WO2022113162A1

WO2022113162A1 - Information processing device, information processing method, information processing system, and computer-readable storage medium

Info

Publication number: WO2022113162A1
Application number: PCT/JP2020/043617
Authority: WO
Inventors: 亜子原
Original assignee: 日本電気株式会社
Priority date: 2020-11-24
Filing date: 2020-11-24
Publication date: 2022-06-02
Also published as: JPWO2022113162A1; JP7459970B2

Abstract

Provided are an information processing device, etc., that can accurately calculate the weight of the contents of a container. An information processing device according to one aspect of the present disclosure comprises: an acquisition means that acquires sensor data, which includes information pertaining to strain of a container or a support member supporting the container, from a sensor attached to the container or the support member; and a calculation means that uses a model that has learned a relationship between the weight of the contents of the container and input data including the information pertaining to the strain, and calculates the weight of the contents from the sensor data.

Description

Information processing equipment, information processing methods, information processing systems and computer-readable storage media

This disclosure relates to a technique for calculating weight.

There is a technology to manage containers for storing materials, etc. For example, in Patent Document 1, various sensors such as a sensor for monitoring the function of a valve, a temperature sensor, a weight sensor, and a strain sensor are installed in a storage tank to be monitored, and based on data obtained from the various sensors. , A technique for detecting an abnormality to be monitored is disclosed.

Here, Patent Document 1 does not disclose a specific method for calculating the weight of the contents of the storage tank. For example, as a method of calculating the weight of the contents of a container such as a storage tank, there is a method using a load cell. Specifically, it is a method of calculating the weight of the contents by installing a load cell at the bottom of the container and detecting the load applied to the load cell. However, in this method, it is necessary to incorporate the load cell in the container when installing the container. Therefore, when the load cell is introduced into an existing container, there is a risk that the cost for replacing the container will be high.

On the other hand, in Patent Document 2, regarding the silo which is a container for storing feed, a strain sensor is fixed to a support member to which the load of the silo is applied, and the stored amount of the silo is measured based on the output value of the strain sensor. The technology to be used is disclosed.

Japanese Patent Publication No. 2020-510248 Japanese Patent Application Laid-Open No. 2003-240623

Patent Document 2 describes that the voltage value corresponding to the amount of strain of the support member, which is the output value of the strain sensor, is acquired. However, Patent Document 2 does not describe how the relationship between the voltage value output by the strain sensor and the weight of the contents of the silo is set. Depending on the relationship between the set voltage value and the weight, the weight may not be calculated accurately.

The present disclosure has been made in view of the above problems, and one of the purposes is to provide an information processing device or the like capable of accurately calculating the weight of the contents of the container.

The information processing apparatus according to one aspect of the present disclosure includes an acquisition means for acquiring sensor data including information on distortion of the container or the support member from a sensor attached to the container or a support member supporting the container. A calculation means for calculating the weight of the contents from the sensor data by using a model that learns the relationship between the input data including the information on the strain and the weight of the contents of the container is provided.

The information processing method according to one aspect of the present disclosure acquires sensor data including information on distortion of the container or the support member from a sensor attached to the container or a support member supporting the container, and relates to the distortion. The weight of the contents is calculated from the sensor data by using the model that learned the relationship between the input data including the information and the weight of the contents of the container.

The computer-readable storage medium according to one aspect of the present disclosure is a process of acquiring sensor data including information on distortion of the container or the support member from a sensor attached to the container or a support member supporting the container. And, using a model that learned the relationship between the input data including the information on the strain and the weight of the contents of the container, the computer is made to execute the process of calculating the weight of the contents from the sensor data. Store the program.

According to the present disclosure, the weight of the contents of the container can be accurately calculated.

It is a figure which shows typically an example of the structure of the information processing system of 1st Embodiment of this disclosure. It is a block diagram which includes an example of the functional structure of the information processing system of 1st Embodiment of this disclosure. It is a sequence diagram which shows an example of the operation of the information processing system of 1st Embodiment of this disclosure. It is a figure which shows typically an example of the structure of the information processing system in the modification 2 of the 1st Embodiment of this disclosure. It is a figure which shows an example of the database in the modification 2 of the 1st Embodiment of this disclosure. It is a block diagram which shows an example of the functional structure of the information processing system of the 2nd Embodiment of this disclosure. It is a sequence diagram which shows an example of the operation of the information processing system of the 2nd Embodiment of this disclosure. It is a block diagram which shows an example of the functional structure of the information processing apparatus of the 3rd Embodiment of this disclosure. It is a flowchart which shows an example of the operation of the information processing apparatus of the 3rd Embodiment of this disclosure. It is a block diagram which shows an example of the hardware composition of the computer apparatus which realizes the information processing apparatus of 1st, 2nd, and 3rd Embodiment of this disclosure.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.

<First Embodiment>
An information processing system including the information processing apparatus of the first embodiment will be described.

FIG. 1 is a diagram schematically showing an example of the configuration of the information processing system 1000 of the first embodiment. As shown in FIG. 1, the information processing system 1000 includes an information processing device 100 and a strain sensor 200. The information processing device 100 is communicably connected to the strain sensor 200 via a network. Further, the information processing device 100 may be connected to the terminal 300 and the storage device 400 in a communicable manner. The terminal 300 may be, for example, a personal computer or a portable terminal such as a smartphone or a tablet terminal. The storage device 400 may be mounted on the information processing device 100.

The strain sensor 200 is a sensor that detects the strain of a member. The strain sensor 200 is attached to the surface of the container or the surface of the support member that supports the container. In the example of FIG. 1, the strain sensor 200 is attached to the surface of the support member. The container stores, for example, feed for feeding livestock. In this specification, an example in which the content of the container is feed will be mainly described, but the content of the container is not limited to this example. For example, the contents of the container may be an object as an industrial raw material or an agricultural product. Further, the contents of the container are not limited to solids, but may be liquids or gases. In the present specification, the contents of the container may be referred to as a material. The container has an input port where the material is input and a discharge port where the material is discharged. If the container is a container for storing feed, the container is installed, for example, on a farm owned by a livestock farmer. The support member is, for example, a strut, and the container is supported by a plurality of strut.

The strain sensor 200 detects the strain of the container or the support member. Then, the strain sensor 200 transmits the sensor data including the information indicating the detected strain to the information processing apparatus 100 via the network. The information processing apparatus 100 calculates the weight of the contents of the container based on the sensor data. As described above, the information processing system 1000 is a system that calculates the weight of the contents of the container based on the information obtained from the strain sensor 200 attached to the container or the support member. The information processing device 100 may be constructed in a cloud environment. That is, the information processing apparatus 100 may acquire the sensor data from the strain sensor 200 via the Internet.

Next, the details of the configuration of the information processing system 1000 will be described with reference to FIG. FIG. 2 is a block diagram showing an example of the configuration of the information processing system 1000 of the first embodiment.

[Details of distortion sensor 200]
As shown in FIG. 2, the strain sensor 200 includes a detection unit 210 and a communication unit 220.

The detection unit 210 detects information regarding the distortion of the member. When an external force is applied to the member, the member expands and contracts. The strain of the member indicates, for example, the amount of deformation of the member when the member expands or contracts. Here, when the metal expands and contracts, the electrical resistance of the metal changes. When the strain sensor 200 is attached to the member, the metal of the strain sensor 200 expands and contracts according to the expansion and contraction of the member, and the electrical resistance of the metal of the strain sensor 200 changes. The detection unit 210 replaces, for example, a change in the electrical resistance of the metal of the strain sensor 200 with a change in voltage. That is, the detection unit 210 detects, for example, the voltage value as information regarding the distortion of the member. The sensor that detects the strain of the member in this way is also called a strain gauge.

The container and the support member that supports the container are distorted by the load of the material that is the content of the container. Therefore, in the present specification, the strain sensor 200 is attached to the surface of the container or the support member where strain is generated due to the load of the material by an adhesive or the like. When the material is, for example, feed, for example, the outer surface of the container near the discharge port, the surface of a support member (for example, a support) in contact with the container, or the like. In the example of FIG. 1, the strain sensor 200 is attached to the surface of the support member of the container, but if the surface is the surface where the strain is generated due to the load of the material, the location where the strain sensor 200 is attached is this example. Not limited to. Further, the strain sensor 200 may be attached to the surface of a container and a support member where the magnitude of strain caused by the load of the material is larger than that of other locations. For example, the strain sensor 200 may be attached to the surface of the container near the discharge port and the surface of the support member in contact with the container by checking the magnitude of strain in advance and the one with the larger strain. This makes it possible to accurately detect changes in strain. Further, a plurality of strain sensors 200 may be attached. Thereby, for example, even when the material is biased in the container, the change in strain can be detected more accurately. Further, by attaching a plurality of strain sensors 200 to one container, it is possible to detect a change in strain even when one of the plurality of strain sensors 200 fails, for example. The detection unit 210 detects the voltage value as information regarding the distortion of the container or the support member, for example. Then, the detection unit 210 generates sensor data including the voltage value. The sensor data may include sensor identification information that identifies the strain sensor 200. In this way, the detection unit 210 detects information about the strain of the container or the support member. The detection unit 210 is an example of the detection means.

The communication unit 220 transmits sensor data including information on distortion to the information processing device 100 via the network. The communication unit 220 is an example of communication means.

[Details of Information Processing Device 100]
The information processing apparatus 100 includes an acquisition unit 110, a calculation unit 120, and an output unit 130.

The acquisition unit 110 acquires sensor data from the strain sensor 200. That is, the acquisition unit 110 acquires sensor data including information on the strain of the container or the support member from the sensor attached to the container or the support member that supports the container. The acquisition unit 110 is an example of acquisition means.

The calculation unit 120 calculates the weight of the contents of the container based on the sensor data acquired by the acquisition unit 110. At this time, the calculation unit 120 calculates the weight of the contents of the container based on the calculation model generated in advance. The calculation model is a model that learns the relationship between the input data including information on distortion (for example, voltage value) and the weight of the contents of the container. For example, the calculation model is a regression equation derived by performing regression analysis with the weight of the contents of the container as the objective variable and the information on strain as the explanatory variable. The weight of the contents and the information about the strain corresponding to the weight are acquired, for example, by detecting the information about the strain by the strain sensor 200 while changing the weight of the contents of the container.

The calculation model is not limited to the above example, and may be generated by using another machine learning algorithm. Other machine learning algorithms are, for example, SVM (Support Vector Machine), neural networks, random forests, and the like, but are not limited to this example. Further, the learning of the calculation model may be performed by the calculation unit 120. Further, the learning may be performed by a device other than the information processing device 100.

Next, the calculation unit 120 calculates the weight of the contents of the container by reading the derived calculation model from the storage device 400 and inputting information on the distortion included in the sensor data into the calculation model. In this way, the calculation unit 120 calculates the weight of the contents from the sensor data by using the model that learned the relationship between the input data including the information on the strain and the weight of the contents of the container. The calculation unit 120 is an example of the calculation means.

(Example 1 of acquisition unit 110 and calculation unit 120)
Even if the weight of the contents of the container and the support member is the same, the strain caused by the temperature may change. In addition, the weight of the contents may change depending on the humidity. Thus, the weather at the location where the container is installed can affect the weight calculation. Therefore, the acquisition unit 110 may acquire the weather data of the place where the container is installed. The meteorological data includes, for example, information indicating at least one of the temperature, humidity, precipitation, and snowfall at the place where the container is installed. The information included in the meteorological data is not limited to this example. The meteorological data may further include weather information such as sunny weather and cloudy weather, information indicating wind speed and wind direction, and information indicating vibration due to an earthquake or the like. The acquisition unit 110 may acquire weather data from an external server device connected via a network. For example, the acquisition unit 110 may acquire information on the place where the container is installed from the database stored in the storage device 400, and may acquire the meteorological data at the acquired place via the Internet. When various sensors such as a temperature sensor, a humidity sensor, and an acceleration sensor are installed around the container, the acquisition unit 110 may acquire the data detected by the sensor as meteorological data. Further, the acquisition unit 110 may acquire the data input to the terminal 300 by the user as meteorological data.

For example, the calculation unit 120 inputs information on distortion and weather data acquired by the acquisition unit 110 to a calculation model generated by machine learning using input data including information on distortion and weather data. To calculate the weight of the contents of the container. The calculation model in this case is, for example, pre-generated by machine learning using meteorological data and information on strain as explanatory variables and the weight of the contents of the container as the objective variable.

(Example 2 of acquisition unit 110 and calculation unit 120)
In addition, the material, structure, installation location, installation condition, etc. of the container may also affect the weight calculation. For example, the distortion may change depending on the material of the container and the support member. Further, for example, if the capacity of the container is 3 tons, the number of columns serving as support members is 3, and if the capacity is 5 tons, the number of columns is 4, and the structure changes depending on the container. When the structure changes, the distortion of the place where the load of the container and the support member is applied may also change. Further, when the container is installed near the road, vibration due to the traveling of the vehicle is transmitted, which may affect the detection of the strain sensor 200. Furthermore, the installation condition, such as whether the container is installed on a concrete base or on the soil, also affects the distortion. Therefore, the acquisition unit 110 obtains environmental data including at least one of information on the material of the container, information on the structure of the container, location information on the place where the container is installed, and information on the installation state of the container. You may get it. The information included in the environmental data is not limited to this example. For example, the environmental data may include information indicating the number of years of installation of the container and the support member, information indicating the altitude of the installation location, and the like. The acquisition unit 110 acquires, for example, environmental data from the storage device 400. In this case, the environment data is, for example, data input from the terminal 300 by the user.

For example, the calculation unit 120 inputs the distortion information and the environment data acquired by the acquisition unit 110 into the calculation model generated by machine learning using the input data including the distortion information and the environment data. , Calculate the weight of the contents of the container. The calculation model in this case is generated in advance by machine learning, for example, using environmental data and information on strain as explanatory variables and the weight of the contents of the container as the objective variable. In this machine learning, meteorological data may be further added as an explanatory variable. Then, the calculation unit 120 may calculate the weight of the contents of the container by inputting information on strain, environmental data, and meteorological data into the calculation model.

(Example 3 of acquisition unit 110 and calculation unit 120)
Further, for example, it is assumed that the content of the container is feed and the container is installed on a farm owned by a livestock farmer. Depending on the feed, the density may differ and it may easily contain water, so the type of feed may affect the calculation of weight. Further, depending on the type and number of livestock to which feed is fed, vibration or the like caused by the movement of the livestock may affect the detection of the strain sensor 200. Therefore, the acquisition unit 110 may further acquire livestock data including information indicating at least one of the type of feed, the type of livestock, and the number of livestock. The information contained in the livestock data is not limited to this example. For example, livestock data may include information indicating the growth stage (eg, age and size) of the livestock, the health status of the livestock, and the like. The acquisition unit 110 acquires livestock data from, for example, a storage device 400. In this case, the livestock data is, for example, data input from the terminal 300 by the user.

For example, the calculation unit 120 inputs the distortion information and the livestock data acquired by the acquisition unit 110 into the calculation model generated by machine learning using the input data including the distortion information and the livestock data. , Calculate the weight of the contents of the container.

The calculation model in this case is generated in advance by machine learning, for example, using livestock data and information on strain as explanatory variables and the weight of the contents of the container as the objective variable. In this machine learning, at least one of meteorological data and environmental data may be further added as explanatory variables. Then, the calculation unit 120 may calculate the weight of the contents of the container by inputting information on strain, livestock data, and at least one of environmental data and meteorological data into the calculation model.

The calculation model described in Examples 1 to 3 may be generated by using a known machine learning algorithm such as the above-mentioned SVM, neural network, random forest, or the like.

Further, the calculation unit 120 stores the acquired sensor data, at least one of the meteorological data, the environmental data, and the livestock data, and the information indicating the calculated weight in the storage device 400 in association with the time when the sensor data is acquired. May be stored.

The output unit 130 outputs the weight calculated by the calculation unit 120. For example, the output unit 130 transmits information indicating the calculated weight to the terminal 300, and causes the display of the terminal 300 to display the calculated weight. As a result, the information processing apparatus 100 allows the user to grasp the remaining amount of the contents. For example, if the user is the owner of the container, the user can efficiently place an order with a company that produces and supplies the materials stored in the container.

[Operation of information processing system 1000]
Next, an example of the operation of the information processing system 1000 will be described with reference to FIG. In this specification, each step of the sequence diagram and the flowchart is expressed by using the number assigned to each step as in "S101".

FIG. 3 is a sequence diagram showing an example of the operation of the information processing system 1000. In this operation example, it is assumed that the storage device 400 stores a calculation model in which meteorological data, environmental data, and livestock data are learned, in addition to information on distortion. In addition, the contents shall be feed, and the container shall be installed on the farm owned by the livestock farmer.

The detection unit 210 of the strain sensor 200 detects information regarding strain of the container or support member (S101). The communication unit 220 transmits sensor data including information on the detected distortion to the information processing device 100 (S102).

The acquisition unit 110 of the information processing apparatus 100 acquires sensor data (S103). In addition, the acquisition unit 110 acquires meteorological data, environmental data, and livestock data (S104). Then, the calculation unit 120 calculates the weight of the contents of the container based on the sensor data, the meteorological data, the environmental data, and the livestock data (S105). At this time, the calculation unit 120 calculates the weight by inputting information on strain, meteorological data, environmental data, and livestock data into the calculation model, for example. The output unit 130 outputs information indicating the calculated weight (S106). For example, the output unit 130 causes the display of the terminal 300 to display information indicating the weight.

As described above, the information processing apparatus 100 of the first embodiment acquires sensor data including information on distortion of the container or the support member from the sensor attached to the container or the support member supporting the container via the network. do. Then, the information processing apparatus 100 calculates the weight of the contents from the sensor data by using the model that learned the relationship between the input data including the information about the distortion and the weight of the contents of the container. As a result, the information processing apparatus 100 of the first embodiment uses a model that learns the relationship between the information on the strain and the weight of the contents of the container when calculating the weight of the contents of the container from the strain. Therefore, the weight of the contents of the container can be calculated accurately.

Further, the information processing apparatus 100 of the first embodiment uses a model that learns the relationship between the weight of the contents and the input data including at least one of the meteorological data, the environmental data, and the livestock data. Calculate the weight of the contents of the container. As described above, since the information processing apparatus 100 of the first embodiment can consider various data, the weight of the contents of the container can be calculated more accurately.

[Modification 1]
The strain sensor 200 may be set at a timing for transmitting sensor data. For example, the detection unit 210 may generate sensor data including information on distortion at predetermined time intervals, and the communication unit 220 may transmit the sensor data to the information processing device 100 in response to the generation of the sensor data. The timing at which the sensor data is transmitted may be, for example, once an hour or twice a day. The acquisition unit 110 acquires sensor data according to the set timing. As a result, the strain sensor 200 does not need to constantly transmit sensor data, so that the load of data transmission can be reduced.

Further, the timing at which the strain sensor 200 transmits the sensor data may be changed depending on the situation. Here, it is assumed that the content of the container is feed and the container is installed on the farm. At this time, the frequency and amount of feed may change depending on the type, number, or growth stage of the livestock to which the feed is fed. For example, when the number of livestock increases, it is possible to increase the frequency and amount of feeding. It is also conceivable to increase the frequency and amount of feeding in order to grow livestock. In such a case, for example, the acquisition unit 110 transmits information indicating the timing of transmitting the sensor data to the distortion sensor 200. The communication unit 220 of the strain sensor 200 sets the timing of generation and transmission of sensor data based on the received information indicating the timing. The acquisition unit 110 may transmit information indicating the timing of transmitting the sensor data when the information indicating the type, number, or growth stage of the livestock stored in the storage device 400 is updated. Further, the acquisition unit 110 may transmit information indicating the timing of transmitting the sensor data by receiving the transmission instruction from the terminal 300.

As described above, the information processing system 1000 in the first modification changes the timing of acquiring the sensor data according to at least one of the type, number, and growth stage of the livestock to which the feed is fed. Further, the information processing system 1000 in the first modification transmits sensor data at a timing changed according to at least one of the type, number, and growth stage of the livestock to which the feed is fed. As a result, the information processing system 1000 in the first modification can acquire the sensor data as needed while considering the load of transmitting and receiving the sensor data.

[Modification 2]
The information processing apparatus 100 may calculate the weight of the contents of each of a plurality of containers installed at different places. At this time, at least one strain sensor 200 is attached to each of the plurality of containers and the support member.

FIG. 4 is a diagram schematically showing an example of the configuration of the information processing system 1000 in the modification 2. In FIG. 4, strain sensors 200-1, 200-2, and 200-3 are attached to each of the containers installed at the three locations. The strain sensors 200-1, 200-2, and 200-3 may be collectively referred to as the strain sensor 200. The acquisition unit 110 of the information processing apparatus 100 acquires sensor data from each of the strain sensors 200. The calculation unit 120 calculates the weight of the contents of each container based on the calculation model and the acquired sensor data. Here, the calculation unit 120 may calculate the weight using the calculation model generated for each container, or may calculate the weight using the calculation model corresponding to any container. When the calculation model corresponding to any container is used, the calculation model may be a model that learns the relationship between the input data including the information of the individual difference of the value output by the strain sensor and the weight of the contents. good.

As described above, the information processing apparatus 100 of the second modification acquires sensor data from each of the sensors when the container and the support member are installed in each of a plurality of different places, and the weight of each content of the container. Is calculated.

Note that the storage device 400 may store, for example, a database in which information about the strain sensor 200 and information about the container to which the strain sensor 200 is attached are associated. FIG. 5 is an example of a database. In the example of FIG. 5, in the database, at least the container identification information for identifying the container, the sensor identification information for identifying the strain sensor, the position information of the container, the structure of the container, and the type of contents are associated with each other. Contains data. The data contained in the database is not limited to this example. The calculation unit 120 may acquire environmental data and livestock data from the database.

Then, the output unit 130 outputs information indicating the weight of the contents of each container to the terminal 300. For example, suppose each of the installed containers is owned by a different owner. The output unit 130 outputs, for example, the weight of the material (contents of the container) for each owner, that is, the remaining amount of the material to the terminal 300. As a result, for example, the material production company can know the current remaining amount of the material for each owner, and can make an efficient material production plan. In addition, since the material delivery company can infer to which owner the material is likely to be delivered, it is possible to efficiently make a delivery plan.

<Second embodiment>
Next, an information processing system including the information processing apparatus of the second embodiment will be described. In the second embodiment, updating the calculation model will be described.

FIG. 6 is a block diagram showing an example of the configuration of the information processing system 1001 of the second embodiment. As shown in FIG. 6, the information processing system 1001 includes an information processing device 101 instead of the information processing device 100 in the first embodiment, and other than that, the information processing system 1000 described in the first embodiment. The same is true. That is, the information processing system 1001 includes an information processing device 101 and a strain sensor 200. The description of the contents in which the configuration and operation of the information processing system 1001 shown in FIG. 6 overlaps with the description of the first embodiment will be omitted.

[Details of information processing device 101]
As shown in FIG. 6, the information processing apparatus 101 includes an acquisition unit 110, a calculation unit 120, an output unit 130, and an update unit 140.

The update unit 140 updates the calculation model. For example, the update unit 140 acquires sensor data, meteorological data, environmental data, and livestock data when the contents are stored in the full capacity of the container or when the contents in the container are exhausted. Then, the update unit 140 uses the acquired sensor data, meteorological data, environmental data, and livestock data, and the weight of the contents (for example, the weight of the contents when the capacity is full or 0) as training data. Update the calculation model. The weight of the contents when the capacity is full is included in, for example, the database shown in the second modification.

Here, when the contents are stored in the full capacity of the container, or when the contents in the container are exhausted, the update unit 140 sends the sensor data, the weather data, the environmental data, and the sensor data to the acquisition unit 110. You may give an instruction to acquire livestock data. In this case, the updating unit 140 gives an instruction when, for example, the terminal 300 receives a notification indicating that the contents are stored in the full capacity of the container or that the contents in the container are exhausted. You may. Further, even if the update unit 140 determines that the content is stored in the full capacity of the container when the weight calculated by the calculation unit 120 is larger than the weight calculated immediately before by a predetermined value or more. good. At this time, the updating unit 140 may determine that the contents in the container have disappeared when the weight is calculated immediately before the calculated weight increases.

In this way, the update unit 140 updates the model based on the data acquired by the acquisition means. The update unit 140 is an example of an update means.

[Operation of information processing system 1001]
Next, the operation of the information processing system 1001 will be described. FIG. 7 is a sequence diagram showing an example of the operation of the information processing system 1001. Since the processing of S101 to S106 in FIG. 7 is the same as the processing of S101 to S106 of FIG. 3, the description thereof will be omitted.

After the processing of S106, the update unit 140 determines whether or not the calculated weight is increased by a predetermined value or more from the weight calculated immediately before (S201). For example, the update unit 140 reads out the weight calculated immediately before from the storage device 400, and compares the read weight with the weight calculated in S106. As a result of comparison, when the weight calculated in S106 is increased by a predetermined value or more from the weight calculated immediately before (Yes in S201), the update unit 140 updates the calculation model (S202). Specifically, the update unit 140 acquires sensor data, meteorological data, environmental data, and livestock data acquired in S103 and S104. Then, the calculation model is updated using the acquired data and the weight of the contents when the capacity is full. Further, for example, the update unit 140 acquires sensor data, meteorological data, environmental data, and livestock data used when the weight calculated immediately before is calculated. Then, the calculation model is updated using the acquired data and the weight (for example, 0) when the contents are lost. As a result of comparison, the updating unit 140 does not update the calculation model when the weight calculated in S106 does not increase by a predetermined value or more from the weight calculated immediately before (No in S201). ..

As described above, the information processing apparatus 101 of the second embodiment updates the calculation model based on the acquired data. As a result, in the information processing apparatus 101 of the second embodiment, for example, even when the distortion of the container and the support member changes or the value detected by the strain sensor 200 changes due to aging, the container The weight of the contents can be calculated accurately.

<Third embodiment>
The information processing apparatus in the present disclosure may have the following configuration.

FIG. 8 is a block diagram showing an example of the functional configuration of the information processing apparatus 102. In the information processing system 1000 shown in FIG. 1, the information processing device 102 may be provided instead of the information processing device 100. As shown in FIG. 8, the information processing apparatus 102 includes an acquisition unit 111 and a calculation unit 121.

The acquisition unit 111 acquires sensor data including information on the strain of the container or the support member from the sensor attached to the container or the support member supporting the container via the network. The sensor is, for example, a strain gauge that detects a voltage value according to the expansion and contraction of a container or a support member. The sensor data includes, for example, a voltage value detected by the sensor as information regarding distortion.

The calculation unit 121 calculates the weight of the contents from the sensor data by using the model that learned the relationship between the input data including the information on the strain and the weight of the contents of the container. The model is, for example, a model generated by using a known machine learning algorithm for the relationship between information about strain and the weight of the contents of the container.

FIG. 9 is a flowchart illustrating an example of the operation of the information processing apparatus 102. First, the acquisition unit 111 acquires sensor data including information on distortion from the sensor attached to the container or the support member (S301). Next, the calculation unit 121 calculates the weight of the contents from the sensor data by using the model that learned the relationship between the input data including the information on the strain and the weight of the contents of the container (S302).

As described above, the information processing apparatus 100 of the first embodiment acquires sensor data including information on distortion of the container or the support member from the sensor attached to the container or the support member that supports the container. Then, the information processing apparatus 100 calculates the weight of the contents from the sensor data by using the model that learned the relationship between the input data including the information about the distortion and the weight of the contents of the container. As a result, when the information processing apparatus 100 of the first embodiment calculates the weight of the contents of the container from the strain, the model learns the relationship between the input data including the information about the strain and the weight of the contents of the container. Therefore, the weight of the contents of the container can be calculated accurately.

<Example of hardware configuration of information processing device>
The hardware constituting the information processing apparatus of the first, second, and third embodiments described above will be described. FIG. 10 is a block diagram showing an example of a hardware configuration of a computer device that realizes the information processing device in each embodiment. Each block shown in FIG. 10 can be realized by a combination of software and a computer device 10 that realizes an information processing device and an information processing method in each embodiment.

As shown in FIG. 10, the computer device 10 includes a processor 11, a RAM (Random Access Memory) 12, a ROM (Read Only Memory) 13, a storage device 14, an input / output interface 15, a bus 16, and a drive device 17. The information processing device may be realized by a plurality of electric circuits.

The storage device 14 stores a program (computer program) 18. The processor 11 executes the program 18 of the information processing apparatus using the RAM 12. Specifically, for example, the program 18 includes a program that causes a computer to execute the processes shown in FIGS. 3, 7, and 9. Depending on the processor 11 executing the program 18, the functions of each component of the information processing apparatus (acquiring

units

110, 111,

calculation units

120, 121, output unit 130, updating unit 140, etc., described above) may be performed. It will be realized. The program 18 may be stored in the ROM 13. Further, the program 18 may be recorded on the storage medium 20 and read out using the drive device 17, or may be transmitted from an external device (not shown) to the computer device 10 via a network (not shown).

The input / output interface 15 exchanges data with peripheral devices (keyboard, mouse, display device, etc.) 19. The input / output interface 15 functions as a means for acquiring or outputting data. The bus 16 connects each component.

There are various variations in the method of realizing the information processing device. For example, the information processing device can be realized as a dedicated device. Further, the information processing device can be realized based on a combination of a plurality of devices.

A processing method in which a program for realizing each component in the function of each embodiment is recorded in a storage medium, the program recorded in the storage medium is read out as a code, and the program is executed in a computer is also included in the category of each embodiment. .. That is, a computer-readable storage medium is also included in the scope of each embodiment. Further, the storage medium in which the above-mentioned program is recorded and the program itself are also included in each embodiment.

The storage medium is, for example, a floppy (registered trademark) disk, a hard disk, an optical disk, a magneto-optical disk, a CD (Compact Disc) -ROM, a magnetic tape, a non-volatile memory card, or a ROM, but the storage medium is not limited to this example. The program recorded on the storage medium is not limited to a program that executes processing by itself, but operates on an OS (Operating System) in cooperation with other software and expansion board functions to execute processing. Programs to be implemented are also included in the category of each embodiment.

Although the invention of the present application has been described above with reference to the embodiment, the invention of the present application is not limited to the above embodiment. Various changes that can be understood by those skilled in the art can be made within the scope of the present invention in terms of the configuration and details of the present invention.

A part or all of the above embodiment may be described as in the following appendix, but is not limited to the following.

<Additional notes>
[Appendix 1]
An acquisition means for acquiring sensor data including information on strain of the container or the support member from a sensor attached to the container or a support member that supports the container.
A calculation means for calculating the weight of the contents from the sensor data by using a model that learns the relationship between the input data including the information on the strain and the weight of the contents of the container is provided.
Information processing equipment.

[Appendix 2]
The input data further includes meteorological data indicating at least one of temperature, humidity, precipitation and snowfall at the place where the container is installed.
The calculation means calculates the weight of the content by using a model that learns the relationship between the input data including the meteorological data and the weight of the content.
The information processing apparatus according to Appendix 1.

[Appendix 3]
The input data is an environment showing at least one of information on the material of the container, information on the structure of the container, location information on the place where the container is installed, and information on the installation state of the container. Including more data
The calculation means calculates the weight of the content by using a model that learns the relationship between the input data including the environment data and the weight of the content.
The information processing apparatus according to Appendix 1 or 2.

[Appendix 4]
If the content is feed,
The input data further includes livestock data indicating at least one of the type of feed, the type of livestock to which the feed is fed, and the number of livestock.
The calculation means calculates the weight of the content by using a model that learns the relationship between the input data including the livestock data and the weight of the content.
The information processing apparatus according to any one of Supplementary note 1 to 3.

[Appendix 5]
If the content is feed,
The acquisition means changes the timing of acquiring the sensor data according to at least one of the type, number and growth stage of the livestock to which the feed is fed.
The information processing apparatus according to any one of Supplementary note 1 to 4.

[Appendix 6]
An update means for updating the model based on the data acquired by the acquisition means.
The information processing apparatus according to any one of Supplementary Provisions 1 to 5.

[Appendix 7]
When the container and the support member are installed in each of a plurality of different locations,
The acquisition means acquires the sensor data from each of the sensors and obtains the sensor data.
The calculation means calculates the weight of the contents of each of the containers.
The information processing apparatus according to any one of Supplementary note 1 to 6.

[Appendix 8]
A detection means for detecting information on the strain of the container or the support member, and
A sensor having a communication means for transmitting the sensor data including information on the distortion.
The information processing apparatus according to any one of Supplementary note 1 to 7 is provided.
Information processing system.

[Appendix 9]
If the content is feed,
The communication means transmits sensor data at a timing changed according to information indicating at least one of the type, number and growth stage of the livestock to which the feed is fed.
The information processing system according to Appendix 8.

[Appendix 10]
From the sensor attached to the container or the support member that supports the container, sensor data including information on the strain of the container or the support member is acquired.
An information processing method for calculating the weight of the contents from the sensor data by using a model in which the relationship between the input data including the information on the distortion and the weight of the contents of the container is learned.

[Appendix 11]
The input data further includes meteorological data indicating at least one of temperature, humidity, precipitation and snowfall at the place where the container is installed.
The weight of the content is calculated using a model that learns the relationship between the input data including the meteorological data and the weight of the content.
The information processing method according to Appendix 10.

[Appendix 12]
The input data is an environment showing at least one of information on the material of the container, information on the structure of the container, location information on the place where the container is installed, and information on the installation state of the container. Including more data
The weight of the content is calculated using a model that learns the relationship between the input data including the environmental data and the weight of the content.
The information processing method according to

Appendix

10 or 11.

[Appendix 13]
If the content is feed,
The input data further includes livestock data indicating at least one of the type of feed, the type of livestock to which the feed is fed, and the number of livestock.
The weight of the contents is calculated by using a model that learns the relationship between the input data including the livestock data and the weight of the contents.
The information processing method according to any one of Supplementary Provisions 10 to 12.

[Appendix 14]
If the content is feed,
The timing of acquiring the sensor data is changed according to at least one of the type, number and growth stage of the livestock to which the feed is fed.
The information processing method according to any one of Supplementary Provisions 10 to 13.

[Appendix 15]
An update means for updating the model based on the data acquired in the acquisition process is provided.
The information processing method according to any one of Supplementary Provisions 10 to 14.

[Appendix 16]
When the container and the support member are installed in each of a plurality of different locations,
The sensor data is acquired from each of the sensors, and the sensor data is acquired.
Calculate the weight of each of the contents of the container,
The information processing method according to any one of Supplementary Provisions 10 to 15.

[Appendix 17]
A process of acquiring sensor data including information on strain of the container or the support member from a sensor attached to the container or a support member that supports the container.
A program that causes a computer to execute a process of calculating the weight of the contents from the sensor data using a model that learns the relationship between the input data including the information on the strain and the weight of the contents of the container. Store,
Computer-readable storage medium.

[Appendix 18]
The input data further includes meteorological data indicating at least one of temperature, humidity, precipitation and snowfall at the place where the container is installed.
In the calculation process, the weight of the content is calculated using a model that learns the relationship between the input data including the meteorological data and the weight of the content.
The computer-readable storage medium according to Appendix 17.

[Appendix 19]
The input data is an environment showing at least one of information on the material of the container, information on the structure of the container, location information on the place where the container is installed, and information on the installation state of the container. Including more data
In the calculation process, the weight of the content is calculated using a model that learns the relationship between the input data including the environmental data and the weight of the content.
A computer-readable storage medium according to

Appendix

17 or 18.

[Appendix 20]
If the content is feed,
The input data further includes livestock data indicating at least one of the type of feed, the type of livestock to which the feed is fed, and the number of livestock.
In the calculation process, the weight of the content is calculated using a model that learns the relationship between the input data including the livestock data and the weight of the content.
A computer-readable storage medium according to any one of Supplementary Notes 17 to 19.

[Appendix 21]
If the content is feed,
In the process of acquisition, the timing of acquiring the sensor data is changed according to at least one of the type, number and growth stage of the livestock to which the feed is fed.
A computer-readable storage medium according to any one of Supplementary Notes 17 to 20.

[Appendix 22]
An update means for updating the model based on the data acquired in the acquisition process is provided.
A computer-readable storage medium according to any one of Supplementary Notes 17 to 21.

[Appendix 23]
When the container and the support member are installed in each of a plurality of different locations,
In the acquisition process, the sensor data is acquired from each of the sensors, and the sensor data is acquired.
In the calculation process, the weight of each of the contents of the container is calculated.
A computer-readable storage medium according to any one of Appendix 17 to 22.

100, 101, 102

Information processing device

110, 111

Acquisition unit

120, 121 Calculation unit 130 Output unit 140 Update unit 200 Distortion sensor 210 Detection unit 220 Communication unit

Claims

An acquisition means for acquiring sensor data including information on strain of the container or the support member from a sensor attached to the container or a support member that supports the container.
A calculation means for calculating the weight of the contents from the sensor data by using a model that learns the relationship between the input data including the information on the strain and the weight of the contents of the container is provided.
Information processing equipment.
The input data further includes meteorological data indicating at least one of temperature, humidity, precipitation and snowfall at the place where the container is installed.
The calculation means calculates the weight of the content by using a model that learns the relationship between the input data including the meteorological data and the weight of the content.
The information processing apparatus according to claim 1.
The input data is an environment showing at least one of information on the material of the container, information on the structure of the container, location information on the place where the container is installed, and information on the installation state of the container. Including more data
The calculation means calculates the weight of the content by using a model that learns the relationship between the input data including the environment data and the weight of the content.
The information processing apparatus according to claim 1 or 2.
If the content is feed,
The input data further includes livestock data indicating at least one of the type of feed, the type of livestock to which the feed is fed, and the number of livestock.
The calculation means calculates the weight of the content by using a model that learns the relationship between the input data including the livestock data and the weight of the content.
The information processing apparatus according to any one of claims 1 to 3.
If the content is feed,
The acquisition means changes the timing of acquiring the sensor data according to at least one of the type, number and growth stage of the livestock to which the feed is fed.
The information processing apparatus according to any one of claims 1 to 4.
An update means for updating the model based on the data acquired by the acquisition means.
The information processing apparatus according to any one of claims 1 to 5.
When the container and the support member are installed in each of a plurality of different locations,
The acquisition means acquires the sensor data from each of the sensors and obtains the sensor data.
The calculation means calculates the weight of the contents of each of the containers.
The information processing apparatus according to any one of claims 1 to 6.
A detection means for detecting information on the strain of the container or the support member, and
A sensor having a communication means for transmitting the sensor data including information on the distortion.
The information processing apparatus according to any one of claims 1 to 7 is provided.
Information processing system.
If the content is feed,
The communication means transmits sensor data at a timing changed according to information indicating at least one of the type, number and growth stage of the livestock to which the feed is fed.
The information processing system according to claim 8.
From the sensor attached to the container or the support member that supports the container, sensor data including information on the strain of the container or the support member is acquired.
An information processing method for calculating the weight of the contents from the sensor data by using a model in which the relationship between the input data including the information on the distortion and the weight of the contents of the container is learned.
The input data further includes meteorological data indicating at least one of temperature, humidity, precipitation and snowfall at the place where the container is installed.
The weight of the content is calculated using a model that learns the relationship between the input data including the meteorological data and the weight of the content.
The information processing method according to claim 10.
The input data is an environment showing at least one of information on the material of the container, information on the structure of the container, location information on the place where the container is installed, and information on the installation state of the container. Including more data
The weight of the content is calculated using a model that learns the relationship between the input data including the environmental data and the weight of the content.
The information processing method according to claim 10 or 11.
If the content is feed,
The input data further includes livestock data indicating at least one of the type of feed, the type of livestock to which the feed is fed, and the number of livestock.
The weight of the contents is calculated by using a model that learns the relationship between the input data including the livestock data and the weight of the contents.
The information processing method according to any one of claims 10 to 12.
If the content is feed,
The timing of acquiring the sensor data is changed according to at least one of the type, number and growth stage of the livestock to which the feed is fed.
The information processing method according to any one of claims 10 to 13.
An update means for updating the model based on the data acquired in the acquisition process is provided.
The information processing method according to any one of claims 10 to 14.
When the container and the support member are installed in each of a plurality of different locations,
The sensor data is acquired from each of the sensors, and the sensor data is acquired.
Calculate the weight of each of the contents of the container,
The information processing method according to any one of claims 10 to 15.
A process of acquiring sensor data including information on strain of the container or the support member from a sensor attached to the container or a support member that supports the container.
A program that causes a computer to execute a process of calculating the weight of the contents from the sensor data using a model that learns the relationship between the input data including the information on the strain and the weight of the contents of the container. Store,
Computer-readable storage medium.
The input data further includes meteorological data indicating at least one of temperature, humidity, precipitation and snowfall at the place where the container is installed.
In the calculation process, a model learned the relationship between the input data including the meteorological data and the weight of the contents is used.
The computer-readable storage medium of claim 17.
The input data is an environment showing at least one of information on the material of the container, information on the structure of the container, location information on the place where the container is installed, and information on the installation state of the container. Including more data
In the calculation process, the weight of the content is calculated using a model that learns the relationship between the input data including the environmental data and the weight of the content.
The computer-readable storage medium of claim 17 or 18.
If the content is feed,
The input data further includes livestock data indicating at least one of the type of feed, the type of livestock to which the feed is fed, and the number of livestock.
In the calculation process, the weight of the content is calculated using a model that learns the relationship between the input data including the livestock data and the weight of the content.
The computer-readable storage medium according to any one of claims 17 to 19.
If the content is feed,
In the process of acquisition, the timing of acquiring the sensor data is changed according to at least one of the type, number and growth stage of the livestock to which the feed is fed.
The computer-readable storage medium according to any one of claims 17 to 20.
An update means for updating the model based on the data acquired in the acquisition process is provided.
The computer-readable storage medium according to any one of claims 17 to 21.
When the container and the support member are installed in each of a plurality of different locations,
In the acquisition process, the sensor data is acquired from each of the sensors, and the sensor data is acquired.
In the calculation process, the weight of each of the contents of the container is calculated.
The computer-readable storage medium according to any one of claims 17 to 22.