, which includes a sensing device, a sensing signal acquisition unit, and a motion posture processing unit. The sensing device includes at least one sensor for being worn by pets. The sensing signal acquisition unit is electrically or communicatively connected to the sensing device. The motion posture processing unit is electrically or communicatively connected to the sensing signal acquisition unit. In the interpretation mode, the action posture processing unit selects the corresponding one from a plurality of action posture reference data created by itself based on the action name, the wearing state information of the sensing device worn on the pet, and the pet individual information. The sensing signal acquisition unit acquires at least one motion sensing signal sensed by the sensing device, and the motion posture processing unit compares the motion posture data formed based on the at least one motion sensing signal with the selected Action posture reference data to determine whether the pet’s action posture is correct.

Optionally, in the embodiment of the present invention, the motion sensing device worn on a pet further includes another sensing device and another sensing signal acquisition unit. The other sensing device includes at least another sensor for being worn by another pet. Another sensing signal acquisition unit is electrically or communicatively connected to the other sensing device and the motion posture processing unit. In the interpretation mode, the action posture processing unit self-creates multiple pieces of information based on another action name, another wearing state information of the another sensing device worn on the another pet, and another pet's individual information One of the action posture reference materials is selected corresponding to the other one, the sensing signal acquiring unit acquires at least one action sensing signal sensed by the another sensing device, and the action posture processing unit is based on the other Another action posture data formed by the at least one action sensing signal of a sensing device and the selected another action posture reference data are used to determine whether the another action posture of the other pet is correct.

Optionally, in the embodiment of the present invention, the action posture processing unit includes two client-side processing units and a server-side processing unit. The two client processing units are electrically connected or communicatively connected to the two sensing signal acquisition units respectively. The server-side processing unit is electrically or communicatively connected to the two client processing units.

Optionally, in the embodiment of the present invention, in the learning mode, the action posture processing unit records the action name, the wearing state information, and the pet individual information, and the sensing signal acquisition unit acquires all At least one training sensing signal sensed by the sensing device, and the action posture processing unit creates all corresponding to the action name, the wearing state information, and the pet individual information according to the training sensing signal Refer to the reference material of the action posture.

Optionally, in the embodiment of the present invention, the wearable device information includes information about the wearing mode and wearing position of the sensing device worn on the pet.

Optionally, in the embodiment of the present invention, the pet individual information includes information about the pet's height, length, weight, gender, age, and health status.

Optionally, in the embodiment of the present invention, the motion posture processing unit further includes a voice input unit, wherein the user controls the motion sensing system for pets through the voice input unit.

Optionally, in the embodiment of the present invention, the sensor includes a nine-axis attitude sensor, a pressure sensor, a tension sensor, a temperature sensor or a vibration sensor.

Optionally, in the embodiment of the present invention, the motion sensing system for pets is further connected to a social network or chat software, and the motion sensing system for pets further includes a positioning device or text/ Voice conversion device.

Based on at least one of the foregoing objectives, an embodiment of the present invention also provides an adaptive motion gesture sensing method, including the following steps. In the interpretation mode: according to the action name, the wear status information of the sensor device worn on the pet, and the pet individual information, select the corresponding one among the multiple action posture reference data created; obtain the sensor worn on the pet At least one motion sensing signal sensed by the device; and comparing the motion posture data formed based on the at least one motion sensing signal with the selected motion posture reference data to determine whether the pet's motion posture is correct. In the learning mode: record the action name, the wearing state information and the pet individual information; acquire at least one training sensing signal sensed by the sensing device; and according to the at least one training sensing signal Create the action posture reference data corresponding to the action name, the wearing state information and the pet individual information.

In short, the motion sensing system and method for pets of the present invention can wear the sensing device to different wearing positions of pets in different wearing ways, and in the learning mode, it can establish corresponding wear patterns and wearable positions. The movement posture reference data of the position and individual pet information is used in the interpretation mode as a reference standard for judging whether the pet’s movement posture is correct. Therefore, the motion sensing system and method for pets of the present invention can not limit the wearing mode, wearing position and wearing object of the sensing device (that is, it can be adapted to pets of different individuals), so it can improve the convenience and convenience of use. flexibility. In addition, the motion sensing system and method for pets of the present invention can not only be applied to the interpretation of the action posture when the user interacts with the pet, but also can be applied to the interpretation of the action posture in pet training and multi-pet competition games. Inventions have great potential for commercialization.

In order to fully understand the purpose, features and effects of the present invention, the following specific embodiments are used in conjunction with the accompanying drawings to give a detailed description of the present invention. The description is as follows.

Embodiments of the present invention provide a motion sensing system and method for pets, which can allow users to flexibly determine the wearing position and manner of wearing the sensing device on the pet, and the motion sensing system and method for pets are not Due to factors such as wearing position, wearing style, and individual differences in pets (including differences in posture, health status, and/or gender differences), etc., the pet's posture cannot be correctly interpreted. Further, the motion sensing system and method for pets have two modes, which are a learning mode and an interpretation mode.

In the learning mode, the motion sensing system and method for pets will record the wearing status information of the sensing device (including at least one of the wearing method and wearing position) and the pet's individual information (including the pet's height, height, and weight). , At least one of age, health status and gender). For each action, the motion sensing system and method for pets will obtain multiple training sensing signals of the pet’s correct motion posture in the learning mode, and use learning algorithms (for example, the depth of the neural network architecture) Learning algorithm, but not limited to this), based on the aforementioned multiple training sensing signals to establish the corresponding action posture reference data.

In the interpretation mode, the motion sensing system and method for pets will acquire the wearing state information of the pet-wearing sensing device, the pet's individual information, and the name of the action, so as to select the corresponding motion posture reference data and obtain the corresponding The motion posture data of a plurality of motion sensing signals generated by sensing the motion posture of the pet. Then, the motion sensing system and method for pets can determine whether the pet's motion posture is correct in the interpretation mode based on the motion posture data and the selected motion posture reference data.

To put it simply, the motion sensing system and method for pets of the embodiments of the present invention have a learning mode and an interpretation mode. In the learning mode, through the acquired multiple training sensing signals, the motion posture reference data of various actions related to the pet wear sensing device and the pet's individual information are established. In the interpretation mode, for one of the actions, select the action posture reference data related to the pet wear sensor device's wearing state information and the pet individual information, and combine the action posture data generated by multiple action sensing signals with the selected action posture Reference materials are compared to determine whether the pet's posture is correct.

In this way, the above motion sensing system and method for pets can be used to train pets to perform specific actions, and when specific actions are completed, snacks or feeds are given to pets as rewards through the connected automatic feeder, thereby achieving interaction with pets , Let pets get satisfaction from it, and it is not easy to suffer from depression. Preferably, the above-mentioned motion sensing system for pets and the method thereof can also send out information about pets performing specific actions through the connected social network, so as to achieve the interaction between pet owners; or, the above-mentioned motion sense for pets The testing system and its method can also allow pet trainers (or owners) to train pets online through connected chat software.

After roughly explaining the specific concepts and achievable methods of the present invention, then, in conjunction with the drawings and various embodiments, at least one implementation of the present invention will be described in detail.

First of all, please refer to Fig. 1. Fig. 1 is a schematic diagram of a situation in which the sensing device in the motion sensing system for pets according to an embodiment of the present invention is worn on pets of different postures. Figure 1 shows a user 11 (owner or pet trainer) interacting with pets 121-123. In Figure 1, the height, height, weight, age, health and gender of pets 121-123 They may not be the same, so the sensing devices 131-133 may be worn on the bodies of the pets 121-123 in different wearing ways and/or different wearing positions. For example, the pet 121 is a large male dog, so the two ends of the sensing device 131 may be surrounded by additional straps around the torso of the pet 131 to fix the sensing device 131 on the torso of the pet 131; the pet 122 has thick legs For small dogs, the sensing device 132 can be tied around the front legs of the pet 122; and the pet 123 is a medium-sized dog with thin legs, so the sensing device 133 can only be tied around the neck of the pet 123.

In the embodiment of Figure 1, the motion sensing system for pets 121-123 includes sensing devices 131-133, multiple sensing signal acquisition units, and motion posture processing units, of which the sensing devices 131-133 Each includes at least one sensor to sense the training sensing signal and the motion sensing signal when the pet moves in the learning mode and the interpretation mode, respectively. The sensing signal acquisition unit can be integrated with the sensing devices 131 to 133 to form a wearable device, and the motion posture processing unit can be implemented by the processing unit and input/output circuit in one or more of the wearable devices, or by The wearable device communicates with a server or a computing device.

Taking the action posture of sitting down as an example, the action posture processing unit of the action sensing system for pets 121-123 can record the wearing state information of the sensing devices 131-133 on the pets 121-123 and the pets in the learning mode. The individual pet information of the pets 121-123 is obtained, and the plurality of training sensing signals sensed by the sensing devices 131-133 of the pets 121-123 when sitting down are obtained through a plurality of sensing signal acquisition units to generate each pet 121- 123 corresponds to the posture reference material for sitting down. Next, in the interpretation mode, the multiple sensing signal acquisition units used in the motion sensing system of the pets 121-123 acquire multiple motion sensing signals sensed by the sensing devices 131-133 when the pets 121-123 are sitting down And the action posture processing unit generates corresponding action posture data accordingly to compare the action posture reference data of the pets 121 to 123 with the action posture data to determine whether the sitting action posture of the pets 121 to 1231 is correct. In addition, the motion sensing system for pets 121 to 123 may also have an automatic feeder 14, wherein the motion posture processing unit can be connected to the automatic feeder 14 in a wired or wireless manner, so as to correctly complete the sitting action of the pets 121 to 123 When the time, the automatic feeder 14 is controlled to send feed or snacks to the pets 121-123, so as to achieve the purpose of interacting with the pets 121-123 and training the pets 121-123 to complete specific actions.

To put it simply, unlike traditional sensing devices that can only be worn in a specific wearing position in a specific wearing manner, the motion sensing system for pets in Figure 1 has the sensing devices 131-133 to be worn on pets in different ways The adaptive design of the different wearing positions of the pets 121-123, and the motion sensing system for the pets 121-123 takes into consideration the individual pets of the pets 121-123 when judging whether the motion posture is correct. Generally speaking, in addition to the difference in the sensing signal due to the way of wearing and the position of wearing, for the same kind of action, because of the harmony and explosive power between different pets 121-123 (with pets 121-123's posture, health and gender) And so on) and so on may be too different, so the sensing signal between different pets 121-123 will also be different. The motion sensing system for pets 121 to 123 in the embodiment of the present invention considers the individual pet conditions of the pets 121 to 123, so that the motion postures of the pets 121 to 123 can be judged more accurately.

Next, please further refer to FIG. 2, which is a schematic plan view of the wearable device in the motion sensing system for pets according to an embodiment of the present invention. The wearing device includes an elastic stretch belt 2 with a first joining unit 221 (for example, first devil felt) on one side of the elastic stretch belt 2 and a second joining unit 222 (for example, second devil felt) on the other side of the elastic stretch belt 2 . The first joining unit 221 and the second joining unit 222 can be joined to each other. In this way, the elastic elastic band 2 can surround the pet's body and be fixed to the pet's body, so that the wearable device can be worn on the pet's body. In addition, when the body of the pet is too large, the first joining unit 221 and the second joining unit 222 can be joined with additional straps so that the wearable device can be worn on the pet's body. Furthermore, there may be a circuit area 21 between the two sides of the elastic elastic band 2, wherein the sensing device may be arranged in the circuit area 21. In addition, as described above, the wearable device may further include a sensing signal acquisition unit and an action posture processing unit, wherein the sensing signal acquisition unit and the action posture processing unit can be disposed in the circuit area 21.

Next, please further refer to FIG. 3, which is a functional block diagram of the motion sensing system for pets according to an embodiment of the present invention. The motion sensing system 3 for pets includes a motion posture processing unit 31, a sensing signal acquisition unit 32, and a sensing device composed of a plurality of sensors S1 to Sn, wherein the plurality of sensors S1 to Sn are electrically connected or The communication connection sensing signal acquisition unit 32 and the sensing signal acquisition unit 32 are electrically connected or the communication connection action posture processing unit 31. In this embodiment, the action posture processing unit 31, the sensing signal acquisition unit 32, and the plurality of sensors S1 to Sn may be integrated into a wearable device, or there are only a plurality of sensors S1 to Sn and the sensor The signal acquisition unit 32 is integrated in a wearable device, and the motion posture processing unit 31 is a server or a computer device such as a computer, a tablet, or a smart phone.

The sensors S1～Sn can be nine-axis attitude sensors (three-axis magnetic field sensor, three-axis accelerometer and three-axis gyroscope), pressure sensor, tension sensor, temperature sensor and vibration sensor Any one of the sensors and its combination are used to sense multiple training sensing signals (in the learning mode) or multiple motion sensing signals (in the interpretation mode) generated by the pet's motion posture. The signal acquisition unit 32 is used to acquire a plurality of training sensing signals (in the learning mode) or a plurality of motion sensing signals (in the interpretation mode) generated by the sensors S1 to Sn to sense the pet's motion posture, and to The acquired multiple training sensing signals (in the learning mode) or multiple motion sensing signals (in the interpretation mode) are sent to the motion posture processing unit 31. The action posture processing unit 31 is used to create action posture reference data corresponding to various actions of the wearing style, wearing position and pet individual information according to the received multiple training sensing signals in the learning mode, and to select and use in the interpretation mode The action posture reference data corresponding to the current wearing style, wearing position and pet individual information is compared with the action posture data generated by the current multiple motion sensing signals, so as to judge whether the corresponding action posture of the pet is correct .

The above-mentioned method of establishing action posture reference data in learning mode can use learning algorithms such as artificial intelligence or data statistics, and the present invention is not limited by this. Other algorithms such as data mining, fuzzy logic, neural network-like or deep learning The law can be applied. In addition, each action posture reference data created corresponds to the way of wearing, wearing position, pet individual information, and action name. Therefore, for different pets, different ways of wearing and wearing positions, the motion sensing system 3 for pets can Accurately interpret the pet's posture. Since the 3 motion sensing systems for pets provide extremely high adaptability, users do not need to purchase multiple wearable devices for different pets, but only need to purchase one without having to interpret the motions of multiple pets at the same time. Therefore, it is possible to have different wearing modes and wearing positions or use for different pets according to its adaptability, so the present invention can also reduce the purchase cost of the wearable device.

Furthermore, the action posture processing unit 31 uses sensor signal fusion filtering technology, user input (action name (or decomposition posture name), pet individual information, wearing status information (wearing method and wearing position), mode selection ( Enter the learning mode or interpretation mode)) and learning algorithm to complete the functions of action posture learning, action posture interpretation, pet identification and action posture interpretation result output. It is worth mentioning that the action posture processing unit 31 may have a voice input unit, so that the user (owner or trainer) can simultaneously set action names, decompose posture names and posture sequence when interacting with pets (or training pets). Thereby enhancing the effectiveness of interaction (or training).

The motion sensing system 3 for pets in FIG. 3 can be used for interaction or training of individual pets, for example, users can define the pet's motion posture by themselves, and use the motion sensing system 3 for pets to evaluate the effectiveness of pet interaction and training. . For example, in the learning mode, the user can set the wearing method and wearing position of the wearable device on the pet's body to be tied to the pet's chest, and the action name is crawling and rolling (rolling after lying down), the user can use voice input to make The motion posture processing unit 31 obtains a plurality of training sensing signals of lying down and rolling after lying down to establish reference data of the action posture. Then, in the interpretation mode, the motion posture processing unit 31 can determine whether the current pet's motion posture is correct according to the motion posture data and the motion posture reference data generated by the acquired multiple motion sensing signals.

Furthermore, the motion posture processing unit 31 can be extended to wired or wirelessly connected to remote or cloud servers, databases, cloud computing, etc., to simultaneously complete the motion posture learning of multiple pets, the motion posture interpretation of multiple pets, Multiple pet identification and multiple pet action posture interpretation results are output, the details of which are shown in the embodiment in Figures 4 and 5.

Next, please refer to FIG. 4, which is a functional block diagram of a motion sensing system for pets according to another embodiment of the present invention. The motion sensing system 4 for pets includes a motion posture processing unit 41, a plurality of sensing signal acquisition units 421 to 42k, and a plurality of sensing devices, each of which is composed of a plurality of sensors S1 to Sn. As a result, a plurality of sensing devices are respectively electrically connected or communicatively connected to a corresponding plurality of sensing signal acquiring units 421 to 42k, and a plurality of sensing signal acquiring units 421 to 42k are electrically connected to or communicating with the action posture processing unit 21.

Please note here that although the number of the multiple sensors of the multiple sensor devices is n, the present invention is not limited by this, and the number of sensors of different sensor devices may be different from each other. In addition, in this embodiment, each sensing device and the corresponding one of the sensing signal acquisition units 421 to 42k are integrated into one wearable device. Therefore, in this embodiment, there are a total of k wearable devices for k Pet wear. The motion posture processing unit 41 may be a server or a computer device such as a computer, a tablet, a smart phone, or one of k wearable devices.

In this embodiment, the adaptive motion posture sensing system 4 can be applied to group training or interaction of multiple pets, such as shaking hands, sitting down, running or standing at attention, etc. Through group (or remote) teaching, pet trainers Or the owner can instruct one of the well-trained pets in the group to demonstrate an action posture in order to set an action posture reference data, and let other pets in the group that have not been fully trained to act according to the demonstrated action posture . Then, the action posture processing unit 41 can compare the action posture data of other pets with the action posture reference data to determine whether the other pets make the action posture correctly, so as to evaluate the effectiveness of training and interaction.

Furthermore, please refer to FIG. 5, which is a functional block diagram of a motion sensing system for pets according to another embodiment of the present invention. The motion sensing system 5 for pets includes a motion posture processing unit 51, a plurality of sensing signal acquisition units 521 to 52k, and a plurality of sensing devices, each of which is composed of a plurality of sensors S1 to Sn. As a result, a plurality of sensing devices are respectively electrically connected or communicatively connected to a corresponding plurality of sensing signal acquiring units 521 to 52k, and a plurality of sensing signal acquiring units 521 to 52k are electrically connected to or communicating with the motion posture processing unit 51.

Please note here that although the number of the multiple sensors of the multiple sensor devices is n, the present invention is not limited by this, and the number of sensors of different sensor devices may be different from each other. In addition, the action posture processing unit 51 is composed of a server-side processing unit 511 and a plurality of client-side processing units 5121 to 512k, wherein the plurality of client-side processing units 5121 to 512k are connected to the server-side processing unit 511 in communication. In this embodiment, each sensing device, one corresponding one of the sensing signal acquisition units 521 to 52k, and one corresponding one of the client processing units 5121 to 512k are integrated in a wearable device, so in this embodiment In the example, there are a total of k wearable devices for k pets to wear.

In this embodiment, the motion sensing system 5 for pets can apply pet competitive games (each pet performs a specific motion posture to determine whose training or interaction is best), through group (also remote) teaching, pet training The teacher or the owner asks a well-trained pet in the group to demonstrate (set) an action posture to set an action posture reference data, and let other pets in the group move according to the demonstrated action posture for a pet competitive game. Then, the action posture processing unit 51 can compare the action posture data of other pets with the action posture reference data to determine whether the other pets have made the action posture correctly, so as to evaluate the performance of the pet competitive game.

Please note here that the action posture processing units 51, 51, and 51 in the aforementioned adaptive action posture sensing systems 3 to 5 are all based on the pet's individual information, wearing style, wearing position and action name input by the user to select the corresponding action Posture reference materials, however, the present invention is not limited by this. As artificial intelligence algorithms have become more and more perfect, the action posture processing units 31, 41, and 51 can also recommend the pet’s possible action posture reference data to the user based on the currently obtained action posture data, and the user can confirm the pet’s status. Whether the reference data for possible motion and posture is correct.

Next, please refer to Fig. 6, which is a schematic diagram of a social network connected to the motion sensing system for pets according to an embodiment of the present invention. The motion sensing system for pets can also be connected to a social network (for example, connected to a social network through a motion posture processing unit), and the wearable device can have a positioning device in addition to a sensing device. Therefore, in the screen 6 of the social network, the motion sensing system for pets can automatically publish the pet's completed actions, location, rewards and specific expressions, etc. For example, if one of the pets may complete 5 handshake actions and 5 turns at a specific time, and get a cookie as a reward, the motion sensing system for pets can compare the 5 handshake actions it completed with The information of the 5 circling movements, the rewards of the cookies, the time and location of the completion of the actions, and other information are posted on the social network screen 6 to achieve communication and interaction between pet owners.

Next, please refer to Fig. 7, which is a schematic diagram of the chat software connected to the motion sensing system for pets according to an embodiment of the present invention. The motion sensing system for pets can also be connected to chat software (for example, connected to the chat software through the motion posture processing unit), and the wearable device may have a text/voice conversion device in addition to the sensing device. In screen 7 of the chat software, the pet trainer (or owner) can input text through the chat software, and the text/voice conversion device of the wearable device converts the text to voice so that the pet can hear the voice, so that the pet can proceed according to the voice The corresponding action. For example, in the screen 7 of the chat software, the remote pet trainer (or owner) inputs the text of a handshake, and the pet will perform a handshake after hearing the voice of the handshake. If the pet performs the correct handshake action, the motion sensing system for the pet can automatically reply to the message on the chat software, for example, complete the action. If the motion sensing system used for pets has been interpreting that the trained pet has been unable to complete the handshake motion, it can be judged that the pet may be sick or what is in the condition, and the motion sensing system used for pets can be automatically installed on the chat software Alert the trainer (or host), for example, to generate a text that needs help in the screen 7 of the chat software. In other words, the motion sensing system for pets can achieve the function of online trainers (or owners) to train or interact with pets through the connection of chat software.

Next, please refer to Fig. 8, which is a flowchart of the steps performed in the learning mode of the motion sensing method for pets according to an embodiment of the present invention. First, in step S801, the action posture processing unit first records the pet's individual information (including the pet's length, weight, height, health status and gender, etc.) and wearing status information (including the wearing mode and wearing of the sensor device on the pet). Location and other information). Next, in step S802, the action posture processing unit records the name of the action to be learned, such as lie down and roll. Then, in step S803, the action posture processing unit records the name of the decomposed posture, such as lie down and roll over. Next, in step S804, the action posture processing unit obtains a plurality of training sensing signals corresponding to the decomposition posture. In step S805, the action posture processing unit confirms whether the multiple training sensing signals of the decomposed posture are correct according to the input of the user (owner or pet trainer). If the multiple training sensing signals of the decomposed posture are not correct, then in step S807, the action posture processing unit discards the multiple training sensing signals of the decomposed posture, and then re-executes step S805; if the multiple training senses of the decomposed posture are If the test signal is correct, in step S806, the action posture processing unit stores a plurality of training sensing signals of the decomposed posture.

Next, in step S808, the action posture processing unit confirms whether there is a next decomposition posture according to the user's input. If there is a next decomposition posture, step S803 is executed; if there is no next decomposition posture, step S809 is executed. For example, there are two decomposition postures of lying down and rolling. Therefore, multiple training sensing signals of the two decomposition positions of lying down and rolling are needed to fully express the rolling down.

Next, in step S809, the motion posture processing unit determines whether the number of samples of the multiple training sensing signals currently acquired is sufficient. If the number of samples is not enough, proceed to step S803; if the number of samples is sufficient, then step S810 is performed. For example, the number of samples can be 10, and the action posture processing unit can obtain 10 sets of multiple training sensing signals of two decomposition postures of lying down and rolling. Then, in step S810, the action posture processing unit establishes the pet's action posture reference data according to the training sensing signals of the multiple action postures.

In step S811, the action posture processing unit determines whether to end the learning mode according to the user's confirmation. If it is determined to end the learning mode, all the processes in FIG. 8 are terminated; if the user still needs to create other reference materials for the action posture of the pampering and it is determined not to end the learning mode, step S801 is executed. Through the process of FIG. 8, action posture reference data corresponding to a variety of different actions corresponding to different wearing methods, wearing positions, and individual pet information can be created. For example, the motion posture reference data corresponding to one of the pets tugging the sensing device to the chest can be created, and the motion posture reference data corresponding to the other pet tugging the sensing device around the front foot It is established.

Next, please refer to Fig. 9, which is a flowchart of the steps performed in the interpretation mode of the motion sensing method for pets according to an embodiment of the present invention. In step S901, the action posture processing unit obtains the wearing state information and the pet individual information. In step S902, the action posture processing unit obtains the action name, and finds the action posture reference data corresponding to the action name, wearing state information, and pet individual information.

Next, in step S903, the motion gesture processing unit acquires a plurality of motion sensing signals. After that, in step S904, the action posture processing unit compares the action posture data formed by the plurality of action sensing signals with the action posture reference data to determine whether the pet's action posture is correct. If the pet's action posture is correct, in step S905, the action posture processing unit accumulates the number of correct action postures; if the pet's action posture is incorrect, step S906 is executed. In step S906, the action posture processing unit determines whether to end the interpretation mode according to the user's confirmation. If it is confirmed that the judgment mode is ended, all the processes in FIG. 9 are terminated; if it is confirmed that the judgment of the next action posture is correct, without ending the judgment mode, step S903 is executed. Please note here that the flow of Figure 9 is not intended to limit the present invention. Without ending the interpretation mode, it is also possible to change the action name, wearing status information, and pet individual information. Therefore, Figure 9 can also be designed to change Multiple judgment steps to allow the user to change the next action posture reference material selected as the comparison benchmark in the interpretation mode.

Accordingly, through the motion sensing system and method for pets provided by the embodiments of the present invention, the user can arbitrarily wear the sensing device on any position of the pet's body and wear it in different ways. Furthermore, the same sensing device can also be adapted to different pets. In short, the motion sensing system and method for pets of the present invention can improve the convenience and flexibility of the sensing device in use.

The present invention has been disclosed in preferred embodiments above, but those skilled in the art should understand that the above-mentioned embodiments are only used to describe the present invention and should not be interpreted as limiting the scope of the present invention. It should be noted that all changes and substitutions equivalent to the foregoing embodiments should be included in the scope of the present invention. Therefore, the protection scope of the present invention should be defined by the scope of the patent application.

11: User 121～123: Pet 131～133: Sensing device 14: Automatic feeder 2: Wearing device 21: Circuit area 221: First joint unit 222: Second joint unit 3～5: Motion sense for pets Measurement systems 31, 41, 51: motion posture processing unit 32, 421～42k, 521～52k: sensing signal acquisition unit 511: server-side processing unit 5121～512k: client-side processing unit 6: social network screen 7: Screen of chat software S1～Sn: Sensors S801～S811, S901～S906: Steps

Figure 1 is a schematic diagram of a situation where the sensing device in the motion sensing system for pets according to an embodiment of the present invention is worn on pets of different postures.

Figure 2 is a schematic plan view of the wearable device in the motion sensing system for pets according to an embodiment of the present invention.

Figure 3 is a functional block diagram of the motion sensing system for pets according to an embodiment of the present invention.

Figure 4 is a functional block diagram of a motion sensing system for pets according to another embodiment of the present invention.

Figure 5 is a functional block diagram of a motion sensing system for pets according to another embodiment of the present invention.

FIG. 6 is a schematic diagram of a social network connected to the motion sensing system for pets according to an embodiment of the present invention.

FIG. 7 is a schematic diagram of the chat software connected to the motion sensing system for pets according to an embodiment of the present invention.

FIG. 8 is a flowchart of the steps performed in the learning mode of the motion sensing method for pets according to an embodiment of the present invention.

FIG. 9 is a flowchart of the steps performed in the interpretation mode of the motion sensing method for pets according to an embodiment of the present invention.

3: Motion sensing system for pets

31: Action posture processing unit

32: Sensing signal acquisition unit

S1~Sn: Sensor

Claims (10)

A motion sensing system for pets includes: a sensing device, including at least one sensor, which is used to be worn by a pet; a sensing signal acquisition unit, electrically connected or communicatively connected to the sensing Device; and an action posture processing unit that is electrically connected or communicatively connected to the sensing signal acquisition unit; in an interpretation mode, the action posture processing unit is based on an action name and the sensing device is worn on the pet A piece of wearing state information and a piece of pet individual information corresponding to one selected from a plurality of established motion posture reference data, the sensing signal acquiring unit acquires at least one motion sensing signal sensed by the sensing device, And the action posture processing unit compares an action posture data formed based on the at least one action sensing signal with the selected action posture reference data to determine whether an action posture of the pet is correct. The motion sensing system for pets according to claim 1, further comprising: another sensing device, including at least another sensor, for being worn by another pet; and another sensing device The signal acquisition unit is electrically connected or communicatively connected to the other sensing device and the action posture processing unit; in the interpretation mode, the action posture processing unit is based on another action name and the other sensing The device is worn on the other pet’s another wearing state information and another pet’s individual information to select one corresponding to the other from a plurality of created action posture reference data, and the sensing signal acquiring unit acquires the other sensing At least one motion sensing signal sensed by the sensing device, and the motion gesture processing unit compares another motion gesture data formed based on the at least one motion sensing signal of the another sensing device with the selected Another action posture reference data to determine whether the other action posture of the other pet is correct. The motion sensing system for pets according to claim 2, wherein the motion posture processing unit includes: two client processing units electrically or communicatively connected to the two sensing signal acquisition units ; And a server-side processing unit, which is electrically or communicatively connected to the two client-side processing units. The motion sensing system for pets according to claim 1, wherein in a learning mode, the motion posture processing unit records the motion name, the wearing state information, and the pet individual information, and The sensing signal acquisition unit acquires at least one training sensing signal sensed by the sensing device, and the motion posture processing unit creates a corresponding motion name, the motion name, and the motion posture processing unit according to the at least one training sensing signal Wearing state information and the action posture reference data of the pet individual information. The motion sensing system for pets according to claim 1, wherein the wearable device information includes information on a wearing mode and a wearing position of the sensing device on the pet. The motion sensing system for pets according to claim 1, wherein the pet individual information includes information about a height, a length, a weight, a gender, an age, and a health condition of the pet. The motion sensing system for pets according to claim 1, wherein the motion posture processing unit further includes a voice input unit, wherein a user controls the motion sense for pets through the voice input unit测系统。 Measurement system. The motion sensing system for pets according to claim 1, wherein the sensors include a nine-axis attitude sensor, a pressure sensor, a force sensor, and a temperature sensor Or a vibration sensor. The motion sensing system for pets as described in claim 1, wherein the motion sensing system for pets is further linked to a social network or a chat software, and the motion for pets The sensing system further includes a positioning device or a text/voice conversion device. A motion sensing method for pets, including: in an interpretation mode: self-created multiple motion posture reference data based on an action name, a wearing state information of a sensing device worn on a pet, and a pet individual information Select one of the corresponding ones; obtain at least one motion sensing signal sensed by the sensing device worn on the pet; and compare a motion posture data formed based on the at least one motion sensing signal with the selected The action posture reference data to determine whether an action posture of the pet is correct; and in a learning mode: record the action name, the wearing state information, and the pet individual information; obtain the sensing device At least one training sensing signal sensed; and establishing the action posture reference data corresponding to the action name, the wearing state information and the pet individual information according to the at least one training sensing signal.

Images