Image forming apparatus, image forming system, remaining amount derivation method, and program

Abstract

To simplify a mechanical configuration and reduce manufacturing cost in deriving the remaining amount of toner.SOLUTION: The present disclosure is an image forming apparatus that derives the amount of toner remaining in a toner container, and has a remaining amount derivation unit that derives the remaining amount of toner on the basis of a current value when a supply motor drives to rotate a toner conveying member.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The present disclosure relates to an image forming apparatus, an image forming system, a remaining amount derivation method, and a program.

Background Art

[0002] Conventionally, in an image forming apparatus that uses toner for printing, such as a printer or a copier, a technique for detecting the remaining amount of toner before the toner in the toner bottle runs out has been proposed (see Patent Document 1). Thereby, the user can grasp the remaining amount of toner at any time, predict the timing when an order for replacement toner should be placed, or predict how much printing can be done based on the remaining amount of toner. Specifically, a conventional image forming apparatus detects the remaining amount of toner in a toner bottle by measuring the capacitance with an electrode disposed so as to cover the toner bottle within the image forming apparatus.

Summary of the Invention

Problems to be Solved by the Invention

[0003] However, a conventional image forming apparatus has a problem in that it is necessary to arrange a large-scale electrode so as to cover the toner bottle, which complicates the mechanical configuration and increases the manufacturing cost.

[0004] The present disclosure has been made in view of the above circumstances, and an object thereof is to simplify the mechanical configuration and suppress the manufacturing cost when deriving the remaining amount of toner.

Means for Solving the Problems

[0005] The invention according to claim 1 is an image forming apparatus for deriving the remaining amount of toner in a toner container, and includes a remaining amount derivation unit that derives the remaining amount of toner based on a current value when a replenishment motor rotationally drives a toner conveyance member.

Effects of the Invention

[0006] As described above, according to the present disclosure, when deriving the remaining toner amount, it is possible to simplify the mechanical configuration and suppress the manufacturing cost.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Modes for Carrying Out the Invention

[0008] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0009] 〔Overall Configuration of the System〕 First, the overall configuration of the communication system according to the present embodiment will be described with reference to FIG. 1. FIG. 1 is an overall configuration diagram of the communication system according to the embodiment.

[0010] As shown in FIG. 1, the communication system 1 of the present embodiment is constructed by an image forming apparatus 3, a machine learning server 5, a data management server 7, and a user terminal 9. The image forming apparatus 3, the machine learning server 5, the data management server 7, and the user terminal 9 can communicate via a communication network 100 such as the Internet or a LAN (Local Area Network). The connection form to the communication network 100 may be either wireless or wired.

[0011] The image forming apparatus 3 is a multifunction peripheral (MFP), a printer, a facsimile apparatus, or the like. The image forming apparatus 3 is equipped with a learned machine learning model Mb of AI (Artificial Intelligence) and performs predetermined inferences. For example, the image forming apparatus 3 derives the remaining toner amount (toner weight) currently remaining in the toner bottle based on the current value of the current when a replenishment motor 408 (see FIG. 3) that drives a toner conveying member 407 (see FIG. 3) for conveying toner in the toner bottle (container) rotates to replenish the toner.

[0012] The machine learning server 5 performs machine learning of the machine learning model Ma in order to generate the learned machine learning model Mb. Note that an image forming system 2 is constructed by the image forming apparatus 3 and the machine learning server 5.

[0013] The data management server 7 collects learning data used for performing machine learning in the machine learning server 5 from external devices such as the image forming apparatus 3 and provides it to the machine learning server 5.

[0014] The user terminal 9 sends a request to execute a job such as printing to the image forming apparatus 3. Note that the user terminal 9 is, for example, a PC (Personal Computer), a tablet terminal, a smart watch, or the like.

[0015] 〔Hardware Configuration〕 <Image Forming Apparatus> FIG. 2 is an electrical hardware configuration diagram of a multifunction peripheral as an image forming apparatus.

[0016] The image forming apparatus 3 includes a controller 310, a short-range communication circuit 320, an engine control device 300, an operation panel 340, and a network I / F 350.

[0017] Among these, the controller 310 has a CPU 301 which is a main part of a computer, a system memory (MEM-P) 302, a north bridge (NB) 303, a south bridge (SB) 304, an ASIC (Application Specific Integrated Circuit) 306, a local memory (MEM-C) 307 which is a storage unit, an HDD controller 308, and an HD 309 which is a storage unit, and is configured to connect between the NB 303 and the ASIC 306 by an AGP (Accelerated Graphics Port) bus 321.

[0018] Among these, the CPU 301 is a control unit that performs overall control of the MFP 3. The NB 303 is a bridge for connecting the CPU 301, the MEM-P 302, the SB 304, and the AGP bus 321, and has a memory controller that controls reading and writing to the MEM-P 302, a PCI (Peripheral Component Interconnect) master, and an AGP target.

[0019] MEM-P302 consists of a ROM302a which is a memory for storing programs and data for realizing each function of the controller 310, and a RAM302b which is used as a memory for expanding programs and data and for drawing during memory printing. Note that the programs stored in the RAM302b may be configured to be recorded and provided on a computer-readable recording medium such as a CD-ROM, CD-R, or DVD in an installable or executable file format.

[0020] SB304 is a bridge for connecting NB303 with a PCI device and peripheral devices. ASIC306 is an IC (Integrated Circuit) for image processing applications having hardware elements for image processing, and has the role of a bridge for connecting an AGP bus 321, a PCI bus 322, an HDD308, and a MEM-C307 respectively. This ASIC306 consists of a PCI target and an AGP master, an arbiter (ARB) forming the core of the ASIC306, a memory controller for controlling MEM-C307, a plurality of DMACs (Direct Memory Access Controllers) for performing operations such as rotation of image data by means of hardware logic, etc., and a PCI unit for performing data transfer via the PCI bus 322 between the scanner unit 331 and the printer unit 332. Note that an interface for USB (Universal Serial Bus) or an interface for IEEE1334 (Institute of Electrical and Electronics Engineers 1394) may be connected to the ASIC306.

[0021] MEM-C307 is local memory used as a copy image buffer and a code buffer. HD309 is storage for accumulating image data, font data used at the time of printing, and forms. HD309 controls the reading or writing of data to HD309 according to the control of CPU301. The AGP bus 321 is a bus interface for a graphics accelerator card proposed to speed up graphic processing. By directly accessing MEM-P302 with high throughput, the graphics accelerator card can be made faster.

[0022] Also, the short-distance communication circuit 320 is provided with a short-distance communication circuit 320a. The short-distance communication circuit 320 is a communication circuit such as NFC or Bluetooth.

[0023] Furthermore, the engine control device 300 is composed of a scanner unit 331 and a printer unit 332. Also, the operation panel 340 includes a panel display unit 340a such as a touch panel that displays current setting values, selection screens, etc. and receives inputs from the operator, and an operation panel 340b consisting of a numeric keypad that receives setting values of conditions related to image formation such as density setting conditions and a start key that receives a copy start instruction. The controller 310 controls the entire MFP3, for example, controls drawing, communication, inputs from the operation panel 340, etc. The scanner unit 331 or the printer unit 332 includes an image processing part such as error diffusion and gamma conversion.

[0024] Note that the MFP3 can sequentially switch and select the document box function, copy function, printer function, and facsimile function by the application switching key on the operation panel 340. When the document box function is selected, it becomes the document box mode, when the copy function is selected, it becomes the copy mode, when the printer function is selected, it becomes the printer mode, and when the facsimile mode is selected, it becomes the facsimile mode.

[0025] The network I / F 350 is an interface for data communication using the communication network 100. The short-range communication circuit 320 and the network I / F 350 are electrically connected to the ASIC 306 via the PCI bus 322.

[0026] <Engine control device> Figure 3 is an electrical hardware configuration diagram of the engine control device in Figure 2.

[0027] As shown in Figure 3, the engine control device 330 includes a CPU (Central Processing Unit) 400, a ROM (Read Only Memory) 401, a RAM (Random Access Memory) 402, an SSD (Solid State Drive) 403, a GPU (Graphics Processing Unit) 404, a connection I / F (Interface) 405, various sensors 406, a toner conveyance member 407, a replenishment motor 408, and a bus line 410.

[0028] Among these, the CPU 400 controls the overall operation of the engine control device 330. The ROM 401 stores programs used for driving the CPU 400 such as IPL. The RAM 402 is used as a work area for the CPU 400.

[0029] The SSD 403 reads or writes various data according to the control of the CPU 400. Note that an HDD (Hard Disk Drive) may be used instead of the SSD 404. The GPU 404 is a semiconductor chip that handles graphics and the like. The GPU 404 may be omitted.

[0030] The connection I / F 405 is an interface for connecting various devices or electrical components provided in the image forming apparatus 3.

[0031] The various sensors 406 are a group of sensors for detecting the operation and environment (e.g., temperature, humidity) of the engine control device 330 and the like.

[0032] The toner conveyance member 407 is a member that conveys the toner in the toner container.

[0033] The replenishment motor 408 is a motor that rotationally drives the toner conveyance member 407 to replenish the toner. Note that at least one of the various sensors 406 detects the current value when the replenishment motor 408 rotationally drives the toner conveyance member 407 and outputs the current value of the replenishment motor.

[0034] The bus line 410 is an address bus, a data bus, etc. for electrically connecting each component such as the CPU 401.

[0035] <Image forming process in the image forming apparatus> Here, the image forming process in the full-color image forming apparatus 3 will be briefly described. In the full-color image forming apparatus 3, it is common to set four toner bottles of KCMY. The toner bottle is provided with an opening that can communicate with the main body of the image forming apparatus 3. By driving the replenishment motor 408, the toner bottle main body provided with spiral unevenness is rotationally driven, and the toner inside the toner bottle is conveyed toward the opening of the toner bottle.

[0036] The toner discharged from the toner bottle through the opening is replenished to the developing device through the replenishment path. The toner replenished into the developing device is developed into an electrostatic latent image exposed by the exposure device on the image carrier uniformly charged by the charging device, transferred to the intermediate transfer body, then transferred to the paper, and fixed by the fixing device to perform a series of image forming processes.

[0037] The developing device used in this embodiment uses a two-component development method consisting of toner and carrier, and the toner concentration is controlled to be constant. The CPU 400 or the GPU 404 calculates the amount of toner to be replenished according to the difference between the detection result by the toner concentration sensor provided in the developing device and the target toner concentration, and issues a replenishment command.

[0038] When a replenishment command is issued, if the replenishment path between the developing device and the toner bottle is directly connected, toner is replenished by the rotation of the toner bottle. On the other hand, in the case of an image forming apparatus provided with a sub-hopper for temporarily storing toner in the replenishment path between the developing device and the toner bottle, the drive motor of the sub-hopper is driven and toner is replenished to the developing device. Then, when the sub-hopper becomes empty, the toner bottle is rotated and the sub-hopper is filled with toner.

[0039] Here, although the toner bottle in which toner is conveyed by rotationally driving the bottle body has been described as an example, a toner bottle of a type that conveys the internal toner toward the opening by driving a conveying member (agitator) inside the toner bottle may also be used. In that case, the replenishment motor refers to the motor that drives the conveying member.

[0040] <Machine learning server> FIG. 4 is an electrical hardware configuration diagram of a machine learning server, a data management server, and a user terminal. Since the data management server 7 and the user terminal 9 have the same configuration as the machine learning server 5, the machine learning server 5 will be described below.

[0041] As shown in FIG. 4, the machine learning server 5, as a computer, includes a CPU (Central Processing Unit) 500, a ROM (Read Only Memory) 501, a RAM (Random Access Memory) 502, an SSD (Solid State Drive) 503, a GPU (Graphics Processing Unit) 504, an external device connection I / F (Interface) 505, a network I / F 506, a display 507, an operation unit 508, a media I / F 509, and a bus line 510, as shown in FIG. 4.

[0042] Among these, the CPU 500 controls the operation of the entire machine learning server 5. The ROM 501 stores programs used for driving the CPU 500 such as IPL. The RAM 502 is used as the work area of the CPU 500.

[0043] The SSD 503 reads or writes various data according to the control of the CPU 500. Note that an HDD (Hard Disk Drive) may be used instead of the SSD 504. The GPU 504 is a semiconductor chip that handles graphics and the like.

[0044] The external device connection I / F 505 is an interface for connecting various external devices. The external devices in this case are a display, a speaker, a keyboard, a mouse, a USB memory, a printer, and the like.

[0045] The network I / F 506 is an interface for data communication via the communication network 100.

[0046] The display 507 is a type of display means such as a liquid crystal or an organic EL (Electro Luminescence) that displays various images.

[0047] The operation unit 508 is a keyboard, a pointing device, etc., and is an example of input means for receiving input operations such as characters, numerical values, and various instructions.

[0048] The media I / F 509 controls the reading or writing (storage) of data with respect to a recording medium 509m such as a flash memory. The recording medium 509m includes DVDs, Blu-ray Disc (registered trademark), and the like.

[0049] The bus line 510 is an address bus, a data bus, etc. for electrically connecting each component such as the CPU 501.

[0050] 〔Functional Configuration of Embodiment〕 Next, the functional configuration of this embodiment will be described with reference to FIGS. 5 and 6.

[0051] <Learning Phase> FIG. 5 is a functional block diagram of the machine learning server in the learning phase. As shown in FIG. 5, the machine learning server 5 in the learning phase includes a reception unit 50, an input unit 51, a learning unit 52, and a transmission unit 59. The reception unit 50 and the transmission unit 59 are functions realized by commands from the CPU 301 in FIG. 2 based on a program. Also, the input unit 51 and the learning unit 52 are functions realized by commands from the CPU 400 or the GPU 404 in FIG. 3 based on a program.

[0052] The reception unit 50 receives learning data from the data management server 7. The learning data includes a data set of input data and correct answer data. The input data includes (1) the current value of the replenishment motor, (2) at least one of temperature and humidity, (3) the elapsed time since the previous bottle drive ended, (4) the previous bottle rotation amount, and (5) the cumulative rotation amount of the bottle. Each of these values (1) to (5) is a value detected by one of the various sensors 406. Note that the learning data exists for each toner color, and the inference of the toner remaining amount is also performed for each color.

[0053] The learning data also includes toner weight data indicating the toner weight as each correct answer data (teacher data) set with each input data. This toner weight is the toner remaining amount under the situation indicated by each input data. Note that, in order to acquire a large amount of learning data, the reception unit 50 indicates the toner weight as the weights of the toner in bottles with known remaining amounts at multiple levels.

[0054] Among these, the current value of the replenishment motor is, for example, the current value when the replenishment motor 408 rotationally drives the toner conveyance member 407. If the remaining amount of toner in the toner bottle is large, the driving torque of the toner bottle is large, and the current value for driving the replenishment motor 408 becomes large. Also, if the remaining amount of toner in the toner bottle is small, the driving torque of the toner bottle is small, and the current value for driving the replenishment motor 408 becomes small. Therefore, the current value of the replenishment motor is related to the inference of the remaining toner amount.

[0055] The temperature and humidity are values inside or around the image forming apparatus 3. For example, when the temperature or humidity rises, the fluidity of the toner decreases, so the current value of the replenishment motor 408 increases. Therefore, the temperature or humidity is related to the inference of the remaining toner amount.

[0056] The elapsed time since the end of the previous bottle drive indicates the elapsed time since the end of the previous drive of the same toner bottle without changing the toner bottle. The previous bottle rotation amount indicates the previous rotation amount of the same toner bottle without changing the toner bottle. The cumulative rotation amount of the bottle indicates the cumulative rotation amount (for example, the cumulative rotation amount in the immediate previous 1 hour) of the same toner bottle within a predetermined time without changing the toner bottle. Note that data indicating at least one of the elapsed time since the end of the previous bottle drive, the previous bottle rotation amount, and the cumulative rotation amount of the bottle is an example of "data on the drive history of the toner bottle".

[0057] When the toner bottle is rotating and the toner inside is in a fluid state, and when it is left stationary for a long time without rotating and the toner inside is compacted, the fluidity of the toner in the toner bottle is different, so the current value of the replenishment motor 408 will vary. Therefore, the drive history of the toner bottle is related to the inference of the remaining toner amount.

[0058] The input unit 51 acquires input data from the reception unit 50 and inputs it to the learning unit 52.

[0059] The learning unit 52 has a machine learning model Ma, and generates a learned machine learning model Mb capable of high-precision output through machine learning using a machine learning algorithm such as a neural network.

[0060] The machine learning model Ma of the present embodiment infers the remaining toner amount in the toner bottle based on input data and outputs the data as output data. For example, the learning unit 52 uses the current value of the above-described replenishment motor as input data and the remaining amount data indicating the remaining toner amount as output data.

[0061] Also, the learning unit 52 has a comparison and change unit 53. The comparison and change unit 53 obtains an error E between the output data from the machine learning model Ma and the correct data, and calculates a loss L representing the error E using a loss function. Further, the comparison and change unit 53 updates the coupling weight coefficients between the nodes of the neural network so that the loss becomes smaller (so that the loss L approaches 0) based on the loss L. The comparison and change unit 53 updates the coupling weight coefficients between the nodes of the neural network using, for example, the error backpropagation method. The error backpropagation method is a method of adjusting the coupling weight coefficients between the nodes of each neural network so that the error E becomes smaller.

[0062] For example, in the present embodiment, the comparison and change unit 53 compares the output data (remaining toner amount) output from the machine learning model Ma with the correct data (toner weight), and changes the model parameters of the machine learning model Ma according to the error. Thereby, the learning unit 52 can perform machine learning of the machine learning model Ma and generate a learned machine learning model Mb.

[0063] <Inference phase> FIG. 6 is a functional block diagram of the image forming apparatus 3 in the inference phase. As shown in FIG. 6, the image forming apparatus 3 in the inference phase has a reception unit 30, an input unit 31, a remaining amount derivation unit 35 as an inference unit, a display control unit 38, and a transmission unit 39.

[0064] The receiving unit 30, the display control unit 38, and the transmitting unit 39 are functions realized by instructions from the CPU 301 in FIG. 2 based on a program. Further, the input unit 31 and the remaining amount derivation unit 35 are functions realized by instructions from the CPU 400 or the GPU 404 in FIG. 3 based on a program.

[0065] The receiving unit 30 receives data of the learned machine learning model Mb from the machine learning server 5 and passes it to the remaining amount derivation unit 35.

[0066] The input unit 31 inputs, as input data, each data of at least one of the current value, temperature, and humidity of the supply motor and the driving history of the toner bottle (the elapsed time since the end of the previous bottle drive, the previous bottle rotation amount, and the cumulative rotation amount of the bottle) from various sensors 406 or the like to the remaining amount derivation unit 35.

[0067] The remaining amount derivation unit 35 has the learned machine learning model Mb. The remaining amount derivation unit 35 acquires input data from the input unit 31. Further, the remaining amount derivation unit 35 inputs, as input data to the learned machine learning model Mb, each data of at least one of the current value, temperature, and humidity of the supply motor and the driving history of the toner bottle, and causes the learned machine learning model Mb to output a derivation result (inference result) which is remaining amount data indicating the toner remaining amount as output data. Thereby, the remaining amount derivation unit 35 outputs the output data which is the derivation result to the display control unit 38 and the transmitting unit 39.

[0068] The display control unit 38 displays information indicating the toner remaining amount of the toner bottle at the current time on the panel display unit 340a shown in FIG. 2.

[0069] The transmitting unit 39 transmits information indicating the toner remaining amount of the toner bottle at the current time from the network I / F 350 shown in FIG. 2 to a server or the like of a sales place or a manufacturer of the image forming apparatus 3.

[0070] 〔Processing or operation of the embodiment〕 Subsequently, the processing or operation of this embodiment will be described with reference to FIGS. 8 to 10.

[0071] <Overall Processing of Communication System> First, the overall processing of the communication system 1 will be described with reference to FIG. 8. FIG. 8 is a sequence diagram showing the processing of the communication system.

[0072] S11: The data management server 7 transmits learning data for machine learning to the machine learning server 5. As a result, the receiving unit 50 of the machine learning server 5 receives the learning data.

[0073] S12: The machine learning server 5 performs learning processing of the machine learning model Ma using the learning data. This learning processing will be described later.

[0074] S13: The transmitting unit 59 of the machine learning server 5 transmits the data of the learned machine learning model Mb to the image forming apparatus 3. As a result, the receiving unit 30 of the image forming apparatus 3 receives (downloads) the data of the learned machine learning model Mb. Note that the learned machine learning model Mb downloaded from the machine learning server 5 may be a learning model created only from learning data in the same region as the country or region where the image forming apparatus 3 is installed. Thus, depending on the learned machine learning model Mb, it is possible to provide a highly accurate model by excluding the difference in the current flowing through the supply motor 408 caused by the difference in the toner bottle materials and manufacturing bases, by separating the inference models for each base among the toner bottles manufactured at a plurality of bases.

[0075] Note that at the time of shipment of the image forming apparatus 3, the learned machine learning model Mb may be included as a preset learning model. Even without performing additional machine learning, it is possible to infer the toner remaining amount using the preset learning model created at the time of design. In this case, the learning data used for learning the learned machine learning model Mb may be learning data from some N number of data at the time of design, or in the case of an image forming apparatus having the same configuration as the previous image forming apparatus, learning data using big data collected from the market data of the previous image forming apparatus may also be used.

[0076] S14: On one hand, the user terminal 9 sends a job execution request such as printing to the image forming apparatus 3. As a result, the receiving unit 30 of the image forming apparatus 3 receives the job execution request.

[0077] S15: The image forming apparatus 3 performs job processing according to the job execution request and also performs inference processing. This inference processing will be described later. Note that the image forming apparatus 3 may execute a job such as copying by direct operation of the user without receiving the job execution request from the user terminal 9.

[0078] S16: The transmitting unit 39 of the image forming apparatus 3 transmits learning data used for additional learning to the data management server 7 at the timing when the toner remaining amount has run out (become zero) or when a new toner bottle has been replaced and set. As a result, the data management server 7 receives the learning data and uses it as the learning data transmitted in process S31. Note that the transmitting unit 39 of the image forming apparatus 3 may transmit the learning data used for additional learning to the machine learning server 5. In this case, the machine learning server 5 performs additional learning using the learning data collected from a plurality of apparatuses including the image forming apparatus 3, and transmits the data of the learned machine learning model Mb after the additional learning to the image forming apparatus 3.

[0079] Here, with reference to FIG. 7, process S16 will be described in more detail. FIG. 7 is a diagram showing an example in which an inference value is corrected using data of bottles with different filling amounts.

[0080] (Learning data that can be obtained at the time of toner replacement and at the end) First, in the image forming apparatus 3, data exchange from when a new toner bottle with a known toner weight is set in the image forming apparatus 3 until this set single toner bottle reaches the end will be described. When a toner bottle having an ID (Identification) chip is set in the image forming apparatus 3, the toner filling amount data stored in the ID chip is read via the reading unit of the main body of the image forming apparatus 3. Then, the current value for driving the replenishment motor 408 during the initial operation when the toner bottle is set, at least one of the temperature and humidity inside or around the image forming apparatus 3, and the toner weight data read from the ID chip are recorded in the RAM 402 or the like as additional learning data.

[0081] After that, as the user outputs an image, the toner is gradually consumed, and the current value for driving the replenishment motor 408 also gradually decreases. During this period, no machine learning is performed, and the remaining amount derivation unit 35 infers the toner remaining amount using the learned machine learning model Mb at that time.

[0082] Finally, when the end sensor (an example of various sensors 406) provided in the sub hopper detects the toner end, the actual remaining amount value (actual result value) in the actual toner bottle is about 0 to 5 g. At this time, with the remaining amount in the toner bottle set to "zero", the correct data indicating the weight data "zero", at least one of the current value, temperature, and humidity of the replenishment motor 408, and the data of the driving history of the toner bottle are recorded in the RAM 402 or the like as additional learning data.

[0083] In this way, two sets of learning data are obtained from the image forming apparatus 3 for each single toner bottle. Then, the learning data at the time of toner fullness and toner end when replacing the toner bottle is transmitted to the data management server 7 by the process S16. By aggregating and learning the data of each color or the same model in the market in this way, the number of data can be increased, and it becomes possible to infer the toner remaining amount with high accuracy.

[0084] In addition, as shown in FIG. 7, in some models, there are toner bottles with multiple weight variations. For example, there are a large bottle B1 of 500 g, a medium bottle B2 of 300 g, and a small bottle B3 of 100 g. Using these learning data, it is possible to perform additional learning on a learned machine learning model Mb that shows the correlation Cc after additional learning calibrated at four points of 100 g, 300 g, and 500 g in addition to the toner end (0 g) from the correlation (preset) Cb at the time of shipment. Thereby, the accuracy of inferring the remaining toner amount can be further improved.

[0085] Note that the learning data for additional learning of the learned machine learning model Mb is stored in the ID chip of the toner bottle. After this toner bottle has been used and then returned and collected by the toner bottle manufacturer, the ID chip information may be read and used for additional learning. Information obtained by the image forming apparatus 3 not connected to the network can also be used to strengthen the machine learning model of the remaining toner amount, enabling model creation for a larger number of units. Thereby, other image forming apparatuses can also accurately infer the remaining toner amount.

[0086] <Learning Process> Subsequently, with reference to FIG. 9, the learning process shown in FIG. 8 will be described in detail. FIG. 9 is a flowchart showing the processing in the learning phase.

[0087] S111: The input unit 51 in FIG. 5 inputs, as input data for machine learning, at least one of the current value, temperature, and humidity of the replenishment motor, and each data of the drive history of the toner bottle, among the learning data received by the receiving unit 50, to the learning unit 52.

[0088] S112: The learning unit 52 performs machine learning of the machine learning model Ma based on the input data from the input unit 51 and the like by machine learning using a machine learning algorithm such as a neural network, and generates a learned machine learning model Mb.

[0089] S113: The learning unit 52 determines whether or not the machine learning has ended. If it has not ended (S113; NO), it returns to the above step S111 to continue the process. On the other hand, if it has ended (S113; YES), the learning process ends.

[0090] <Inference process> Subsequently, with reference to FIG. 10, the inference process shown in FIG. 8 will be described in detail. FIG. 10 is a flowchart showing the process in the inference phase.

[0091] S131: The input unit 31 in FIG. 6 acquires at least one of the current value, temperature, and humidity of the supply motor, and each data of the drive history of the toner bottle output by various sensors 406 in FIG. 3, and inputs them to the remaining amount derivation unit 35.

[0092] S132: The remaining amount derivation unit 35 uses at least one of the current value, temperature, and humidity of the supply motor, and each data of the drive history of the toner bottle as input data, derives (infers) the current toner remaining amount, and makes it output data.

[0093] S133: The display control unit 38 causes the panel display unit 340a to display information indicating the derived toner remaining amount. Thereby, the user using the image forming apparatus 3 can grasp the toner remaining amount of the image forming apparatus 3, and can print with confidence or perform processes such as ordering the next toner bottle.

[0094] S134: The transmission unit 39 transmits information indicating the derived toner remaining amount to the user terminal 9 or the like. Thereby, the user of the user terminal 9 or the like can grasp the toner remaining amount of the image forming apparatus 3, and can print with confidence or perform processes such as ordering the next toner bottle.

[0095] In addition, when the user terminal 9 is the terminal of an employee of the toner bottle sales company and the remaining toner amount is equal to or less than a predetermined value, the transmission unit 39 may transmit data for automatically ordering a toner bottle. Further, the transmission unit 39 may determine whether to automatically order a toner bottle in consideration of not only the remaining toner amount but also the drive history of the toner bottle. By determining the timing at which the transmission unit 39 orders the next toner bottle according to the inferred remaining toner amount and the drive history of the toner bottle, the next replacement toner bottle can be delivered to the user of the image forming apparatus 3 in a timely manner. This can solve the problem that if the toner bottle arrives too early, the toner bottle may be replaced by the user of the image forming apparatus 3 before the toner runs out, resulting in wasted toner. On the other hand, if there is no next toner at the time of toner end, it will cause downtime for the user of the image forming apparatus 3, leading to a problem of reduced customer satisfaction, but this can also be solved.

[0096] [Another Example of Machine Learning Server] Next, another example of the machine learning server 5 will be described with reference to FIGS. 11 and 12. In the above embodiment, the image forming apparatus 3 performs the inference process. Here, an example will be described in which the machine learning server 5 performs the inference process as an inference server.

[0097] <Other Functional Configurations of Machine Learning Server> FIG. 11 is another functional block diagram of the machine learning server (inference server) in the inference phase.

[0098] As shown in FIG. 11, the machine learning server 5 in the inference phase includes a reception unit 50, an input unit 51, a remaining amount derivation unit 55 as an inference unit, and a transmission unit 59. Since the reception unit 50, the input unit 51, and the transmission unit 59 have been described with reference to FIG. 5, the description thereof will be omitted.

[0099] The remaining amount derivation unit 55 is a function realized by an instruction from the CPU 501 or GPU 504 in FIG. 4 based on a program. Further, the remaining amount derivation unit 55 has a learned machine learning model Mb learned by the machine learning server 5 itself.

[0100] <Other processes of the entire communication system> Subsequently, with reference to FIG. 12, the overall processing of the communication system 1 when the machine learning server 5 performs inference processing will be described. FIG. 12 is a sequence diagram showing another example 1 of the processing of the communication system.

[0101] S31: The data management server 7 transmits learning data for machine learning to the machine learning server 5. As a result, the receiving unit 50 of the machine learning server 5 receives the learning data.

[0102] S32: The machine learning server 5 performs learning processing of the machine learning model Ma using the learning data. Since this learning processing is the same as the content described with reference to FIG. 9, the description thereof will be omitted.

[0103] S33: On the other hand, the user terminal 9 transmits a job execution request such as printing to the image forming apparatus 3. As a result, the receiving unit 30 of the image forming apparatus 3 receives the job execution request.

[0104] S34: The image forming apparatus 3 performs job processing according to the job execution request. Note that the image forming apparatus 3 may execute a job such as copying by a direct operation of the user without receiving the job execution request from the user terminal 9.

[0105] S35: The transmitting unit 39 of the image forming apparatus 3 transmits an inference request to the machine learning server 5. This inference request includes each data (at least one of the current value of the replenishment motor, temperature, and humidity, and the drive history of the toner bottle) that the remaining amount derivation unit 35 shown in FIG. 6 should use to infer the toner remaining amount. As a result, the receiving unit 50 of the machine learning server 5 receives the inference request.

[0106] S36: The machine learning server 5 acting as an inference server performs inference processing. Since this inference processing is the same as the content (S131, S132) described with reference to FIG. 10, the description thereof is omitted.

[0107] S37: The transmission unit 59 of the machine learning server 5 transmits data of the inference result corresponding to the inference request in process S35 to the image forming apparatus 3. This inference result includes information indicating the current toner remaining amount. As a result, the reception unit 30 of the image forming apparatus 3 receives the data of the inference result. Thereafter, in the image forming apparatus 3, processes S133 and S134 shown in FIG. 10 are performed.

[0108] S38: The transmission unit 39 of the image forming apparatus 3 transmits learning data to the data management server 7 at the timing when the toner remaining amount has become zero or when a new toner bottle has been replaced and set, in the same manner as in process S16. As a result, the data management server 7 receives the learning data and uses it as the learning data transmitted in process S31.

[0109] 〔Another example of the image forming apparatus〕 Subsequently, another example of the image forming apparatus 3 will be described with reference to FIGS. 13 and 14. In the above embodiment, the machine learning server 5 performs learning processing, but here, an example in which the image forming apparatus 3 performs learning processing will be described.

[0110] <Another functional configuration of the image forming apparatus> FIG. 13 is another functional block diagram of the image forming apparatus in the learning phase.

[0111] As shown in FIG. 13, the image forming apparatus 3 in the learning phase includes a reception unit 30, an input unit 31, and a learning unit 32. Since the reception unit 30 and the input unit 31 have been described in FIG. 6, the description thereof is omitted.

[0112] The learning unit 32 is a function realized by instructions from the CPU 401 or GPU 404 in FIG. 3 based on a program. Also, the learning unit 32 has the machine learning model Ma in the initial state, but has the learned machine learning model Mb after machine learning. When the learning unit 32 has the learned machine learning model Mb, the learning unit 32 performs additional learning.

[0113] Also, the learning unit 32 has a comparison and change unit 33 with the same function as the comparison and change unit 53. The output data (toner remaining amount) output from the machine learning model Ma or the learned machine learning model Mb is compared with the correct answer data (toner weight which is the toner remaining amount), and the model parameters of the machine learning model Ma or the learned machine learning model Mb are changed according to the error. Thereby, the learning unit 32 can perform machine learning on the machine learning model Ma to generate the learned machine learning model Mb, or perform additional learning on the learned machine learning model Mb.

[0114] <Other processes of the entire communication system> Subsequently, with reference to FIG. 14, the overall processing of the communication system 1 when the image forming apparatus 3 performs learning processing will be described. FIG. 14 is a sequence diagram showing another example 2 of the processing of the communication system.

[0115] S51: The data management server 7 transmits learning data for machine learning to the image forming apparatus 3. Thereby, the receiving unit 30 of the image forming apparatus 3 receives the learning data.

[0116] S52: The image forming apparatus 3 performs learning processing on the machine learning model Ma using the learning data. Since this learning processing is the same as the content described with reference to FIG. 9, the description is omitted.

[0117] S53: On the other hand, similar to process S14, the user terminal 9 transmits a job execution request such as printing to the image forming apparatus 3. Thereby, the receiving unit 30 of the image forming apparatus 3 receives the job execution request.

[0118] S54: Similar to process S15, the image forming apparatus 3 performs job processing according to a job execution request and also performs inference processing. Note that the image forming apparatus 3 may execute a job such as copying by direct operation of the user without receiving a job execution request from the user terminal 9.

[0119] S55: The transmission unit 39 of the image forming apparatus 3 transmits learning data to the data management server 7 at the timing when the toner remaining amount has run out (become zero) or when a new toner bottle has been replaced and set, in the same manner as in process S16. Thereby, the data management server 7 receives the learning data and uses it as the learning data to be transmitted in process S51.

[0120] 〔Main effects of the embodiment〕 As described above, according to the present embodiment, when deriving the toner remaining amount, there is an effect that the mechanical configuration can be simplified and the manufacturing cost can be suppressed.

[0121] 〔Supplementary explanation〕 Although the embodiment has been described above, the present invention is not limited to such an embodiment at all, and various modifications and substitutions can be made without departing from the gist of the present invention.

[0122] (1) In the communication between the image forming apparatus 3, the machine learning server 5, the data management server 7, and the user terminal 9, another device (such as a server or a router) may relay data and the like. For example, in this specification, for the sake of simplicity, it is described that the image forming apparatus 3 receives data (information) from the machine learning server 5 or the image forming apparatus 3 transmits data (information) to the machine learning server 5, but each of these reception and transmission processes includes the case where another device relays data (information).

[0123] (2) Each function of the above-described embodiment can be realized by one or more processing circuits. Here, the "processing circuit" in this specification includes a processor programmed to execute each function by software, such as a processor implemented by an electronic circuit, an ASIC (Application Specific Integrated Circuit) designed to execute each function described above, a DSP (digital signal processor), an FPGA (field programmable gate array), and devices such as conventional circuit modules.

[0124] (3) Further, as a (non-transitory) recording medium such as a DVD-ROM in which each program of the above embodiment is stored, a program product can be provided domestically or abroad.

[0125] (4) The processors (for example, CPU301, CPU400, GPU404, CPU500, GPU504) may be singular or plural respectively.

Explanation of Signs

[0126] 1 Communication system 2 Image forming system 3 Image forming apparatus 5 Machine learning server 7 Data management server 9 User terminal (an example of a communication terminal) 30 Receiving unit 31 Input unit 32 Learning unit 33 Comparison and change unit 35 Remaining amount derivation unit (inference unit) 38 Display control unit 39 Transmitting unit 50 Receiving unit 51 Input unit 52 Learning unit 53 Comparison and change unit 55 Remaining amount derivation unit (inference unit) 58 Display control unit 59 Transmission unit 340a Panel display unit (an example of a display unit) Ma Machine learning model Mb Trained machine learning model

Prior art documents

Patent documents

[0127]

Patent Document 1

Claims

1. An image forming apparatus for deriving the remaining amount of toner in a toner container, comprising: a remaining amount deriving unit that derives the remaining amount of toner based on a current value when a replenishment motor rotationally drives a toner conveying member.

2. The image forming apparatus according to claim 1, wherein the remaining amount deriving unit uses a learned machine learning model that takes data indicating the current value as input data and infers the remaining amount of toner as output data, and infers the remaining amount of toner based on the data indicating the current value to derive the remaining amount of toner.

3. The input data includes data indicating at least one of the temperature and humidity inside or around the image forming apparatus, and the remaining amount deriving unit further infers the remaining amount of toner based on data indicating at least one of the temperature and humidity. The image forming apparatus according to claim 2.

4. The input data includes data on the drive history of the toner container, and the remaining amount deriving unit further infers the remaining amount of toner based on data on the drive history of the toner container. The image forming apparatus according to claim 3.

5. The drive history of the toner container indicates at least one of the elapsed time since the end of the previous drive of the same toner container without changing the toner container, the previous rotation amount of the same toner container without changing the toner container, and the cumulative rotation amount of the same toner container within a predetermined time without changing the toner container. The image forming apparatus according to claim 4.

6. The value of the remaining amount of toner among the learning data used for additional learning of the learned machine learning model is stored in an ID chip attached to the toner container as the initial toner weight in the toner container. The image forming apparatus according to any one of claims 2 to 5.

7. The image forming apparatus according to any one of claims 2 to 5, wherein the learned machine learning model is included as a preset learning model at the time of shipment of the image forming apparatus.

8. An image forming apparatus according to any one of claims 1 to 5, comprising: a display control unit that causes a display unit to display information indicating the remaining amount of toner derived by the remaining amount deriving unit.

9. An image forming apparatus according to any one of claims 1 to 5, comprising: a transmission unit that automatically places an order for the toner container based on the remaining amount of toner derived by the remaining amount deriving unit.

10. An image forming system constructed by the image forming apparatus according to any one of claims 2 to 5 and a machine learning server that generates a learned machine learning model, wherein the image forming apparatus transmits learning data for additional learning of the learned machine learning model to the machine learning server, and the machine learning server performs the additional learning using the learning data collected from a plurality of apparatuses including the image forming apparatus, and transmits the data of the learned machine learning model after the additional learning to the image forming apparatus. Image forming system.

11. A remaining amount derivation method executed by an image forming apparatus that derives a remaining amount of toner in a toner container, wherein the image forming apparatus executes a remaining amount derivation process for deriving the remaining amount of toner based on a current value when a replenishment motor rotationally drives a toner conveyance member. Remaining amount derivation method.

12. A program for causing a computer to execute the method according to claim 11.

Images