Document processing apparatus, image forming apparatus, trained model generation apparatus, and image forming system

The document processing apparatus addresses the issue of subjective sound discomfort in image forming devices by estimating and adjusting for perceived sound pleasantness, enhancing environmental comfort.

JP2026123715APending Publication Date: 2026-07-30ETRIA CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
ETRIA CO LTD
Filing Date
2025-01-17
Publication Date
2026-07-30

AI Technical Summary

Technical Problem

Existing image forming devices do not consider the subjective perception of sound comfort, leading to varying degrees of discomfort despite similar noise levels, which affects the overall environment's comfort.

Method used

The document processing apparatus includes a tray, transport unit, reading unit, and an estimation unit that acquires processing information to estimate the perceived sound pleasantness during document transport and reading, allowing for adjustments to enhance sound comfort.

Benefits of technology

This approach improves the overall comfort of the surrounding environment by considering subjective sound perception, thereby reducing discomfort caused by generated sounds.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2026123715000001_ABST
    Figure 2026123715000001_ABST
Patent Text Reader

Abstract

To improve the comfort of the surrounding environment. [Solution] The document processing device according to the present disclosure comprises: a tray for loading documents; a transport unit for transporting documents from the tray; a reading unit for reading an image represented on a document while the document is being transported by the transport unit; an acquisition unit for acquiring processing information including at least one of the settings for the transport unit to transport the document and the settings for the reading unit to read the document; and an estimation unit for estimating the pleasantness of sounds that a person would perceive in relation to sounds generated during the transport or reading of a document, based on the processing information acquired by the acquisition unit.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a document processing apparatus, an image forming apparatus, a learned model generation apparatus, and an image forming system.

Background Art

[0002] Devices including a document processing apparatus are placed in various environments. When placed in a relatively quiet environment such as an office, it is necessary to consider the generated sound.

[0003] In Patent Document 1, for an image forming apparatus provided with an image reading unit, a technique has been proposed to acquire a noise value generated according to an operation mode and change the operation mode so that the noise value becomes small.

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in Patent Document 1, it is a change in the operation mode for reducing the noise value (decibel), and what kind of sound is generated is not considered. That is, even if the noise value is the same, the impression that a person feels about the generated sound varies depending on the type of the generated sound and the like. That is, in the conventional technology, the viewpoint of sound comfort that a person feels about the sound has not been considered.

[0005] An embodiment of the present invention aims to provide a document processing apparatus, an image forming apparatus, a learned model generation apparatus, and an image forming system that suppress the degree of discomfort to a person caused by the generated sound by considering the sound comfort that a person feels about the sound, and improve the comfort of the surrounding environment.

Means for Solving the Problems

[0006] To solve the above-mentioned problems, the document processing apparatus according to the present invention comprises: a tray for loading documents; a transport unit for transporting documents from the tray; a reading unit for reading images represented on documents while the documents are being transported by the transport unit; an acquisition unit for acquiring processing information including at least one of the settings for the transport unit to transport the documents and the settings for the reading unit to read the documents; and an estimation unit for estimating the pleasantness of sounds that a person would perceive in relation to the sounds generated during the transport or reading of documents, based on the processing information acquired by the acquisition unit. [Effects of the Invention]

[0007] According to embodiments of the present invention, it is possible to improve the comfort of the surrounding environment. [Brief explanation of the drawing]

[0008] [Figure 1] This is a schematic diagram showing a copier according to one embodiment. [Figure 2] This is a partial diagram showing a part of the internal configuration of an image forming apparatus according to one embodiment. [Figure 3] This is a partially enlarged view showing a part of the tandem section according to one embodiment. [Figure 4] A perspective view showing the scanner and ADF of a copier according to one embodiment. [Figure 5] This is an enlarged diagram showing the main components of an ADF according to one embodiment, along with the upper part of the scanner. [Figure 6] This is a diagram showing an example configuration of a copier according to the first embodiment. [Figure 7] This figure illustrates the estimation of pleasant sound quality and productivity using a learning model according to the first embodiment. [Figure 8] This figure shows an example of the functional configuration of the document processing system according to the first embodiment. [Figure 9] This is a flowchart illustrating the document processing procedure in the ADF controller according to the first embodiment. [Figure 10] This figure shows an example of a screen related to document processing of the ADF according to the first embodiment. [Figure 11] This is an explanatory diagram showing the estimation of sound quality and productivity for each piece of document processing information by the estimation unit according to the first embodiment. [Figure 12] This flowchart illustrates the document processing procedure in the ADF controller for a modified example. [Figure 13] This is an explanatory diagram showing the learning phase from when the information processing device according to the first embodiment generates a learning model until it is loaded into the ADF. [Figure 14] This flowchart shows the procedure for collecting the information necessary to generate training data according to the first embodiment. [Figure 15] This figure shows the structure of the training data according to the first embodiment. [Figure 16] This is a flowchart showing the procedure for generating a learning model in the information processing device according to the first embodiment. [Figure 17] This is a diagram showing an example configuration of a copier according to the second embodiment. [Figure 18] This figure shows an example configuration of a copier and cloud server according to the third embodiment. [Modes for carrying out the invention]

[0009] Hereinafter, embodiments of the document processing apparatus, image forming apparatus, trained model generation apparatus, and image forming system according to the present invention will be described in detail with reference to the attached drawings.

[0010] (First embodiment) The copier according to this embodiment may, for example, be a multifunction full-color digital copier (MFP (Multifunction Peripheral / Product / Printer)) that forms color images using an electrophotographic method.

[0011] Hereinafter, an embodiment using an electrophotographic copying machine (hereinafter simply referred to as a copying machine) will be described. First, the basic configuration of the copying machine according to the embodiment will be described.

[0012] FIG. 1 is a schematic configuration diagram of a copying machine according to an embodiment. In the example of FIG. 1, the copying machine 100 includes an image forming apparatus 1 as an image forming device, a sheet feeding apparatus 40, and an image reading system 50. The image reading system 50 has a scanner 150 as an image reading device fixed on the image forming apparatus 1, and an original document processing apparatus (hereinafter referred to as an ADF) 51 supported by the scanner 150.

[0013] The sheet feeding apparatus 40 includes two paper feed cassettes 42 arranged in multiple stages in a paper bank 41, a delivery roller 43 that sends out a recording sheet from the paper feed cassette 42, a separation roller 45 that separates the sent-out recording sheets one by one, and the like. Also, for a paper feed path 37 as a conveyance path of the image forming apparatus 1, it also has a plurality of conveyance roller pairs 46 and the like for conveying the recording sheet.

[0014] The paper feed cassette 42 accommodates recording sheets inside in a state of a sheet bundle in which a plurality of recording sheets are stacked. And the top recording sheet of the sheet bundle is pressed by the delivery roller 43. When the delivery roller 43 rotates, the top recording sheet of the sheet bundle is sent out from the paper feed cassette 42.

[0015] Near the paper feed cassette 42, a first conveyance roller of the conveyance roller pair 46 and a second conveyance roller arranged on the side (right side in the figure) of this first conveyance roller are in contact with each other to form a conveyance nip. Also, a separation roller 45 is arranged below the first conveyance roller, and is in contact with the first conveyance roller from below to form a separation conveyance nip.

[0016] The recording sheet, fed out from the paper feed cassette 42 by the rotational drive of the delivery roller 43, enters a separation transport nip formed by the contact between the first transport roller of the transport roller pair 46 and the separation roller 45 located below the first transport roller. In the separation transport nip, the first transport roller, which is in contact with the upper surface of the recording sheet, rotates counterclockwise in the figure, applying a transport force to the recording sheet from the paper feed cassette 42 side towards the feed path 44 side. In contrast, the separation roller 45, which is in contact with the lower surface of the recording sheet, rotates counterclockwise in the figure, applying a transport force to the recording sheet from the feed path 44 side towards the paper feed cassette 42 side, attempting to return the recording sheet to the paper feed cassette 42.

[0017] When only one recording sheet is fed from the paper feed cassette 42, the first transport roller and the separation roller 45 apply transporting forces to the recording sheet in opposite directions at the separation transport nip. This places a load exceeding a predetermined threshold on the drive transmission system of the separation roller 45. When this occurs, a torque limiter installed in the drive transmission system activates, cutting off the transmission of driving force from the DC brushless motor to the separation roller 45. As a result, the separation roller 45 moves along with the recording sheet being transported by the first transport roller, and the recording sheet is discharged from the separation transport nip towards the feed path 44.

[0018] On the other hand, when multiple recording sheets are fed from the paper feed cassette 42 stacked on top of each other, the first transport roller in the separation transport nip applies a transport force to the top recording sheet from the paper feed cassette 42 side toward the feed path 44 side. The top recording sheet is fed out of the separation transport nip toward the feed path 44 side. In response, the separation roller 45 applies a transport force to the lower recording sheet toward the feed path 44 side toward the paper feed cassette 42 side, causing the lower recording sheet to return from the separation transport nip toward the paper feed cassette 42 side. As a result, in the separation transport nip, the top recording sheet is separated from the other recording sheets and fed into the feed path 44 as a single sheet.

[0019] The recording sheet that enters the feed path 44 enters the transport nip of the transport roller pair 46 and is subjected to a transport force directed from the vertical downward to the upward. As a result, within the feed path 44, the recording sheet is transported toward the paper feed path 37 of the image forming apparatus 1.

[0020] The image forming apparatus 1 includes an optical writing device 2, four image forming units 3K, 3Y, 3M, and 3C that form toner images of black, yellow, magenta, and cyan (K, Y, M, C), and also includes a transfer unit 24, a paper transport unit 28, a pair of registration rollers 33, a fixing device 34, a switchback device 36, and a paper feed path 37. The optical writing device 2 drives a light source such as a laser diode or LED located inside the optical writing device 2 to irradiate the four drum-shaped photoreceptors 4K, 4Y, 4M, and 4C with laser light L. Irradiation with laser light L forms an electrostatic latent image on the surface of the photoreceptors 4K, 4Y, 4M, and 4C. This electrostatic latent image is developed into a toner image through a predetermined development process.

[0021] Figure 2 is a partial diagram showing a part of the internal configuration of an image forming apparatus according to one embodiment. Figure 3 is a partially enlarged view showing a part of the tandem section according to one embodiment. Note that the four imaging units 3K, 3Y, 3M, and 3C of the tandem section have almost the same configuration except for the different toner colors they use, so the subscripts K, Y, M, and C attached to each reference numeral are omitted in Figure 3.

[0022] Each of the image-forming units 3K, 3Y, 3M, and 3C supports a photoreceptor 4K, 4Y, 4M, and 4C, along with various devices arranged around it, as a single unit on a common support, and is detachable from the main body of the image forming apparatus 1. Taking the image-forming unit 3K for black as an example, the image-forming unit 3K has a charging device 5, a developing device 6, a drum cleaning device 15, and a static elimination lamp 22, etc., around the photoreceptor 4K. In this copier, the four image-forming units 3K, 3Y, 3M, and 3C are arranged opposite each other along the endless movement direction of the intermediate transfer belt 25, which will be described later, in a so-called tandem configuration.

[0023] For the 4K, 4Y, 4M, and 4C photoreceptors, drum-shaped structures are used, in which a photosensitive layer is formed by coating a photosensitive organic photosensitive material onto a base tube made of aluminum or similar material. However, endless belt-shaped structures may also be used.

[0024] The developing units 6K, 6Y, 6M, and 6C develop latent images using a two-component developer containing a magnetic carrier and a non-magnetic toner. They have an agitation unit 7 that transports the two-component developer contained inside while agitating it and supplies it to the developing sleeve 12, and a developing unit 11 that transfers the toner in the two-component developer supported on the developing sleeve 12 to the photoreceptors 4K, 4Y, 4M, and 4C.

[0025] The stirring unit 7 is located at a lower position than the developing unit 11 and includes two transport screws 8 arranged parallel to each other, a partition plate between the transport screws 8, and a toner density sensor 10 located on the bottom surface of the developing case 9.

[0026] The developing unit 11 includes a developing sleeve 12 that faces the photoreceptors 4K, 4Y, 4M, and 4C through an opening in the developing case 9, a magnetic roller 13 that is not rotatable inside the developing sleeve 12, and a doctor blade 14 that brings its tip close to the developing sleeve 12. The developing sleeve 12 is a non-magnetic, rotatable cylindrical shape.

[0027] The magnetic roller 13 has multiple magnetic poles that are arranged sequentially from a position opposite the doctor blade 14 toward the rotational direction of the developing sleeve 12. Each of these magnetic poles acts a magnetic force on the two-component developer on the developing sleeve 12 at a predetermined position in the rotational direction. This attracts and supports the two-component developer sent from the agitator 7 onto the surface of the developing sleeve 12, and also forms a magnetic brush on the surface of the developing sleeve 12 along the magnetic field lines.

[0028] As the developing sleeve 12 rotates, the magnetic brush passes through a position opposite the doctor blade 14, where it is restricted to an appropriate layer thickness before being transported to the developing area opposite the photoreceptors 4K, 4Y, 4M, and 4C. Thereafter, the development bias applied to the developing sleeve 12 and the potential difference between that and the electrostatic latent image on the photoreceptors 4K, 4Y, 4M, and 4C transfer the toner onto the electrostatic latent image, contributing to the development process.

[0029] Furthermore, as the developing sleeve 12 rotates, the two-component developer returns to the developing unit 11, and after being separated from the sleeve surface by the repulsive magnetic field formed between the magnetic poles of the magnetic roller 13, the two-component developer is returned to the stirring unit 7. In the stirring unit 7, an appropriate amount of toner is supplied to the two-component developer based on the detection result by the toner density sensor 10. Note that instead of using a two-component developer, a developing device 6 that uses a one-component developer without magnetic carriers may also be used.

[0030] In this example, the drum cleaning devices 15K, 15Y, 15M, and 15C use a system in which an elastic cleaning blade 16 is pressed against the photoreceptor 4, but other systems may also be used. To improve cleaning performance, this example employs a system in which a contact conductive fur brush 17, whose outer surface is in contact with the photoreceptors 4K, 4Y, 4M, and 4C, is rotatable in the direction of the arrow in the figure.

[0031] The fur brush 17 also serves the purpose of scraping off the lubricant from the solid lubricant and applying it to the surface of the photoreceptor 4K, 4Y, 4M, and 4C in a fine powder. The metal electric field roller 18, which applies a bias to the fur brush 17, is rotatably mounted in the direction indicated by the arrow in the figure. The tip of the scraper 19 is pressed against the electric field roller 18. The toner adhering to the fur brush 17 is transferred to the electric field roller 18, which is rotating in a counter-direction relative to the fur brush 17 and to which a bias is applied. After being scraped off the electric field roller 18 by the scraper 19, the recovered toner falls onto the recovery screw 20. The recovery screw 20 transports the recovered toner toward the end of the drum cleaning device 15 in a direction perpendicular to the plane of the figure, and hands it over to an external recycling transport device. The recycling transport device sends the received toner to the developing devices 6K, 6Y, 6M, and 6C for recycling.

[0032] The static elimination lamp 22 eliminates static electricity from the photoreceptors 4K, 4Y, 4M, and 4C by light irradiation. After the static elimination, the surfaces of the photoreceptors 4K, 4Y, 4M, and 4C are uniformly charged by the charging device 5, and then light writing is performed by the light writing device 2. The charging device 5 shown in Figure 3 uses a charging roller to which a charging bias is applied, which is rotated while in contact with the photoreceptors 4K, 4Y, 4M, and 4C. The charging device 5 may also use a scorotron charger or the like, which performs non-contact charging on the photoreceptors 4K, 4Y, 4M, and 4C.

[0033] K, Y, M, C toner images are formed on the photoreceptors 4K, 4Y, 4M, and 4C of the imaging units 3K, 3Y, 3M, and 3C by the process described above. Below the imaging units 3K, 3Y, 3M, and 3C, a transfer unit 24 is positioned. The transfer unit 24 moves an intermediate transfer belt 25, which is stretched by multiple rollers, in an endless clockwise direction as shown in the figure, while keeping it in contact with the photoreceptors 4K, 4Y, 4M, and 4C. This forms a primary transfer nip for K, Y, M, C where the photoreceptors 4K, 4Y, 4M, and 4C and the endless intermediate transfer belt 25 come into contact.

[0034] Near the primary transfer nip for K, Y, M, C, the intermediate transfer belt 25 is pressed toward the photoreceptors 4K, 4Y, 4M, 4C by primary transfer rollers 26K, 26Y, 26M, and 26C, which are located inside the belt loop. A primary transfer bias is applied to each of these primary transfer rollers 26K, 26Y, 26M, and 26C by a power supply. As a result, a primary transfer electric field is formed at the primary transfer nip for K, Y, M, C, causing the toner image on the photoreceptors 4K, 4Y, 4M, 4C to be electrostatically moved toward the intermediate transfer belt 25.

[0035] As the intermediate transfer belt 25 moves endlessly in a clockwise direction as shown in the diagram, it sequentially passes through the primary transfer nips for K, Y, M, and C. On the front surface of the intermediate transfer belt 25, the toner images are sequentially superimposed and transferred at each primary transfer nip. Through this superimposed primary transfer, a four-color superimposed toner image (hereinafter referred to as the four-color toner image) is formed on the front surface of the intermediate transfer belt 25.

[0036] Below the transfer unit 24 in the diagram, a paper transport unit 28 is provided, which stretches an endless paper transport belt 29 between the drive roller 30 and the secondary transfer roller 31, causing it to move endlessly. The intermediate transfer belt 25 and the paper transport belt 29 are sandwiched between the secondary transfer roller 31 and the lower tension roller 27 of the transfer unit 24. This forms a secondary transfer nip where the front surface of the intermediate transfer belt 25 and the front surface of the paper transport belt 29 come into contact. A secondary transfer bias is applied to the secondary transfer roller 31 by a power supply. Meanwhile, the lower tension roller 27 of the transfer unit 24 is grounded. As a result, a secondary transfer electric field is formed in the secondary transfer nip.

[0037] A pair of resist rollers 33 is positioned on the right side of the secondary transfer nip in the diagram. A resist roller sensor is also positioned near the entrance of the resist nip of the resist roller pair 33. The recording sheet, which is being transported from the sheet supply device 40 toward the resist roller pair 33, temporarily stops being transported after a predetermined time when its leading edge is detected by the resist roller sensor, and the leading edge comes into contact with the resist nip of the resist roller pair 33.

[0038] When the leading edge of the recording sheet hits the resist nip, the resist roller pair 33 restarts its roller rotation drive at a timing that allows the recording sheet to be synchronized with the four-color toner image on the intermediate transfer belt 25, and feeds the recording sheet to the secondary transfer nip. Inside the secondary transfer nip, the four-color toner image on the intermediate transfer belt 25 is transferred to the recording sheet all at once by the action of the secondary transfer electric field or nip pressure, and combined with the white of the recording sheet, it becomes a full-color image. After passing through the secondary transfer nip, the recording sheet separates from the intermediate transfer belt 25 and is held on the front surface of the paper transport belt 29, and is transported to the fixing device 34 as it moves endlessly.

[0039] Furthermore, residual toner that was not transferred to the recording sheet by the secondary transfer nip adheres to the surface of the intermediate transfer belt 25 after it has passed through the secondary transfer nip. This residual toner is scraped off by the belt cleaning device 32, which comes into contact with the intermediate transfer belt 25.

[0040] The recording sheet, transported to the fixing device 34, has the full-color image fixed by pressurization and heating within the fixing device 34. After that, it is sent from the fixing device 34 to the paper discharge roller pair 35 and then discharged outside the machine.

[0041] In Figure 1, a switchback device 36 is positioned below the paper transport unit 28 and the fixing device 34. As a result, after image fixing on one side of the recording sheet is completed, a switching claw switches the recording sheet's path towards the switchback device 36, where it is reversed and re-enters the secondary transfer nip. The recording sheet then undergoes secondary image transfer and fixing on the other side before being ejected onto the output tray.

[0042] The scanner 150, fixed on the image forming apparatus 1, has a movable reading unit 152. The scanner 150 and the ADF 51 each have a fixed reading unit. The movable reading unit 152 is positioned directly below the second contact glass 155 (see Figure 4), which is fixed to the upper wall of the scanner 150 casing so as to contact the original document MS, and can move the optical system, consisting of a light source and reflective mirrors, in the left-right direction in the figure. As the optical system moves from left to right in the figure, the light emitted from the light source is reflected by the original document MS placed on the second contact glass 155, and then, after passing through multiple reflective mirrors, is received by the image reading sensor 153 fixed to the scanner body.

[0043] On the other hand, the fixed reading unit consists of a first fixed reading unit 151 disposed inside the scanner 150 and a second fixed reading unit 95 (see Figure 5) disposed inside the ADF 51. The first fixed reading unit 151, which has a light source, a reflective mirror, an image reading sensor such as a CCD, is disposed directly below the first contact glass 154 (see Figure 4), which is fixed to the upper wall of the scanner 150 casing so as to contact the original document MS. When the sheet-like original document MS, transported by the ADF 51 (described later), passes over the first contact glass 154, the light emitted from the light source is sequentially reflected from the surface of the document and received by the image reading sensor after passing through multiple reflective mirrors. This scans the first surface of the original document MS without moving the optical system consisting of the light source and reflective mirrors. The second fixed reading unit 95 scans the second surface of the original document MS after it has passed through the first fixed reading unit 151. Note that the first fixed reading unit 151 and the moving reading unit 152 may be the same. In this case, the movable reading unit 152 functions as the first fixed reading unit 151 by performing readings while it is located below the first contact glass 154.

[0044] The ADF 51, positioned above the scanner 150, has a document tray 53 on its main body cover 52, which is a document placement means for placing the original document MS before scanning. The ADF 51 also holds a transport unit 54 for transporting the original document MS as a sheet, and a document stacking table 55 for stacking the scanned original document MS.

[0045] Figure 4 is a perspective view of the scanner and ADF of a copier according to one embodiment. As shown in Figure 4, the ADF 51 is supported so as to be able to swing vertically by a hinge 159 fixed to the scanner 150. The ADF 51 moves like an opening and closing door through its swing, and when opened, exposes the first contact glass 154 and the second contact glass 155 on the upper surface of the scanner 150. In the case of single-sided bound documents, such as books bound at one corner of the stack, the documents cannot be separated one by one, and therefore cannot be transported by the ADF. In the case of single-sided bound documents, after opening the ADF 51 as shown in Figure 4, the single-sided bound document with the pages to be scanned facing downwards is placed on the second contact glass 155, and then the ADF is closed. Then, the image of the page is read by the moving reading unit 152 of the scanner 150 shown in Figure 1.

[0046] On the other hand, in the case of a stack of multiple independent original documents MS, the original documents MS can be automatically transported one by one by the ADF 51 and sequentially read by the first fixed reading unit 151 in the scanner 150 and the second fixed reading unit 95 in the ADF 51 (see Figure 5).

[0047] In this case, after placing the stack of documents on the document tray 53, the copy start key 158 is pressed. The ADF 51 then feeds the documents MS from the stack of documents placed on the document tray 53 into the transport unit 54 from top to bottom, and transports them toward the document stacking table 55 while inverting them. During this transport process, immediately after inverting the documents MS, they pass directly over the first fixed reading unit 151 of the scanner 150. At this time, the image of the first side of the documents MS is read by the first fixed reading unit 151 of the scanner 150.

[0048] Figure 5 is an enlarged diagram showing the main components of the ADF 51 according to one embodiment, along with the upper part of the scanner 150. The ADF 51 includes a document setting section A, a separation and feeding section B, a resist section C, a turning section D, a first reading and transport section E, a second reading and transport section F, a paper discharge section G, a stacking section H, etc. It also includes a document transport path for transporting the document MS from the document tray 53 toward the first fixed reading section 151, which is the image reading position.

[0049] The document setting unit A has a document tray 53, etc., into which a stack of document MS is set. The separation and feeding unit B separates and feeds the document MS one by one from the set stack of document MS. The resist unit C temporarily bumps into the fed document MS to align it before feeding it out. The turning unit D has a curved transport unit that curves in a C shape, and within this curved transport unit, it folds the document MS back and inverts its top and bottom. The first reading and transport unit E transports the document MS on the first contact glass 154 and causes the first fixed reading unit 151, which is located inside the scanner below the first contact glass 154, to read the first side of the document MS. The second reading and transport unit F transports the document MS below the second fixed reading unit 95 and causes the second side of the document MS to be read by the second fixed reading unit 95. The paper discharge unit G discharges the document MS, from which images have been read on both sides, toward the stack unit H. The stacking unit H stacks the original documents MS on the original document stacking platform 55.

[0050] The original document MS is set with its leading edge resting on a movable document table 60, which can pivot in the directions of arrows a and b in the figure according to the thickness of the stack of original documents MS, and its trailing edge resting on the document tray 53. On the document tray 53, the position of the original document MS in the width direction is adjusted by abutting side guides against both ends in the width direction (the direction perpendicular to the paper plane). The original document MS set in this way pushes up a lever member 62 that is pivotably positioned above the movable document table 60. Accordingly, the document set sensor 63 detects the setting of the original document MS and transmits a detection signal to the controller 904 (see Figure 6). The detection signal is then sent from the controller 904 to the scanner's reading control unit 903 via an interface.

[0051] The document tray 53 is a tray for placing documents to be scanned into the ADF 51. The document tray 53 corresponds to, for example, the document setting unit A.

[0052] The document tray 53 holds a first length sensor 57, a second length sensor 58, a third length sensor 202, and a fourth length sensor 201, which are reflective photosensors or actuator-type sensors that detect the length of the document MS in the transport direction. The third length sensor 202 is, for example, a check length sensor. The fourth length sensor 201 is, for example, a business card length sensor. Below, we will describe an example in which the third length sensor 202 is a check length sensor and the fourth length sensor 201 is a business card length sensor.

[0053] The length of the document MS in the transport direction is detected by the first length sensor 57, the second length sensor 58, the third length sensor 202, and the fourth length sensor 201. The third length sensor 202 is positioned so that it is slightly off-center when a check is placed in the document tray. The fourth length sensor 201 is positioned so that it is slightly off-center when a business card is placed in the document tray.

[0054] The detection information from the first length sensor 57, the second length sensor 58, the third length sensor 202, and the fourth length sensor 201 makes it possible to detect whether a document of a specific size, such as a business card or a check, has been placed. As a guideline for the positions of the third length sensor 202 and the fourth length sensor 201, since a check is 185 mm long and a business card is 91 mm long, the third length sensor 202 is positioned at approximately 190 mm and the fourth length sensor 201 at approximately 96 mm, using the fence that the leading edge of the document will hit when it is placed in the document tray as a reference.

[0055] Above the stack of documents MS placed on the movable document table 60, a pickup roller 80 is provided, which is supported by a cam mechanism so as to be movable in the vertical direction (arrows c and d in the figure). This cam mechanism can be driven by a pickup motor 56 to move the pickup roller 80 up and down. When the pickup roller 80 moves upward, the movable document table 60 swings in the direction of arrow a in the figure, and the pickup roller 80 comes into contact with the uppermost document MS in the stack of documents MS.

[0056] As the movable document table 60 rises further, the table rise detection sensor 59 eventually detects that the movable document table 60 has risen to its upper limit. As a result, the pickup motor 56 stops, and the upward movement of the movable document table 60 also stops.

[0057] The user (operator) performs key operations on the operation unit 902, which consists of a numeric keypad 160 on the main body of the copier and a touch panel 161 on the display unit 905, to set the reading mode, such as whether to use double-sided or single-sided scanning mode, and to press the copy start key 158. When the copy start key 158 is pressed by the user, the ADF 51 controller 904 receives a document feed signal from the main unit control unit 901 (see Figure 6). Then, the pickup roller 80 is rotated by the forward rotation of the paper feed motor 76, and the document MS on the movable document table 60 is fed out from the movable document table 60.

[0058] When setting the scanning mode to either double-sided or single-sided, it is possible to set all documents placed on the movable document table 60 to double-sided or single-sided scanning mode at once. Alternatively, it is also possible to set the scanning mode individually for each document, for example, setting the first and tenth documents to double-sided scanning mode and the other documents to single-sided scanning mode.

[0059] The original document MS, fed by the pickup roller 80, enters the separation and feeding section B and is fed to a contact position with the paper feed belt 84. The paper feed belt 84 is stretched by a drive roller 82 and the like, and is moved endlessly in a clockwise direction in the figure by the rotation of the drive roller 82 accompanying the forward rotation of the paper feed motor 76. A separation roller 85, which is rotated clockwise in the figure by the forward rotation of the paper feed motor 76, is in contact with the lower tension surface of the paper feed belt 84. At the contact point, the surface of the paper feed belt 84 moves in the paper feeding direction. In contrast, the separation roller 85 is in contact with the paper feed belt 84 with a predetermined pressure. When the separation roller 85 is in direct contact with the paper feed belt 84, or when only one original document MS is caught in the contact area, it rotates along with the belt or the original document MS. However, when multiple original documents MS are caught in the contact area, the rotational force becomes lower than the torque limiter, so it rotates clockwise in the opposite direction to the rotational force shown in the diagram. As a result, the original documents MS below the top are subjected to a moving force in the opposite direction to the paper feed by the separation roller 85, and only the top original document MS is separated from several other documents (hereinafter, this operation is referred to as the paper feed / separation operation).

[0060] The original document MS, separated into a single sheet by the action of the paper feed belt 84 and the separation roller 85, enters the registration section C. As it passes directly beneath the abutment sensor 72, its leading edge is detected by the abutment sensor 72. At this time, the pickup roller 80, which is driven by the pickup motor 56, is still rotating. However, as the movable document table 60 descends, the pickup roller 80 moves away from the original document MS, and the original document MS is transported solely by the endless movement force of the paper feed belt 84. The endless movement of the paper feed belt 84 continues for a predetermined time from the moment the leading edge of the original document MS is detected by the abutment sensor 72. As a result, the leading edge of the original document MS abuts against the contact point between the pull-out drive roller 86 and the pull-out driven roller 87, which rotates while in contact with it. At this time, by moving away from the original document MS using the moment the leading edge of the original document MS is detected by the abutment sensor 72 as the starting point, the timing at which the original document MS begins to be transported solely by the endless movement force of the paper feed belt 84 can be advanced or delayed. The amount of contact between the original document MS and the pull-out driven roller 87 can be adjusted by advancing or delaying the timing at which the document begins to be transported solely by the endless movement force of the paper feed belt 84.

[0061] Assuming the document speed is 500 mm / s, increasing the contact distance by 1 mm can be achieved by delaying the timing of moving away from the document MS by 2 ms. (500 mm / s × 0.002 s = 1 mm)

[0062] The pull-out driven roller 87 is responsible for transporting the original document MS to the intermediate roller pair 66 downstream in the document transport direction, and is rotationally driven by the reverse rotation of the paper feed motor 76. When the paper feed motor 76 reverses, the pull-out driven roller 87 and one of the rollers in the intermediate roller pair 66, which are in contact with each other, begin to rotate, and the endless movement of the paper feed belt 84 stops. At this time, the rotation of the pickup roller 80 also stops.

[0063] The document MS, fed out from the pull-out driven roller 87, passes directly beneath the document width sensor 73. The document width sensor 73 has multiple paper detection units, each consisting of a reflective photosensor or the like. These paper detection units are arranged in the document width direction (the direction perpendicular to the drawing plane). The width of the document MS is detected based on which paper detection unit detects it. The length of the document MS in the transport direction is detected based on the timing from when the leading edge of the document MS is detected by the stop sensor 72 until the trailing edge of the document MS is no longer detected by the stop sensor 72.

[0064] The leading edge of the document MS, whose width has been detected by the document width sensor 73, enters the turn section D and is caught between the contact points of the intermediate roller pair 66. The transport speed of the document MS by this intermediate roller pair 66 is set to be faster than the transport speed of the document MS in the first reading transport section E, which will be described later. This shortens the time it takes to feed the document MS to the first reading transport section E.

[0065] Thus, the size of the original document (MS) can be detected by the document width sensor 73, the first length sensor 57, the second length sensor 58, the third length sensor 202, and the fourth length sensor 201. On the other hand, the user can also specify the size of the original document (scanning size) using the control unit 902. For example, the user can select and specify business card (55mm x 91mm) and check (85mm x 185mm) sizes from a range of size options.

[0066] As the leading edge of the document MS is transported within the turn section D, it passes a position opposite the reading entrance sensor 67. When the leading edge of the document MS is detected by the reading entrance sensor 67, the document transport speed by the intermediate roller pair 66 is reduced until the leading edge is transported to the position of the reading entrance roller pair (the pair of 89 and 90) on the downstream side in the transport direction. In addition, as the rotational drive of the reading motor 77 (see Figure 6) begins, one roller in the reading entrance roller pair, one roller in the reading exit roller pair 92, and one roller in the second reading exit roller pair 93 each begin to rotate.

[0067] Within the turn section D, the original document MS is transported along a curved transport path between the intermediate roller pair 66 and the reading entrance roller pair, during which its upper and lower surfaces are reversed and its transport direction is reversed. The leading edge of the original document MS, having passed through the nip between the rollers of the reading entrance roller pair, then passes directly beneath the resist sensor 65. Hereafter, the operation up to this point after the paper feeding / separation operation is referred to as the pull-out operation.

[0068] When the leading edge of the document MS is detected by the resist sensor 65, the document transport speed is reduced while traveling a predetermined transport distance. Then, the transport motor 192 (see Figure 6) stops, stopping the rotational drive of the pull-out drive roller 86 and the intermediate roller pair 66, and the read motor 77 stops, stopping the rotational drive of the read inlet roller pair. As a result, the transport of the document MS is temporarily stopped at the resist position in front of the first read transport unit E. A resist stop signal is also sent to the read control unit 903.

[0069] In this embodiment, the separation and feeding unit B, the resist unit C, the turning unit D, the first reading and transport unit E, the second reading and transport unit F, the paper discharge unit G, and the stacking unit H, etc., function as transport units that transport documents from the document tray 53.

[0070] In this embodiment, either the first fixed reading unit 151 or the second fixed reading unit 95 functions as a reading unit that reads the image represented on the original document while it is being transported by the configuration described above as a transport unit.

[0071] Furthermore, the ADF51 is equipped with a sound-collecting microphone 200. The sound signal representing the sound collected by the sound-collecting microphone 200 is transmitted to the controller 904 of the ADF51. The sound-collecting microphone 200 is capable of measuring the noise around the ADF51, and the sound signal collected by the sound-collecting microphone 200 is converted into PCM data by the AD converter in the controller 904 and stored in the RAM 904C. The arrangement of the sound-collecting microphone 200 shown in Figure 4 is just one example, and it may be placed in any location as long as it is capable of measuring the noise around the ADF51.

[0072] <System Configuration> Figure 6 shows an example configuration of a copier 100 according to the first embodiment. The copier 100 includes, for example, an image forming apparatus 1 and an ADF 51 mounted on the image forming apparatus 1. The copier 100 is also connected to a design PC 909 in a communication manner.

[0073] The ADF51 is an example of a document processing device that is mounted on an image forming apparatus and features an autonomous paper feeding mode that allows for paper feeding operations without instructions from the image forming apparatus.

[0074] (Configuration of an image forming apparatus) In the example shown in Figure 6, the image forming apparatus 1 includes, for example, a main control unit 901, an operation unit 902, a reading control unit 903, a display unit 905, and an external communication interface 907. The main control unit 901 has a computer configuration including a CPU (Central Processing Unit) 901A, a ROM (Read Only Memory) 901B, and a RAM (Random Access Memory) 901C.

[0075] The operation unit 902 is an input device, such as a touch panel or operation buttons, that accepts user input. The display unit 905 is a display device, such as a display, that shows display screens, such as operation screens or setting screens. The external communication interface 907 is a communication device for communicating with external devices such as cloud servers.

[0076] (ADF configuration) Figure 6 shows an example of a block diagram of part of the electrical circuit of the ADF (Automatic Document Feeder) 51. In the example in Figure 6, the ADF 51 includes a controller 904, a second fixed reading unit 95, abutment sensor 72, a document width sensor 73, a reading inlet sensor 67, a registration sensor 65, a document set sensor 63, a paper discharge sensor 61, a first length sensor 57, a second length sensor 58, a third length sensor 202, and a fourth length sensor 201, a paper feed motor 76, a reading motor 77, a transport motor 192, a pull-out clutch 193, a paper discharge clutch 194, a design communication I / F 195, a sound collection microphone 200, and the like.

[0077] The controller 904 comprises a computer configuration including a CPU 904A, ROM 904B, and RAM 904C, etc. Preferably, the controller 904 further comprises a storage device. The design communication I / F 195 is a communication device for communicating with the design PC 909.

[0078] The main unit control unit 901 and the reading control unit 903, and the reading control unit 903 and the controller 904 are each connected to each other in a way that allows them to communicate with one another. The controller 904 and the main unit control unit 901 are connected to each other in a way that allows them to communicate with one another via the communication interface 910. In addition, the second fixed reading unit 95 and the main unit control unit 901 are connected to each other in a way that allows them to communicate with one another via the communication interface 911.

[0079] The transport motor 192, connected to the controller 904, is the rotational drive source for the pull-out drive roller 86 and the paper discharge roller pair 94 in the ADF 51. The pull-out clutch 193, also connected to the controller 904, connects and disconnects the rotational drive force of the transport motor 192 to the pull-out drive roller 86. The paper discharge clutch 194 connects and disconnects the rotational drive force of the transport motor 192 to the paper discharge roller pair 94, which is the paper feeding and transporting means.

[0080] Upon receiving a registration stop signal from the controller 904, the reading control unit 903 transmits a reading start signal, which is a paper feed permission signal, to the controller 904. Upon receiving the reading start signal, the controller 904 resumes the rotation of the transport motor 192 and the reading motor 77. Then, at the timing when the leading edge of the document MS, calculated based on the pulse count of the reading motor 77, reaches the reading position by the first fixed reading unit 151 (see Figure 5), the controller 904 transmits a gate signal to the reading control unit 903 indicating the effective image area in the sub-scanning direction of the first surface of the document MS. This transmission continues until the trailing edge of the document MS leaves the reading position by the first fixed reading unit 151, and the first surface of the document MS is read by the first fixed reading unit 151.

[0081] After the document MS has passed through the first reading transport unit E, it passes through the reading exit roller pair 92, and its leading edge is detected by the paper discharge sensor 61. When the single-sided reading mode is set, reading the second side of the document MS by the second fixed reading unit 95 is unnecessary. Therefore, when the leading edge of the document MS is detected by the paper discharge sensor 61, the driving force of the transport motor 192 is connected to the paper discharge roller pair 94 by the paper discharge clutch 194. Then, based on the pulse count of the paper discharge motor since the leading edge of the document MS was detected by the paper discharge sensor 61, the timing for the trailing edge of the document MS to exit the nip of the paper discharge roller pair 94 is calculated. Based on this calculation result, the operation of the paper discharge clutch 194 is stopped.

[0082] On the other hand, when the double-sided reading mode is set, the timing from when the leading edge of the document MS is detected by the paper ejection sensor 61 until it reaches the second fixed reading unit 95 is calculated based on the pulse count of the reading motor 77. The controller 904 then transmits a gate signal to the reading control unit 903 at the timing calculated, indicating the effective image area in the sub-scanning direction on the second side of the document MS. This transmission continues until the trailing edge of the document MS leaves the reading position of the second fixed reading unit 95, and the second side of the document MS is read by the second fixed reading unit 95.

[0083] The second fixed reading unit 95 consists of a contact image sensor (CIS), and its reading surface is coated to prevent vertical streaks caused by adhesive foreign matter adhering to the document MS adhering to the reading surface. Opposite the second fixed reading unit 95, a second reading roller 96 is provided as a document support means for supporting the document MS from the non-reading side. The second reading roller 96 prevents the document MS from lifting at the reading position by the second fixed reading unit 95 and also functions as a reference white area for acquiring shading data in the second fixed reading unit 95.

[0084] <Explanation of Pleasant Sound Judgment> Traditionally, there have been technologies to change the operating mode of photocopiers and similar devices to reduce noise levels (decibels) according to the surrounding environment. However, the perception of how the sounds generated by photocopiers and similar devices affect people has not been considered. For example, even if the noise level (decibels) is the same, the degree of discomfort caused to people will differ depending on whether the sound is rhythmic or dissonant.

[0085] Therefore, in the ADF 51 according to this embodiment, the document reading control is performed taking into consideration the perspective of how pleasant a sound is perceived by humans. For this purpose, the controller 904 of the ADF 51 determines the pleasantness of the sound generated when the ADF 51 reads the document MS. In this embodiment, a learning model 1100 is used to determine the pleasantness of the sound. In this embodiment, the learning model 1100 is stored in the ROM 904B of the controller 904. The CPU 904A of the controller 904 then loads the learning model 1100 into RAM 904C or the like and uses it for processing.

[0086] The learning model 1100 is a model trained using training data, with manuscript processing information as input data and sound quality and productivity (number of manuscripts processed per predetermined time) as output data.

[0087] In other words, the learning model 1100 estimates the pleasantness of the sound generated by the ADF 51 and the productivity of the ADF 51 when the ADF 51 processes the document according to the document processing information.

[0088] The document processing information includes at least one of the following: settings for transporting the document by the transport unit (e.g., the separation and feeding unit B, the resist unit C, the turning unit D, the first reading and transport unit E, the second reading and transport unit F, the paper discharge unit G, and the stacking unit H); and settings for reading the document by the reading unit (e.g., either the first fixed reading unit 151 or the second fixed reading unit 95). The document processing information according to this embodiment further includes information about the document placed in the document tray 53.

[0089] Document processing information includes, for example, information such as scanning settings (single-sided / double-sided), paper feed speed, first abutment depth, pull-out speed, second abutment depth, document interval time, and whether the pull-out driven roller stops at the second abutment. Document processing information also includes, for example, document size, paper type, and paper thickness. Of the document processing information, those that do not affect the scanning function and can be changed include, for example, paper feed speed, first abutment depth, pull-out speed, second abutment depth, document interval time, and whether the pull-out driven roller stops at the second abutment.

[0090] The paper feed speed is the maximum transport speed from the start of separate feeding until the leading edge of the document reaches the pull-out driven roller 87. The pull-out speed is the maximum transport speed from the leading edge of the document from the pull-out driven roller 87 until it reaches the reading inlet roller pair (89, 90). The first abutment amount is the amount the document abuts against the pull-out driven roller 87, and the second abutment amount is the amount the document abuts against the reading inlet roller pair (89, 90). The document interval time is the time from when the trailing edge of one continuously transported document passes the first fixed reading unit 151 until the leading edge of the next document reaches the first fixed reading unit 151.

[0091] The "stopping of the pull-out driven roller at the second abutment" indicates whether the abutment occurs with the pull-out driven roller completely stopped (stopped) or whether the abutment occurs while the pull-out driven roller is rotating at the reading speed (not stopped).

[0092] The document processing information according to this embodiment includes, in addition to settings for when the document is transported and settings for reading the document, information about the document placed in the document tray 53 (e.g., document size, paper type, and paper thickness). However, the document processing information is not limited to including information about the document placed in the document tray 53, and does not need to include information about the document placed in the document tray 53. The document processing information described above is merely an example of settings for transporting the document and settings for reading the document, and may include any settings related to the transporting or reading of the document.

[0093] "Pleasantness of sound" is an index that indicates the level of comfort a person feels when listening to a sound. For example, if the sound waveform produced by the operation of the ADF51 has regularity, in other words, if a rhythmic sound is produced, the pleasantness of sound is considered to be high. Conversely, if dissonance occurs due to multiple sounds resonating from the multiple components of the ADF51, the pleasantness of sound is considered to be low. Furthermore, if a sudden loud sound is heard, the pleasantness of sound is also considered to be low.

[0094] In this embodiment, the pleasantness of a sound is represented by a numerical value from 1 to 10. That is, a pleasantness of "1" represents the most unpleasant sound, and the higher the pleasantness of the sound, the more pleasant the sound, with a pleasantness of "10" representing the most pleasant sound. Note that this embodiment shows an example of using a numerical value to represent pleasantness, and is not limited to the method of representing pleasantness with a numerical value.

[0095] The "pleasantness" of the sound used in the training data for the learning model 1100 is set based on evaluation results from users who have actually listened to the sound in question.

[0096] Productivity indicates the number of pages that can be read per given time (e.g., one minute).

[0097] Figure 7 is a diagram illustrating the estimation of noise level and productivity by the learning model 1100 according to this embodiment. In this embodiment, the ADF 51 estimates noise level and productivity by the learning model 1100 when reading a document placed on the document tray 53. For example, the ADF 51 controller 904 provides the learning model 1100 with document processing information set in the image forming apparatus 1 as input data, and receives noise level and productivity as output data from the learning model 1100.

[0098] The ADF51's controller 904 determines whether the perceived pleasantness of the sound received from the learning model 1100 exceeds a predetermined standard. If it determines that the pleasantness of the sound is below the standard, it changes the settings to increase the pleasantness of the sound. In addition to pleasantness, the controller 904 may also change the settings based on productivity. For example, the controller 904 may change to the setting that has the highest productivity among the settings where the pleasantness of the sound is higher than the standard. The controller 904 may change the settings automatically, or it may change the settings when it receives a request for a change from the user.

[0099] <Functional Configuration> Figure 8 shows an example of the functional configuration of a document processing system according to the first embodiment. The document processing system is implemented, for example, by an ADF (Document Processing Unit) 51. In the example in Figure 8, the ADF 51 implements an acquisition unit 1801, a communication control unit 1802, a determination unit 1803, an estimation unit 1804, a setting change unit 1805, a display control unit 1806, and an operation reception unit 1807 by the CPU 904A executing a program stored in the ROM 904B. The learning model 1100 is stored in the ROM 904C of the ADF 51.

[0100] The acquisition unit 1801 acquires detection results from various sensors. For example, the acquisition unit 1801 acquires the noise level of the surrounding environment from the sound-collecting microphone 200.

[0101] Furthermore, the acquisition unit 1801 receives document processing information from the image forming apparatus 1. In addition, the acquisition unit 1801 acquires image forming apparatus information from the image forming apparatus 1.

[0102] The image forming apparatus information is information that indicates the current status for confirming sounds, etc., being generated by the image forming apparatus 1, and includes, for example, whether or not the image forming apparatus 1 is in operation, and the current operating mode set for the image forming apparatus 1.

[0103] The communication control unit 1802 transmits or receives information with various devices. For example, the communication control unit 1802 performs processing to transmit or receive information with the design PC 909, which is connected via the design communication interface 195.

[0104] The determination unit 1803 determines whether the surrounding environment is quiet enough for the ADF 51 to consider the pleasantness of the sound. In other words, the controller 904 according to this embodiment controls the ADF 51 to emit a highly pleasant sound when the surrounding environment is quiet, and when the surrounding environment is noisy, it is presumed that the sound emitted by the ADF 51 will be drowned out, so it processes without considering the pleasantness of the sound. The specific determination details will be described later.

[0105] The estimation unit 1804, when it determines that the surrounding environment is quiet enough for the ADF 51 to consider the pleasantness of the sound it emits when transporting or reading a document, estimates the pleasantness of the sound emitted by the ADF 51 based on the document processing information. Furthermore, the estimation unit 1804 according to this embodiment also estimates the number of documents that can be processed per predetermined time (for example, 1 minute), in other words, productivity. As a specific example, when document processing information is input to the learning model 1100, the estimation unit 1804 receives the estimation results of pleasantness and productivity from the learning model 1100.

[0106] The setting change unit 1805 changes the settings to increase the pleasant sound quality if the estimation unit 1804 estimates that the pleasant sound quality based on the original processing information is lower than the standard. The specific processing procedure will be described later.

[0107] The display control unit 1806 controls the display of information on the display unit 905 of the image forming apparatus 1. For example, the display control unit 1806 controls the transmission of information to be displayed to the image forming apparatus 1 via the connection I / F 910.

[0108] The operation reception unit 1807 receives operations related to the ADF 51 that are input to the operation unit 902. For example, the operation reception unit 1807 receives operations related to the operating mode of the ADF 51.

[0109] Note that the functional configuration of the document processing system shown in Figure 8 is just one example. For example, at least some of the functional configurations of the ADF51 shown in Figure 8 may be provided by the image forming apparatus 1, the design PC 909, or an external device (e.g., a cloud server).

[0110] <Processing flow> Next, the processing flow of the document processing method performed by the ADF51 according to this embodiment will be described.

[0111] Figure 9 is a flowchart illustrating the document processing procedure in the controller 904 of the ADF51 according to the first embodiment.

[0112] Figure 10 shows an example of a screen related to document processing of the ADF 51 according to the first embodiment. Figure 10(a) is an example of the sound mode setting screen included in the settings screen of the ADF 51 displayed by the display control unit 1806. The sound mode setting screen shown in Figure 10(a) shows a radio button 2001A for selecting the sound mode, a radio button 2001B for selecting the productivity priority mode, a radio button 2001C for selecting the mode each time a mode is selected for document processing, and a confirmation button 2002. The operation reception unit 1807 receives the selection of radio button 2001A, radio button 2001B, or radio button 2001C via the operation unit 902, and when it receives the press of the confirmation button 2002, the controller 904 proceeds with processing according to the selected mode during document processing.

[0113] When the operation reception unit 1807 receives a selection of radio button 2001A (pleasant sound mode), the controller 904 performs the processing shown in Figure 9, without displaying the screen as shown in S1910 in Figure 9, and automatically performs the processing for the "YES" case in the branching process at S1911 in Figure 9. When the operation reception unit 1807 receives a selection of radio button 2001B (productivity priority mode), the controller 904 performs the processing shown in Figure 9, without displaying the screen as shown in S1910 in Figure 9, and automatically performs the processing for the "NO" case in the branching process at S1911 in Figure 9. When the operation reception unit 1807 receives a selection of radio button 2001C (select each time mode), the controller 904 performs the processing according to the procedure shown in Figure 9.

[0114] In this embodiment, the operation reception unit 1807 has been described in an example where it accepts the selection of a radio button as an operation related to changing settings. However, this embodiment is not limited to accepting the selection of a radio button, and any configuration that can accept confirmation regarding the change of settings is acceptable.

[0115] Returning to Figure 9, the acquisition unit 1801 collects (acquires) ambient noise levels from the sound-collecting microphone 200 (S1901). The timing for collecting ambient noise levels is such that all drive mechanisms of the image forming apparatus 1 and ADF 51 are stopped, so as not to collect the operating sounds of the image forming apparatus 1 and ADF 51.

[0116] Next, the determination unit 1803 determines whether the collected noise level exceeds a predetermined threshold and records the determination result in the RAM 904B (S1902).

[0117] Then, the operation reception unit 1807 receives a scan start command from the operation unit 902 (S1903).

[0118] The acquisition unit 1801 acquires document processing information and image forming apparatus information from the image forming apparatus 1 (S1904). The document processing information indicates the settings for processing the document in accordance with the start of scanning. The image forming apparatus information includes whether the image forming apparatus 1 is currently operating or not, as well as the operating mode set for the image forming apparatus 1.

[0119] Then, the determination unit 1803 determines whether the noise level exceeded a predetermined threshold in the determination result recorded in the RAM 904B (S1905). If the determination unit 1803 determines that the noise level exceeded a predetermined threshold (S1905: YES), the controller 904 determines that there is no need to consider noise levels because the surrounding noise level is high, in other words, there is no need to change the settings for the transport unit to transport the document, and (without estimating noise levels) starts the paper feeding and reading operations of the ADF 51 based on the document processing information (S1913). Thus, the controller 904 can maintain productivity.

[0120] On the other hand, if the determination unit 1803 determines in the determination result recorded in RAM 904B that the noise level does not exceed a predetermined threshold (S1905: NO), it determines, based on the image forming apparatus information, whether the image forming apparatus 1 is not operating, or whether it is operating but in silent low-speed mode (S1906). If the determination unit 1803 determines that the image forming apparatus 1 is operating and not in silent low-speed mode (S1906: NO), the controller 904 determines that even if the ADF 51 improves its noise level due to the operating noise generated from the image forming apparatus 1, people in the surrounding area will not perceive the noise level as pleasant, and based on the document processing information, it starts the paper feeding and reading operations of the ADF 51 (S1913).

[0121] On the other hand, if the determination unit 1803 determines that the image forming apparatus 1 is not operating, or is operating but in quiet low-speed mode (S1906: YES), the estimation unit 1804 assumes that the noise level of the ADF 51 is important because the surrounding environment is relatively quiet, and estimates the noise level from the document processing information (S1907). Specifically, the estimation unit 1804 inputs the document processing information into the learning model 1100 and receives information indicating the noise level and productivity from the learning model 1100.

[0122] The estimation unit 1804 then determines whether the received pleasant sound quality is below the standard (S1908). If the estimation unit 1804 determines that the pleasant sound quality is above the standard (S1908: YES), the controller 904 starts the paper feeding and reading operations of the ADF 51 based on the document processing information (S1913).

[0123] On the other hand, if the estimation unit 1804 determines that the pleasing sound quality is below the standard (S1908: NO), the estimation unit 1804 generates multiple candidate document processing information from the document processing information, with some parameters that do not affect the reading function being changed. The estimation unit 1804 estimates the pleasing sound quality and productivity for each of the multiple candidate document processing information, and identifies the candidate with the highest productivity among the candidates whose pleasing sound quality is higher than the standard (S1909). The estimation unit 1804 can receive the pleasing sound quality and productivity for each candidate by inputting the multiple candidate document processing information, with parameters that do not affect the reading function being changed from the document processing information, into the learning model 1100. Next, the method for determining whether the pleasing sound quality is below the standard will be explained.

[0124] Figure 11 is an explanatory diagram showing the estimation of noise level and productivity for each piece of document processing information by the estimation unit 1804 according to this embodiment. In the example shown in Figure 11, candidate document processing information changes 1 to 5 are generated by varying the paper feed speed, first abutment amount, pull-out speed, second abutment amount, document interval time, and whether or not the pull-out driven roller stops at the second abutment, which do not affect the reading function.

[0125] In the example shown in Figure 11, the "average value of the pleasant sound level (estimated)" and the "standard deviation of the pleasant sound level (estimated)" are used as examples of parameters indicating pleasant sound. In this embodiment, as a method for comprehensively evaluating pleasant sound, it is determined whether the pleasant sound level is below a standard based on two elements: the "average value of the pleasant sound level (estimated)" and the "standard deviation of the pleasant sound level (estimated)".

[0126] The average value (estimated) of the pleasantness level is the estimated value obtained by multiple people listening to the sound in question. The standard deviation of the pleasantness level is the value obtained by multiple people listening to the sound in question, expressed as the standard deviation of the variation in pleasantness. A larger standard deviation of the pleasantness level indicates that there is a greater variation in the perception of the sound between those who find it unpleasant and those who find it pleasant. Therefore, a smaller standard deviation (estimated) of the pleasantness level indicates a more desirable pleasantness. Note that this embodiment does not limit the parameters indicating pleasantness to the use of "average value (estimated) of the pleasantness level" and "standard deviation (estimated) of the pleasantness level." For example, only "average value (estimated) of the pleasantness level" may be used, or other parameters such as the sum of the pleasantness levels may be used.

[0127] In this embodiment, these two elements are used because pleasantness of sound cannot be simply quantified by measuring noise with a sound level meter, as people perceive it differently. In other words, even if the operating sound is the same, it is thought that there will be variations in whether or not it is perceived as pleasant depending on the person or environment. Therefore, if the judgment is made only by the average pleasantness level, it may not be a problem for many users, but it may be very unpleasant for some other users. Accordingly, in this embodiment, a high average pleasantness level and a small standard deviation of pleasantness level are considered preferable as an overall evaluation.

[0128] Furthermore, "estimated number of pages readable per hour" is used as an example of a parameter indicating productivity.

[0129] The criterion for determining the "average value (estimated) of the pleasant sound level" is whether or not it is greater than the baseline value of 5.5 for the average. The criterion for determining the "standard deviation (estimated) of the pleasant sound level" is whether or not it is less than the baseline value of 0.35 for the standard deviation.

[0130] In other words, the estimation unit 1804 determines that the pleasantness of the sound is higher than the standard if the "average value of the pleasantness level (estimated)" is greater than the standard value for the average of 5.5, and the "standard deviation of the pleasantness level (estimated)" is less than the standard value for the standard deviation of 0.35. On the other hand, the estimation unit 1804 determines that the pleasantness of the sound is below the standard if the "average value of the pleasantness level (estimated)" is less than or equal to the standard value for the average of 5.5, or if the "standard deviation of the pleasantness level (estimated)" is greater than or equal to the standard value for the standard deviation of 0.35.

[0131] In the example shown in Figure 11, the original manuscript processing information shows that the "average value of the pleasant sound level (estimated)" is "3" and the "standard deviation of the pleasant sound level (estimated)" is "0.4". Therefore, the estimation unit 1804 estimates that the "average value of the pleasant sound level (estimated)" and the "standard deviation of the pleasant sound level (estimated)" are below the standard for pleasantness.

[0132] Furthermore, in the example shown in Figure 11, whether or not the comfort level is exceeded is indicated in parentheses with "○" or "×".

[0133] The estimation unit 1804 then estimates the "average value of the pleasant sound level (estimated)", "standard deviation of the pleasant sound level (estimated)", and "number of pages that can be read per unit of time (estimated)" for each of the five candidate document processing information changes, which involve modifying parameters that do not affect the reading function.

[0134] Change candidates 1 through 5 are automatically generated by changing parameters that do not affect the reading function. Therefore, sound quality and other aspects have not been measured.

[0135] However, the estimation unit 1804 according to this embodiment is able to estimate the pleasantness and productivity of each of the automatically generated change candidates 1 to 5 by using the learning model 1100.

[0136] In this embodiment, the estimation unit 1804 inputs document processing information corresponding to each of the change candidates 1 to 5 to the learning model 1100. As a result, the estimation unit 1804 receives from the learning model 1100 the "average value of pleasant sound level (estimated)", the "standard deviation of pleasant sound level (estimated)", and the "number of readable pages per unit time (estimated)" for each of the change candidates 1 to 5.

[0137] The estimation unit 1804 then identifies conversion candidates that meet the criteria for comfort based on the received estimation results. In the example shown in Figure 11, the estimation unit 1804 identifies conversion candidates 4 and 5 as conversion candidates that meet the criteria.

[0138] The estimation unit 1804 then identifies conversion candidate 4, which has a higher "estimated number of readable pages per unit of time" among conversion candidates 4 and 5, as the setting for conversion.

[0139] Returning to Figure 9, the display control unit 1806 displays the sound quality setting notification screen (S1910). In other words, the display control unit (an example of an output control unit) 1806 outputs a notification to the display unit 905 regarding a change in the settings for transporting the document by the transport unit.

[0140] Figure 10(b) shows an example of the sound quality setting notification screen displayed by the display control unit 1806 in S1910. The sound quality setting notification screen shown in Figure 10(b) shows a "Yes" button 2011 and a "No" button 2012. The operation reception unit 1807, via the operation unit 902, changes the determination result in S1911 in Figure 9 depending on which of the "Yes" button 2011 and the "No" button 2012 is pressed.

[0141] Returning to Figure 9, the setting change unit 1805 determines whether the operation reception unit 1807 has received confirmation that the "Yes" button 2011 has been pressed (S1911). If the setting change unit 1805 determines that the "No" button 2012 has not been pressed, in other words, that the "No" button 2012 has been pressed (S1911; NO), the controller 904 considers that the productivity priority mode has been selected and starts the paper feeding and scanning operations of the ADF 51 based on the document processing information (S1913). In this way, if the user does not mind the noise of the ADF 51 or does not want to reduce productivity, the ADF 51 can be operated without making changes based on the document processing information. Therefore, productivity can be maintained using the ADF 51.

[0142] On the other hand, if the setting change unit 1805 determines that the "Yes" button 2011 has been pressed (S1911; YES), it considers that the "Pleasant Sound Mode" has been selected and changes the settings for processing the document according to the identified candidate document processing information (S1912). In this way, the setting change unit 1805 changes the settings for transporting the document based on the estimation result of the pleasant sound level by the estimation unit 1804.

[0143] Then, the controller 904 starts the paper feeding and reading operations of the ADF 51 based on the changed settings (S1913).

[0144] The display control unit 1806 determines whether the conditions for displaying the questionnaire have been met (S1914). The conditions for displaying the questionnaire can be determined according to the embodiment; for example, it may be when the settings are changed in S1912, or when a predetermined probability is met in the lottery among cases where the settings are changed in S1912. If the display control unit 1806 determines that the conditions for displaying the questionnaire have not been met (S1914: NO), the process ends.

[0145] If the display control unit 1806 determines that the conditions for displaying the questionnaire have been met (S1914: YES), it displays the satisfaction questionnaire screen (S1915).

[0146] Figure 10(c) shows an example of a satisfaction survey screen. The satisfaction survey screen shown in Figure 10(c) shows a pull-down menu 2021 for selecting a satisfaction level from "1" to "10", and a confirmation button 2022. The operation reception unit 1807 receives the selection of a satisfaction level from the pull-down menu 2021 via the operation unit 902, and when the confirmation button 2022 is pressed, the controller 904 considers that the satisfaction level input is complete and proceeds with processing.

[0147] Returning to Figure 9, the communication control unit 1802 associates the original document processing information (an example of the settings before the change), the changed settings, and the selected satisfaction level options, and sends them to an external device (e.g., the design PC 909) (S1916), and terminates the process. The timing of transmission is not limited to sending each time a survey is conducted. For example, the controller 904 may store the number of times the settings have been changed in the ROM 904A, and at any time, associate the original document processing information, the changed settings, and the selected satisfaction level options, and send all of that number of times together to the external device.

[0148] The external device can recognize changes in sound quality for each environment and setting based on the received information. Then, by conducting sound quality evaluation experiments according to the received information, it is possible to obtain training data suitable for machine learning. Therefore, the designers of the ADF51 can recognize under what conditions the sound quality deteriorates when the user actually uses it. Furthermore, the designers can efficiently obtain training data by conducting measurements and sound quality evaluation experiments based on the received information. Therefore, this embodiment can improve the accuracy of sound quality estimation using the learning model 1100.

[0149] Furthermore, it is thought that the sounds perceived as pleasant differ depending on the industry or site of the destination of the copier 100; in other words, the average level of pleasant sound and the variation (standard deviation) of the pleasant sound level will differ. In response to this, the copier 100 according to this embodiment can collect actual satisfaction levels by accepting input on a satisfaction questionnaire screen. External devices can generate training data that takes into account the choices and other information included in the received information and perform additional learning to generate a learning model 1100 that takes into account the industry or site of the destination.

[0150] As shown in the flowchart above, the setting change unit 1805 can improve the sound quality by changing the settings for transporting the document based on the estimation result of the sound quality estimation by the estimation unit 1804.

[0151] The processing procedure shown in Figure 9 illustrates an example of operating the ADF 51 in a loud noise mode as needed, since the ADF 51 is expected to make noise when the image forming apparatus 1 is not operating or is operating in silent, low-speed mode. However, the controller 904 according to this embodiment is not limited to the method of switching processing according to the operating status of the image forming apparatus 1 as shown in Figure 9. As a modification, the controller 904 may also notify the image forming apparatus 1 of the desire to operate the ADF 51 in loud noise mode, and then operate the image forming apparatus 1 in silent, low-speed mode.

[0152] Figure 12 is a flowchart illustrating the document processing procedure in the controller 904 of the ADF51 according to a modified example. The controller 904 performs the same processing as S1901 to S1905 of the processing procedure shown in Figure 9 (S2101 to S2105).

[0153] In the modified ADF 51, after processing in S2105, the controller 904 does not perform a determination as shown in S1906 in Figure 9, but instead the estimation unit 1804 estimates the pleasantness of the sound from the document processing information (S2106). Specifically, the estimation unit 1804 inputs the document processing information to the learning model 1100 and receives information indicating the pleasantness of the sound and productivity from the learning model 1100.

[0154] The estimation unit 1804 then determines whether the received pleasant sound quality is below the standard (S2007). The method for determining whether the pleasant sound quality is below the standard is as described above and will not be explained further. If the estimation unit 1804 determines that the pleasant sound quality is above the standard (S2007: YES), the controller 904 starts the paper feeding and reading operations of the ADF 51 based on the document processing information (S2113).

[0155] On the other hand, if the estimation unit 1804 determines that the pleasant sound quality is below the standard (S2007: NO), it performs the same processing as in Figure 9 and S1909-S1910, up to displaying the pleasant sound quality setting notification screen (S2108-S2109). The pleasant sound quality setting notification screen is the same as in Figure 10(b).

[0156] Then, the setting change unit 1805 determines whether or not the operation reception unit 1807 has received confirmation that the "yes" button 2011 has been pressed (S2110). If the setting change unit 1805 determines that it has received confirmation that the "yes" button 2011 has not been pressed, in other words, that the "no" button 2012 has been pressed (S2110; NO), the controller 904 assumes that the productivity priority mode has been selected and starts the paper feeding and reading operations of the ADF 51 based on the document processing information (S2113).

[0157] On the other hand, if the setting change unit 1805 determines that the operation reception unit 1807 has received confirmation that the "yes" button 2011 has been pressed (S2110; YES), it considers that the "pleasant sound mode" has been selected and changes the settings for processing the document according to the identified candidate document processing information (S2111).

[0158] Furthermore, the setting change unit 1805 notifies the image forming apparatus 1 that a setting change has been made for quieter operation (S2112). When the main control unit 901 of the image forming apparatus 1 receives this notification, it switches the operating mode to the quiet low-speed mode. In the quiet low-speed mode, the image forming apparatus 1 lowers the drive speed of the drive mechanisms included in the image forming apparatus 1, such as the transport motor 192, paper feed motor 76, and reading motor 77, compared to the normal mode.

[0159] In other words, even if the ADF 51 improves noise reduction, if the operating noise of the image forming apparatus 1 is loud, people around the copier 100 will not be able to perceive the improved noise reduction of the ADF 51. Therefore, in this modified example, when the noise reduction mode is selected for the ADF 51, the main unit control unit 901 controls the operating noise of the image forming apparatus 1 to prevent it from resonating, thereby suppressing discomfort to people around the copier 100.

[0160] Then, the controller 904 starts the paper feeding and reading operations of the ADF 51 based on the changed settings (S2113).

[0161] The display control unit 1806 determines whether the conditions for displaying the questionnaire have been met (S2114). The conditions for displaying the questionnaire may be determined according to the embodiment. If the display control unit 1806 determines that the conditions for displaying the questionnaire have not been met (S2114: NO), the process terminates.

[0162] If the display control unit 1806 determines that the conditions for displaying the questionnaire have been met (S2114: YES), it displays the satisfaction questionnaire screen (S2115). Then, the operation reception unit 1807 receives the satisfaction level selection from the satisfaction questionnaire screen via the operation unit 902.

[0163] The communication control unit 1802 associates the original document processing information, the changed settings, and the selected satisfaction level options, transmits them to an external device (e.g., the design PC 909) (S2116), and terminates the processing.

[0164] In this embodiment and the modified version described above, when the operating noise of the image forming apparatus 1 is low, control is performed to improve the pleasantness of the sound of the ADF 51, thereby preventing the pleasant sound produced by the ADF 51 from being drowned out by the operating noise of the image forming apparatus 1. Therefore, in this embodiment and the modified version of the copier 100, when the operating noise of the image forming apparatus 1 is low, the ADF 51 is controlled to emit only pleasant sounds, thus preventing it from causing discomfort to those nearby.

[0165] Next, we will describe the generation of a learning model 1100 for determining sound quality and productivity. In this embodiment, we will describe an example in which the training phase and the inference phase are performed on different devices.

[0166] Figure 13 is an explanatory diagram showing the learning phase from when the information processing device 1200 according to this embodiment generates the learning model 1100 until it is loaded onto the ADF 51.

[0167] As shown in Figure 13, the learning model 1100 generated by the information processing device 1200 is mounted on the ADF 51. This embodiment describes an example in which the learning phase and the inference phase are performed on different devices, but it is not limited to the method of performing the learning phase and the inference phase on different devices, and the learning phase and the inference phase may be performed on the same device.

[0168] The information processing device 1200 is an example of a trained model generation device and executes the training phase. The information processing device 1200 may be a cloud server, a desktop PC (Personal Computer), or a portable terminal device such as a smartphone or tablet.

[0169] The information processing device 1200 generates a learning model 1100 by performing machine learning based on a training dataset. The learning model 1100 is generated by applying supervised learning based on training data to the base neural network.

[0170] The training data is information for generating the learning model 1100, and includes settings for processing manuscripts, such as manuscript processing information, and information indicating the quality and productivity when using those settings. Furthermore, the training data according to this embodiment also includes manuscript information. This embodiment can improve the accuracy of estimation by including the above-mentioned information in the training data. Specific training data will be described later.

[0171] For example, a neural network may be applied as the machine learning method used to generate the learning model 1100. Another example is machine learning using a deep neural network (DNN), which is deep learning. For example, convolutional neural networks, RNNs (Recurrent Neural Networks), and LSTMs (Long Short-Term Memory) may be applied as deep learning methods.

[0172] In this embodiment, the ADF51 stores a configuration corresponding to the learning model 1100 generated by the information processing device 1200 in the ROM 904B. The learning model 1100 is a type of computation algorithm and is modularized and stored as part of the control program of the ADF51's controller 904.

[0173] The example in Figure 13 shows the case where the learning model 1100 is stored in the ROM 904B of the ADF 51. However, the learning model 1100 may be implemented in the main control unit 901 of the image forming apparatus 1, or it may be implemented in an external device such as a cloud server 908.

[0174] Next, the training data used to generate the learning model 1100 will be described. Figure 14 is a flowchart showing the procedure for collecting the information necessary to generate the training data according to this embodiment. The ADF 51 used to generate the training data may be connected to the image forming apparatus 1, or it may be operated independently without being connected to the image forming apparatus 1. If the ADF 51 is operated independently, only power needs to be supplied. For this reason, the user should set up in advance to supply power to the ADF 51 using a stabilized power supply or the like.

[0175] Then, the designer (user) turns on the power to the ADF51 board (S2301). When power is supplied, the ADF51 enters a state of waiting for communication from the image forming apparatus 1.

[0176] The design PC909 instructs the ADF51 via the design communication I / F195 to start the autonomous paper feed mode according to the designer's (user's) instructions (S2302). In autonomous paper feed mode, the ADF51 is configured to automatically start paper feeding when the document set sensor 63 detects that a document has been placed.

[0177] In this embodiment, the data collection process can be simplified by collecting the information necessary for generating training data in autonomous paper feeding mode. Furthermore, since the main body of the image forming apparatus 1 is not operated, it becomes possible to collect the information necessary for generating training data without being affected by noise generated from the image forming apparatus 1.

[0178] The design PC 909 transmits document processing information, which indicates the settings for evaluating noise level and productivity, to the ADF 51 via the design communication I / F 195, according to the designer's (user's) instructions (S2303). The ADF 51's controller 904 then sets the settings according to the received document processing information. The document processing information includes, for example, the scanning setting (single-sided / double-sided), paper feed speed, first stop amount, pull-out speed, second stop amount, document interval time, and whether or not the pull-out driven roller stops at the second stop.

[0179] The ADF51 controller 904 starts recording with the sound-collecting microphone 200 before the document is set, in accordance with instructions from the design PC 909 (S2304). The recorded sound data is used to determine the pleasantness of the sound emitted by the ADF51. The designer (user) shall place the document in the ADF51's document tray 53 in advance in order to collect noise.

[0180] The ADF51 controller 904 determines whether or not a document has been placed in the document tray 53 based on a signal from the document set sensor 63 (S2305). If it is determined that no document has been placed in the document tray 53 (S2305: NO), the process in S2305 is repeated until a document is placed.

[0181] If the ADF51 controller 904 determines that a document has been placed in the document tray 53 (S2305: YES), it performs paper feeding and transport operations in autonomous paper feeding mode (S2306). Each time a sheet of paper is fed, the ADF51 controller 904 determines whether or not a document is present in the document tray 53 based on a signal from the document set sensor 63 (S2307). If the ADF51 controller 904 determines that a document is present in the document tray 53 (S2307: YES), it performs the process in S2306.

[0182] If the ADF51 controller 904 determines that no documents are present in the document tray 53 (S2307: NO), it calculates productivity and then terminates the paper feeding and transport operation (S2308). Productivity is calculated, for example, by dividing the time from the start to the end of the paper feeding and transport operation by the number of documents transported.

[0183] The ADF51 controller 904 stops recording by the sound-collecting microphone 200 (S2309).

[0184] Then, the design PC909 determines whether or not it has sent all the document processing information to be evaluated for noise level and productivity to the ADF51 (S2310). If it determines that it has not sent all the document processing information to be evaluated for noise level and productivity to the ADF51 (S2310: NO), it resumes processing from S2303.

[0185] Then, when the design PC909 determines that it has sent all the document processing information to the ADF51 for evaluation of noise level and productivity (S2310:YES), it terminates the process.

[0186] The design PC909 according to this embodiment can acquire information indicating productivity and sound data when operating according to the said document processing information for each piece of document processing information by performing the processing described above.

[0187] The design PC909 then plays the sound data to various people and collects information from them via the control unit, etc., indicating the level of pleasantness of the sound between "1" and "10". Based on the level of pleasantness of the sound input from each of the multiple people, the design PC909 calculates the "average value of pleasantness of sound (estimated)" and the "standard deviation of pleasantness of sound (estimated)".

[0188] Then, any computer, such as the design PC909, generates training data for each document processing information for which sound quality and productivity are to be evaluated, by associating productivity with the "average value of sound quality level (estimated)" and the "standard deviation of sound quality level (estimated)," according to the operator's instructions.

[0189] Figure 15 shows the structure of the training data according to this embodiment. As shown in Figure 15, the training data associates the average noise level, the standard deviation of the noise level, and (reading) productivity with each piece of document processing information. The document processing information includes, as in the example described above, the reading setting (single-sided / double-sided), paper feed speed, first stop amount, pull-out speed, second stop amount, document interval time, and whether the pull-out driven roller stops at the second stop. The information processing device 1200 then generates a learning model based on the training data.

[0190] In this embodiment, the document processing information includes information on the operation of the ADF 51, as well as information on the document size, paper type, and paper thickness. In this embodiment, including document information in the document processing information improves the accuracy of estimation. This embodiment is just one example of document processing information, and it does not necessarily have to include document information. When the estimation unit 1804 performs estimation using the learning model 1100, if it uses document information, the user may input the document size and paper type / thickness. When the estimation unit 1804 performs estimation, using document information as input data improves the estimation accuracy of sound quality and productivity.

[0191] Thus, the training data includes input data, which is document processing information, and output data, which is sound quality (average sound quality level and standard deviation of sound quality level) and productivity (reading productivity).

[0192] Figure 16 is a flowchart showing the procedure for generating a learning model in the information processing device 1200 according to this embodiment.

[0193] The flowchart shown in Figure 16 illustrates an example of the process from generating a learning model using a neural network (NN) to deep learning (DL). Note that this embodiment is not limited to using deep learning (DL); a deep neural network (DNN) may also be used. Examples of deep learning methods that may be applied include convolutional neural networks, recurrent neural networks (RNNs), and long short-term memory (LSTMs).

[0194] The information processing device 1200 collects (acquires) training data generated by other computers, etc. (S2501).

[0195] The information processing device 1200 uses the collected training data to machine-learn a neural network and generate a learning model (S2502). The learning model can be generated using a general AI (Artificial Intelligence) framework. Examples of AI frameworks that can be applied include TensorFlow®, MATLAB®, PyTorch®, or ONNX®.

[0196] The information processing device 1200 converts the learning model generated by machine learning into embedded code for the ADF51's controller 904 and sends it to the ADF51 (S2503). The learning model generated by the AI ​​framework is often not in a format that can be processed by the ADF51's CPU 904A. Therefore, the information processing device 1200 converts the learning model 1100 into embedded code (for example, C language, etc.) and outputs it to the ADF51's controller 904. The ADF51's controller 904 stores the learning model 1100 in the ROM 904B based on the received embedded code.

[0197] Incidentally, there are countless combinations of parameters included in the document processing information. Therefore, if the designers of the ADF51 were to perform transport operations under various conditions during the design phase and evaluate the sound quality based on the sounds produced, it would be extremely time-consuming and costly, and there is a possibility that combinations would not be adequately considered.

[0198] In contrast, the controller 904 according to this embodiment can estimate the pleasantness of sound and productivity with a certain degree of accuracy even for unknown combinations not included in the training data by performing inference using the learning model 1100.

[0199] For example, in document processing information based on specific parameter combinations included in training data, a combination of multiple operations may result in an improvement or decrease in sound quality that was not anticipated by the designer. The information processing device 1200 according to this embodiment performs machine learning based on such training data. Therefore, the controller 904 can use the learned model 1100, which has undergone machine learning, to estimate an improvement or decrease in sound quality that was not anticipated by the designer, even when it operates according to document processing information not included in the training data.

[0200] As a concrete example, depending on the combination of multiple parameters included in the document processing information, the learning model 1100 may be able to predict that the sound of the document hitting a roller will overlap with the sound of other rollers hitting each other. Furthermore, depending on the combination of multiple parameters included in the document processing information, the learning model 1100 may be able to predict that the sound of the document hitting a roller will have a rhythmic pattern that is pleasing to the listener, even though this was not designed by the designer.

[0201] In this embodiment, an example was described in which the information processing device 1200 generates a learning model 1100 and incorporates the generated learning model 1100 into all ADF 51 produced. However, this embodiment is just one example, and in other examples, it is also possible to generate a learning model 1100 from acquiring training data using each assembled ADF 51 during the ADF 51 assembly process at the factory, and then incorporate the completed learning model 1100 into the ADF 51. In this case, the learning model 1100 will be optimized for that ADF 51, thus improving the accuracy of estimation.

[0202] As described above, the controller 904 of the ADF51 in this embodiment can improve the accuracy of sound quality estimation by using the learning model 1100.

[0203] (Second embodiment) In the embodiments described above, the case in which the ADF 51 controller 904 performs the estimation phase using the learning model 1100 was explained. However, the configuration for performing the estimation phase is not limited to the ADF controller. In the second embodiment, the case in which it is performed in an image forming apparatus will be explained.

[0204] Figure 17 shows an example of the configuration of the copier 100_1 according to the second embodiment. In the copier 100_1 shown in Figure 17, components similar to those of the copier 100 in the first embodiment are assigned the same reference numerals and their descriptions are omitted.

[0205] The main control unit 901_1 of the image forming apparatus 1_1 shown in Figure 17 stores the learning model 1100 in the ROM 901B.

[0206] Then, the main control unit 901_1 of the image forming apparatus 1_1 implements the learning estimation unit 2601 by executing a program stored in the ROM 901B.

[0207] The learning estimation unit 2601 implements the estimation phase using the learning model 1100.

[0208] The controller 904 of the ADF (Document Processing Unit) 51 according to this embodiment includes an acquisition unit 1801, a communication control unit 1802, a determination unit 1803, an estimation unit 1804, a setting change unit 1805, a display control unit 1806, and an operation reception unit 1807, similar to the embodiment described above.

[0209] However, the estimation unit 1804 of the ADF (autograph processing unit) 51 outputs the document processing information to the main unit control unit 901_1 of the image forming apparatus 1 without performing estimation using the learning model within the ADF 51.

[0210] The learning estimation unit 2601 of the main control unit 901_1 receives the input document processing information and passes it to the learning model 1100, from which it receives the "average value of pleasant sound level (estimated)", "standard deviation of pleasant sound level (estimated)", and "number of readable pages per unit time (estimated)".

[0211] The learning estimation unit 2601 then outputs the "average value of the pleasant sound level (estimated)", the "standard deviation of the pleasant sound level (estimated)", and the "number of pages that can be read per unit of time (estimated)" to the estimation unit 1804 of the ADF (document processing device) 51.

[0212] The estimation unit 1804 then uses the input "average value of pleasant sound level (estimated)" and "standard deviation of pleasant sound level (estimated)" to determine whether the pleasant sound level is below the standard.

[0213] If the estimation unit 1804 determines that the noise level is better than the standard, the controller 904 starts the paper feeding and reading operations of the ADF 51 based on the document processing information.

[0214] If the estimation unit 1804 determines that the result is below the standard, it outputs to the main control unit 901_1 of the image forming apparatus 1_1 a list of candidate document processing information, in which some parameters that do not affect the reading function have been modified. The learning estimation unit 2601 again uses the input candidate document processing information to perform estimation using the learning model 1100 and outputs the estimation result to the estimation unit 1804. The following steps are the same as those described in the embodiment above and will be omitted from the explanation.

[0215] In this embodiment, the estimation phase is executed using the CPU 901A of the image forming apparatus 1_1. Since the CPU 901A of the image forming apparatus 1_1 is more powerful than the CPU 904A of the ADF 51, the processing time of the estimation phase can be shortened. Furthermore, since the performance of the CPU 904A of the ADF 51 can be reduced, costs can be reduced.

[0216] (Third embodiment) The embodiments described above described a case where the configuration within the copier performs the estimation phase using the learning model 1100. However, the configuration for performing the estimation phase is not limited to within the copier. In the third embodiment, an example is described in which an external device capable of communicating with the copier performs the estimation phase.

[0217] Figure 18 shows an example configuration of a copier 100_2 and a cloud server 908 according to the third embodiment. In Figure 18, components of the copier 100_2 with the same configuration as those of the copier 100_1 in the second embodiment are assigned the same reference numerals, and their descriptions are omitted. In the example shown in Figure 18, a cloud server 908 is provided as an external device capable of communicating with the copier 100_2. Note that this embodiment does not limit the device executing the estimation phase to a cloud server; any device external to the copier may be used.

[0218] The cloud server 908 shown in Figure 18 has a computer configuration including a CPU 908A, ROM 908B, and RAM 908C, etc. The cloud server 908 stores the learning model 1100 in ROM 908B.

[0219] Then, the CPU 908A of the cloud server 908 implements the learning estimation unit 2701 by executing the program stored in the ROM 908B.

[0220] The learning estimation unit 2701 implements the estimation phase using the learning model 1100.

[0221] The estimation unit 1804 of the ADF51 receives the estimation results from the learning model 1100 by transmitting the document processing information to the cloud server 908. The specific processing procedure is the same as that used in the second embodiment, etc., and will not be described further.

[0222] Figure 18 shows an example where one copier 100_2 is connected to the cloud server 908, but multiple copiers 100_2 may be connected to the cloud server 908. The cloud server 908 then estimates the noise level and productivity based on the document processing information transmitted from each of the multiple copiers 100_2.

[0223] The learning model 1100 of the cloud server 908 is machine-learned using training data based on each of the multiple copiers 100_2 in order to estimate the noise level and productivity of each of the multiple copiers 100_2.

[0224] If the types of ADF51 installed in multiple copiers 100_2 are different, the designer acquires sound data for each type of ADF51 and prepares training data using that sound data. The information processing device 1200 (see Figure 13) then generates a learning model 1100 by performing machine learning using this training data. Therefore, the learning model 1100 on the cloud server 908 can estimate the noise level and productivity for each of the multiple copiers 100_2.

[0225] Furthermore, the information processing device 1200 according to this embodiment collects original document processing information, modified settings, and user-inputted options indicating sound quality from each of the multiple copiers 100_2 that can be connected to the cloud server 908, similar to the first embodiment. Based on the collected information, it generates training data and uses the generated training data to perform additional training on the learning model 1100. In this embodiment, additional training can be performed based on information collected from multiple copiers 100_2, thereby improving estimation accuracy.

[0226] Furthermore, the training data according to this embodiment may include information that identifies the type of copier 100_2 or ADF51. In this case, the cloud server 908 inputs the document processing information and the identification information into the learning model 1100 and receives the noise level and productivity from the learning model 1100.

[0227] By performing the above-described processing, the cloud server 908 according to this embodiment can estimate the noise level and productivity of each copier 100_2, even when various copiers 100_2 are connected to the cloud server 908.

[0228] Furthermore, this embodiment can reduce costs because it is possible to suppress the performance of the CPU 904A of the ADF 51 and the CPU 901A of the image forming apparatus 1, which are included in the copier 100_2.

[0229] (modified version) In the embodiments described above, an example was explained in which a device such as the CPU 904A estimates sound quality and productivity from document processing information using the learning model 1100. However, the embodiments described above are not limited to estimation using the learning model 1100.

[0230] For example, the processing device may maintain table information that associates document processing information with sound quality and productivity, and may use a method to estimate sound quality and productivity based on the document processing information by referring to the correspondence in the table information.

[0231] In the embodiments and modifications described above, when a document is transported or read by the ADF, the pleasantness of the sound generated during the transport or reading of the document can be estimated, enabling control or notification that takes pleasantness into consideration, thereby suppressing the unpleasantness caused to people in the surrounding area. Therefore, the copier according to the embodiments and modifications can improve the comfort of the surrounding environment.

[0232] Although several embodiments for carrying out the present invention have been described above, the present invention is not limited in any way to these embodiments, and various modifications and substitutions can be made without departing from the spirit of the invention. Furthermore, the elements shown in the embodiments described above can be combined in any way as appropriate, as long as no technical inconsistencies arise. [Explanation of Symbols]

[0233] 100, 100_1, 100_2 Photocopier 51 ADF 904 Controller 1801 Acquisition Department 1802 Communication Control Unit 1803 Judgment Department 1804 Estimation Department 1805 Settings Change Section 1806 Display Control Unit 1807 Operation Reception Section 1.1_1 Image forming apparatus 901, 901_1 Main Unit Control 2601 Learning Estimation Unit 908 Cloud Server 2701 Learning Estimation Unit 1100 Learning Models 1200 Information Processing Device [Prior art documents] [Patent Documents]

[0234] [Patent Document 1] Japanese Patent Publication No. 2014-221536

Claims

1. A tray for stacking manuscripts, A transport unit that transports the document from the tray, While the document is being transported by the transport unit, a reading unit reads the image represented on the document, An acquisition unit that acquires processing information including at least one of the following: settings for the transport unit to transport the document, and settings for the reading unit to read the document; Based on the processing information acquired by the acquisition unit, when the document is transported or read, an estimation unit estimates the pleasantness of the sound that a person perceives in relation to the sound generated during the transport or reading of the document. A document processing device equipped with the following features.

2. The estimation unit receives the estimation result of the pleasant sound from the learning model when the processing information is input to the learning model that has been machine-learned to estimate the pleasant sound in the document processing device. The document processing apparatus according to claim 1.

3. The system further includes a modification unit that changes the settings for transporting the document based on the estimation result of the pleasant sound quality. The document processing apparatus according to claim 1.

4. The processing information acquired by the acquisition unit further includes information about the document placed on the tray. The document processing apparatus according to claim 2.

5. The learning model is capable of estimating the number of documents that the transport unit can process per predetermined time, The estimation unit receives from the learning model the number of documents that can be processed per predetermined time, The system further includes a modification unit that changes the settings for transporting the documents based on the number of documents that can be processed and the estimated sound quality. The document processing apparatus according to claim 2.

6. An output control unit that outputs a notification regarding a change in the settings for transporting the document, based on the estimation result of the pleasant sound quality, The system further includes an operation reception unit that accepts operations related to changing the aforementioned settings, The modification unit modifies the settings for transporting the document in accordance with the operation received by the operation reception unit. The document processing apparatus according to claim 3.

7. The aforementioned modified part is, A first mode indicates the settings for the transport unit to transport the documents, based on the number of documents that can be processed and the estimated result of the pleasant sound quality. A second mode is provided, which is a setting that increases the pleasant sound quality compared to the first mode, thereby reducing the number of documents that can be processed per predetermined time compared to the first mode. The document processing apparatus according to claim 3.

8. A sound collection device for collecting sounds from the surrounding area of ​​the document processing device, The system further includes a determination unit that determines whether or not to change the settings for transporting the document based on the sound collected by the sound collection device, The document processing apparatus according to claim 3.

9. The transmission control unit further includes a transmission control unit that transmits the settings before the change and the settings after the change when the settings for transporting the document are changed by the change unit. The document processing apparatus according to claim 5.

10. The document processing device further includes an operation reception unit that receives information indicating the level of satisfaction regarding the sound emitted when the document is transported by the transport unit, The transmission control unit further transmits the input satisfaction level. The document processing apparatus according to claim 9.

11. It is further equipped with a communication device for communicating with external devices, The estimation unit transmits the processing information acquired by the acquisition unit to an external device via the communication device, and receives the estimation result of the pleasantness of the sound that a person perceives in relation to the sound generated during the transport and reading of the document from the external device. The document processing apparatus according to claim 1.

12. An interface for communicating with a document processing device having a tray for loading documents, a transport unit for transporting documents from the tray, and a reading unit for reading images represented on the documents while the documents are being transported by the transport unit, An acquisition unit that acquires processing information including at least one of the following: settings for the transport unit to transport the document, and settings for the reading unit to read the document; Based on the processing information acquired by the acquisition unit, when the document is transported and read, an estimation unit estimates the pleasantness of the sound that a person would perceive in the sound generated during the transport and reading of the document. An image forming apparatus comprising:

13. A learning unit generates a learning model by performing machine learning using data that associates processing information, which includes at least one of the settings for the transport unit that transports the document from the tray of the document processing device to transport the document and the settings for the reading unit of the document processing device to read the document, with the pleasantness of the sounds that people perceive in the transport and reading of the document, as training data. A pre-trained model generator equipped with the following features.

14. The learning unit further associates information about the document placed in the tray of the document processing device with training data for generating the learning model. The trained model generation device according to claim 13.

15. The learning unit further includes, as training data for generating the learning model, the processing information collected when the document processing device autonomously feeds and transports the document using its autonomous paper feeding mode. The trained model generation device according to claim 13.

16. A document processing device having a tray for loading documents, a transport unit for transporting documents from the tray, a reading unit for reading the image represented on the document while the document is being transported by the transport unit, and an interface for communicating with an image forming apparatus, An image forming apparatus comprising an image forming apparatus having a drive mechanism that drives for image formation, The aforementioned document processing device is An acquisition unit that acquires processing information including at least one of the following: settings for the transport unit to transport the document, and settings for the reading unit to read the document; Based on the processing information acquired by the acquisition unit, when the document is transported and read, an estimation unit estimates the pleasantness of the sound that a person would perceive in the sound generated during the transport and reading of the document. The system includes a communication control unit that transmits information based on the estimation result of the pleasant sound quality to the image forming apparatus, The image forming apparatus changes the control of the drive mechanism based on the received information. Image forming system.