JP2022101296A - Animal intention determination program - Google Patents

Abstract

To allow for automatically and accurately determining the intention of an animal without having to have any special skill or experience.SOLUTION: An animal intention determination program for determining an intention of an animal makes a computer perform: an information acquisition step of acquiring audio information where voices of a target animal are recorded; and a determination step of referring to three or more levels of association between previously acquired reference audio information where voices of animals are recorded and intentions of the animals so as to determine an intention of the target animal based on the audio information acquired in the information acquisition step.SELECTED DRAWING: Figure 1

Description

The present invention relates to an animal discrimination program for discriminating the intentions of mammalian animals such as cows, horses, pigs, dogs and cats.

Mammalian animals such as cows, horses, pigs, dogs, and cats estrus or want food at certain times, and even when they are sick, they make an intention to do so. In particular, estrus is the period during which males are accepted, and mating takes place during this period, and estrus stops when conceived. Especially in livestock farmers, when inseminating, it is necessary for the manager to accurately discover this estrus and seed it. In addition, when a pet animal indicates an intention such as wanting food, excretion, or playing, the owner can respond to this, which can improve the convenience of breeding. You can communicate and communicate smoothly with your pet.
However, it is often difficult to determine the intention of this animal even if it is an expert. If you miss your intention, you will not be able to seed and it will be a big loss for livestock farmers. In addition, if an animal is hungry and wants food but misses the feeding opportunity, it will stop the growth of the animal and the meat production will decrease. For this reason, it has been conventionally desired to provide a tool that assists in discriminating the intention of an animal.

Therefore, the present invention has been devised in view of the above-mentioned problems, and an object thereof is to automatically and highly accurately determine the intention in an animal intention determination program for determining the intention of an animal. Is to provide a possible animal decision-making program.

In order to solve the above-mentioned problems, the animal decision-making program according to the present invention includes an information acquisition step of acquiring voice information obtained by recording the voice of an animal to be discriminated in the animal decision-making program for discriminating the intention of an animal. Based on the voice information acquired in the above information acquisition step, the intention of the animal to be discriminated is determined by referring to the reference voice information obtained by recording the voice of the animal acquired in advance and the degree of association with the intention of the animal in three or more stages. It is characterized in that a computer is made to execute a discrimination step for discrimination.

Even if you do not have any special skills or experience, it is possible to determine the will of an animal automatically and with high accuracy.

It is a block diagram which shows the whole structure of the system to which this invention is applied. It is a figure which shows the specific configuration example of a search device. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention.

Hereinafter, the animal decision-making program to which the present invention is applied will be described in detail with reference to the drawings.

The first embodiment FIG. 1 is a block diagram showing an overall configuration of an animal decision-making system 1 to which an animal decision-making program to which the present invention is applied is implemented. The animal intention determination system 1 includes an information acquisition unit 9, a search device 2 connected to the information acquisition unit 9, and a database 3 connected to the search device 2.

The information acquisition unit 9 is a device for a person using this system to input various commands and information, and specifically, is composed of a keyboard, buttons, a touch panel, a mouse, a switch, and the like. The information acquisition unit 9 is not limited to a device for inputting text information, and may be configured by a device such as a microphone that can detect voice and convert it into text information. Further, the information acquisition unit 9 may be configured as an image pickup device capable of capturing an image of a camera or the like. The information acquisition unit 9 may be configured by a scanner having a function of recognizing a character string from a paper-based document. Further, the information acquisition unit 9 may be integrated with the search device 2 described later. The information acquisition unit 9 outputs the detected information to the search device 2. Further, the information acquisition unit 9 may be configured by means for specifying the position information by scanning the map information. The information acquisition unit 9 also includes a temperature sensor, a humidity sensor, a flow rate sensor, and other sensors capable of identifying substances and physical properties. The information acquisition unit 9 may be configured by means for automatically fetching character strings and data posted on a site on the Internet. The information acquisition unit also includes an acceleration sensor attached to the animal.
The term "animal" as used herein means any animal belonging to mammals, and among them, in addition to livestock such as cows, horses, pigs and sheep, animals such as dogs and cats raised in each household are also included. In addition to the animals to be bred, wild animals are also included in this.

The database 3 stores various information necessary for discriminating animal intentions. The information necessary for determining the animal's intention is reference acceleration information according to the movement of the animal detected by the acceleration sensor attached to the body of the animal acquired in advance, and reference image information that captures the movement of the animal. , Reference audio information recorded animal voice, reference intention history information regarding the history of the animal's intention acquired in advance, reference biological information detected from each animal in advance, reference attribute information regarding the attributes of the animal acquired in advance. , Reference time zone information regarding the time zone in which the reference image information was captured, reference position information indicating the position of the animal at the time when the reference image information was captured, and data of the intention of the animal to be discriminated. The set is remembered.

That is, in the database 3, such reference acceleration information, reference image information, reference audio information, reference food consumption information, reference intention history information, reference biological information, reference attribute information, and reference Any one or more of the time zone information and the reference position information and the intention of the animal to be discriminated are stored in association with each other.

The search device 2 is composed of, for example, an electronic device such as a personal computer (PC), but is embodied in any other electronic device such as a mobile phone, a smartphone, a tablet terminal, a wearable terminal, etc., in addition to the PC. It may be the one to be converted. The user can obtain a search solution by the search device 2.

FIG. 2 shows a specific configuration example of the search device 2. The search device 2 performs wired communication or wireless communication with a control unit 24 for controlling the entire search device 2 and an operation unit 25 for inputting various control commands via an operation button, a keyboard, or the like. A communication unit 26 for the purpose, an estimation unit 27 for making various judgments, and a storage unit 28 for storing a program for performing a search to be executed represented by a hard disk or the like are connected to the internal bus 21, respectively. .. Further, a display unit 23 as a monitor that actually displays information is connected to the internal bus 21.

The control unit 24 is a so-called central control unit for controlling each component mounted in the search device 2 by transmitting a control signal via the internal bus 21. Further, the control unit 24 transmits various control commands via the internal bus 21 according to the operation via the operation unit 25.

The operation unit 25 is embodied by a keyboard or a touch panel, and an execution command for executing a program is input from the user. When the execution command is input by the user, the operation unit 25 notifies the control unit 24 of the execution command. Upon receiving this notification, the control unit 24, including the estimation unit 27, executes a desired processing operation in cooperation with each component. The operation unit 25 may be embodied as the information acquisition unit 9 described above.

The estimation unit 27 estimates the search solution. The estimation unit 27 reads out various information stored in the storage unit 28 and various information stored in the database 3 as necessary information when executing the estimation operation. The estimation unit 27 may be controlled by artificial intelligence. This artificial intelligence may be based on any well-known artificial intelligence technique.

The display unit 23 is configured by a graphic controller that creates a display image based on the control by the control unit 24. The display unit 23 is realized by, for example, a liquid crystal display (LCD) or the like.

When the storage unit 28 is composed of a hard disk, predetermined information is written to each address based on the control by the control unit 24, and is read out as needed. Further, the storage unit 28 stores a program for executing the present invention. This program will be read and executed by the control unit 24.

The operation in the animal intention discrimination system 1 having the above-described configuration will be described.

In the animal intention determination system 1, it is premised that a combination of the reference acceleration information and the reference image information is formed, for example, as shown in FIG. The reference acceleration information is acceleration data detected by an acceleration sensor attached to the neck or body of a mammalian animal such as a cow, a horse, or a pig, or a mammalian pet such as a dog or a cat. This reference acceleration information clearly reflects the movement of the animal. It is said that the cow of intention becomes restless and the speed and frequency of walking change, but such behavior is reflected as reference acceleration information detected by the acceleration sensor. In addition, the cow of intention also shows a behavior of riding on another cow, and such behavior is reflected as reference acceleration information detected by the acceleration sensor. In addition, hungry horses and cows may take actions to indicate their hunger, or they may lose energy and slow down, and such actions are reflected as reference acceleration information detected by the accelerometer. Will be.

The reference image information is composed of image data obtained by capturing the movements and behaviors of such animals with a camera. Acquire image data of behavior such as restlessness of the cow of intention, frequency and speed of walking, and riding on other cows, and acquire this by image analysis of the image data as necessary. .. In addition, the image data of the operation when hungry or poor physical condition is acquired, and this is acquired by performing image analysis of the image data as necessary. If necessary, a deep learning technique may be used to automatically discriminate based on the feature amount of the analyzed image and convert it into data. Further, the behaviors and movements of such animals may be categorized based on the feature amount of the analysis image and automatically arranged.

As the input data, such reference acceleration information and reference image information are arranged side by side. The intermediate node 61 shown in FIG. 3 is a combination of reference image information and reference acceleration information as such input data. Each intermediate node 61 is further connected to an output. In this output, the animal intentions A to E are displayed. The intention of this animal may be indicated as the time when the actual animal is in estrus, such as days, hours, estrus, days, hours, etc., and the intention is terminated. The date and time and the date and time of the end point of the intention may be indicated. Alternatively, various desires are set such as the animal is currently hungry, wants to clean the body, wants to drink water, wants to excrete, and wants to improve because it is sick, and wants to improve the environment. You may be. In addition to this, the animal's will includes emotional things such as likes, dislikes, cuteness, bad mood, frustration, and comfort.

The determination of what the intention is may be determined by experts, experts, livestock farmers, etc., or it may be determined from the results of actual seeding, feeding, excretion, and washing. It may be something that is done. In such a case, if the seeding is actually performed and succeeded, it is judged that the period is intentional, and if the seeding is performed and failed, or if the seeding itself is not accepted, it is judged that it is not intentional. You may try to do it. Further, as a result of feeding, it may be determined from the goodness of biting, the amount of food consumed, and the like. In addition, desire and emotional intentions are specified by the judgment of a veterinarian or other specialist, and data is created.

Through the reference acceleration information and the reference image information, various signs of the animal's intention can be extracted, and a data set can be created from the extracted intention data. By creating and learning such a data set, it is possible to output what kind of intention the animal has from the reference acceleration information and the reference image information.

Each combination (intermediate node) of the reference acceleration information and the reference image information is associated with each other through three or more levels of association with the intention as this output solution. The reference acceleration information and the reference image information are arranged on the left side through the degree of association, and the intentions A, B, C, D, E, ... Are arranged on the right side through the degree of association. The degree of association indicates the degree of intention and relevance to the reference acceleration information arranged on the left side and the reference image information. In other words, this degree of association is an index indicating what kind of intention each reference acceleration information and reference image information is likely to be associated with, and each reference acceleration information and reference image information. Therefore, it shows the accuracy in selecting the most appropriate intention. In the example of FIG. 3, w13 to w22 are shown as the degree of association. These w13 to w22 are shown in 10 stages as shown in Table 1 below, and the closer to 10 points, the higher the degree of relevance of each combination as an intermediate node to the intention as an output. On the contrary, the closer to one point, the lower the degree of relevance of each combination as an intermediate node to the intention as an output.

The search device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, the search device 2 accumulates past data as to which of the reference acceleration information, the reference image information, and the intention in that case is suitable for determining the actual search solution, and analyzes these. , The degree of association shown in FIG. 3 is created by analysis.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference acceleration information P01 and the reference image information P16, the intention is analyzed from the past data. If there are many cases of A, the degree of association that leads to A is set higher, and if there are many cases of B and there are few cases of A, the degree of association that leads to B is increased and the degree of association that leads to A. Is set low. For example, in the example of the intermediate node 61a, the output of intention A and B is linked, but from the previous case, the degree of association of w13 connected to intention A is set to 7 points, and the degree of association of w14 connected to intention B is set to 2 points. It is set.

Further, the degree of association shown in FIG. 3 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

In the example of the degree of association shown in FIG. 3, the node 61b is a node in which the reference image information P14 is combined with the reference acceleration information P01, the degree of association of intention C is w15, and the degree of association of intention E is w16. It has become. The node 61c is a node in which the reference image information P15 and P17 are combined with respect to the reference acceleration information P02, and the degree of association of intention B is w17 and the degree of association of intention D is w18.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, the above-mentioned learned data will be used in the actual search for decision determination. In such a case, image information is acquired in addition to acceleration information from the animal to be discriminated to newly discriminate the intention. In addition to the acceleration information, the method of acquiring the image information is the same as the above-mentioned reference acceleration information and reference image information.

Based on the newly acquired acceleration information and image information in this way, the optimum intention is searched for. In such a case, the degree of association shown in FIG. 3 (Table 1) acquired in advance is referred to. For example, when the newly acquired acceleration information is the same as or similar to P02 and the image information is the same as or similar to P17, the node 61d is associated via the degree of association. In this node 61d, intention C is associated with w19 and intention D is associated with a degree of association w20. In such a case, the intention C having the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the intention D, which has the lowest degree of association but is recognized for the association itself, may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and any other output solution may be selected in any other priority as long as it is based on the degree of association.

Further, an example of the degree of association w1 to w12 extending from the input is shown in Table 2 below.

The intermediate node 61 may be selected based on the degree of association w1 to w12 extending from this input. That is, the larger the degree of association w1 to w12, the heavier the weighting in the selection of the intermediate node 61 may be. However, the degrees of association w1 to w12 may all have the same value, and the weights in the selection of the intermediate node 61 may all be the same.

It should be noted that the animal for which the reference acceleration information and the reference image information constituting the above-mentioned association degree are acquired and the animal for which the discrimination target for newly acquiring the acceleration information and the image information are newly acquired do not have to be the same.

FIG. 4 shows an example in which the combination of the above-mentioned reference acceleration information, the reference voice information, and the intention for the combination are set to three or more levels of association.

Reference audio information can be obtained by recording animal audio. Animals often raise or cry when they have some intention. Therefore, the intention of the animal can be determined by analyzing the voice of the animal. Animal sounds can be detected, for example, through a microphone installed in a stable or the like.

As the reference voice information, the recorded voice may be frequency-analyzed, or the tone and strength thereof may be included in the analysis. This reference voice information may be obtained by acquiring voice in a certain period in time series and analyzing it.

In the example of FIG. 4, it is assumed that the input data is, for example, reference acceleration information P01 to P03 and reference voice information P18 to 21. The intermediate node shown in FIG. 4 is a combination of reference acceleration information and reference voice information as such input data. Each intermediate node is further linked to the output. In this output, the will of the animal as an output solution is displayed.

Each combination (intermediate node) of the reference acceleration information and the reference voice information is associated with each other through three or more levels of association with the intention as this output solution. The reference acceleration information and the reference voice information are arranged on the left side through this degree of association, and the intentions are arranged on the right side through this degree of association. The degree of association indicates the degree of high intention and relevance to the reference acceleration information and the reference voice information arranged on the left side. In other words, this degree of association is an index showing what kind of intention each reference acceleration information and reference voice information is likely to be associated with, and is most likely from the reference acceleration information and the reference voice information. It shows the accuracy in selecting each intention. In addition to the acceleration information, the intention changes depending on what the actual animal voice is. Therefore, the optimum intention is searched for by combining the reference acceleration information and the reference voice information.

In the example of FIG. 4, w13 to w22 are shown as the degree of association. As shown in Table 1, these w13 to w22 are shown in 10 steps, and the closer to 10 points, the higher the degree of relevance of each combination as an intermediate node to the output, and conversely, to 1 point. The closer they are, the less relevant each combination as an intermediate node is to the output.

The search device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, the search device 2 accumulates past data as to which of the reference acceleration information and the reference voice information and the intention in that case is suitable for determining the actual search solution, and stores these. By analyzing and analyzing, the degree of association shown in FIG. 4 is created.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference acceleration information P01 and the reference voice information P20, the intention of the animal is analyzed from the past data. For example, in the example of the intermediate node 61a, the output of intention A and B is linked, but from the previous case, the degree of association of w13 connected to intention A is set to 7 points, and the degree of association of w14 connected to intention B is set to 2 points. It is set.

Further, the degree of association shown in FIG. 4 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

In the example of the degree of association shown in FIG. 4, the node 61b is a node in which the reference voice information P18 is combined with the reference acceleration information P01, the degree of association of intention C is w15, and the degree of association of intention E is w16. It has become. The node 61c is a node in which the reference voice information P19 and P21 are combined with respect to the reference acceleration information P02, and the degree of association of intention B is w17 and the degree of association of intention D is w18.

Such a degree of association is what is called learned data in artificial intelligence. After creating such trained data, when actually giving advice from now on, the above-mentioned trained data will be used. In such a case, in addition to the acceleration information described above, the voice information of the animal to be discriminated to newly determine the intention is acquired. The method of acquiring the voice information is the same as that of the reference voice information.

Such reference audio information and the method of capturing the audio information are based on the feature amount of the analyzed image by image analysis of the description of the document in which the above-mentioned audio information is described and, if necessary, deep learning technology. It may be automatically determined and converted into data.

Based on the newly acquired acceleration information and voice information in this way, the intention of the animal is searched. In such a case, the degree of association shown in FIG. 4 (Table 1) acquired in advance is referred to. For example, when the newly acquired acceleration information is the same as or similar to P02 and the voice information is P21, the node 61d is associated via the degree of association, and this node. In 61d, intention C is associated with w19 and intention D is associated with a degree of association w20. In such a case, the intention C having the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the intention D, which has the lowest degree of association but is recognized for the association itself, may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and any other output solution may be selected in any other priority as long as it is based on the degree of association.

FIG. 5 shows an example in which the combination of the above-mentioned reference image information, the reference audio information, and the intention for the combination are set to three or more levels of association. In this way, the degree of association between the combination of the reference image information, the reference audio information, and the intention for the combination is acquired in advance. At the time of actual determination, the image information and audio information of the animal to be discriminated are acquired. Then, after referring to the degree of association, the intention of the animal is determined in the same manner as described above based on the newly acquired image information and audio information.

In FIG. 6, in addition to the above-mentioned reference acceleration information and reference image information, a combination of reference food consumption information and the animal's intention for the combination are set to three or more levels of association. Here is an example.

Reference food consumption is information that indicates the actual food consumption of the animal. This reference food consumption information may be obtained by the breeder measuring the food consumption actually ingested by the animal each time. As the measuring method, the weight of the bait box containing the bait may be measured before and after the bait, and the consumption of the bait may be calculated from the difference value. In addition, the inside of the container containing food (hay, etc.) may be imaged from an external camera, and the obtained image information may be analyzed before and after feeding to calculate the consumption of food. ..

In such a case, as shown in FIG. 6, the degree of association is such that the set of the combination of the reference acceleration information, the reference image information, and the reference food consumption information is the node 61a to 61e of the intermediate node as described above. Will be expressed as.

For example, in FIG. 6, in the node 61c, the reference acceleration information P02 is associated with the association degree w3, the reference image information P15 is associated with the association degree w7, and the reference food consumption information W is associated with the association degree w11. Similarly, in the node 61e, the reference acceleration information P03 is associated with the association degree w5, the reference image information P15 is associated with the association degree w8, and the reference food consumption information V is associated with the association degree w10.
The reference food consumption information may be obtained as one data of changes in food consumption over time. This makes it possible to grasp the tendency of whether the consumption of the latest food has decreased or increased as compared with the consumption of the normal food.

Similarly, when such a degree of association is set, the intention of the animal is discriminated based on the acceleration information newly acquired from the animal to be discriminated, the image information, and the food consumption information.

In determining this intention, the degree of association shown in FIG. 6 acquired in advance is referred to. For example, it can be specified that the acceleration information is the same as or similar to the reference acceleration information P02, the acquired image information is the same as or similar to the reference image information P15, and the acquired food consumption information is the reference food consumption. When it can be identified that the quantity information W is the combination, the node 61c is associated with the node 61c, and the intention B is associated with the association degree w17 and the intention D is associated with the association degree w18. As a result of such a degree of association, based on w17 and w18, the intention of the animal to be discriminated is actually obtained by newly acquiring the acceleration information, the image information, and the food consumption information.

It is said that the animal's intention is reflected in the food consumption, and it is possible to determine the animal's intention with high accuracy by referring to such food consumption information.

In FIG. 7, in addition to the above-mentioned reference acceleration information and reference image information, a combination of reference vulva information and the animal's intention for the combination are set to three or more levels of association. An example is shown.

The reference vulva information is information indicating the vulva of an animal. This reference vulva information may be composed of image information obtained by capturing the vulva of an animal with a camera, or is input as data after actually visually observing and observing the vulva and grasping the situation. It may be a thing. Further, the reference vulva information may be composed of data as a result of detecting and confirming the presence or absence of estrus mucus coming out of the vulva by an image, a sensor, or visual recognition by a groom.

In such a case, as shown in FIG. 7, the degree of association is such that the set of the combination of the reference acceleration information, the reference image information, and the reference vulva information is the nodes 61a to 61e of the intermediate node as described above. It will be expressed.

For example, in FIG. 7, the reference acceleration information P02 is associated with the reference degree w3, the reference image information P15 is associated with the association degree w7, and the reference vulva information W is associated with the association degree w11. Similarly, in the node 61e, the reference acceleration information P03 is associated with the association degree w5, the reference image information P15 is associated with the association degree w8, and the reference vulva information V is associated with the association degree w10.

Similarly, when such a degree of association is set, the intention of the animal is discriminated based on the acceleration information newly acquired from the animal to be discriminated, the image information, and the vulva information.

In determining this intention, the degree of association shown in FIG. 7 acquired in advance is referred to. For example, it can be specified that the acceleration information is the same as or similar to the reference acceleration information P02, the acquired image information is the same as or similar to the reference image information P15, and the acquired vulva information is the reference vulva information. When it can be identified as W, the combination is associated with the node 61c, in which the intention B is associated with the degree of association w17 and the intention D is associated with the degree of association w18. As a result of such a degree of association, based on w17 and w18, the intention of the animal to be discriminated is actually obtained by newly acquiring the acceleration information, the image information, and the vulva information.

In particular, it is said that the condition of the vulva changes and mucus is released from the vulva in female animals of intention, and it is possible to discriminate the intention of the animal with high accuracy by referring to such information on the vulva. Is possible.

In FIG. 8, in addition to the above-mentioned reference acceleration information and reference image information, a combination of reference raw milk amount information and the animal's intention for the combination are set to three or more levels of association. An example is shown.

The reference raw milk amount information is the amount of raw milk that can be collected from female animals, and can be detected from animals that can collect raw milk, such as dairy cows and goats. This reference raw milk amount information indicates the amount of raw milk collected per day, once, or per unit time.

In such a case, as shown in FIG. 8, the degree of association is such that the set of the combination of the reference acceleration information, the reference image information, and the reference raw milk amount information is the node 61a to 61e of the intermediate node as described above. It will be expressed.

For example, in FIG. 8, in the node 61c, the reference acceleration information P02 is associated with the association degree w3, the reference image information P15 is associated with the association degree w7, and the reference raw milk amount information W is associated with the association degree w11. Similarly, in the node 61e, the reference acceleration information P03 is associated with the association degree w5, the reference image information P15 is associated with the association degree w8, and the reference raw milk amount information V is associated with the association degree w10.

Similarly, when such a degree of association is set, the intention of the animal is discriminated based on the acceleration information newly acquired from the animal to be discriminated, the image information, and the raw milk amount information.

In determining this intention, the degree of association shown in FIG. 8 acquired in advance is referred to. For example, it can be specified that the acceleration information is the same as or similar to the reference acceleration information P02, the acquired image information is the same as or similar to the reference image information P15, and the acquired raw milk amount information is the reference raw milk amount information. When it can be identified as W, the combination is associated with the node 61c, in which the intention B is associated with the degree of association w17 and the intention D is associated with the degree of association w18. As a result of such a degree of association, based on w17 and w18, the intention of the animal to be discriminated is actually obtained by newly acquiring the acceleration information, the image information, and the raw milk amount information.

Since the intention of the animal may be reflected in the amount of raw milk that can be collected, it is possible to determine the intention of the animal with high accuracy by referring to such information on the amount of raw milk.

Further, according to the present invention, the intention history information regarding the past intention history of each animal to be discriminated may be further acquired. This intention history information includes the type and timing of intention determined each year, the conception history if the animal has been conceived and delivered many times, the process from conception to delivery, the postpartum situation, and delivery. Includes the situation of the child. Further, in the case of appetite, the intention history information may be composed of history information such as the type and amount of food given daily and the amount of food consumed. In addition to this, for the animal, what kind of result was obtained when the acquired (acceleration information, image information, ... raw milk amount information) was seeded at what timing, and at what timing the feed was given. It may indicate what kind of result the consumption amount and the bite were.

When discriminating the intention, the discrimination accuracy may be improved by referring to such intention history information. The intention determined through the above-mentioned degree of association may be further modified based on the intention history information, or the weighting may be changed. For example, in the intention history information, for animals that have an intention relatively early every year, the intention determined through the degree of association may be set early, or the weighting of the degree of association that leads to the early intention may be increased. You may do it.

The reference to such intention history information may be performed in the same manner at all the above-mentioned degrees of association.

Further, in the present invention, the reference food consumption information may be applied as an alternative to the reference voice information in the degree of association shown in FIG. In such a case, there are three or more stages of a combination having a reference image information that captures the motion of the animal acquired in advance, a reference food consumption amount information regarding the consumption amount of the animal food acquired in advance, and the intention of the animal. The degree of association is formed.

Next, the image information obtained by capturing the motion of the animal to be discriminated and the food consumption information regarding the food consumption of the animal to be discriminated are acquired in the same manner as described above. Then, the intention of the animal is determined based on the reference image information according to the acquired image information and the reference food consumption information according to the acquired food consumption information by referring to the formed degree of association. The details of this intention determination method are the same as described above.

Further, in the present invention, the reference intention history information may be applied as a substitute for the reference voice information in the degree of association shown in FIG. In such a case, the combination of the reference image information obtained by capturing the motion of the animal acquired in advance, the reference intention history information regarding the history of the animal's intention acquired in advance, and the association of the animal's intention in three or more stages. Form the degree.

Next, the image information obtained by capturing the motion of the animal to be discriminated and the intention history information regarding the past intention history of each animal to be discriminated are acquired in the same manner as described above. Then, the intention of the animal is determined based on the reference image information according to the acquired image information and the reference intention history information according to the acquired intention history information by referring to the formed degree of association. The details of this intention determination method are the same as described above.

Further, in the present invention, the reference biometric information may be applied as a substitute for the reference voice information in the degree of association shown in FIG. In such a case, a combination having the reference image information obtained by capturing the motion of the animal acquired in advance and the reference biological information previously detected from each animal forms a degree of association of three or more stages with the intention of the animal. Keep it.

The reference biological information and biological information include all biological information detected from animals, and are composed of, for example, body temperature, heart rate, pulse, blood oxygen concentration, blood carbon dioxide amount, and the like. The body temperature may be measured through, for example, a thermo sensor, and the heart rate and blood oxygen concentration may be measured by using, for example, a chip sensor, an IC tag having a sensing function, or the like. Since such biometric information may also express the intention clearly, this is used as an explanatory variable.

Next, the image information obtained by capturing the motion of the animal to be discriminated and the biological information regarding the history of the past intention of each animal to be discriminated are acquired in the same manner as described above. Then, the intention of the animal is discriminated based on the reference image information according to the acquired image information and the reference biological information according to the acquired biological information by referring to the formed degree of association. The details of this intention determination method are the same as described above.

Further, in the present invention, the reference attribute information may be applied as a substitute for the reference voice information in the degree of association shown in FIG. In such a case, a combination having the reference image information obtained by capturing the motion of the animal acquired in advance and the reference attribute information regarding the attribute of the animal acquired in advance forms a degree of association of three or more levels with the intention of the animal. I will do it.

The reference attribute information and attribute information are composed of data such as age, sex, type, pedigree, past medical history, past birth history, size and weight of the animal. These data may be manually input by a livestock farmer or the like. Since such attribute information may also express the intention clearly, this is used as an explanatory variable.

Next, the image information obtained by capturing the motion of the animal to be discriminated and the attribute information regarding the attributes of the animal to be discriminated are acquired in the same manner as described above. Then, the intention of the animal is determined based on the reference image information according to the acquired image information and the reference attribute information according to the acquired attribute information by referring to the formed degree of association. The details of this intention determination method are the same as described above.

Further, in the present invention, the reference time zone information may be applied as a substitute for the reference voice information in the degree of association shown in FIG. In such a case, there are three or more stages of a combination having reference image information that captures the motion of the animal acquired in advance, reference time zone information regarding the time zone in which the reference image information is captured, and the intention of the animal. Form the degree of association.

The reference time zone information and the time zone information may be, for example, grouped in the morning or afternoon, or may be indicated by an hourly or minute pitch as the time zone in which the reference image information is captured. .. Since the behavior of the animal's intention may differ depending on the time zone, this is also used as an explanatory variable.

Next, the image information obtained by capturing the motion of the animal to be discriminated and the time zone information relating to the time zone in which the image information is captured are acquired in the same manner as described above. Then, the intention of the animal is determined based on the reference image information according to the acquired image information and the reference time zone information according to the acquired time zone information by referring to the formed degree of association. The details of this intention determination method are the same as described above.

Further, in the present invention, the reference position information may be applied as a substitute for the reference voice information in the degree of association shown in FIG. In such a case, the combination of the reference image information obtained by capturing the motion of the animal acquired in advance and the reference position information indicating the position of the animal at the time when the reference image information is captured, and the intention of the animal. Form three or more levels of association.

The reference position information and the position information may be composed of the position coordinates detected by, for example, GPS or the like as the position where the reference image information is captured. Since the behavior of the animal's intention may differ depending on the position where the animal is positioned, this is also used as an explanatory variable.

Next, the image information obtained by capturing the motion of the animal to be discriminated and the position information indicating the position of the animal at the time when the image information is captured are acquired in the same manner as described above. Then, the intention of the animal is determined based on the reference image information according to the acquired image information and the reference position information according to the acquired position information by referring to the formed degree of association. The details of this intention determination method are the same as described above.

Further, as shown in FIG. 9, as the reference information U, reference acceleration information, reference image information, reference audio information, reference food consumption information, reference genital area information, reference raw milk amount information, etc. As the reference information V, the reference acceleration information, the reference image information, the reference audio information, the reference food consumption information, the reference genital information, and the reference, which are combined with the reference information U to form the degree of association. The raw milk amount information may be used for discrimination based on the degree of association between these combinations. The output solution is the intention described above.

At this time, the output obtained for the reference information U may be used as the input data as it is, and may be associated with the output via the intermediate node 61 in combination with the reference information V. For example, for the reference information U, after the output solution is output, this may be used as an input as it is, and the output may be searched by using the degree of association with other reference information V.

In the above-mentioned degree of association, the degree of association is expressed by a 10-step evaluation, but it is not limited to this, and it may be expressed by a degree of association of 3 or more levels, and conversely, it may be expressed by 3 or more levels. For example, 100 steps or 1000 steps may be used. On the other hand, this degree of association does not include those expressed in two stages, that is, whether or not they are related to each other, either 1 or 0.

According to the present invention having the above-described configuration, anyone can easily search for the intention of an animal without any special skill or experience. Further, according to the present invention, it is possible to make a judgment of this search solution with higher accuracy than that made by a human being. Further, by configuring the above-mentioned degree of association with artificial intelligence (neural network or the like), it is possible to further improve the discrimination accuracy by learning this.

Since there are many cases where the above-mentioned input data and output data are not completely the same in the process of learning, the input data and the output data may be classified by type. That is, the information P01, P02, ... P15, 16, ... That constitute the input data are classified according to the criteria classified in advance on the system side or the user side according to the content of the information, and the classified inputs. A dataset may be created between the data and the output data and trained.

Further, according to the present invention, there is a feature that the optimum solution search is performed through the degree of association set to three or more stages. The degree of association can be described by a numerical value from 0 to 100%, for example, in addition to the above-mentioned 10 levels, but is not limited to this, and any stage can be described as long as it can be described by a numerical value of 3 or more levels. It may be configured.

By discriminating the will of an animal with higher credibility and less misunderstanding based on the degree of association expressed by such numerical values of three or more stages, multiple candidates for the possibility of a search solution can be considered. Under the circumstances, it is also possible to search and display in descending order of the degree of association.

In addition to this, according to the present invention, it is possible to judge without overlooking the discrimination result of the output having an extremely low degree of association such as 1%. It warns the user that even a judgment result with an extremely low degree of association is connected as a slight sign, and may be useful as the judgment result once every tens or hundreds of times. be able to.

Further, according to the present invention, there is an advantage that the search policy can be determined by the method of setting the threshold value by performing the search based on the degree of association of three or more stages. If the threshold value is lowered, even if the above-mentioned degree of association is 1%, it can be picked up without omission, but it is unlikely that a more appropriate discrimination result can be detected favorably, and a lot of noise may be picked up. be. On the other hand, if the threshold value is raised, there is a high possibility that the optimum search solution can be detected with high probability, but the degree of association is usually low and it is passed through, but it is suitable to appear once in tens or hundreds of times. Sometimes the solution is overlooked. It is possible to decide which one should be emphasized based on the ideas of the user side and the system side, but it is possible to increase the degree of freedom in selecting the points to be emphasized.

Further, in the present invention, the above-mentioned degree of association may be updated. This update may reflect information provided, for example, via a public communication network such as the Internet. Further, when knowledge, information, and data regarding acceleration information, image information, audio information, food consumption information, genital area information, and raw milk amount information are acquired, the degree of association is increased or decreased according to these.

In other words, this update corresponds to learning in the sense of artificial intelligence. It can be said that it is a learning act because it acquires new data and reflects it in the learned data.

In addition, this update of the degree of association is done by the system side or the user side based on the contents of research data, papers, conference presentations, newspaper articles, books, etc. by experts, except when it is based on information that can be obtained from the public communication network. It may be updated artificially or automatically. Artificial intelligence may be utilized in these update processes.

Further, the process of first creating a trained model and the above-mentioned update may use not only supervised learning but also unsupervised learning, deep learning, reinforcement learning, and the like. In the case of unsupervised learning, instead of reading and learning the data set of input data and output data, information corresponding to the input data is read and learned, and the degree of association related to the output data is self-formed from there. You may let it.

In the above-described embodiment, the reference image information is used as the basic reference information, and the reference acceleration information, the reference voice information, the reference food consumption information, and the reference information are used as other reference information. An example of a case where the degree of association is configured by a combination of any of genital area information, raw milk volume information for reference, intention history information for reference, biological information for reference, attribute information for reference, time zone information for reference, and position information for reference. I explained it to you, but it is not limited to this. As the basic reference information, reference acceleration information other than reference image information, reference audio information, reference food consumption information, reference genital area information, reference raw milk amount information, reference intention history information, reference Biological information, reference attribute information, reference time zone information, and reference position information are used, and as other reference information, any reference information other than the reference information that is the basis thereof is combined to form a degree of association. You may do so.

Further, according to the present invention, as shown in FIG. 10, the degree of association between the reference information as the keynote and the other reference information may be used in three or more stages. In such a case, the solution search is performed based on the degree of association between the reference information, which is the keynote according to the newly acquired information, and the other reference information.

Similarly, in these cases, when the information corresponding to the reference information used as the learning data is input, the solution search is performed based on the above-mentioned method.

The search solution obtained through the degree of association may be further modified based on other reference information, or the weighting may be changed.

The other reference information referred to here corresponds to any reference information other than the reference information which is the keynote when any of the above-mentioned reference information is used as the keynote reference information.

For example, as one of the other reference information, when the body temperature in the reference biological information is very high, it is assumed that it has been previously determined that the physical condition is poor. At this time, as the intention of the animal, a process of increasing the weighting of the search solution "I want to improve my physical condition" is performed, in other words, a process of increasing the probability that "I want to improve my physical condition" leads to the search solution. Set in advance to do so.

For example, the analysis result in which the other reference information G more suggests the animal's intention "I want to improve my physical condition", and the reference information F more suggests the animal's intention "fullness". It shall be the result. In this way, after setting with the reference information, if the actually acquired information is the same as or similar to the reference information G, the animal's intention "I want to improve my physical condition" is weighted up. .. On the other hand, when the actually acquired information is the same as or similar to the reference information F, a process of increasing the weighting of the animal's intention "fullness" is performed. That is, the degree of association itself that leads to the intention of the animal may be controlled based on the reference information F to H. Alternatively, after the intention of the animal is determined only by the above-mentioned degree of association, the obtained search solution may be modified based on the reference information F to H. In the latter case, how to modify the animal's intention as a search solution based on the reference information F to H will reflect what was designed on the system side each time.

Further, the reference information is not limited to the case where it is composed of any one type, and the solution search may be performed based on two or more types of reference information. Similarly, in such a case, the case where the animal's intention suggested by the reference information leads to a higher one, the higher the correction of the animal's intention as the search solution obtained through the degree of association, and the suggestion of the reference information. The lower the intention of the animal to be, the lower the intention of the animal as the search solution obtained through the degree of association may be modified.

2nd Embodiment In the 2nd embodiment, the intention of the animal as a search solution is obtained independently from the above-mentioned image information, acceleration information, voice information, and the like.

For example, as shown in FIG. 11, three or more levels of association between the reference image information and the will of the animal are used.

In the example of FIG. 11, it is assumed that the input data is the reference image information P01, P02, P03 in each area. The reference image information P01, P02, and P03 as such input data are linked to the will of the animal as an output.

The reference image information P01, P02, and P03 are associated with each other through three or more levels of association with the animal intentions A to D as the output solution.

The reference image information is arranged on the left side through this degree of association, and the intention of each animal is arranged on the right side through this degree of association. The degree of association indicates the degree of which animal's intention is highly related to the reference image information arranged on the left side. In other words, this degree of association is an indicator of what animal intentions each reference image information is likely to be associated with, and selects the most probable animal intention for each reference image information. It shows the accuracy above. In the example of FIG. 11, w13 to w19 are shown as the degree of association. These w13 to w19 are shown in 10 stages as shown in Table 1 below, and the closer to 10 points, the higher the degree of relevance of each combination as an intermediate node to the animal's intention as an output. On the contrary, the closer to one point, the lower the degree of relevance of each combination as an intermediate node to the intention of the animal as an output.

The search device 2 acquires in advance the degree of association w13 to w19 of three or more stages shown in FIG. That is, the search device 2 accumulates the past data set as to which of the reference image information of each region and the intention of the animal in that case was adopted and evaluated in determining the actual search solution. By analyzing and analyzing these, the degree of association shown in FIG. 11 is created.

Further, the degree of association shown in FIG. 11 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

In such a case, as shown in FIG. 12, reference image information of each region is input as input data, the intention of the animal is output as output data, and at least one hidden layer between the input node and the output node. May be provided and machine learning may be performed. The above-mentioned degree of association is set in either one or both of the input node and the hidden layer node, and this is the weighting of each node, and the output is selected based on this. Then, when this degree of association exceeds a certain threshold value, the output may be selected.

Such a degree of association is what is called learned data in artificial intelligence. After creating such trained data through the data set of the reference image information of each region before and the animal's intention, the above-mentioned trained data is actually used to determine the animal's intention from now on. The data will be used to search for the will of the animal. These data sets may be created by reading from a database managed by the vendor.

Next, the acquired image information is collated with the reference image information. In such a case, the degree of association shown in FIG. 11 (Table 1) acquired in advance is referred to. For example, when the newly acquired image information is the same as or similar to P02, the animal intention B is associated with w15 and the animal intention C is associated with the association degree w16 through the degree of association. In such a case, the intention B of the animal having the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the intention C of the animal, which has the lowest degree of association but the association itself is recognized, may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and any other output solution may be selected in any other priority as long as it is based on the degree of association.

By the way, the collation of the image information and the reference image information is whether or not the data average is within the range of ± several% or ± several tens% even if these data do not completely match. May be used to determine whether they are the same or similar. Further, as long as the image information is shown in a time-series transition graph, it may be discriminated based on the similarity of the trends.

In this way, it is possible to search for the most suitable animal intention from the newly acquired image information and display it to the user. By looking at this search result, it is possible to determine in advance what kind of animal's intention can be in the area in the future, and it is possible to notify the animal's intention via an alarm or the like, and the animal's intention. Can be understood, and breeding can be carried out accordingly.

As an alternative to the reference image information, as shown in FIG. 13, a degree of association may be formed between the reference acceleration information and the intention of the animal for learning. The reference acceleration information is the same as that described in the first embodiment.

In such a case, the degree of association between the reference acceleration information and the intention of the animal is trained in three or more stages. Then, the acceleration information is newly acquired. Then, the search solution of the animal's intention is searched by giving priority to the reference acceleration information according to the acquired acceleration information and the one having a higher degree of association with the animal's intention in three or more stages.

As an alternative to the reference image information, as shown in FIG. 14, a degree of association may be formed between the reference audio information and the intention of the animal for learning. The reference voice information is the same as that described in the first embodiment.

In such a case, the reference voice information and the intention of the animal are learned in three or more stages of association. Then, the voice information is newly acquired. Then, the search solution of the animal's intention is searched by giving priority to the reference voice information corresponding to the acquired voice information and the one having a higher degree of association with the animal's intention at three or more stages.

As an alternative to the reference image information, as shown in FIG. 15, a degree of association may be formed between the reference biological information and the will of the animal for learning. The reference biological information and biological information include all biological information detected from domestic animals, and are composed of, for example, body temperature, heart rate, pulse, blood oxygen concentration, blood carbon dioxide amount, and the like. The body temperature may be measured through, for example, a thermo sensor, and the heart rate and blood oxygen concentration may be measured by using, for example, a chip sensor, an IC tag having a sensing function, or the like. Since such biological information may also express the intentions and various desires of animals, this is used as an explanatory variable.

In such a case, the degree of association between the reference biological information and the intention of the animal is learned in three or more stages. Then, new biological information is acquired. Then, the search solution of the animal's intention is searched by giving priority to the reference biological information according to the acquired biological information and the one having a higher degree of association with the animal's intention at three or more stages.

In the example of FIG. 16, it is premised that a combination of the reference image information and the reference food consumption information is formed. It is assumed that the input data is, for example, reference image information P11 to P13 and reference food consumption information P14 to 17. The intermediate node shown in FIG. 16 is a combination of the reference image information and the reference food consumption information as such input data. Each intermediate node is further linked to the output. In this output, the increase / decrease data of the will of the animal as an output solution is displayed.

Each combination (intermediate node) of the reference image information and the reference food consumption information is associated with each other through three or more levels of association with the animal intention increase / decrease data or the market price as this output solution. There is. The reference image information and the reference food consumption information are arranged on the left side through this degree of association, and the increase / decrease data or the market price of each animal's intention is arranged on the right side through this degree of association. The degree of association indicates the degree of association with which animal's intention is high with respect to the reference image information and the reference food consumption information arranged on the left side. In other words, this degree of association is an index showing what kind of animal's intention each reference image information and reference food consumption information is likely to be associated with, and is a reference image information and reference food. It shows the accuracy in selecting the most probable increase / decrease data or market price of the animal's intention from the consumption information.

The estimation device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, the estimation device 2 accumulates past data on the reference image information, the reference food consumption information, and the intention of the animal in that case in determining the actual search solution. By analyzing and analyzing these, the degree of association shown in FIG. 16 is created.

Further, the degree of association shown in FIG. 16 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, when actually newly determining the increase / decrease data or market price (market price data) of the animal's intention from now on, the above-mentioned learned data is used to increase / decrease data of the animal's intention or The market price will be determined. In such a case, the image information is newly acquired and the food consumption information is acquired.

Based on the newly acquired image information and the food consumption information in this way, the increase / decrease data or the market price of the intention of the animal that actually acquired the newly acquired image information and the food consumption information is predicted. In such a case, the degree of association shown in FIG. 16 (Table 1) acquired in advance is referred to, and the solution having the highest degree of association is selected as the optimum solution. The details of the method for selecting the optimum solution are the same as those described in the first embodiment described above.

In this second embodiment, as other reference information to be combined with the reference image information, as an alternative to the reference food consumption information, the reference intention history information, the reference biological information, the reference attribute information, and the reference The time zone information and the reference position information may be learned.

The reference intention history information and intention history information relate to the past intention history of each animal to be discriminated. The reference intention history information is the time of the animal's intention determined every year, the conception history if the animal has been conceived and delivered many times, the process from conception to delivery, the postpartum situation, and delivery. Includes the situation of the child. In addition to this, it shows what kind of result was obtained when the animals were seeded at what timing with respect to the acquired (acceleration information, image information, ... raw milk amount information). You may.

The reference attribute information and attribute information are composed of data such as age, sex, type, pedigree, past medical history, past birth history, size and weight of the animal. These data may be manually input by a livestock farmer or the like. Since such attribute information may also express the intention of an animal or the desire of an individual animal, this is used as an explanatory variable.

The reference time zone information and the time zone information may be, for example, grouped in the morning or afternoon, or may be indicated by an hourly or minute pitch as the time zone in which the reference image information is captured. .. Since the intentions of animals and the behaviors of individual animal desires may differ depending on the time of day, this is also used as an explanatory variable.

The reference position information and the position information may be composed of the position coordinates detected by, for example, GPS or the like as the position where the reference image information is captured. Since the behavior of the animal's desire may differ depending on the position where the animal is positioned, this is also used as an explanatory variable.

As reference information to be combined with reference image information, as an alternative to reference food consumption information, reference intention history information may be learned.

In such a case, the combination of the reference image information and the reference intention history information and the degree of association with the animal's intention at three or more levels are learned. Then, the image information and the animal's intention history information are newly acquired. Then, a combination having reference image information according to the acquired image information and reference intention history information according to the animal's intention history information, and a combination having a higher degree of association with the animal's intention at three or more stages are selected. Prioritize and explore the will of animals.

As reference information to be combined with reference image information, reference biometric information may be learned as an alternative to reference food consumption information.

In such a case, the combination of the reference image information and the reference biological information and the degree of association with the intention of the animal at three or more levels are learned. Then, the image information and the biological information are newly acquired. This biological information is detected from the animal to be discriminated through various biological sensors. Then, priority is given to a combination having reference image information according to the acquired image information and reference biological information according to the biological information, and one having a higher degree of association with the intention of the animal at three or more stages. Explore the will of animals.

As reference information to be combined with reference image information, reference attribute information may be learned as an alternative to reference food consumption information.

In such a case, the combination of the reference image information and the reference attribute information and the degree of association with the intention of the animal at three or more levels are learned. Then, the image information and the attribute information are newly acquired. Then, priority is given to a combination having reference image information according to the acquired image information and reference attribute information according to the attribute information, and one having a higher degree of association with the intention of the animal at three or more stages. Explore the will of animals.

As reference information to be combined with reference image information, reference time zone information may be learned as an alternative to reference food consumption information.

In such a case, the combination of the reference image information and the reference time zone information and the degree of association with the intention of the animal in three or more stages are learned. Then, the image information and the time zone information are newly acquired. This time zone information may be a time zone at the time when the image information of the animal to be discriminated is captured or before and after the image. Then, the combination having the reference image information according to the acquired image information and the reference time zone information according to the time zone information, and the market data of the animal's intention have a higher degree of association of three or more stages. Prioritize and explore the will of animals.

As reference information to be combined with reference image information, reference position information may be learned as an alternative to reference food consumption information.

In such a case, the combination having the reference image information and the reference position information and the degree of association with the intention of the animal in three or more stages are learned. Then, the image information and the position information are newly acquired. Then, priority is given to a combination having reference image information according to the acquired image information and reference position information according to the position information, and one having a higher degree of association with the intention of the animal at three or more stages. Explore the will of animals.

The reference image information is an analysis image in units of pixels of the image, or, for example, in units of block areas which are aggregates of a plurality of pixels, using deep learning technology as necessary based on well-known image analysis. You may try to find the feature amount of. This makes it possible to obtain a feature map that emphasizes the featured portion of the object to be discriminated from the image. Such a characteristic portion may be associated with a relationship with a pre-categorized animal behavior pattern. Thereby, the reference image information can be associated with the behavior pattern of the animal categorized in advance through the feature portion. Examples of behavioral patterns may be categorized as standing, ruminating, lying down, lying down, standing still, hungry, exercising, resting, eating, drinking water, etc. ..

When such a categorized behavior pattern is used as a reference behavior pattern, the intention of the animal may be similarly associated with it through the degree of association. On the other hand, the newly acquired image information is similarly applied to the behavior pattern of the animal categorized in advance through the characteristic portion. Then, it is possible to obtain a search solution having a high degree of association with the reference behavior pattern corresponding to the applied behavior pattern.

Further, both the first embodiment and the second embodiment are not limited to the above-described embodiment, and as shown in FIG. 17, for example, there are three or more stages of the reference information as the keynote and the intention of the animal. You may try to use the degree of association of. In such a case, the solution search will be performed based on the degree of association between the reference information according to the newly acquired information and the intention of the animal in three or more stages. The reference information as the keynote is, for example, reference image information and the like, but is not limited thereto, and any reference information (reference audio information, reference acceleration) in the first embodiment and the second embodiment. Information, reference food consumption information, reference intention history information, reference biological information, reference attribute information, reference time zone information, reference position information) are also applicable.

Similarly, in these cases, when the information corresponding to the reference information used as the learning data is input, the solution search is performed based on the above-mentioned method.

The search solution obtained through the degree of association may be further modified based on other reference information, or the weighting may be changed.

The other reference information referred to here corresponds to any reference information other than the reference information which is the keynote when any of the above-mentioned reference information is used as the keynote reference information.

For example, as one of the other reference information, it is assumed that there is a sign that the animal's intention is earlier in a certain reference food consumption P14. When the food consumption amount corresponding to the reference food consumption amount P14 is newly acquired, the process of increasing the weighting is performed for the search solution of the date and time when the animal's intention to excrete is earlier.

For example, the other reference information G is an analysis result suggesting that the animal's intention to excrete is earlier, and the reference information F suggests that the animal's intention to excrete is later. It is assumed that the analysis result is as follows. In this way, after setting with the reference information, if the actually acquired information is the same as or similar to the reference information G, the process of increasing the weighting of the search solution that makes the animal's intention to excrete earlier. I do. On the other hand, when the actually acquired information is the same as or similar to the reference information F, a process of increasing the weighting of the search solution suggesting that the intention of excreting the animal is delayed is performed. That is, the degree of association itself that leads to the intention of the animal may be controlled based on the reference information F to H. Alternatively, after the intention of the animal is determined only by the above-mentioned degree of association, the obtained search solution may be modified based on the reference information F to H. In the latter case, how to modify the animal's intention as a search solution based on the reference information F to H will reflect what was designed on the system side each time.

Further, the other reference information is not limited to the case where it is composed of any one type, and the solution search may be performed based on two or more types of reference information. Similarly, in such a case, the case that leads to the animal's intention suggested by the reference information is modified so as to be closer to the animal's intention as the search solution obtained through the degree of association.

As shown in FIG. 18, the reference information which is the keynote constituting the degree of association with the intention of the animal is any reference information (reference audio information, reference) in the first embodiment and the second embodiment. For acceleration information, reference food consumption information, reference intention history information, reference biological information, reference attribute information, reference time zone information, reference position information) are also applicable.

Similarly, as shown in FIG. 19, even when the degree of association of the animal's intention with respect to the combination having the reference information as the keynote and the other reference information is formed, the reference information as the keynote is still available. Any reference information (reference voice information, reference acceleration information, reference food consumption information, reference intention history information, reference biometric information, reference attribute information, reference) in the first embodiment and the second embodiment. Time zone information, reference position information) are also applicable. The other reference information includes any reference information (reference voice information, reference acceleration information, reference food consumption information, reference intention) in the first embodiment and the second embodiment other than the reference information which is the keynote. History information, biological information for reference, attribute information for reference, time zone information for reference, position information for reference) are included.

At this time, if the reference information that is the keynote is the reference voice information, the other reference information includes any reference information in the other one embodiment and the second embodiment. Further, if the reference information as the keynote is the reference acceleration information, the other reference information includes any reference information in the other one embodiment and the second embodiment. Further, if the reference information as the keynote is the reference biometric information, the other reference information includes any reference information in the other one embodiment and the second embodiment.

In such a case as well, the intention of the animal can be determined by performing a solution search in the same manner as in the explanation in FIG.

Also in the second embodiment, the degree of association may be learned by combining not only one but also two or more other reference information.
Of course, in the present invention, the intention of the animal obtained as a search result may be transmitted to a user terminal such as a smartphone owned by each user.

1 Animal intention discrimination system 2 Search device 21 Internal bus 23 Display unit 24 Control unit 25 Operation unit 26 Communication unit 27 Estimating unit 28 Storage unit 61 Node

Claims (9)

In the animal willing discriminant program that discriminates the will of animals
An information acquisition step to acquire voice information recorded from the voice of the animal to be discriminated,
The intention of the animal to be discriminated is determined based on the voice information acquired in the above information acquisition step by referring to the reference audio information obtained by recording the voice of the animal acquired in advance and the degree of association with the intention of the animal in three or more stages. An animal discriminant program characterized by having a computer perform a discriminant step. In the above information acquisition step, further acquisition of food consumption information regarding the food consumption of the animal to be discriminated is performed.
In the determination step, the combination having the reference audio information and the reference food consumption information regarding the animal food consumption acquired in advance and the degree of association with the animal's intention in three or more stages are referred to, and the above The animal intention discrimination program according to claim 1, wherein the intention of the animal to be discriminated is discriminated based on the voice information acquired in the information acquisition step and the food consumption information. In the above information acquisition step, the intention history information regarding the past intention history of each animal to be discriminated is further acquired.
In the determination step, the combination having the reference voice information and the reference intention history information regarding the past intention history of the animal acquired in advance and the degree of association with the animal intention in three or more stages are referred to, and the above The animal intention discrimination program according to claim 1, wherein the intention of the animal to be discriminated is discriminated based on the voice information acquired in the information acquisition step and the intention history information. In the above information acquisition step, biological information detected from the animal to be discriminated is further acquired.
In the discrimination step, the combination of the reference audio information and the reference biological information detected in advance from each animal and the degree of association with the intention of the animal in three or more stages are referred to and acquired in the information acquisition step. The animal intention discrimination program according to claim 1, wherein the intention of the animal to be discriminated is discriminated based on the voice information and the biological information. In the above information acquisition step, further attribute information regarding the attributes of the animal to be discriminated is acquired.
In the determination step, the combination of the reference voice information and the reference attribute information regarding the animal attribute acquired in advance and the degree of association with the intention of the animal in three or more stages are referred to, and the information is acquired in the information acquisition step. The animal intention discrimination program according to claim 1, wherein the intention of the animal to be discriminated is discriminated based on the voice information and the attribute information. In the above information acquisition step, the time zone information regarding the time zone in which the voice information is captured is further acquired.
In the determination step, the combination of the reference voice information and the reference time zone information regarding the time zone in which the reference voice information is captured is referred to, and the degree of association with the intention of the animal in three or more stages is referred to. The animal intention discrimination program according to claim 1, wherein the intention of the animal to be discriminated is discriminated based on the voice information and the time zone information acquired in the information acquisition step. In the information acquisition step, the position information indicating the position of the animal at the time when the voice information is imaged is further acquired.
In the discrimination step, a combination having the reference voice information and the reference position information indicating the position of the animal at the time when the reference voice information is imaged, and the degree of association with the intention of the animal in three or more stages are determined. The animal intention determination program according to claim 1, wherein the animal intention determination target is determined based on the voice information acquired in the information acquisition step and the time zone information. The animal intention discrimination program according to any one of claims 1 to 7, wherein in the discrimination step, the degree of association corresponding to the weighting coefficient of each output of the node of the neural network in artificial intelligence is used. In the animal willing discriminant program that discriminates the will of animals
An information acquisition step for acquiring voice information obtained by recording the voice of the animal to be discriminated and biological information detected from the animal.
The reference audio information obtained by recording the animal's voice acquired in advance and the reference audio information according to the audio information acquired in the above information acquisition step by referring to the degree of association with the animal's intention in three or more stages, and the animal's An animal intention discrimination program characterized in that priority is given to those having a higher degree of association with intention at three or more stages, and the intention of the animal to be discriminated is discriminated based on the acquired biometric information.

Images