Estimation device

Abstract

It can sometimes be difficult to properly manufacture feed that meets the required conditions. [Solution] The estimation device includes an acquisition unit that acquires image data of manufactured feed as the subject, a detection unit that detects the state of the feed using the image data acquired by the acquisition unit, and an estimation unit that estimates the input amount, which is the amount of raw materials needed to produce a predetermined amount of appropriate feed that satisfies predetermined conditions, according to the detection result by the detection unit.

Description

Technical Field

[0001] The present invention relates to an estimation device, an estimation method, and a program.

Background Art

[0002] Techniques used in the production of feed or for the produced feed are known.

[0003] For example, Patent Document 1 discloses a system for measuring the moisture content in silage, which is a type of feed. According to Patent Document 1, the system measures the moisture content in silage by taking a photograph of a sample and processing the acquired image with a machine learning model.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] When producing feed such as dry pellets or extruded pellets according to raw materials, defective products may be mixed in the produced feed at a certain ratio. The ratio of such defective products mixed varies depending on various factors such as raw material characteristics including the moisture content in the raw materials and other environmental factors. Therefore, the ratio of defective products mixed, etc., has to be judged relying on the sense of skilled workers, and there has been a problem that it may be difficult to appropriately produce feed that meets conditions such as not being defective.

[0006] Solving the above - mentioned problems cannot be achieved even by using the techniques described in Patent Document 1. Therefore, one of the objectives of the present disclosure is to provide an estimation device, an estimation method, and a program capable of solving the above - mentioned problems. [Means for solving the problem]

[0007] To achieve this objective, the estimation apparatus in this disclosure is An acquisition unit that acquires image data of manufactured feed as the subject, A detection unit that detects the state of the feed using the image data acquired by the acquisition unit, An estimation unit estimates the amount of raw materials needed to produce a predetermined amount of appropriate feed that meets predetermined conditions, in accordance with the detection results from the detection unit, has This is the structure it takes.

[0008] Furthermore, the estimation method in this disclosure is Information processing device, By acquiring image data of manufactured feed as the subject, The state of the feed is detected using the acquired image data. Based on the detection results, the input amount, which is the amount of raw material needed to produce a predetermined quantity of appropriate feed that meets the specified conditions, is estimated. This is the structure it takes.

[0009] Furthermore, the program in this disclosure is In an information processing device, By acquiring image data of manufactured feed as the subject, The state of the feed is detected using the acquired image data. Based on the detection results, the input amount, which is the amount of raw material needed to produce a predetermined quantity of appropriate feed that meets the specified conditions, is estimated. This is a program for performing the processing. [Effects of the Invention]

[0010] According to the configurations described above, it is possible to properly manufacture feed that meets the requirements. [Brief explanation of the drawing]

[0011] [Figure 1]It is a diagram showing the configuration of the estimation system in the present disclosure. [Figure 2] It is a block diagram showing a configuration example of the estimation device. [Figure 3] It is a diagram for explaining a processing example of the detection unit. [Figure 4] It is a diagram for explaining a processing example of the production amount estimation unit. [Figure 5] It is a flowchart showing an operation example of the estimation device. [Figure 6] It is a block diagram showing another configuration example of the estimation device. [Figure 7] It is a block diagram showing a hardware configuration example of the estimation device in the second embodiment of the present disclosure. [Figure 8] It is a block diagram showing a configuration example of the estimation device. [Mode for Carrying Out the Invention]

[0012] [First Embodiment] A configuration example of the estimation system 100 in the present disclosure will be described with reference to FIGS. 1 to 6. FIG. 1 is a diagram showing the configuration of the estimation system 100. FIG. 2 is a block diagram showing a configuration example of the estimation device 300. FIG. 3 is a diagram for explaining a processing example of the detection unit 353. FIG. 4 is a diagram for explaining a processing example of the production amount estimation unit 355. FIG. 5 is a flowchart showing an operation example of the estimation device 300. FIG. 6 is a block diagram showing another configuration example of the estimation device 300. Note that in the present disclosure, the drawings may be associated with one or more embodiments.

[0013] In the present disclosure, an estimation system 100 that estimates the input amount of raw materials according to the state of feed detected using image data with the manufactured feed as the subject will be described. For example, the estimation system 100 can estimate the input amount required when manufacturing a proper amount of proper feed that satisfies predetermined conditions such as not being a defective product according to the detected state of the feed. As will be described later, the estimation system 100 acquires image data with the manufactured feed as the subject during a period until a predetermined condition is satisfied, such as from the start of feed production until the first 10% of the feed is manufactured. For example, the estimation system 100 periodically acquires time-series image data, such as every second, until a predetermined condition is satisfied. The estimation system 100 may also acquire image data at the stage when a predetermined condition is satisfied. Further, the estimation system 100 detects the state of the feed using the acquired image data. Then, the estimation system 100 estimates the input amount according to the detection result of the state. As an example, the estimation system 100 calculates the ratio of defective feed among the manufactured feed using the detection result of the state. Then, the estimation system 100 estimates the input amount by, for example, inputting the calculation result into a model that has been learned in advance. At this time, the estimation system 100 may estimate the input amount in consideration of environmental data such as temperature and humidity. Thus, the estimation system 100 estimates the input amount required when manufacturing a predetermined amount of proper feed according to the feed state detection result at the stage when a part of the feed has been manufactured.

[0014] Further, the estimation system 100 can be configured to feedback estimation results such as the input amount to a manufacturing device 110 that manufactures feed. In other words, the estimation system 100 may be configured to input information according to the estimation result into a system such as factory automation. For example, the estimation system 100 may instruct the manufacturing device 110 to input raw materials corresponding to the input amount. According to such a configuration, the estimation system 100 can automatically perform feed production until the required amount of proper feed is satisfied.

[0015] In this disclosure, the estimation system 100 detects cracks in the feed as a condition of the feed. The estimation system 100 may also detect the length and diameter of each manufactured feed as a condition of the feed. Furthermore, the estimation system 100 can detect whether the buoyancy of the feed when it is placed in water is as expected, for example, by acquiring image data after the manufactured feed is placed in water. For example, the estimation system 100 can detect at least one of the feed conditions exemplified above. The estimation system 100 may also detect any other conditions.

[0016] Furthermore, the estimation system 100 may estimate arbitrary information in addition to the input amount, such as the details of the processes used to adjust the conditions during manufacturing. For example, the estimation system 100 may estimate at least some of the details of the adjustments to the proportion of materials contained in the raw materials, and the adjustments to the processing conditions when manufacturing feed in the manufacturing apparatus 110, such as heating temperature, time, and applied pressure.

[0017] The estimation system 100 described in this disclosure will now be described in more detail. Figure 1 shows an example configuration of the estimation system 100. Referring to Figure 1, the estimation system 100 includes an imaging device 200 and an estimation device 300. As shown in Figure 1, the imaging device 200 and the estimation device 300 are connected to each other so that they can communicate with one another.

[0018] Furthermore, as shown in Figure 1, the estimation system 100 may include a manufacturing device 110 that produces feed such as aquatic feed according to the raw materials. As will be described later, the manufacturing device 110 and the estimation device 300 may be configured to communicate with each other. Here, the manufacturing device 110 is a device that produces feed such as dry pellets or extruded pellets by performing predetermined processing on the raw materials put into the device. The manufacturing device 110 may be configured to receive instructions from the estimation device 300, for example, to input raw materials, or to adjust processing conditions for producing feed such as heating temperature, time, and applied pressure. For example, the manufacturing device 110 can perform at least some of the following processes: sorting of raw materials, input of raw materials, crushing of raw materials, stirring of raw materials, expanding process for shaping by heating and pressurizing, granulation of pellets, and other arbitrary processes. In other words, the manufacturing device 110 may include at least some of the following: a roll mill for crushing raw materials, a mixer for stirring raw materials, an expander for expanding process, a pellet mill for shaping, and other arbitrary devices.

[0019] The imaging device 200 is a camera or other device that captures image data of the feed produced by the manufacturing device 110. The imaging device 200 can capture image data when it meets any conditions, such as receiving operation input or instructions from the estimation device 300. The imaging device 200 also transmits the acquired image data to the estimation device 300. The imaging device 200 may also transmit the image data to the estimation device 300 in association with information such as the time the image data was captured.

[0020] In this disclosure, the imaging device 200 captures image data while the manufacturing device 110 is manufacturing feed. For example, the imaging device 200 can capture image data of the manufactured feed as the subject during a period of time until predetermined conditions are met, such as from the time the manufacturing device 110 starts manufacturing feed until the first 10% of the feed is manufactured. The imaging device 200 may capture time-series image data periodically, such as every second, until the conditions are met. Alternatively, the imaging device 200 may be configured to capture image data when predetermined conditions are met. The conditions under which the imaging device 200 performs imaging, the imaging interval, etc., can be set arbitrarily.

[0021] The imaging device 200 may capture image data of the feed in its as-manufactured state, or, as described above, it may capture image data of the feed after it has been placed in water. The feed may be placed in water by any means. The imaging device 200 may be configured to capture image data of the feed in its as-manufactured state, and then to place the feed in water using any means, and then capture image data of the feed after it has been placed in water.

[0022] Furthermore, the imaging device 200 may transmit the image data it has captured to the estimation device 300 at any time. For example, the imaging device 200 can transmit the image data it has captured to the estimation device 300 each time it captures an image. The imaging device 200 may also transmit the image data it has captured to the estimation device 300 when certain conditions are met, such as when the manufacturing device 110 has started manufacturing feed and has produced the first 10% of the feed. In addition, the imaging device 200 may transmit the image data to the estimation device 300 at any time, such as when it receives instructions from the estimation device 300.

[0023] The estimation device 300 is an information processing device that estimates the amount of raw materials to be input to produce the required amount of appropriate feed, based on the results of detecting the state of the feed at the stage in which a portion of the feed has been produced. Figure 2 shows an example of the main configuration of the estimation device 300. Referring to Figure 2, the estimation device 300 has as its main components an operation input unit 310, a screen display unit 320, a communication interface unit 330, a storage unit 340, and an arithmetic processing unit 350.

[0024] Figure 3 illustrates a case where the functions of the estimation device 300 are realized using a single information processing device. However, at least a part of the functions of the estimation device 300 may be realized using multiple information processing devices, for example, by being implemented on the cloud. Furthermore, the estimation device 300 does not have to include some of the configurations exemplified above, such as not having an operation input unit 310 or a screen display unit 320, and may have configurations other than those exemplified above.

[0025] The operation input unit 310 consists of an operation input device such as a keyboard or mouse. The operation input unit 310 detects the operation of the operator operating the estimation device 300 and outputs it to the calculation processing unit 350.

[0026] The screen display unit 320 consists of a screen display device such as a liquid crystal display or an organic EL (electro-luminescence) display. The screen display unit 320 can display various information stored in the storage unit 340 on the screen in response to instructions from the arithmetic processing unit 350.

[0027] The communication interface unit 330 consists of data communication circuits and the like. The communication interface unit 330 performs data communication with external devices connected via a communication line.

[0028] The storage unit 340 is a storage device such as a hard disk or memory. The storage unit 340 stores processing information and programs 343 necessary for various processes in the arithmetic processing unit 350. The programs 343 are read into the arithmetic processing unit 350 and executed to realize various processing functions. The programs 343 are pre-read from external devices or recording media via data input / output functions such as the communication interface unit 330 and stored in the storage unit 340. The main information stored in the storage unit 340 includes, for example, image data information 341 and environmental data information 342.

[0029] Image data information 341 includes image data acquired by the imaging device 200. Image data information 341 may also include time-series image data. Furthermore, in image data information 341, the image data may be associated with the time the image data was acquired. Image data information 341 can be updated by means of image data acquisition by the image data acquisition unit 351.

[0030] Environmental data information 342 includes environmental data such as temperature and humidity during feed production. Environmental data information 342 may also associate environmental data with the time the environmental data was acquired. Environmental data information 342 can be updated by means of environmental data acquisition by the environmental data acquisition unit 352. Note that environmental data information 342 may also include arbitrary environmental data other than temperature and humidity.

[0031] The arithmetic processing unit 350 has an arithmetic device such as a CPU (Central Processing Unit) and its peripheral circuits. The arithmetic processing unit 350 reads and executes a program 343 from the storage unit 340, thereby realizing various processing functions by having the hardware and the program 343 work together. The main processing functions realized by the arithmetic processing unit 350 include, for example, an image data acquisition unit 351, an environmental data acquisition unit 352, a detection unit 353, a defective product rate calculation unit 354, a production volume estimation unit 355, an additional processing estimation unit 356, and an output unit 357.

[0032] The arithmetic processing unit 350 may have a GPU (Graphic Processing Unit), DSP (Digital Signal Processor), MPU (Micro Processing Unit), FPU (Floating Point Number Processing Unit), PPU (Physics Processing Unit), TPU (Tensor Processing Unit), quantum processor, microcontroller, or a combination thereof, instead of the CPU described above.

[0033] The image data acquisition unit 351 acquires image data from the imaging device 200 or any other external device connected via the communication interface unit 330. The image data acquisition unit 351 also stores the acquired image data as image data information 341 in the storage unit 340.

[0034] The image data acquisition unit 351 may instruct the imaging device 200 to transmit image data at any time. For example, the image data acquisition unit 351 may instruct the imaging device 200 to transmit image data at a time when it can determine that predetermined conditions have been met, such as when the manufacturing device 110 has produced the first 10% of the feed after starting feed production.

[0035] The environmental data acquisition unit 352 acquires environmental data such as temperature and humidity during feed production. The environmental data acquisition unit 352 may acquire environmental data using any method. For example, the environmental data acquisition unit 352 can acquire environmental data from various sensors provided by or around the manufacturing apparatus 110. The environmental data acquisition unit 352 may also acquire environmental data by communicating with external devices. The environmental data acquisition unit 352 stores the acquired environmental data as environmental data information 342 in the storage unit 340.

[0036] The detection unit 353 detects the state of the feed using the image data acquired by the image data acquisition unit 351.

[0037] For example, as shown in Figure 3, the detection unit 353 detects cracks in the feed as a condition of the feed. The detection unit 353 may detect not only the presence or absence of cracks, but also the size and area of ​​the cracks. The detection unit 353 can also detect the length and diameter of each manufactured feed as a condition of the feed. The detection unit 353 may detect at least some of the conditions exemplified above. The detection unit 353 can perform the detection of cracks and the like by using any image recognition method, such as inputting image data into a pre-trained model or performing template matching. The detection unit 353 may also recognize each of the multiple feeds included in the image data and then detect the crack locations. The detection unit 353 may also perform only the detection of crack locations without recognizing each feed.

[0038] Furthermore, the detection unit 353 may detect states other than those exemplified, in addition to or instead of the exemplified states. For example, as described above, if image data of the state in which the feed is placed in water is acquired, the detection unit 353 may detect whether the buoyancy of the feed is as previously expected for the feed being manufactured. In other words, the detection unit 353 may detect whether the feed floats in water and confirm whether the detection result is within expectations. The detection unit 353 may also detect any other arbitrary states.

[0039] The defective product rate calculation unit 354 calculates a defective product rate corresponding to the proportion of defective feed among the manufactured feed, based on the detection results from the detection unit 353.

[0040] For example, the defective product rate calculation unit 354 can calculate the defective product rate by using the crack detection results from the detection unit 353 to calculate the crack rate for the entire feed. In other words, the defective product rate calculation unit 354 may calculate the defective product rate as the crack rate for the entire manufactured feed. As an example, the defective product rate calculation unit 354 can calculate the crack rate by dividing the area of ​​the cracked areas detected by the detection unit 353 by the area of ​​the entire feed in the image data. In this way, the defective product rate calculation unit 354 can calculate the defective product rate as the overall crack rate without individually recognizing each feed.

[0041] Furthermore, the defective product rate calculation unit 354 may calculate the defective product rate by recognizing each feed in the image data and confirming whether each recognized feed can be considered a defective product. For example, the defective product rate calculation unit 354 has a pre-defined definition of what constitutes a defective feed. Therefore, the defective product rate calculation unit 354 uses the detection results from the detection unit 353 and the pre-defined definition to confirm whether each recognized feed in the image data is a defective product. As an example, the defective product rate calculation unit 354 uses the detection results from the detection unit 353 to calculate the crack rate for each feed by dividing the area of ​​cracks present in the corresponding feed by the area of ​​the individual feed. Then, the defective product rate calculation unit 354 confirms whether each recognized feed is a defective product by checking whether the calculated crack rate meets the defined conditions for a defective product. After that, the defective product rate calculation unit 354 can calculate the defective product rate by dividing the number of feeds confirmed to be defective by the number of feeds in the image data.

[0042] For example, a product can be defined as defective if it falls under one or more of the following conditions. However, the definition of a defective product may differ from those exemplified. • Feed that deviates by 5% or more from the normal length. • Feed with a diameter that deviates by 5% or more from that of a normal product. • Items with a cracking rate greater than 5% • Items whose buoyancy differs from expectations when placed in water.

[0043] The production volume estimation unit 355 estimates the amount of appropriate feed that meets the conditions from the total amount of feed that can be produced from the raw materials. In other words, the production volume estimation unit 355 estimates the amount of appropriate feed when the production of the feed is completed. For example, the production volume estimation unit 355 can estimate the amount of appropriate feed using the defect rate calculated by the defect rate calculation unit 354 and the environmental data acquisition unit 352.

[0044] Figure 4 shows an example of the estimation process by the production volume estimation unit 355. Referring to Figure 4, the production volume estimation unit 355 can estimate the appropriate amount of feed by inputting the defect rate calculated by the defect rate calculation unit 354 and the environmental data acquisition unit 352 into a pre-trained model. The above model may be pre-trained by performing machine learning using multiple pre-prepared training data. The training data may be based on past performance or simulation results, such as labeling the defect rate and environmental data with the amount of appropriate feed that was actually produced. However, the model is not limited to the example given above, and the training data may also be other than those given above.

[0045] Furthermore, if the image data information 341 includes time-series image data, the defect rate calculation unit 354 can calculate the defect rate corresponding to each image data. The production volume estimation unit 355 may be configured to input the time-series defect rate corresponding to each image data into the model, or it may be configured to calculate statistical values ​​such as the average value from each defect rate and input the calculated statistical values ​​into the model.

[0046] Furthermore, the production volume estimation unit 355 may estimate the appropriate amount of feed using methods other than those exemplified above. For example, the production volume estimation unit 355 may estimate the appropriate amount of feed by inputting the defect rate calculated by the defect rate calculation unit 354 into a pre-trained model without inputting environmental data. Alternatively, the production volume estimation unit 355 may be configured to input information such as the amount of remaining raw materials scheduled to be added, in addition to the defect rate and environmental data, into the model. Alternatively, the production volume estimation unit 355 may be used to estimate the appropriate amount of feed by inputting detection results from the detection unit 353 into a pre-trained model instead of the defect rate. Alternatively, the production volume estimation unit 355 may estimate the appropriate amount of feed by substituting the defect rate calculated by the defect rate calculation unit 354 into a predetermined formula, without using a pre-trained model.

[0047] The additional processing estimation unit 356 estimates the processing required to produce the appropriate amount of feed up to a predetermined amount, based on the estimation results from the production volume estimation unit 355. For example, the additional processing estimation unit 356 can estimate the amount of raw materials, such as the input amount, required to produce the appropriate amount of feed up to a predetermined amount, based on the estimation results from the production volume estimation unit 355.

[0048] For example, the additional processing estimation unit 356 identifies the deficit by subtracting the estimated appropriate amount of feed from the desired production quantity stored in advance. Then, the additional processing estimation unit 356 estimates the input amount according to the identified deficit. As an example, the additional processing estimation unit 356 uses the amount of appropriate feed estimated by the production quantity estimation unit 355, information indicating the amount of raw materials initially input, etc., to calculate the proportion of appropriate feed that can be produced according to the amount of raw materials to be input. Then, the additional processing estimation unit 356 can estimate the input amount by applying the result of the above calculation to the deficit. Note that the additional processing estimation unit 356 may also estimate the input amount by using methods other than those exemplified above, such as inputting information indicating the deficit into a pre-trained model.

[0049] Furthermore, the additional processing estimation unit 356 may estimate the input amount as well as other processing methods not exemplified above. For example, the additional processing estimation unit 356 may estimate the adjustments to the proportion of materials contained in the raw materials when the raw materials consist of multiple materials. The additional processing estimation unit 356 may also estimate the adjustments to the processing conditions when manufacturing feed in the manufacturing apparatus 110, such as heating temperature, time, and applied pressure. The additional processing estimation unit 356 may perform the above estimations using predetermined information, or it may perform the above estimations using a pre-learned model.

[0050] The output unit 357 outputs information corresponding to the various processes performed by the estimation device 300. The output unit 357 may display the various information on the screen display unit 320 or transmit it to an external device via the communication interface unit 330.

[0051] For example, the output unit 357 can output information corresponding to the processing results of various processing units, such as the calculation results by the defective product rate calculation unit 354, the estimation results by the production volume estimation unit 355, and the estimation results by the additional processing estimation unit 356. In addition to the information exemplified above, the output unit 357 may also output image data acquired by the image data acquisition unit 351, environmental data acquired by the environmental data acquisition unit 352, information corresponding to the detection results by the detection unit 353, and other arbitrary information.

[0052] The above is an example of the configuration of the estimation device 300. Next, an example of the operation of the estimation device 300 will be described with reference to Figure 5. Note that Figure 5 is an example of the operation of the estimation device 300, and the operation of the estimation device 300 is not limited to the example shown in Figure 5.

[0053] Referring to Figure 5, the image data acquisition unit 351 acquires image data from the imaging device 200 (step S101). The image data acquisition unit 351 can acquire image data for a period of time until predetermined conditions are met, such as from the start of feed production until the first 10% of the feed is produced (step S102, NO).

[0054] If the predetermined conditions are met (step S102, YES), the detection unit 353 detects the condition of the feed using the image data acquired by the image data acquisition unit 351 (step S103). For example, the detection unit 353 may detect information such as cracks in the feed or the size of the feed.

[0055] The defective product rate calculation unit 354 calculates a defective product rate corresponding to the proportion of defective feed among the manufactured feed, based on the detection results from the detection unit 353 (step S104).

[0056] The production volume estimation unit 355 estimates the amount of appropriate feed that satisfies the conditions from the total amount of feed that can be produced from the raw materials (step S105). For example, the production volume estimation unit 355 may estimate the amount of appropriate feed by inputting the defect rate calculated by the defect rate calculation unit 354 and the environmental data acquisition unit 352 into a trained model.

[0057] The additional processing estimation unit 356 estimates the processing required to produce the appropriate feed up to a predetermined amount, in accordance with the estimation results from the production volume estimation unit 355 (step S106). For example, the additional processing estimation unit 356 can estimate the input amount, which is the amount of raw materials that need to be input when producing the appropriate feed up to a predetermined amount.

[0058] The output unit 357 outputs information corresponding to the various processes performed by the estimation device 300 (step S107). The output unit 357 may display the various information on the screen display unit 320 or transmit it to an external device via the communication interface unit 330.

[0059] The above is an example of the configuration of the estimation device 300.

[0060] Thus, the estimation device 300 includes a detection unit 353, a production volume estimation unit 355, and an additional processing estimation unit 356. With this configuration, the production volume estimation unit 355 can estimate the amount of appropriate feed that satisfies the conditions from the total amount of feed that can be produced from the raw materials by inputting the detection results from the detection unit 353 into a model. As a result, the additional processing estimation unit 356 can estimate input amounts, etc., by performing predetermined processing on the estimated amount of appropriate feed. This makes it possible to appropriately produce the appropriate amount of feed that satisfies the conditions without relying on the intuition of skilled workers.

[0061] Note that the configuration of the estimation device 300 is not limited to the example shown in Figure 2. For example, the estimation device 300 does not need to have a production volume estimation unit 355, etc. In this case, the additional processing estimation unit 356 may use the defect rate calculated by the defect rate calculation unit 354 to estimate the input amount, etc. The estimation device 300 may also estimate the input amount, etc., using the defect rate calculated by the defect rate calculation unit 354, environmental data acquired by the environmental data acquisition unit 352, etc.

[0062] In this case, the additional processing estimation unit 356 can estimate input quantities, etc., by inputting the defect rate calculated by the defect rate calculation unit 354, etc., into a pre-trained model. Here, the above model may be pre-trained by performing machine learning using multiple pre-prepared training data. For example, the training data may be based on past performance or simulation results, such as labeling the actual input quantities required for the defect rate and environmental data. However, the model is not limited to the example given above, and the training data may also be other than those exemplified above. The additional processing estimation unit 356 may also be configured to estimate input quantities, etc., by inputting the detection results from the detection unit 353, etc., into the model. Furthermore, the additional processing estimation unit 356 can have the same modifications as the production volume estimation unit 355.

[0063] Thus, the estimation device 300 may have a detection unit 353 and an additional processing estimation unit 356 without having a production volume estimation unit 355, etc. With this configuration, the additional processing estimation unit 356 can estimate input amounts, etc., by inputting the detection results from the detection unit 353 into a model. This makes it possible to appropriately produce the appropriate amount of feed that meets the conditions without relying on the intuition of skilled workers.

[0064] Furthermore, Figure 6 shows a modified example of the estimation device 300. Referring to Figure 6, the arithmetic processing unit 350 of the estimation device 300 can implement a control unit 358 and other components in addition to the configuration exemplified in Figure 2 by reading and executing the program 343.

[0065] The control unit 358 instructs the manufacturing apparatus 110, etc., to execute the processing estimated by the additional processing estimation unit 356. For example, the control unit 358 instructs the manufacturing apparatus 110 to input the amount of raw materials estimated by the additional processing estimation unit 356. The control unit 358 may also instruct the manufacturing apparatus 110, etc., to adjust the ratio of raw materials to be input or adjust the processing conditions in the manufacturing apparatus 110, etc., as estimated by the additional processing estimation unit 356. In addition to the above examples, the control unit 358 can perform any control according to the estimation results by the additional processing estimation unit 356.

[0066] Thus, the control unit 358 functions as a modified version of the output unit 357, which outputs information corresponding to various processes performed by the estimation device 300, such as outputting predetermined instructions. For example, by performing control (output) by the control unit 358, the appropriate amount of raw materials can be fed into the manufacturing device 110. As a result, the manufacturing device 110 can automatically produce the appropriate amount of suitable feed.

[0067] [Second Embodiment] Next, with reference to Figures 7 and 8, we will describe the estimation device 400, which is a modified version of the estimation device 300. Figure 7 is a diagram showing an example of the hardware configuration of the estimation device 400. Figure 8 is a block diagram showing an example of the configuration of the estimation device 400.

[0068] The estimation device 400 is an information processing device that estimates the amount of raw materials to be input to produce a predetermined amount of appropriate feed, based on the results of detecting the state of the feed using image data captured during feed production. Figure 7 shows an example of the hardware configuration of the estimation device 400. Referring to Figure 7, the estimation device 400 has the following hardware configuration as an example. ·CPU(Central Processing Unit)401(Arithmetic unit) ROM (Read Only Memory) 402 (Storage Device) • RAM (Random Access Memory) 403 (storage device) • Programs loaded into RAM403 (404) • Storage device 405 for storing the program group 404 • Drive device 406 for reading and writing to recording medium 410 outside the information processing device. • Communication interface 407 connecting to a communication network 411 outside the information processing device. • Input / output interface 408 for data input and output. • Bus 409 connecting each component

[0069] Furthermore, the estimation device 400 can realize the functions of the acquisition unit 421, detection unit 422, and estimation unit 423 shown in Figure 11 by having the CPU 401 acquire the program group 404 and execute it. The program group 404 is, for example, stored in advance in a storage device 405 or ROM 402, and the CPU 401 loads it into RAM 403 or the like and executes it as needed. Alternatively, the program group 404 may be supplied to the CPU 401 via a communication network 411, or it may be stored in advance in a recording medium 410, and the drive device 406 may read the program and supply it to the CPU 401.

[0070] Figure 7 shows an example of the hardware configuration of the estimation device 400. The hardware configuration of the estimation device 400 is not limited to the case described above. For example, the estimation device 400 may consist of only a part of the configuration described above, such as not having a drive device 406. Also, the CPU 401 may be a GPU or the like as exemplified in the first embodiment.

[0071] The acquisition unit 421 acquires image data of the manufactured feed as the subject. The acquisition unit 421 may acquire image data from a connected imaging device or any other external device.

[0072] The detection unit 422 detects the condition of the feed using the image data acquired by the acquisition unit 421. For example, the detection unit 422 can detect cracks or other defects in the feed contained in the image data by performing arbitrary image recognition processing.

[0073] The production volume estimation unit 423 estimates the input amount, which is the amount of raw materials needed to produce a predetermined amount of appropriate feed that meets predetermined conditions, in accordance with the detection results from the detection unit 422. The production volume estimation unit 423 may perform the estimation process using any method, such as using a pre-trained model.

[0074] Thus, the estimation device 400 includes a detection unit 422 and a production volume estimation unit 423. With this configuration, the production volume estimation unit 423 can estimate the input amount by inputting the results detected by the detection unit 422 into a model. As a result, it becomes possible to appropriately produce the appropriate amount of feed that meets the conditions without relying on the intuition of skilled workers.

[0075] The estimation device 400 described above can be realized by incorporating a predetermined program into an information processing device such as the estimation device 400. Specifically, another form of the program described herein is a program that enables the information processing device such as the estimation device 400 to perform the following processes: acquire image data of manufactured feed as the subject, detect the state of the feed using the acquired image data, and estimate the input amount, which is the amount of raw materials needed to produce a predetermined amount of appropriate feed that satisfies predetermined conditions, according to the detection result.

[0076] Furthermore, the estimation method performed by the information processing device such as the estimation device 400 described above involves the information processing device such as the estimation device 400 acquiring image data of the manufactured feed, detecting the state of the feed using the acquired image data, and estimating the input amount, which is the amount of raw materials needed to produce a predetermined amount of appropriate feed that satisfies predetermined conditions, according to the detection result.

[0077] Even a program having the configuration described above, or a recording medium readable by a computer on which the program is recorded, or an estimation method, can achieve the same effects and benefits as the estimation device 400 described above, and thus the objectives of this disclosure described above can be achieved.

[0078] <Note> Some or all of the above embodiments may also be described as follows. The outline of the estimation device and the like in this disclosure is described below. However, this disclosure is not limited to the following configurations.

[0079] (Note 1) An acquisition unit that acquires image data of manufactured feed as the subject, A detection unit that detects the state of the feed using the image data acquired by the acquisition unit, An estimation unit estimates the amount of raw materials needed to produce a predetermined amount of appropriate feed that meets predetermined conditions, in accordance with the detection results from the detection unit, has Estimation device. (Note 2) The system includes a calculation unit that calculates a defect rate corresponding to the proportion of defective feed among the manufactured feed, based on the detection results from the aforementioned detection unit. The estimation unit estimates the input amount according to the calculation result by the calculation unit. The estimation device described in Appendix 1. (Note 3) The system includes an environmental data acquisition unit that acquires data corresponding to the environment when manufacturing the aforementioned feed, The estimation unit estimates the input amount based on the calculation result by the calculation unit and the data acquired by the environmental data acquisition unit. Estimation device as described in Appendix 2. (Note 4) The detection unit detects cracks in the feed as a condition of the feed. An estimation device as described in any one of the items from Appendix 1 to Appendix 3. (Note 5) The acquisition unit acquires the image data at predetermined intervals from the start of the production of the feed until a predetermined amount of the feed is produced. The detection unit detects the state of the feed for each of the image data acquired by the acquisition unit, The estimation unit estimates the input amount according to the results detected by the detection unit for each of the image data. An estimation device as described in any one of the items from Appendix 1 to Appendix 4. (Note 6) The control unit has a control unit that causes the raw materials in the amount estimated by the estimation unit to be supplied to the manufacturing apparatus for producing the feed. An estimation device as described in any one of the items from Appendix 1 to Appendix 5. (Note 7) The system includes a production quantity estimation unit that estimates the amount of appropriate feed that satisfies the conditions from the total amount of feed that can be produced from the raw materials, in accordance with the detection results from the detection unit. The estimation unit estimates the input amount according to the result of the estimation by the production volume estimation unit. An estimation device as described in any one of the items from Appendix 1 to Appendix 6. (Note 8) The estimation unit estimates the input amount and also estimates the content of the process to adjust the conditions during manufacturing. An estimation device as described in any one of the items from Appendix 1 to Appendix 7. (Note 9) Information processing device, By acquiring image data of manufactured feed as the subject, The state of the feed is detected using the acquired image data. Based on the detection results, the amount of raw materials to be input is estimated in order to produce a predetermined amount of appropriate feed that meets the specified conditions. Estimation method. (Note 10) In an information processing device, By acquiring image data of manufactured feed as the subject, The state of the feed is detected using the acquired image data. Based on the detection results, the input amount, which is the amount of raw material needed to produce a predetermined quantity of appropriate feed that meets the specified conditions, is estimated. A program to perform the processing.

[0080] Furthermore, some or all of the configurations described in Appendices 2 to 8, which are dependent on the estimation device described in Appendice 1, may also be dependent on the estimation method described in Appendice 9, the program described in Appendice 10, etc., through a similar dependency relationship. Moreover, not limited to Appendices 9 and 10, some or all of the configurations described in the appendices may also be dependent on various hardware, software, various recording means, methods, programs, or systems for recording software, without departing from the embodiments described above.

[0081] Furthermore, the programs described in each of the above embodiments and appendices can be stored and supplied to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). Programs may also be supplied to a computer using various types of transient computer-readable media. Examples of transient computer-readable media include electrical signals, optical signals, and electromagnetic waves. Transitory computer-readable media can be supplied to a computer via wired communication channels such as electric wires and optical fibers, or via wireless communication channels.

[0082] Although the present disclosure has been described above with reference to the embodiments described above, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure can be made as can be understood by those skilled in the art within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate. [Explanation of Symbols]

[0083] 100 Estimation Systems 110 Manufacturing equipment 200 Imaging device 300 Estimation device 310 Operation Input Section 320 Screen display section 330 Communication Interface Section 340 Storage section 341 Image data information 342 Environmental Data Information 343 Programs 350 Arithmetic Processing Unit 351 Image Data Acquisition Unit 352 Environmental Data Acquisition Unit 353 Detection unit 354 Defective product rate calculation section 355 Production Estimation Department 356 Additional Processing Estimation Unit 357 Output section 358 Control Unit 400 Estimator 401 CPU 402 ROM 403 RAM 404 Program Group 405 Storage device 406 Drive unit 407 Communication Interface 408 Input / Output Interfaces Bus 409 410 Recording media 411 Communication Network 421 Acquisition Department 422 Detection unit 423 Estimation Department 424 Output section

Claims

1. An acquisition unit that acquires image data of manufactured feed as the subject, A detection unit that detects the state of the feed using the image data acquired by the acquisition unit, An estimation unit estimates the amount of raw materials needed to produce a predetermined amount of appropriate feed that meets predetermined conditions, in accordance with the detection results from the detection unit, has Estimation device.

2. The system includes a calculation unit that calculates a defect rate corresponding to the proportion of defective feed among the manufactured feed, based on the detection results from the aforementioned detection unit. The estimation unit estimates the input amount according to the calculation result by the calculation unit. The estimation device according to claim 1.

3. The system includes an environmental data acquisition unit that acquires data corresponding to the environment when manufacturing the aforementioned feed, The estimation unit estimates the input amount based on the calculation result by the calculation unit and the data acquired by the environmental data acquisition unit. The estimation device according to claim 2.

4. The detection unit detects cracks in the feed as a condition of the feed. The estimation device according to claim 1.

5. The acquisition unit acquires the image data at predetermined intervals from the start of the production of the feed until a predetermined amount of the feed is produced. The detection unit detects the state of the feed for each of the image data acquired by the acquisition unit, The estimation unit estimates the input amount according to the results detected by the detection unit for each of the image data. The estimation device according to claim 1.

6. The control unit has a control unit that causes the raw materials in the amount estimated by the estimation unit to be supplied to the manufacturing apparatus for producing the feed. The estimation device according to claim 1.

7. The system includes a production quantity estimation unit that estimates the amount of appropriate feed that satisfies the conditions from the total amount of feed that can be produced from the raw materials, in accordance with the detection results from the detection unit. The estimation unit estimates the input amount according to the result of the estimation by the production volume estimation unit. The estimation device according to claim 1.

8. The estimation unit estimates the input amount and also estimates the content of the process to adjust the conditions during manufacturing. The estimation device according to claim 1.

9. Information processing device, By acquiring image data of manufactured feed as the subject, The state of the feed is detected using the acquired image data. Based on the detection results, the amount of raw materials to be input is estimated in order to produce a predetermined amount of appropriate feed that meets the specified conditions. Estimation method.

10. In an information processing device, By acquiring image data of manufactured feed as the subject, The state of the feed is detected using the acquired image data. Based on the detection results, the input amount, which is the amount of raw material needed to produce a predetermined quantity of appropriate feed that meets the specified conditions, is estimated. A program to perform the processing.

Images