Drying time prediction method, drying time prediction system, and drying machine

Abstract

The drying time prediction method acquires an operation condition at the time when a first drying machine (10) starts operation; acquires a first actual operation time of each of one or more first operations performed in the past with respect to the first drying machine (10); acquires operation end time information output from a learned model (245) by inputting the operation condition and first actual information based on the first actual operation time to the learned model (245), the operation end time information being about a time of end of operation resulting from the start of the operation; and outputs first information based on the operation end time information.

Description

Technical Field

[0001] This disclosure relates to the prediction of drying time. Background Technology

[0002] Techniques for making predictions about future events (things and phenomena) are known (e.g., see Patent Document 1).

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: Japanese Patent Application Publication No. 2014-85914 Summary of the Invention

[0006] The problem that the invention aims to solve

[0007] For users who use dryers or similar devices to dry clothes, it is desirable to display the remaining drying time of the drying cycle.

[0008] Therefore, the purpose of this disclosure is to provide a method for predicting drying time, etc.

[0009] Methods used to solve problems

[0010] A drying time prediction method of the present disclosure includes: obtaining the operating conditions when a first dryer starts operating; obtaining the first actual operating time of each of the first operations performed by the first dryer more than once in the past; obtaining operation end time information output from the learned model by inputting the operating conditions and the first actual information based on the first actual operating time into the learned model, wherein the operation end time information relates to the end time of the operation caused by the start of the operation; and outputting first information based on the operation end time information.

[0011] A drying time prediction system according to the present disclosure comprises: an operating condition acquisition unit that acquires the operating conditions when a first dryer starts operating; a first actual operating time acquisition unit that acquires the first actual operating time for each of the first operations performed by the first dryer more than once in the past; a learned model that, given the input of the operating conditions and the first actual information based on the first actual operating time, outputs operation end time information about the end time of the operation caused by the start of the operation; and an output unit that outputs first information based on the operation end time information.

[0012] A dryer according to a technical solution of the present disclosure is the first dryer using the drying time prediction system described above, comprising: a providing unit that provides the operating conditions, the sensing information, and the first actual operating time to the drying time prediction system; an acquiring unit that acquires the first information from the drying time prediction system; and a display unit that displays the first information.

[0013] Invention Effects

[0014] According to the drying time prediction method of a technical solution disclosed herein, the drying time can be predicted. Attached Figure Description

[0015] Figure 1 This is a schematic diagram showing the relationship between the remaining drying time displayed according to conventional methods and the actual remaining drying time.

[0016] Figure 2 This is a schematic diagram illustrating the relationship between the remaining drying time shown by the learning-based model and the actual remaining drying time.

[0017] Figure 3 This is a block diagram illustrating an example of the configuration of a drying time prediction system according to an embodiment.

[0018] Figure 4 This is a block diagram illustrating an example of the configuration of a dryer according to an embodiment.

[0019] Figure 5 This is a block diagram illustrating an example of the configuration of a server device according to an implementation method.

[0020] Figure 6 This is a schematic diagram illustrating an example of how the standardization department calculates the actual operating time of the standardization implementation.

[0021] Figure 7 This is a block diagram illustrating an example of the configuration of a smartphone according to an implementation method.

[0022] Figure 8 This is a flowchart of the drying time prediction process for the implementation method.

[0023] Figure 9 This is a flowchart of the standardization process for implementing the method. Detailed Implementation

[0024] (The process of obtaining a technical solution disclosed herein)

[0025] In the past, the remaining drying time of dryers and the like was displayed by showing the remaining drying time at the start of the drying operation, which was the result of adding a correction value to a default value preset per fabric weight, and then counting down the remaining drying time as time went on.

[0026] In addition, in order to accurately display the remaining drying time, the degree of dryness was determined by using sensor information about the status of the dryer at fixed points (e.g., every 10 minutes) during the drying process, and the displayed remaining drying time was adjusted based on the determination result.

[0027] Figure 1 This is a schematic diagram showing the relationship between the remaining drying time displayed according to conventional methods and the actual remaining drying time.

[0028] like Figure 1 As shown, in the display of remaining drying time in conventional methods, there are instances where the displayed remaining drying time changes discontinuously, or the countdown of the displayed remaining drying time stops at certain intervals. These phenomena can cause confusion for users who visually confirm the displayed remaining drying time.

[0029] In view of this problem, the inventors conducted repeated experiments and research to develop a method for predicting drying time with greater accuracy than before. As a result, the inventors realized that by utilizing a learned model, they could predict drying time with greater accuracy than before. This learned model was pre-trained to output the remaining drying time when given the operating conditions of the dryer, the sensing information about the state of the dryer at the start of operation, and the actual operating time of the dryer in the past.

[0030] Figure 2 This is a schematic diagram showing the relationship between the remaining drying time displayed using the method of the learned model described above and the actual remaining drying time.

[0031] according to Figure 1 and Figure 2 It can be seen that by using the method of the learned model mentioned above to predict the drying time, the remaining drying time can be displayed with better accuracy than before.

[0032] Based on this understanding, the inventors conducted further and repeated experimental studies, and came up with the following method for predicting drying time.

[0033] A drying time prediction method of the present disclosure includes: obtaining the operating conditions when a first dryer starts operating; obtaining the first actual operating time of each of the first operations performed by the first dryer more than once in the past; obtaining operation end time information output from the learned model by inputting the operating conditions and the first actual information based on the first actual operating time into the learned model, wherein the operation end time information relates to the end time of the operation caused by the start of the operation; and outputting first information based on the operation end time information.

[0034] According to the above-mentioned drying time prediction method, the drying time can be predicted using a pre-trained learned model. The learned model outputs the end time of the operation caused by the start of the operation when the first dryer starts operating, given the operating conditions when the first dryer starts operating and the first actual operating time of the first dryer in the past.

[0035] Alternatively, sensing information about the state of the first dryer during operation can be obtained; in the process of obtaining the operation end time information, the operation end time information output from the learned model is obtained by inputting the operation conditions, the first actual information, and the sensing information into the learned model.

[0036] Therefore, the content of the sensed information is also reflected in the operation end time information output from the learned model. As a result, the drying time can be predicted with greater accuracy.

[0037] Alternatively, for each of the aforementioned one or more first operations, the first actual operating conditions at the start of the first operation can be correlated with the aforementioned first actual operating time; for each of the aforementioned two operations in one or more previous second operations of the second dryer, the second actual operating time of the second operation and the second actual operating conditions at the start of the second operation correlated with the second actual operating time can be obtained; for each of the aforementioned first actual operating times, the first actual operating time can be standardized based on the distribution of the aforementioned second actual operating times correlated with the aforementioned second actual operating conditions, thereby calculating a standardized actual operating time, wherein the second actual operating conditions are consistent with the aforementioned first actual operating conditions correlated with the first actual operating time; the aforementioned first actual information is based on the aforementioned standardized actual operating times calculated for the aforementioned first actual operating times respectively.

[0038] Therefore, the standardized actual operating time also reflects the trend of the drying time of the first dryer in the past, which tends to be longer or shorter, when observed from the distribution of drying time in the past operations of more than one second dryer under various actual operating conditions. Thus, drying time can be predicted with greater accuracy.

[0039] Alternatively, the average of the standardized actual operating times for each of the first actual operating times can be calculated; the first actual information is based on the average value.

[0040] Therefore, the average value reflects the aforementioned trend of prolonged or shortened operation under all actual operating conditions. Thus, the predicted drying time can reflect the aforementioned trend of prolonged or shortened operation under all actual operating conditions.

[0041] Alternatively, the first operation mentioned above may be the operation performed by the first dryer during a specified period in the past; the second operation mentioned above may be the operation performed by one or more second dryers during the specified period in the past.

[0042] Typically, the types of inputs fed into a dryer tend to remain relatively unchanged over a certain period. Therefore, drying time can be predicted with greater accuracy.

[0043] Alternatively, the aforementioned operating conditions and the aforementioned first actual operating conditions may include the amount of feed material fed into the aforementioned first dryer and the operating mode of the aforementioned first dryer, as set by the user of the aforementioned first dryer; the aforementioned second actual operating conditions may include the amount of feed material fed into the aforementioned one or more second dryers and the operating mode of the aforementioned one or more second dryers, as set by the users of each of the aforementioned one or more second dryers.

[0044] Therefore, the drying time can be predicted based on the amount of material fed into the dryer and the operating mode of the dryer, as set by the user.

[0045] Alternatively, the first dryer and one or more second dryers mentioned above may be the same type of machine.

[0046] This allows for more accurate prediction of drying time.

[0047] A drying time prediction system according to the present disclosure includes: an operating condition acquisition unit that acquires the operating conditions when a first dryer starts operating; a first actual operating time acquisition unit that acquires the first actual operating time for each of the first operations performed by the first dryer in the past; a learned model that, given the input of the operating conditions and the first actual information based on the first actual operating time, outputs operation end time information about the end time of the operation caused by the start of the operation; and an output unit that outputs first information based on the operation end time information.

[0048] According to the above-mentioned drying time prediction system, the drying time can be predicted using a pre-trained learned model. The learned model outputs the end time of the operation caused by the start of the operation when the first dryer starts operating, given the operating conditions when the first dryer starts operating and the first actual operating time of the first dryer in the past.

[0049] A dryer according to a technical solution of this disclosure is the first dryer using the drying time prediction system described above, comprising: a providing unit that provides the operating conditions and the first actual operating time to the drying time prediction system; an acquiring unit that acquires the first information from the drying time prediction system; and a display unit that displays the first information.

[0050] The aforementioned dryer obtains the first information from the aforementioned drying time prediction system. Therefore, it is able to predict the drying time.

[0051] The following is a reference to the appendix. Figure 1 The following describes specific examples of a drying time prediction method, drying time prediction system, and dryer related to the technical solution of this disclosure. The embodiments shown herein are all specific examples of this disclosure. Therefore, the values, shapes, materials, constituent elements, arrangement and connection forms of constituent elements, steps (processes), and order of steps shown in the following embodiments are merely examples and are not intended to limit this disclosure. Furthermore, the figures are schematic diagrams and are not necessarily strictly illustrated.

[0052] Furthermore, the inclusive or specific technical solutions disclosed herein can be implemented by systems, methods, integrated circuits, computer programs, or recording media such as computer-readable CD-ROMs, or by any combination of systems, methods, integrated circuits, computer programs, and recording media.

[0053] (Implementation Method)

[0054] [1. Composition]

[0055] Figure 3This is a block diagram illustrating an example of the configuration of a drying time prediction system according to an embodiment.

[0056] like Figure 3 As shown, the drying time prediction system 1 of the embodiments includes multiple dryers 10, a server device 20, multiple smartphones 30 and a network 40.

[0057] exist Figure 3 In this document, multiple dryers 10 correspond to dryer 10A, dryer 10B, dryer 10M, etc. Hereinafter, unless explicitly distinguishing each individual dryer, dryer 10A, dryer 10B, dryer 10M, etc., will be simply referred to as dryer 10. This explanation assumes that the multiple dryers 10 are of the same type, but it is not limited to the example where the multiple dryers 10 are necessarily of the same type.

[0058] exist Figure 3 In this context, multiple smartphones 30 correspond to smartphones 30A, 30B, 30N, etc. Hereinafter, unless explicitly distinguishing the specific details of each individual smartphone, smartphones 30A, 30B, 30N, etc., will be simply referred to as smartphones 30.

[0059] Network 40 relays communication between connected devices. Among the devices connected to network 40 are multiple dryers 10, server devices 20, and multiple smartphones 30.

[0060] Network 40 can be, for example, the Internet, a cellular network, or a LAN (Local Area Network).

[0061] Figure 4 This is a block diagram illustrating an example of the configuration of the dryer 10.

[0062] The dryer 10 is connected to the network 40 and has the function of drying clothes, etc. The dryer 10 can also be a washer-dryer with the function of washing clothes, etc.

[0063] like Figure 4 As shown, the dryer 10 includes a communication unit 100, an input receiving unit 110, an operation control unit 120, a drying unit 130, a past data storage unit 140, a sensing unit 150, a providing unit 160, an acquisition unit 170, and a display unit 180.

[0064] The communication unit 100 is connected to the network 40 and communicates with external devices connected to the network 40 via the network 40. The external devices include a server device 20 and multiple smartphones 30.

[0065] The communication unit 100, for example, has an input / output interface (not shown), and is implemented by executing a program stored in the memory (not shown) of the dryer 10 through a processor (not shown) of the dryer 10 and controlling the input / output interface.

[0066] The drying section 130 is equipped with a drying chamber (not shown) to dry clothes and other items placed inside the drying chamber.

[0067] The drying section 130 includes, for example, a rotary drum-type drying chamber (not shown), a heater (not shown), and a blower fan (not shown). While rotating the rotary drum-type drying chamber to agitate the clothes or other items placed inside, air heated by the heater is introduced into the rotary drum-type drying chamber through the blower fan, thereby drying the clothes or other items placed inside the drying chamber.

[0068] The drying unit 130 also includes sensors for sensing the state of the drying chamber and / or the state of clothing and other items placed inside the drying chamber. These sensors may include, for example, a thermometer for sensing the temperature of the air being expelled into the drying chamber, a thermometer for sensing the temperature of the air being drawn in from the drying chamber, an angular velocity meter for sensing the rotational speed of the drying chamber, an accelerometer for sensing the weight imbalance of the drying chamber, and a motor current meter for sensing the amount of fabric in the clothing and other items placed inside the drying chamber.

[0069] The input receiving unit 110 receives input from users of the dryer 10. The input received by the input receiving unit 110 includes the operating conditions when the dryer 10 starts operating. These operating conditions include, for example, the amount of clothing or other items placed into the dryer 10 and the operating mode of the dryer 10. While the input receiving unit 110 receives the amount of clothing input by the user, it can also receive the amount of clothing obtained by the sensing unit 150, which will be described later.

[0070] The input receiving unit 110, for example, has a touchpad (not shown), and the touchpad is controlled by the processor of the dryer 10 executing the program stored in the memory of the dryer 10.

[0071] The operation control unit 120 controls the operation of the drying unit 130 based on the input received by the input receiving unit 110, thereby operating the dryer 10.

[0072] The operation control unit 120 is implemented, for example, by executing a program stored in the memory of the dryer 10 through a processor provided with the dryer 10.

[0073] The past data accumulation unit 140 stores the actual operating conditions and actual operating time of the dryer 10 in the past by establishing a correlation.

[0074] In the past, the data storage unit 140 was equipped with a hard disk (not shown), and the program stored in the memory of the dryer 10 was executed by the processor of the dryer 10 and the hard disk was controlled.

[0075] The sensing unit 150 controls the sensors provided in the drying unit 130 to obtain sensing information about the status of the operating dryer 10. This sensing information includes, for example, the ejection temperature, the intake temperature, the rotational speed of the drying chamber, and any imbalance within the drying chamber. Furthermore, the sensing unit 150 can also control the sensors provided in the drying unit 130 when the dryer 10 starts operating to obtain the amount of clothing or other items placed in the drying chamber.

[0076] The sensing unit 150 repeatedly acquires sensing information during the operation of the dryer 10. For example, the sensing unit 150 acquires sensing information every minute from the start to the end of the operation of the dryer 10.

[0077] The sensing unit 150 is implemented, for example, by executing a program stored in the memory of the dryer 10 through a processor provided by the dryer 10.

[0078] The providing unit 160 provides the server device 20 with the operating conditions received by the input receiving unit 110, the correlated actual operating conditions and actual operating times stored in the past data accumulation unit 140, and the sensing information obtained by the sensing unit 150 via the communication unit 100. More specifically, whenever the input receiving unit 110 receives operating conditions, the providing unit 160 provides these operating conditions to the server device 20; whenever the past data accumulation unit 140 updates the correlated actual operating information and actual operating times, the providing unit 160 sends these correlated actual operating information and actual operating times to the server device 20; and whenever the sensing unit 150 obtains sensing information, the providing unit 160 provides this sensing information to the server device 20.

[0079] The provision unit 160 is implemented, for example, by executing a program stored in the memory of the dryer 10 through a processor provided by the dryer 10.

[0080] The acquisition unit 170 obtains first information indicating the remaining drying time (described later) from the server device 20 via the communication unit 100. More specifically, the acquisition unit 170 acquires the first information whenever it is sent from the server device 20.

[0081] The acquisition unit 170 is implemented, for example, by executing a program stored in the memory of the dryer 10 through a processor provided with the dryer 10.

[0082] The display unit 180 displays the first information acquired by the acquisition unit 170. More specifically, whenever the acquisition unit 170 acquires the first information, the display unit 180 displays the remaining drying time indicated by that first information.

[0083] The display unit 180 includes, for example, a touchpad (not shown), which is implemented by executing a program stored in the memory of the dryer 10 through the processor of the dryer 10 and controlling the touchpad.

[0084] Figure 5 This is a block diagram illustrating an example of the configuration of server device 20.

[0085] Server device 20 is connected to network 40 and has the function of predicting the remaining drying time of dryer 10, which operates to dry clothes and the like.

[0086] like Figure 5 As shown, the server device 20 includes a communication unit 200, a past data accumulation unit 205, a sensor information acquisition unit 210, an operating condition acquisition unit 215, a first actual operating time acquisition unit 220, a second actual operating time acquisition unit 225, a standardization unit 230, a representative value calculation unit 235, a prediction unit 240, and an output unit 250. Here, the prediction unit 240 includes a learned model 245.

[0087] The communication unit 200 is connected to the network 40 and communicates with external devices connected to the network 40 via the network 40. These external devices include multiple dryers 10 and multiple smartphones 30.

[0088] The communication unit 200, for example, has an input / output interface (not shown), and is implemented by executing a program stored in the memory (not shown) of the server device 20 through a processor (not shown) of the server device 20 and controlling the input / output interface.

[0089] The sensing information acquisition unit 210 acquires sensing information provided by the providing unit 160 via the communication unit 200. Whenever sensing information is provided from the providing unit 160, the sensing information acquisition unit 210 acquires this sensing information.

[0090] The sensing information acquisition unit 210 is implemented, for example, by executing a program stored in the memory of the server device 20 through a processor of the server device 20.

[0091] The operation condition acquisition unit 215 acquires the operation conditions provided by the supply unit 160 via the communication unit 200. Whenever operation conditions are provided from the supply unit 160, the operation condition acquisition unit 215 acquires these operation conditions.

[0092] The operating condition acquisition unit 215 is implemented, for example, by executing a program stored in the memory of the server device 20 through the processor of the server device 20.

[0093] The past data accumulation unit 205 obtains the interconnected actual operating conditions and actual operating times provided by the provision unit 160 via the communication unit 200, and stores the obtained interconnected actual operating conditions and actual operating times. Whenever interconnected actual operating conditions and actual operating times are provided from the provision unit 160, the past data accumulation unit 205 obtains and stores these interconnected actual operating conditions and actual operating times.

[0094] That is, the past data accumulation unit 205 establishes and stores the actual operating conditions and actual operating time of all the dryers 10 that constitute the drying time prediction system 1 in the past.

[0095] In the past, the data storage unit 205 may have included a hard disk (not shown), and the processor of the server device 20 executes the program stored in the memory of the server device 20 and controls the hard disk.

[0096] The first actual operating time acquisition unit 220 obtains the actual operating conditions (hereinafter, also referred to as "first actual operating conditions") and actual operating time (hereinafter, also referred to as "first actual operating time") that are interrelated and obtained by the operation of a dryer 10 (hereinafter also referred to as "first dryer 10") during a specified period in the past from the interrelated actual operating conditions and actual operating time stored in the past data accumulation unit 205.

[0097] Here, the specified period can be, for example, a period from the present to a date and time up to a predetermined number of days in the past, or a period of the same season as the current season (for example, if the current month is April, then since April is spring, it is the period of the current and past springs (for example, March, April, and May)). That is, the specified period can also be a period in which the types of inputs put into the dryer 10 tend to remain substantially unchanged.

[0098] The first actual operating time acquisition unit 220 is implemented, for example, by executing a program stored in the memory of the server device 20 through the processor of the server device 20.

[0099] The second actual operating time acquisition unit 225 acquires, from the past data accumulation unit 205, the actual operating conditions (hereinafter, also referred to as "second actual operating conditions") and actual operating times (hereinafter, also referred to as "second actual operating times") obtained through operation of one or more arbitrary dryers 10 (hereinafter also referred to as "one or more second dryers 10") that are interconnected, the interconnected actual operating conditions and actual operating times. Here, it is assumed that the one or more second dryers 10 includes the first dryer 10, that is, it is assumed that the one or more second dryers 10 includes all dryers 10, but it is also possible that the one or more second dryers 10 does not include the first dryer 10.

[0100] The second actual operating time acquisition unit 225 is implemented, for example, by executing a program stored in the memory of the server device 20 through the processor of the server device 20.

[0101] For each first actual operating time, the standardization department 230 standardizes the first actual operating time based on the distribution of the second actual operating time that is associated with the second actual operating conditions, and calculates the standardized actual operating time therefrom. The aforementioned second actual operating conditions are consistent with the first actual operating conditions that are associated with the first actual operating time.

[0102] Here, as an example that does not necessarily need to be limited, for example, the standardization department 230 uses (Equation 1) shown below to calculate the standardized actual operating time for each first actual operating time.

[0103] n=(t-mean(Tc)) / std(Tc)(Formula 1)

[0104] In Equation 1, n is the standardized actual operating time, t is the first actual operating time, Tc is the set of second actual operating times associated with the second operating condition, the second operating condition is the same as the first operating condition associated with the first actual operating time, mean(Tc) is the average of all second actual operating times contained in set Tc, and std(Tc) is the variance of all second actual operating times contained in set Tc.

[0105] As shown in Equation 1, when the first actual operating time is consistent with mean(Tc), that is, when the first actual operating time is consistent with the average actual operating time of all dryers 10 operating under the same actual operating conditions, the standardized actual operating time is 0.

[0106] Furthermore, when the first actual operating time is greater than mean(Tc), that is, when the first actual operating time is greater than the average actual operating time of all dryers 10 operating under the same actual operating conditions, that is, when the first actual operating time has a long-term tendency compared to the actual operating time of all dryers 10 operating under the same actual operating conditions, the standardized actual operating time is a positive value.

[0107] Furthermore, when the first actual operating time is smaller than mean(Tc), that is, when the first actual operating time is smaller than the average actual operating time of all the dryers 10 operating under the same actual operating conditions, that is, when the first actual operating time tends to be shorter compared to the actual operating time of all the dryers 10 operating under the same actual operating conditions, the standardized actual operating time is negative.

[0108] Thus, the tendency of the first actual operating time to become longer or shorter, as observed on the distribution of the second actual operating conditions that are associated with the second actual operating conditions, is reflected in the standardized actual operating time calculated by the standardization department 230. The aforementioned second actual operating conditions are consistent with the first actual operating conditions that are associated with the first actual operating time.

[0109] Figure 6 This is a schematic diagram illustrating an example of how the Standardization Department calculates the actual operating time of standardization in 230.

[0110] exist Figure 6 The upper graph is a graph plotting the first actual operating time of each operation in the first dryer 10 with the horizontal axis representing the date and time of operation and the vertical axis representing the first actual operating time. The lower graph is a graph plotting the standardized actual operating time of each operation in the first dryer 10 with the horizontal axis representing the date and time of operation and the vertical axis representing the actual operating time.

[0111] In the curve above, the first actual operating time 601 to the first actual operating time 606 are the first actual operating times of the first dryer 10 during the specified period.

[0112] Here, the first actual operating time 605 is the actual operating time under the actual operating conditions of condition A (e.g., the amount of fabric is 2 kg, and the operating mode is the fully drying mode); the first actual operating time 602 and the first actual operating time 604 are the actual operating times under the actual operating conditions of condition B (e.g., the amount of fabric is 2 kg, and the operating mode is the standard drying mode); the first actual operating time 601 and the first actual operating time 603 are the actual operating times under the actual operating conditions of condition C (e.g., the amount of fabric is 3 kg, and the operating mode is the fully drying mode); and the first actual operating time 606 is the actual operating time under the actual operating conditions of condition D (e.g., the amount of fabric is 3 kg, and the operating mode is the standard drying mode).

[0113] Standardization Department 230 standardizes the first actual operating time 605 based on the distribution of the second actual operating time associated with the actual operating conditions of condition A, thereby calculating the standardized actual operating time 655. It standardizes the first actual operating time 602 and 604 respectively based on the distribution of the second actual operating time associated with the actual operating conditions of condition B, thereby calculating the standardized actual operating time 652 and 654. It standardizes the first actual operating time 601 and 603 respectively based on the distribution of the second actual operating time associated with the actual operating conditions of condition C, thereby calculating the standardized actual operating time 651 and 653. It standardizes the first actual operating time 606 based on the distribution of the second actual operating time associated with the actual operating conditions of condition D, thereby calculating the standardized actual operating time 656.

[0114] exist Figure 6 In the example shown, the standardized actual operating times 651 to 654 and 656 are smaller than 0. Therefore, it can be seen that the first actual operating times 601 to 604 and 606 tend to be shorter compared to the actual operating times of all dryers 10 operating under the same actual operating conditions. Furthermore, the standardized actual operating time 655 is larger than 0, therefore, it can be seen that the first actual operating time 605 tends to be longer compared to the actual operating times of all dryers 10 operating under the same actual operating conditions.

[0115] Back to Figure 5 Continuing with the description of server device 20.

[0116] Standardization 230 is implemented, for example, by executing a program stored in the memory of the server device 20 through a processor of the server device 20.

[0117] The representative value calculation unit 235 calculates the representative value of the standardization actual operating time calculated by the standardization unit 230.

[0118] Here, the representative value of the standardized actual operating time calculated by the representative value calculation unit 235 is explained as the average value of the standardized actual operating time. That is, the representative value calculation unit 235 calculates the average value of the standardized actual operating time calculated by the standardization unit 230. However, the representative value of the standardized actual operating time calculated by the representative value calculation unit 235 does not necessarily have to be limited to the average value of the standardized actual operating time. For example, the representative value of the standardized actual operating time calculated by the representative value calculation unit 235 can be the maximum value, the minimum value, the median, or the mode of the standardized actual operating time.

[0119] The average value of the standardized actual operating time calculated by the representative value calculation unit 235 reflects the long-term or short-term trend of the actual operating time under all actual operating conditions of the operation carried out by the first dryer 10 in the past specified period.

[0120] The representative value calculation unit 235 is implemented, for example, by executing a program stored in the memory of the server device 20 through a processor of the server device 20.

[0121] The learned model 245 is a machine learning model pre-trained to output operation end time information in the case of input operating conditions, sensed information, and the average of standardized actual operating time. The operation end time information relates to the end time of the operation that started under the aforementioned operating conditions. Here, the operation end time information is explained as the remaining drying time until the end of the operation that was started by that operation.

[0122] The learned model 245 is implemented, for example, by a neural network built on the server device 20 by executing a program stored in the memory of the server device 20 through a processor of the server device 20.

[0123] The learned model 245 is created, for example, by using the average of operating conditions, sensing information and standardized actual operating time as input data, and the remaining drying time pre-made based on measured values ​​obtained from the actual operation of the dryer 10 as positive solution data, and training the machine learning model.

[0124] The prediction unit 240 obtains the operation end time information output from the learned model 245 by inputting the operation conditions obtained by the operation condition acquisition unit 215, the sensing information obtained by the sensing information acquisition unit 210, and the average value calculated by the representative value calculation unit 235 into the learned model 245. More specifically, whenever the sensing information is obtained by the sensing information acquisition unit 210, the prediction unit 240 inputs the operation conditions, the sensing information, and the average value into the learned model 245 to obtain the operation end time information output from the learned model 245.

[0125] Furthermore, whenever the end-of-operation time information is obtained, the prediction unit 240 calculates first information indicating the remaining drying time of the operation of the first dryer 10 for drying clothes, etc., based on the obtained end-of-operation time information.

[0126] The prediction unit 240 is implemented, for example, by executing a program stored in the memory of the server device 20 through a processor of the server device 20.

[0127] The output unit 250 outputs the first information calculated by the prediction unit 240 to the first dryer 10 and the smartphone 30 associated with the first dryer 10 via the communication unit 200. More specifically, whenever the prediction unit 240 calculates the first information, the output unit 250 sends the first information to the first dryer 10 and the smartphone 30 associated with the first dryer 10 via the communication unit 200.

[0128] The output unit 250 is implemented, for example, by executing a program stored in the memory of the server device 20 through a processor of the server device 20.

[0129] Figure 7 This is a block diagram illustrating an example of the configuration of a smartphone 30.

[0130] The smartphone 30 is connected to the network 40 and associated with at least one of the multiple dryers 10, and has the function of displaying information sent from the server device 20.

[0131] like Figure 7 As shown, the smartphone 30 includes a communication unit 300, an acquisition unit 310, and a display unit 320.

[0132] The communication unit 300 is connected to the network 40 and communicates with external devices connected to the network 40 via the network 40. The external devices include multiple dryers 10 and server devices 20.

[0133] The communication unit 300, for example, has an input / output interface (not shown), and is implemented by executing a program stored in the memory (not shown) of the smartphone 30 through the processor (not shown) of the smartphone 30 and controlling the input / output interface.

[0134] The acquisition unit 310 obtains the first information from the server device 20 via the communication unit 300. More specifically, whenever the first information is sent from the server device 20, the acquisition unit 310 obtains the first information.

[0135] The acquisition unit 310 is implemented, for example, by executing a program stored in the memory of the smartphone 30 through the processor of the smartphone 30.

[0136] The display unit 320 displays the first information acquired by the acquisition unit 310. More specifically, whenever the acquisition unit 310 acquires the first information, the display unit 320 displays the remaining drying time indicated by the first information.

[0137] The display unit 320 includes, for example, a touchpad (not shown), which is implemented by executing a program stored in the memory of the smartphone 30 through the processor of the smartphone 30 and controlling the touchpad.

[0138] [2. Action]

[0139] The following describes the operation of the drying time prediction system 1 constructed as described above.

[0140] The drying time prediction system 1 performs a drying time prediction process, which predicts the drying time of the first dryer 10 during the drying operation that dries the clothes and other items that have been put in.

[0141] Figure 8 This is a flowchart of the drying time prediction process.

[0142] The drying time prediction process is initiated by starting the drying operation in the first dryer 10.

[0143] When drying operation begins in the first dryer 10, the supply unit 160 of the first dryer 10 provides the operating conditions received by the input receiving unit 110 of the first dryer 10 to the server device 20. Then, the operating condition acquisition unit 215 acquires the operating conditions (step S5).

[0144] When the operating condition acquisition unit 215 acquires the operating conditions, the first actual operating time acquisition unit 220 investigates whether there are any first actual operating conditions and first actual operating times that are correlated and obtained through the operation of the first dryer 10 during a specified period in the past among the actual operating conditions and actual operating times stored in the past data accumulation unit 205 (step S10).

[0145] If there are matching first actual operating conditions and first actual operating time in the processing of step S10 (step S10: Yes), the drying time prediction system 1 performs a standardization process on each first actual operating time, which standardizes the first actual operating time based on the distribution of the second actual operating time that is associated with the second actual operating conditions. The second actual operating conditions are consistent with the first actual operating conditions that are associated with the first actual operating time (step S15).

[0146] Figure 9 It is a flowchart for standardized processing.

[0147] When standardization processing begins, the first actual operating time acquisition unit 220 acquires, from the interrelated actual operating conditions and actual operating times stored in the past data accumulation unit 205, the first actual operating conditions and first actual operating times obtained through the operation of the first dryer 10 over a specified period, which are interrelated (step S110). Furthermore, the second actual operating time acquisition unit 225 acquires, from the interrelated actual operating conditions and actual operating times stored in the past data accumulation unit 205, the second actual operating conditions and second actual operating times obtained through the operation of one or more second dryers 10 over a specified period, which are interrelated.

[0148] If the process in step S110 ends, or if there is an unselected first actual operating time in the process in step S170 (step S170: Yes), the first actual operating time acquisition unit 220 selects one unselected first actual operating time (step S120). Here, the unselected first actual operating time refers to the first actual operating time that has not yet been selected in the loop process formed by the processes in steps S120 to S170 where "Yes" is indicated among the first actual operating times obtained through the process in step S110.

[0149] When one unselected first actual operating time is selected, the standardization department 230 investigates among the second actual operating times obtained by the second actual operating time acquisition department 225 whether there is a second actual operating time that is associated with the second actual operating condition, and the second actual operating condition is consistent with the first actual operating condition that is associated with the unselected first actual operating time (step S130).

[0150] In the process of step S130, if there is a matching second actual operating time (step S130: Yes), the standardization unit 230 obtains the matching second actual operating time (step S140), and standardizes one of the selected first actual operating times based on the distribution of the matching second actual operating times, thereby calculating the standardized actual operating time (step S150).

[0151] In the process of step S130, if there is no matching second actual operating time (step S130: No), the standardization unit 230 calculates the preset default value as the standardized actual operating time (step S160).

[0152] If the processing in step S150 or step S160 is completed, the first actual operating time acquisition unit 220 investigates whether there is an unselected first actual operating time (step S170).

[0153] In the process of step S170, if there is an unselected first actual operating time (step S170: Yes), the drying time prediction system 1 proceeds to the process of step S120.

[0154] In the process of step S170, if there is no unselected first actual operating time (step S170: No), the drying time prediction system 1 ends the standardization process.

[0155] Back to Figure 8 Explanation of the continued drying time prediction process.

[0156] When the standardization process is completed, the representative value calculation unit 235 calculates the average value of the actual standardization operation time calculated in the standardization process (step S20).

[0157] In the process of step S10, if there is no matching first actual operating condition and first actual operating time (step S10: No), the representative value calculation unit 235 calculates the preset default value as the average value (step S25).

[0158] If the processing in step S20 ends or the processing in step S25 ends, the sensing information acquisition unit 210 investigates whether sensing information has been provided from the supply unit 160 of the first dryer 10 (step S30).

[0159] In the process of step S30, if no sensing information is provided (step S30: No), the sensing information acquisition unit 210 stands by until sensing information is provided (step S30: No is repeated).

[0160] In the process of step S30, if sensing information is provided (step S30: Yes), or in the process of step S60 described later, if new sensing information is provided (step S60: Yes), the sensing information acquisition unit 210 acquires the sensing information (step S35).

[0161] When the sensing information acquisition unit 210 acquires sensing information, the prediction unit 240 inputs the operating conditions obtained through the processing in step S5, the average value calculated through the processing in step S20, and the sensing information obtained through the processing in step S35 into the learned model 245 (step S40), and acquires the operation end time information output from the learned model 245 (step S45).

[0162] Upon obtaining the operation end time information, the prediction unit 240 calculates first information based on the obtained operation end time information. This first information indicates the remaining drying time for the operation of drying clothes, etc., performed by the first dryer 10. Furthermore, the output unit 250 outputs the first information indicating the remaining drying time to the first dryer 10 and the smartphone 30 associated with the first dryer 10 (step S50).

[0163] When the output unit 250 outputs the first information, the acquisition unit 170 of the first dryer 10 acquires the first information, and the display unit 180 of the first dryer 10 displays the remaining drying time indicated by the first information (step S55). Furthermore, the acquisition unit 310 of the smartphone 30 associated with the first dryer 10 acquires the first information, and the display unit 320 of the smartphone 30 associated with the first dryer 10 displays the remaining drying time indicated by the first information.

[0164] On the other hand, the sensing information acquisition unit 210 investigates whether new sensing information has been provided from the supply unit 160 of the first dryer 10 (step S60).

[0165] In the process of step S60, if no new sensing information is provided (step S60: No), the sensing information acquisition unit 210 will stand by until new sensing information is provided as long as the operation of the first dryer 10 has not ended (step S65: No). (Steps S60: No and S65: No are repeated).

[0166] In the process of step S60, if new sensing information is provided (step S60: Yes), the drying time prediction system 1 proceeds to the process of step S35.

[0167] If the operation of the first dryer 10 ends during the standby period until new sensing information is provided (step S65: Yes), the drying time prediction system 1 ends the drying time prediction process.

[0168] [3. Site Visit]

[0169] like Figure 6 As shown in the upper graph, the operation of the first dryer 10 over the past specified period was typically carried out under various actual operating conditions. Furthermore, the actual operating time starting under different actual operating conditions usually varies. Therefore, simply calculating the average of the actual operating time of the first dryer 10 over the past specified period does not adequately reflect any tendency for the first dryer 10 to operate for an extended or shortened period.

[0170] In addition, such as Figure 6 As shown in the upper graph, the number of times the first dryer 10 was operated under a single actual operating condition during a specified period is generally limited, so it is possible that no statistically valid number of operations were performed. Therefore, simply calculating the average actual operating time of the first dryer 10 under a single actual operating condition during a specified period may not adequately reflect the tendency of the first dryer 10 to operate for a longer or shorter period during that period in the average value.

[0171] In contrast, according to the drying time prediction system 1 constructed above, as described above, the average value of the standardized actual operating time calculated by the representative value calculation unit 235 reflects the long-term trend or the shortening trend of the actual operating time under all actual operating conditions of the operation of the first dryer 10 during the past specified period.

[0172] Therefore, the drying time prediction system 1 can predict drying time with better accuracy than before.

[0173] (Replenish)

[0174] The above describes a drying time prediction system based on an embodiment of the present disclosure, but the present disclosure is not limited to this embodiment. As long as it does not depart from the spirit of the present disclosure, various modifications that can be conceived by those skilled in the art, or forms constructed by combining the constituent elements of different embodiments, may also be included within the scope of one or more forms of the present disclosure.

[0175] (1) In this embodiment, the server device 20 is described with a prediction unit 240. However, it is not necessary to limit the configuration of the server device 20 with a prediction unit 240 as long as the same function as the drying time prediction system 1 can be achieved. For example, the prediction unit 240 may be a configuration provided by one of the multiple dryers 10, or it may be a configuration provided by one of the multiple smartphones 30.

[0176] Similarly, as long as the same function as the drying time prediction system 1 can be achieved, at least a portion of the components of the server device 20 can be the structure of at least one of the multiple dryers 10, or the structure of at least one of the multiple smartphones 30. Furthermore, at least a portion of the components of the dryer 10 can be the structure of the server device 20, or the structure of at least one of the multiple smartphones 30. Similarly, at least a portion of the components of the smartphone 30 can be the structure of the server device 20, or the structure of at least one of the multiple dryers 10.

[0177] (2) In the embodiment, it was described that multiple dryers 10 were included in the drying time prediction system 1. In contrast, as another configuration example, it is also possible to consider a configuration in which the multiple dryers 10 are external devices of the drying time prediction system 1. In this case, the multiple dryers 10 respectively provide the drying time prediction system 1 with the operating conditions received by the input receiving unit 110, the actual operating conditions and actual operating time that are linked together and stored in the past data accumulation unit 140, and the sensing information obtained by the sensing unit 150, and obtain first information indicating the remaining drying time from the drying time prediction system 1.

[0178] (3) In the embodiment, it was described with multiple smartphones 30 included in the drying time prediction system 1. However, it is not necessary to limit the example to the case where multiple smartphones 30 are a necessary component of the drying time prediction system 1. As another configuration example, a configuration in which multiple smartphones 30 are not included in the drying time prediction system 1 can also be considered.

[0179] (4) In this embodiment, the learned model 245 is described as a machine learning model pre-trained as follows: given the input operating conditions, sensing information, and the average of the standardized actual operating time, it outputs operating end time information relating to the end time of the operation that began under the aforementioned operating conditions. Alternatively, as another configuration example, the learned model 245 can be configured as a machine learning model pre-trained as follows: given the input operating conditions, sensing information, and the standardized actual operating time, it outputs operating end time information relating to the end time of the operation that began under the aforementioned operating conditions. In this case, the prediction unit 240 obtains the operating end time information output from the learned model 245 by inputting the operating conditions obtained by the operating condition acquisition unit 215, the sensing information obtained by the sensing information acquisition unit 210, and the standardized actual operating time calculated by the standardization unit 230 into the learned model 245. Furthermore, as another possible configuration, the learned model 245 can be configured as a pre-trained machine learning model that, given the input operating conditions and standardized actual operating time, outputs operating end time information relating to the end time of the operation that began under the aforementioned operating conditions. In this case, the prediction unit 240 obtains the operating end time information output from the learned model 245 by inputting the operating conditions obtained by the operating condition acquisition unit 215 and the standardized actual operating time calculated by the standardization unit 230 into the learned model 245.

[0180] (5) In this embodiment, the prediction unit 240 has been described with one learned model 245. However, as another configuration example, it is also possible to consider a configuration in which the prediction unit 240 has multiple learned models 245. For example, the prediction unit 240 may also have multiple learned models 245 pre-trained based on the elapsed time since the start of operation in the dryer 10. In this case, the prediction unit 240 selects the learned model 245 from the multiple learned models 245 that corresponds to the elapsed time since the start of operation in the first dryer 10, and inputs the operating conditions obtained by the operating condition acquisition unit 215, the sensing information obtained by the sensing information acquisition unit 210, and the average value calculated by the representative value calculation unit 235 into the selected learned model 245, thereby obtaining the operation end time information output from the learned model 245.

[0181] (6) This disclosure can be implemented not only as a system or apparatus, but also as a method comprising a processing mechanism constituting a system or apparatus, or as a program for causing a computer to execute these steps, or as a recording medium such as a computer-readable CD-ROM containing the program, or as information, data, or signals representing the program. Furthermore, these programs, information, data, and signals can also be distributed via communication networks such as the Internet.

[0182] Industrial availability

[0183] This disclosure can be widely used in systems, apparatuses, etc., for predicting drying time.

[0184] Label Explanation

[0185] 1. Drying time prediction system; 10, 10A, 10B, 10M dryers; 20. Server device; 30, 30A, 30B, 30N smartphones; 40. Network; 100, 200, 300. Communication unit; 110. Input receiving unit; 120. Operation control unit; 130. Drying unit; 140, 205. Past data accumulation unit; 150. Sensing unit; 160. Providing unit; 170, 310. Acquisition unit; 180, 320. Display unit; 210. Sensing information acquisition unit; 215 Operating condition acquisition unit; 220 First actual operating time acquisition unit; 225 Second actual operating time acquisition unit; 230 Standardization unit; 235 Representative value calculation unit; 240 Prediction unit; 245 Learned model; 250 Output unit; 601, 602, 603, 604, 605, 606 First actual operating time; 651, 652, 653, 654, 655, 656 Standardized actual operating time.

Claims

1. A method for predicting drying time, characterized in that, Obtain the operating conditions when the first dryer starts operating. Obtain sensing information regarding the operational status of the first dryer as described above. For each of the first operations performed by the aforementioned first dryer more than once in the past, the first actual operating time of that first operation is obtained. The system obtains operation end time information output from the learned model by inputting the aforementioned operating conditions, the first actual information based on the aforementioned first actual operating time, and the aforementioned sensing information. This operation end time information pertains to the end time of the operation resulting from the start of the aforementioned operation. and then, For each of the aforementioned first operations (more than one), the first actual operating conditions at the start of that first operation are correlated with the aforementioned first actual operating time to obtain the result. For one or more previous second operations of a second dryer, obtain the second actual operating time of that second operation and the second actual operating conditions at the start of that second operation that are associated with that second actual operating time. To reflect the long-term or short-term trend of actual operating time under all past operating conditions of the first dryer, for each of the first actual operating times, the first actual operating time is standardized based on the distribution of the second actual operating times associated with the second actual operating conditions. The standardized actual operating time is then calculated, where the second actual operating conditions are consistent with the first actual operating conditions associated with the first actual operating time. The aforementioned first actual information is based on the standardized actual operating time calculated for each of the aforementioned first actual operating times. Output the first piece of information based on the above operation end time information.

2. The drying time prediction method as described in claim 1, characterized in that, The average of the standardized actual operating times for each of the aforementioned first actual operating times is also calculated. The first piece of actual information mentioned above is based on the average value mentioned above.

3. The drying time prediction method as described in claim 1, characterized in that, The aforementioned first operation refers to the operation performed by the aforementioned first dryer during the previously specified period. The aforementioned second operation refers to the operation performed by one or more of the aforementioned second dryers during the period specified above.

4. The drying time prediction method as described in claim 1, characterized in that, The aforementioned operating conditions and the aforementioned first actual operating conditions include: the amount of feed material set by the user of the first dryer and the operating mode of the first dryer. The aforementioned second actual operating conditions include: the amount of feed material to be put into the aforementioned one or more second dryers set by the users of each of the aforementioned one or more second dryers, and the operating mode of the aforementioned one or more second dryers.

5. The drying time prediction method as described in claim 1, characterized in that, The first dryer mentioned above and the one or more second dryers mentioned above are the same type of machine.

6. A drying time prediction system, characterized in that, have: The operating conditions acquisition unit acquires the operating conditions at the start of operation of the first dryer. The sensing information acquisition unit acquires sensing information about the state of the first dryer during operation as described above. The first actual operating time acquisition unit acquires the first actual operating time of each of the first operations performed by the first dryer more than once in the past. The learned model, given the aforementioned operating conditions, the first actual information based on the first actual operating time, and the aforementioned sensing information, outputs operating end time information relating to the end time of the operation resulting from the start of the operation; and The output unit outputs the first piece of information based on the aforementioned operation end time information. The aforementioned first actual operating time acquisition unit then, for each of the aforementioned one or more first operations, establishes a correlation between the first actual operating conditions at the start of that first operation and the aforementioned first actual operating time. The above-mentioned drying time prediction system also has the following features: The second actual operating time acquisition unit acquires the second actual operating time of each of the more than one second operations performed in the past by the second dryer, and the second actual operating conditions at the start of the second operation that are associated with the second actual operating time. as well as In order to reflect the long-term or shortening trend of actual operating time under all actual operating conditions in the past operation of the aforementioned first dryer, the standardization department standardizes each of the aforementioned first actual operating times based on the distribution of the aforementioned second actual operating times that are associated with the aforementioned second actual operating conditions, thereby calculating the standardized actual operating time, wherein the aforementioned second actual operating conditions are consistent with the aforementioned first actual operating conditions that are associated with the first actual operating time. The aforementioned first actual information is based on the standardized actual operating time calculated for the aforementioned first actual operating time.

7. A dryer, specifically the first dryer described above using the drying time prediction system of claim 6. have: The supply department provides the aforementioned operating conditions and the aforementioned first actual operating time to the aforementioned drying time prediction system; The acquisition unit obtains the first information from the aforementioned drying time prediction system; and The display unit displays information related to the first piece of information mentioned above.

Images