Remaining amount prediction system and remaining amount prediction program

Abstract

To provide a remaining amount prediction system and a remaining amount prediction program capable of reducing the time required for predicting a date on which the amount of remaining consumable goods falls below a predetermined amount.SOLUTION: A remaining amount prediction system includes a remaining amount prediction unit which predicts an empty date on which toner level falls to 0%, using a plurality of machine learning models configured to predict a remaining amount of toner used in an image forming apparatus, in S124, S127 or S130. The machine learning models are configured to predict toner level on a date specific days after the latest date, out of dates corresponding to each toner level for a day and toner levels higher than that, as a basis for explanatory variable which is to be input to the machine learning models. Each of the machine learning models uses the number of specific days different from those used in all the other machine learning models, and uses the number of specific days different by one from any of the other machine learning models. The remaining amount prediction unit is configured to generate (S121 and S131) common explanatory variable for the machine learning models.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present invention relates to a remaining amount prediction system and a remaining amount prediction program for predicting the remaining amount of consumables used in electronic devices. [Background technology]

[0002] BACKGROUND ART Conventionally, there is known a remaining amount prediction system that predicts the remaining amount of a consumable item used in an electronic device using a machine learning model that predicts the remaining amount of the consumable item (see, for example, Patent Document 1).

[0003] For example, in a conventional remaining amount prediction system, when a machine learning model is used to predict the remaining amount of toner one day after the latest date among dates corresponding to one or more days' worth of remaining amounts of consumables that form the basis of explanatory variables input into the machine learning model, when predicting the date on which the remaining amount of a consumable will fall below a specific amount, the remaining amount of the consumable one day after the latest date indicated in the actual measurement value data can be predicted by first inputting explanatory variables into the machine learning model that are generated based on the daily remaining amounts of the consumables indicated in actual measurement value data that indicate actual measurements of the remaining amounts of the consumables in an electronic device once a day. Next, the remaining amount of the consumable two days after the latest date indicated in the actual measurement value data can be predicted by inputting explanatory variables into the machine learning model that are generated based on the daily remaining amounts of the consumables indicated in the actual measurement value data and the already predicted remaining amounts of the consumables one day after the latest date indicated in the actual measurement value data. Next, by inputting explanatory variables generated based on the daily remaining amount of the consumable indicated in the actual measurement data and the previously predicted remaining amounts of the consumable one day and two days after the latest date indicated in the actual measurement data into a machine learning model, it is possible to predict the remaining amount of the consumable three days after the latest date indicated in the actual measurement data. By repeating the above-described operations, it is possible to predict the day on which the remaining amount of the consumable will be equal to or less than a specific amount. Therefore, in conventional remaining amount prediction systems, when predicting the day on which the remaining amount of the consumable will be equal to or less than a specific amount, if the date X days after the latest date indicated in the actual measurement data is the day on which the remaining amount of the consumable will be equal to or less than the specific amount, it is necessary to execute the process of generating explanatory variables to be input into the machine learning model X times. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2020-151879 Summary of the Invention [Problem to be solved by the invention]

[0005] However, in conventional remaining quantity prediction systems, when predicting the day when the remaining quantity of a consumable will fall below a specific amount, if there are many days between the latest date shown in the actual measurement data and the predicted day when the remaining quantity of the consumable will fall below a specific amount, the number of times the process to generate the explanatory variables to be input into the machine learning model must be executed increases, resulting in a problem in that it takes a long time to predict the day when the remaining quantity of the consumable will fall below a specific amount.

[0006] Therefore, an object of the present invention is to provide a remaining quantity prediction system and a remaining quantity prediction program that can reduce the time required to predict the day when the remaining quantity of a consumable item will fall below a specific amount. [Means for solving the problem]

[0007] The remaining quantity prediction system of the present invention includes a remaining quantity prediction unit that uses multiple machine learning models to predict the remaining quantities of consumables used in electronic devices and predicts the date on which the remaining quantity of the consumables will fall below a specific amount, wherein the machine learning models predict the remaining quantity of the consumables a specific number of days after the latest date among dates corresponding to one or more days' worth of remaining quantities of the consumables that form the basis of explanatory variables input to the machine learning models, and among the multiple machine learning models, each machine learning model has a different specific number of days from all other machine learning models and differs by one day from any of the other machine learning models, and the remaining quantity prediction unit generates the explanatory variables that are common to the multiple machine learning models.

[0008] With this configuration, when the remaining quantity prediction system of the present invention predicts the day when the remaining quantity of a consumable will fall below a specific amount using multiple machine learning models that predict the remaining quantity of a consumable on different dates when the same explanatory variables are input, it generates common explanatory variables for the multiple machine learning models, thereby reducing the number of times the process of generating explanatory variables to be input into the machine learning models is executed, and as a result, the time required to predict the day when the remaining quantity of a consumable will fall below a specific amount can be shortened.

[0009] The remaining quantity prediction program of the present invention causes a computer to implement a remaining quantity prediction unit that uses multiple machine learning models to predict the remaining quantities of consumables used in electronic devices and predicts the date on which the remaining quantity of the consumables will fall below a specific amount, wherein the machine learning models predict the remaining quantity of the consumables a specific number of days after the latest date among dates corresponding to one or more days' worth of remaining quantities of the consumables that form the basis of explanatory variables input to the machine learning models, and among the multiple machine learning models, each machine learning model has a different number of specific days from all other machine learning models and differs by one day from any of the other machine learning models, and the remaining quantity prediction unit generates the explanatory variables that are common to the multiple machine learning models.

[0010] With this configuration, when a computer executing the remaining quantity prediction program of the present invention predicts the day when the remaining quantity of a consumable will fall below a specific amount using multiple machine learning models that predict the remaining quantity of a consumable on different dates when the same explanatory variables are input, the computer generates common explanatory variables for the multiple machine learning models, thereby reducing the number of times the process of generating explanatory variables to be input into the machine learning models is executed, and as a result, the time required to predict the day when the remaining quantity of a consumable will fall below a specific amount can be shortened. [Effects of the Invention]

[0011] The remaining amount prediction system and remaining amount prediction program of the present invention can reduce the time required to predict the day when the remaining amount of a consumable item will fall below a specific amount. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a block diagram of a system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a block diagram of the remaining amount prediction system shown in FIG. 1 when configured by one computer. [Figure 3] 3 is a diagram showing an example of the remaining amount of toner for each day indicated in the actual measurement value data shown in FIG. 2. FIG. [Figure 4]FIG. 2 is a block diagram of the image forming apparatus shown in FIG. 1 when it is an MFP. [Figure 5] 2 is a sequence diagram of the operation of the system shown in FIG. 1 when the remaining amount prediction system records the actual measured value of the remaining amount of toner in the image forming apparatus. [Figure 6] 3 is a flowchart of the operation of the remaining amount prediction system shown in FIG. 2 when predicting the toner empty date of the image forming apparatus. [Figure 7] (a) is a diagram showing an example of the remaining amount of toner for each day shown in the actual measurement value data shown in Fig. 2 and the predicted remaining amount of toner for one day after the latest date shown in the actual measurement value data. (b) is a diagram showing an example of the remaining amount of toner for each day shown in the actual measurement value data shown in Fig. 2 and the predicted remaining amount of toner for each day up to two days after the latest date shown in the actual measurement value data. (c) is a diagram showing an example of the remaining amount of toner for each day shown in the actual measurement value data shown in Fig. 2 and the predicted remaining amount of toner for each day up to three days after the latest date shown in the actual measurement value data. [Figure 8] (a) is a diagram showing an example of the remaining toner amount for each day shown in the actual measurement value data shown in Fig. 2 and the predicted remaining toner amount for each day up to four days after the latest date shown in the actual measurement value data. (b) is a diagram showing an example of the remaining toner amount for each day shown in the actual measurement value data shown in Fig. 2 and the predicted remaining toner amount for each day up to five days after the latest date shown in the actual measurement value data. (c) is a diagram showing an example of the remaining toner amount for each day shown in the actual measurement value data shown in Fig. 2 and the predicted remaining toner amount for each day up to six days after the latest date shown in the actual measurement value data. [Figure 9] This figure shows an example of a target variable and the remaining amount of toner for one day or more that serves as the basis for the explanatory variables in the training data for generating the remaining amount prediction model after one day, the remaining amount prediction model after two days, and the remaining amount prediction model after three days shown in Figure 2. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0014] First, the configuration of a system according to an embodiment of the present invention will be described.

[0015] FIG. 1 is a block diagram of a system 10 according to the present embodiment.

[0016] As shown in Fig. 1, system 10 includes a remaining amount prediction system 20 that predicts the remaining amount of toner, which is a consumable item used in an image forming apparatus, which is an electronic device. Remaining amount prediction system 20 may be configured with a single computer such as a PC (Personal Computer), or may be configured with multiple computers. Remaining amount prediction system 20 may also be configured on the cloud.

[0017] The system 10 includes an image forming device 30, such as an MFP (Multifunction Peripheral) or a dedicated printer. The system 10 can include at least one other image forming device in addition to the image forming device 30 that has the same configuration as the image forming device 30.

[0018] The remaining amount prediction system 20 and the image forming apparatus can communicate with each other via a network 11 such as a LAN (Local Area Network) or the Internet.

[0019] FIG. 2 is a block diagram of a remaining amount prediction system 20 configured by one computer.

[0020] As shown in Figure 2, the remaining amount prediction system 20 includes an operation unit 21, which is an operation device such as a keyboard or mouse through which various operations are input; a display unit 22, which is a display device such as an LCD (Liquid Crystal Display) that displays various information; a communication unit 23, which is a communication device that communicates with external devices via a network such as a LAN or the Internet, or directly via a wired or wireless connection without using a network; a memory unit 24, which is a non-volatile memory device such as a semiconductor memory or an HDD (Hard Disk Drive) that stores various information; and a control unit 25 that controls the entire remaining amount prediction system 20.

[0021] The storage unit 24 can store a remaining amount prediction program 24a for predicting the remaining amount of toner in the image forming apparatus 30. The remaining amount prediction program 24a may be installed in the remaining amount prediction system 20 during the manufacturing stage of the remaining amount prediction system 20, or may be additionally installed in the remaining amount prediction system 20 from an external storage medium such as a USB (Universal Serial Bus) memory, or may be additionally installed in the remaining amount prediction system 20 from a network.

[0022] The memory unit 24 can store a one-day remaining amount prediction model 24b as a machine learning model that predicts the remaining toner amount one day after a base latest date, which is the latest date among dates corresponding to one or more days' worth of remaining toner amounts that serve as the basis for the explanatory variables input to the machine learning models; a two-day remaining amount prediction model 24c as a machine learning model that predicts the remaining toner amount two days after the base latest date; and a three-day remaining amount prediction model 24d as a machine learning model that predicts the remaining toner amount three days after the base latest date. The one-day remaining amount prediction model 24b, the two-day remaining amount prediction model 24c, and the three-day remaining amount prediction model 24d are machine learning models that can use common explanatory variables. The explanatory variables of the one-day remaining amount prediction model 24b, the two-day remaining amount prediction model 24c, and the three-day remaining amount prediction model 24d may include the remaining toner amount itself on a specific day, such as the remaining toner amount on the base latest date, the remaining toner amount one day before the base latest date, or the remaining toner amount two days before the base latest date. In addition, the explanatory variables of the one-day remaining amount prediction model 24b, the two-day remaining amount prediction model 24c, and the three-day remaining amount prediction model 24d may include a specific value calculated based on the remaining amount of toner on a specific day, such as the average value of the remaining amount of toner on the most recent base date, the remaining amount of toner one day before the most recent base date, and the remaining amount of toner two days before the most recent base date.

[0023] The storage unit 24 can store actual measurement value data 24e indicating the actual daily measurement value of the remaining amount of toner in the image forming device 30. Similarly, the storage unit 24 can store actual measurement value data indicating the actual daily measurement value of the remaining amount of toner in the image forming device for each image forming device.

[0024] FIG. 3 is a diagram showing an example of the remaining amount of toner for each day indicated in the actual measurement data 24e.

[0025] As shown in Fig. 3, the actual measurement data 24e shows the date and the actual measurement value of the remaining amount of toner for each day. In the example shown in Fig. 3, the actual measurement values ​​of the remaining amount of toner for eight days from January 1 to January 8 are shown. The remaining amount of toner is expressed as a percentage indicated by an integer between 100 and 0.

[0026] 2 includes, for example, a CPU (Central Processing Unit), a ROM (Read Only Memory) that stores programs and various data, and a RAM (Random Access Memory) that serves as a memory used as a work area for the CPU of the control unit 25. The CPU of the control unit 25 executes programs stored in the storage unit 24 or the ROM of the control unit 25.

[0027] By executing the remaining amount prediction program 24a, the control unit 25 realizes the remaining amount prediction unit 25a that predicts the remaining amount of toner using the one-day remaining amount prediction model 24b, the two-day remaining amount prediction model 24c, and the three-day remaining amount prediction model 24d.

[0028] FIG. 4 is a block diagram of the image forming apparatus 30 in the case of an MFP.

[0029] As shown in FIG. 4, the image forming apparatus 30 includes an operation unit 31, which is an operation device such as a button through which various operations are input; a display unit 32, which is a display device such as an LCD that displays various information; a printer 33, which is a printing device that prints images on a recording medium such as paper; a remaining amount sensor 34 that detects the amount of toner remaining in a toner container that stores toner consumed by the printer 33; a scanner 35, which is a reading device that reads images from a document; a communication unit 36, which is a communication device that communicates with an external device via a network such as a LAN or the Internet, or directly via a wired or wireless connection without using a network; a memory unit 37, which is a non-volatile memory device such as a semiconductor memory or HDD that stores various information; and a control unit 38 that controls the entire image forming apparatus 30.

[0030] The printer 33 has a replaceable toner container.

[0031] The remaining amount of toner detected by the remaining amount sensor 34 becomes 100% when a used toner container in the image forming apparatus 30 is replaced with a new toner container.

[0032] Control unit 38 includes, for example, a CPU, a ROM that stores programs and various data, and a RAM as memory used as a work area for the CPU of control unit 38. The CPU of control unit 38 executes programs stored in storage unit 37 or the ROM of control unit 38.

[0033] The operation of the system 10 will now be described.

[0034] First, the operation of the remaining amount prediction system 20 when recording the actual measured value of the remaining amount of toner in the image forming device 30 will be described.

[0035] FIG. 5 is a sequence diagram of the operation of the remaining amount prediction system 20 when the remaining amount prediction system 20 records the actual measured value of the remaining amount of toner in the image forming device 30. In FIG.

[0036] As shown in FIG. 5, the image forming device 30 transmits the actual measured value of the remaining amount of toner each day to the remaining amount prediction system 20, for example, by transmitting the latest actual measured value of the remaining amount of toner detected by the remaining amount sensor 34 before the end of the previous day after the end of each day to the remaining amount prediction system 20 (S101).

[0037] When the actual measurement value of the remaining amount of toner is transmitted from the image forming device 30, the remaining amount prediction unit 25a of the remaining amount prediction system 20 records the transmitted actual measurement value in the actual measurement value data 24e of the image forming device 30 (S102).

[0038] The above describes the operation of the remaining amount prediction system 20 when recording the actual measured value of the remaining amount of toner in the image forming device 30, but the operation of the remaining amount prediction system 20 when recording the actual measured value of the remaining amount of toner in an image forming device other than the image forming device 30 is also similar.

[0039] Next, the operation of the remaining amount prediction system 20 when predicting an empty day when the remaining amount of toner in the image forming device 30 is 0%, that is, when the image forming device 30 is empty, will be described.

[0040] FIG. 6 is a flowchart of the operation of the remaining amount prediction system 20 when predicting the toner empty date of the image forming device 30.

[0041] As shown in FIG. 6, the remaining amount prediction unit 25a generates common explanatory variables for the one-day remaining amount prediction model 24b, the two-day remaining amount prediction model 24c, and the three-day remaining amount prediction model 24d based on the daily remaining toner amount indicated in the actual measurement value data 24e (S121).

[0042] When the processing of S121 is completed, the remaining amount prediction unit 25a inputs the explanatory variables generated just before into the one-day remaining amount prediction model 24b, thereby predicting the remaining amount of toner one day after the latest base date of the explanatory variables generated just before (S122).

[0043] Fig. 7(a) is a diagram showing an example of the remaining toner amount for each day indicated in the actual measurement value data 24e and the predicted remaining toner amount for one day after the latest date indicated in the actual measurement value data 24e. Fig. 7(b) is a diagram showing an example of the remaining toner amount for each day indicated in the actual measurement value data 24e and the predicted remaining toner amount for each day up to two days after the latest date indicated in the actual measurement value data 24e. Fig. 7(c) is a diagram showing an example of the remaining toner amount for each day indicated in the actual measurement value data 24e and the predicted remaining toner amount for each day up to three days after the latest date indicated in the actual measurement value data 24e.

[0044] If the remaining amount of toner from January 1st to January 8th shown in the actual measurement data 24e used in S121 is as shown in Figure 3, the remaining amount prediction unit 25a, in the first S122 of the operation shown in Figure 6, predicts the remaining amount of toner one day after January 8th, which is the latest base date of the explanatory variables generated in the previous S121, i.e., the remaining amount of toner on January 9th, as shown in Figure 7(a), for example.

[0045] As shown in FIG. 6, when the process of S122 is completed, the remaining amount predicting unit 25a determines whether the remaining amount of toner predicted in the immediately preceding S122 is 0% or less (S123).

[0046] If the remaining amount predicting unit 25a determines in S123 that the remaining amount of toner predicted in the previous S122 is 0% or less, it determines the date one day after the latest base date of the explanatory variable generated immediately before as the toner empty date (S124).

[0047] When the remaining amount prediction unit 25a determines in S123 that the remaining amount of toner predicted in the previous S122 is not 0% or less, it inputs the explanatory variables generated immediately before into the two-day remaining amount prediction model 24c, thereby predicting the remaining amount of toner two days after the latest base date of the explanatory variables generated immediately before (S125).

[0048] If the remaining amount of toner from January 1st to January 8th shown in the actual measurement data 24e used in S121 is as shown in Figure 3, the remaining amount prediction unit 25a, in the first S125 of the operation shown in Figure 6, predicts the remaining amount of toner two days after January 8th, which is the latest base date of the explanatory variables generated in the previous S121, i.e., the remaining amount of toner on January 10th, as shown in Figure 7(b), for example.

[0049] As shown in FIG. 6, when the process of S125 is completed, the remaining amount predicting unit 25a determines whether the remaining amount of toner predicted in the immediately preceding S125 is 0% or less (S126).

[0050] If the remaining amount predicting unit 25a determines in S126 that the remaining amount of toner predicted in the previous S125 is 0% or less, it determines the date two days after the latest base date of the explanatory variable generated immediately before as the toner empty date (S127).

[0051] If the remaining amount prediction unit 25a determines in S126 that the remaining amount of toner predicted in the previous S125 is not 0% or less, it inputs the explanatory variables generated immediately before into the three-day remaining amount prediction model 24d, thereby predicting the remaining amount of toner three days after the latest base date of the explanatory variables generated immediately before (S128).

[0052] If the remaining amount of toner from January 1st to January 8th shown in the actual measurement data 24e used in S121 is as shown in Figure 3, the remaining amount prediction unit 25a, in the first S128 of the operation shown in Figure 6, predicts the remaining amount of toner three days after January 8th, which is the latest base date of the explanatory variables generated in the previous S121, i.e., the remaining amount of toner on January 11th, as shown in Figure 7(c), for example.

[0053] As shown in FIG. 6, when the process of S128 is completed, the remaining amount predicting unit 25a determines whether the remaining amount of toner predicted in the immediately preceding S128 is 0% or less (S129).

[0054] If the remaining amount prediction unit 25a determines in S129 that the remaining amount of toner predicted in the previous S128 is 0% or less, it determines the date three days after the latest base date of the explanatory variable generated immediately before as the toner empty date (S130).

[0055] When the remaining amount prediction unit 25a determines in S129 that the remaining amount of toner predicted in the previous S128 is not 0% or less, it generates common explanatory variables for the 1-day remaining amount prediction model 24b, the 2-day remaining amount prediction model 24c, and the 3-day remaining amount prediction model 24d based on the daily remaining amount of toner shown in the actual measurement data 24e, the daily remaining amount of toner predicted in all S122 in the current operation shown in Figure 6, the daily remaining amount of toner predicted in all S125 in the current operation shown in Figure 6, and the daily remaining amount of toner predicted in all S128 in the current operation shown in Figure 6 (S131), and executes the processing of S122.

[0056] Fig. 8(a) is a diagram showing an example of the remaining toner amount for each day indicated in the actual measurement value data 24e and the predicted remaining toner amount for each day up to four days after the most recent date indicated in the actual measurement value data 24e. Fig. 8(b) is a diagram showing an example of the remaining toner amount for each day indicated in the actual measurement value data 24e and the predicted remaining toner amount for each day up to five days after the most recent date indicated in the actual measurement value data 24e. Fig. 8(c) is a diagram showing an example of the remaining toner amount for each day indicated in the actual measurement value data 24e and the predicted remaining toner amount for each day up to six days after the most recent date indicated in the actual measurement value data 24e.

[0057] If the remaining amount of toner from January 1st to January 8th shown in the actual measurement data 24e used in S121, the remaining amount of toner on January 9th predicted in the first S122 of the current operation shown in Figure 6, the remaining amount of toner on January 10th predicted in the first S125 of the current operation shown in Figure 6, and the remaining amount of toner on January 11th predicted in the first S128 of the current operation shown in Figure 6 are as shown in Figure 7(c), the remaining amount prediction unit 25a will predict, in the second S122 of the current operation shown in Figure 6, for example, as shown in Figure 8(a), the remaining amount of toner one day after January 11th, which is the latest base date of the explanatory variables generated in the previous S131, i.e., the remaining amount of toner on January 12th.

[0058] If the remaining amount of toner from January 1st to January 8th shown in the actual measurement data 24e used in S121, the remaining amount of toner on January 9th predicted in S122 for the first time in the current operation shown in Figure 6, the remaining amount of toner on January 10th predicted in S125 for the first time in the current operation shown in Figure 6, and the remaining amount of toner on January 11th predicted in S128 for the first time in the current operation shown in Figure 6 are as shown in Figure 7(c), the remaining amount prediction unit 25a will predict, in the second S125 of the current operation shown in Figure 6, for example, as shown in Figure 8(b), the remaining amount of toner two days after January 11th, which is the latest base date of the explanatory variables generated in the previous S131, i.e., the remaining amount of toner on January 13th.

[0059] If the remaining amount of toner from January 1st to January 8th shown in the actual measurement data 24e used in S121, the remaining amount of toner on January 9th predicted in the first S122 of the current operation shown in Figure 6, the remaining amount of toner on January 10th predicted in the first S125 of the current operation shown in Figure 6, and the remaining amount of toner on January 11th predicted in the first S128 of the current operation shown in Figure 6 are as shown in Figure 7(c), the remaining amount prediction unit 25a will predict, in the second S128 of the current operation shown in Figure 6, for example, as shown in Figure 8(c), the remaining amount of toner three days after January 11th, which is the latest base date of the explanatory variables generated in the previous S131, i.e., the remaining amount of toner on January 14th.

[0060] When the process of S124, S127, or S130 is completed, the remaining amount predicting unit 25a ends the operation shown in FIG.

[0061] Next, a method for generating the one-day remaining amount prediction model 24b, the two-day remaining amount prediction model 24c, and the three-day remaining amount prediction model 24d will be described.

[0062] For example, if the actual measurement data 24e shown in Figure 3 exists, the target variable and the remaining amount of toner for one day or more that forms the basis of the explanatory variables in the training data for generating the one-day remaining amount prediction model 24b, the two-day remaining amount prediction model 24c, and the three-day remaining amount prediction model 24d can be generated as shown in Figure 9, for example.

[0063] Figure 9 is a diagram showing an example of a target variable and a remaining amount of toner of one day or more that serves as the basis for the explanatory variables in training data for generating one-day remaining amount prediction model 24b, two-day remaining amount prediction model 24c, and three-day remaining amount prediction model 24d.

[0064] As shown in FIG. 9, the objective variable in the training data for one-day remaining amount prediction model 24b, in which 100, the remaining amount of toner on January 1st, is the only explanatory variable, is 99, the remaining amount of toner on January 2nd. The objective variable in the training data for two-day remaining amount prediction model 24c, in which 100, the remaining amount of toner on January 1st, is the only explanatory variable, is 98, the remaining amount of toner on January 3rd. The objective variable in the training data for three-day remaining amount prediction model 24d, in which 100, the remaining amount of toner on January 1st, is the only explanatory variable, is 97, the remaining amount of toner on January 4th.

[0065] The objective variable in the training data for one-day remaining amount prediction model 24b, in which the explanatory variables are 100 and 99, which are the remaining amounts of toner on January 1st and January 2nd, respectively, is 98, which is the remaining amount of toner on January 3rd. The objective variable in the training data for two-day remaining amount prediction model 24c, in which the explanatory variables are 100 and 99, which are the remaining amounts of toner on January 1st and January 2nd, respectively, is 97, which is the remaining amount of toner on January 4th. The objective variable in the training data for three-day remaining amount prediction model 24d, in which the explanatory variables are 100 and 99, which are the remaining amounts of toner on January 1st and January 2nd, respectively, is 96, which is the remaining amount of toner on January 5th.

[0066] The objective variable in the training data for one-day-later remaining amount prediction model 24b, whose explanatory variables are 100, 99, and 98, which are the remaining amounts of toner on January 1st, January 2nd, and January 3rd, respectively, is 97, which is the remaining amount of toner on January 4th. The objective variable in the training data for two-day-later remaining amount prediction model 24c, whose explanatory variables are 100, 99, and 98, which are the remaining amounts of toner on January 1st, January 2nd, and January 3rd, respectively, is 96, which is the remaining amount of toner on January 5th. The objective variable in the training data for three-day-later remaining amount prediction model 24d, whose explanatory variables are 100, 99, and 98, which are the remaining amounts of toner on January 1st, January 2nd, and January 3rd, respectively, is 95, which is the remaining amount of toner on January 6th.

[0067] The objective variable in the training data for one-day-later remaining amount prediction model 24b, whose explanatory variables are 100, 99, 98, and 97, which are the remaining amounts of toner on January 1st, January 2nd, January 3rd, and January 4th, respectively, is 96, which is the remaining amount of toner on January 5th. The objective variable in the training data for two-day-later remaining amount prediction model 24c, whose explanatory variables are 100, 99, 98, and 97, which are the remaining amounts of toner on January 1st, January 2nd, January 3rd, and January 4th, respectively, is 95, which is the remaining amount of toner on January 6th. The objective variable in the training data for three-day-later remaining amount prediction model 24d, whose explanatory variables are 100, 99, 98, and 97, which are the remaining amounts of toner on January 1st, January 2nd, January 3rd, and January 4th, respectively, is 94, which is the remaining amount of toner on January 7th.

[0068] The objective variable in the training data for one-day-later remaining amount prediction model 24b, in which the explanatory variables are 100, 99, 98, 97, and 96, which are the remaining amounts of toner on January 1st, January 2nd, January 3rd, January 4th, and January 5th, respectively, is the remaining amount of toner on January 6th, 95. The objective variable in the training data for two-day-later remaining amount prediction model 24c, in which the explanatory variables are 100, 99, 98, 97, and 96, which are the remaining amounts of toner on January 1st, January 2nd, January 3rd, January 4th, and January 5th, respectively, is 94, which is the remaining amount of toner on January 7th. The objective variable in the training data for the three-day remaining amount prediction model 24d, whose explanatory variables are 100, 99, 98, 97, and 96, which are the remaining toner amounts on January 1st, January 2nd, January 3rd, January 4th, and January 5th, respectively, is 93, which is the remaining toner amount on January 8th.

[0069] The objective variable in the training data for one-day-later remaining amount prediction model 24b, in which the explanatory variables are 100, 99, 98, 97, 96, and 95, which are the remaining amounts of toner on January 1st, January 2nd, January 3rd, January 4th, January 5th, and January 6th, respectively, is 94, which is the remaining amount of toner on January 7th. The objective variable in the training data for two-day-later remaining amount prediction model 24c, in which the explanatory variables are 100, 99, 98, 97, 96, and 95, which are the remaining amounts of toner on January 1st, January 2nd, January 3rd, January 4th, January 5th, and January 6th, respectively, is 93, which is the remaining amount of toner on January 8th.

[0070] The objective variable in the training data for one-day remaining amount prediction model 24b, whose explanatory variables are 100, 99, 98, 97, 96, 95, and 94, which are the remaining toner amounts on January 1st, January 2nd, January 3rd, January 4th, January 5th, January 6th, and January 7th, respectively, is 93, which is the remaining toner amount on January 8th.

[0071] The one-day remaining amount prediction model 24b, the two-day remaining amount prediction model 24c, and the three-day remaining amount prediction model 24d can be generated by training using a large amount of training data, such as the training data described above.

[0072] As described above, when the remaining amount prediction system 20 predicts the toner empty date (S124, S127 or S130) using the one-day remaining amount prediction model 24b, the two-day remaining amount prediction model 24c and the three-day remaining amount prediction model 24d, which predict the remaining toner amount on different dates when the same explanatory variables are input, it generates common explanatory variables for the one-day remaining amount prediction model 24b, the two-day remaining amount prediction model 24c and the three-day remaining amount prediction model 24d (S121 and S131), thereby reducing the number of times the process of generating explanatory variables to be input into the one-day remaining amount prediction model 24b, the two-day remaining amount prediction model 24c and the three-day remaining amount prediction model 24d is executed. 6, if the date X days after the latest date shown in the actual measurement value data 24e is an empty day, the number of times the process for generating explanatory variables is executed, i.e., the number of times the process of S121 or S131 is executed, is ceil(X / 3) times when expressed using the ceiling function ceil(x), which indicates the smallest integer equal to or greater than the real number x. For example, if the date 1 to 3 days after the latest date shown in the actual measurement value data 24e is an empty day, the number of times the process for generating explanatory variables is executed is 1, and if the date 100 to 102 days after the latest date shown in the actual measurement value data 24e is an empty day, the number of times the process for generating explanatory variables is executed is 34.

[0073] The remaining amount prediction system 20 can reduce the number of times the process for generating explanatory variables to be input into the one-day remaining amount prediction model 24b, the two-day remaining amount prediction model 24c, and the three-day remaining amount prediction model 24d is executed, thereby shortening the time required to predict the toner empty date.

[0074] In this embodiment, the multiple machine learning models of the present invention are a one-day remaining amount prediction model 24b that predicts the remaining amount of toner one day after the most recent base date, a two-day remaining amount prediction model 24c that predicts the remaining amount of toner two days after the most recent base date, and a three-day remaining amount prediction model 24d that predicts the remaining amount of toner three days after the most recent base date. However, the multiple machine learning models of the present invention may also be a machine learning model that predicts the remaining amount of toner a specific number of days other than one day after the most recent base date, a machine learning model that predicts the remaining amount of toner one day after a specific number of days after the most recent base date, and a machine learning model that predicts the remaining amount of toner two days after a specific number of days after the most recent base date. For example, the multiple machine learning models of the present invention may also be a machine learning model that predicts the remaining amount of toner two days after the most recent base date, a machine learning model that predicts the remaining amount of toner three days after the most recent base date, and a machine learning model that predicts the remaining amount of toner four days after the most recent base date. For example, if the remaining toner amount per day shown in the actual measurement data 24e is as shown in Figure 3, when the remaining toner amount prediction system 20 predicts the remaining toner amount on January 9th using a machine learning model that predicts the remaining toner amount two days after the base latest date, the base latest date of the explanatory variables input into this machine learning model can be set to January 7th.

[0075] In this embodiment, the remaining amount prediction system 20 predicts the empty date using three machine learning models. However, the remaining amount prediction system 20 may predict the empty date using two machine learning models, or may predict the empty date using four or more machine learning models. When the remaining amount prediction system 20 predicts the empty date using Y machine learning models, when the empty date is X days after the latest date indicated in the actual measurement value data 24e, the number of times the process for generating explanatory variables is executed is ceil(X / Y).

[0076] In this embodiment, the remaining amount prediction system 20 predicts the empty date. However, the remaining amount prediction system 20 may predict the date when the remaining amount of the consumable item will be equal to or less than a specific amount other than 0%.

[0077] In this embodiment, the consumable of the present invention is toner used in an image forming apparatus, but the consumable of the present invention may be a consumable other than toner used in an image forming apparatus, or may be a consumable used in an electronic device other than an image forming apparatus. [Explanation of symbols]

[0078] 20 Remaining amount prediction system (computer) 24a Remaining amount prediction program 24b 1-day remaining amount prediction model (machine learning model) 24c 2-day remaining amount prediction model (machine learning model) 24d 3-day remaining amount prediction model (machine learning model) 25a Remaining amount prediction section 30 Image forming equipment (electronic equipment)

Claims

1. a remaining amount prediction unit that predicts the date on which the remaining amount of a consumable item used in an electronic device will be equal to or less than a specific amount by using a plurality of machine learning models that predict the remaining amount of the consumable item; the machine learning model predicts the remaining amount of the consumable a specific number of days after the latest date among dates corresponding to the remaining amounts of the consumable for one or more days that are the basis of explanatory variables to be input to the machine learning model; Among the plurality of machine learning models, each machine learning model differs from all other machine learning models by the specific number of days, and differs from any other machine learning model by one day; The remaining amount prediction system is characterized in that the remaining amount prediction unit generates the explanatory variables that are common to the plurality of machine learning models.

2. a remaining amount prediction unit that predicts the date when the remaining amount of a consumable used in an electronic device will be equal to or less than a specific amount by using a plurality of machine learning models that predict the remaining amount of the consumable used in the electronic device; the machine learning model predicts the remaining amount of the consumable a specific number of days after the latest date among dates corresponding to the remaining amounts of the consumable for one or more days that are the basis of explanatory variables to be input to the machine learning model; Among the plurality of machine learning models, each machine learning model differs from all other machine learning models by the specific number of days, and differs from any other machine learning model by one day; The remaining amount prediction program is characterized in that the remaining amount prediction unit generates the explanatory variables that are common to the plurality of machine learning models.

Images