# US 2026/0277145 A1 · Information processing system, recording medium accommodating device, image forming apparatus, non-transitory computer readable medium storing program, and information processing method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0277145 A1 - Document ID: US20260277145A1 - Status: Published application - Kind: A1 - Application number: 19/277,402 - Filed: 2025-07-23 - Published: 2026-09-17 - Earliest claimed: 2025-03-17 - Assignees: FUJIFILM Business Innovation Corp. - Applicants: FUJIFILM Business Innovation Corp. - Inventors: Ryosuke YONESAKA; Kazuhiko HORIKAWA; Yuichi ARAKI - Web page: https://patentgrep.com/patent/US20260277145A1 ## CPC - B65H 3/48: Air blast acting on edges of, or under, articles - G03G 15/6511: {Feeding devices for picking up or separation of copy sheets} - G03G 15/5029: {by measuring the copy material characteristics, e.g. weight, thickness} - G03G 15/6558: {Feeding path after the copy sheet preparation and up to the transfer point, e.g. registering; Deskewing; Correct timing of sheet feeding to the transfer point} - G03G 15/657: {Feeding path after the transfer point and up to the fixing point, e.g. guides and feeding means for handling copy material carrying an unfused toner image} - G03G 2215/004: Separation device - G03G 2215/00616: Optical detector - B65H: HANDLING THIN OR FILAMENTARY MATERIAL, e.g. SHEETS, WEBS, CABLES - G03G: ELECTROGRAPHY; ELECTROPHOTOGRAPHY; MAGNETOGRAPHY ## Abstract An information processing system includes a processor configured to: acquire a medium image that is an image of a bundle of recording media including plural recording media, the bundle of recording media being in a state in which gas is being blown from a lateral side of the recording media; and generate information regarding a floating state of the bundle of recording media shown in the acquired medium image by using a trained model generated through machine learning using training data including an image of a bundle of recording media that is in a state in which gas is being blown from a lateral side and information regarding a floating state of the bundle of recording media shown in the image. ## Claims ### Claim 1 An information processing system comprising: a processor configured to: acquire a medium image that is an image of a bundle of recording media consisting of a plurality of recording media, the bundle of recording media being in a state in which gas is being blown from a lateral side of the recording media; and generate information regarding a floating state of the bundle of recording media shown in the acquired medium image by using a trained model generated through machine learning using training data including an image of a bundle of recording media that is in a state in which gas is being blown from a lateral side and information regarding a floating state of the bundle of recording media shown in the image. ### Claim 2 (depends on 1) The information processing system according to claim 1, wherein the trained model is a trained model generated through machine learning using training data including an image of a bundle of recording media that is in a state in which gas is being blown from a lateral side and information indicating whether floating of the bundle of recording media shown in the image is favorable or not, and the processor is configured to: use the trained model to generate information indicating whether floating of the bundle of recording media shown in the acquired medium image is favorable or not. ### Claim 3 (depends on 1) The information processing system according to claim 1, wherein the trained model is a trained model generated through machine learning using training data including an image of a bundle of recording media that is in a state in which gas is being blown from a lateral side, the image being obtained by an imaging unit that is in a state in which powder has adhered, and information regarding a floating state of the bundle of recording media shown in the image, and the processor is configured to: generate the information regarding the floating state of the bundle of recording media shown in the acquired medium image by using the trained model generated through machine learning using the training data including the image obtained by the imaging unit that is in a state in which powder has adhered. ### Claim 4 (depends on 3) The information processing system according to claim 3, wherein the powder that has adhered to the imaging unit is paper dust, and the processor is configured to: generate the information regarding the floating state of the bundle of recording media shown in the acquired medium image by using the trained model generated through machine learning using the training data including the image obtained by the imaging unit that is in a state in which the paper dust has adhered. ### Claim 5 (depends on 1) The information processing system according to claim 1, wherein the trained model is prepared for each type of recording medium constituting the bundle of recording media, and the processor is configured to: acquire type information that is information regarding a type of recording medium constituting the bundle of recording media shown in the medium image; and generate the information regarding the floating state of the bundle of recording media shown in the acquired medium image by using the trained model corresponding to the type specified by the type information. ### Claim 6 (depends on 1) The information processing system according to claim 1, wherein the processor is configured to: acquire a plurality of medium images in which blowing conditions of gas are different from each other; and use the trained model to generate, for each of the plurality of acquired medium images, the information regarding the floating state of the bundle of recording media shown in the medium image. ### Claim 7 (depends on 6) The information processing system according to claim 6, wherein the trained model is a trained model generated through machine learning using training data including an image of a bundle of recording media that is in a state in which gas is being blown from a lateral side and information indicating whether floating of the bundle of recording media shown in the image is favorable or not, and the processor is configured to: use the trained model to generate, for each of the plurality of acquired medium images, information indicating whether floating of the bundle of recording media shown in the medium image is favorable or not. ### Claim 8 (depends on 1) The information processing system according to claim 1, wherein the processor is configured to: operate a blowing device that blows gas onto the bundle of recording media under each of a plurality of conditions different from each other, and use the trained model to generate, for each medium image obtained under each of the conditions, state information that is information regarding the floating state of the bundle of recording media shown in the medium image. ### Claim 9 (depends on 8) The information processing system according to claim 8, wherein the processor is configured to: in operating the blowing device under each of the plurality of conditions, obtain a plurality of medium images under each of the conditions; use the trained model to generate, for each of the plurality of medium images obtained under each of the conditions, the state information that is information regarding the floating state of the bundle of recording media shown in the medium image; and set a blowing condition of the blowing device in a case where feeding out of a recording medium is to be performed, based on a plurality of pieces of state information generated under each of the conditions. ### Claim 10 (depends on 8) The information processing system according to claim 8, wherein the processor is configured to: in operating the blowing device under each of the plurality of conditions different from each other, operate the blowing device under each of a smaller number of conditions than a total number of all conditions included in the plurality of conditions, and set another condition in a case of operating the blowing device under the other condition, based on respective pieces of state information generated in correspondence with the smaller number of conditions. ### Claim 11 (depends on 10) The information processing system according to claim 10, wherein the processor is configured to: set the other condition, based on a condition for operating the blowing device in a case where state information indicating a most favorable floating state is obtained, among the respective pieces of state information generated in correspondence with the smaller number of conditions. ### Claim 12 (depends on 11) The information processing system according to claim 11, wherein the processor is configured to: set, as the other condition, a condition between the condition for operating the blowing device in a case where the state information indicating the most favorable floating state is obtained and a condition for operating the blowing device in a case where state information indicating a second most favorable floating state is obtained, among the respective pieces of state information generated in correspondence with the smaller number of conditions. ### Claim 13 (depends on 1) The information processing system according to claim 1, wherein the processor is configured to: operate a blowing device that blows gas onto the bundle of recording media shown in the medium image under each of a plurality of conditions different from each other; use the trained model to generate, for each medium image obtained under each of the conditions, state information that is information regarding the floating state of the bundle of recording media shown in the medium image; set a blowing condition of the blowing device in a case where feeding out of a recording medium included in the bundle of recording media shown in the medium image is to be performed, based on the state information generated under each of the conditions; store medium information that is information regarding the bundle of recording media shown in the medium image and the set blowing condition in an information storage unit in a state of being associated with each other; and in a case where medium information that matches medium information regarding a newly installed bundle of recording media has been stored in the information storage unit, decide on a blowing condition of the blowing device in a case where feeding out of a recording medium included in the newly installed bundle of recording media is to be performed, based on the blowing condition associated with the medium information stored in the information storage unit. ### Claim 14 (depends on 1) The information processing system according to claim 1, wherein the trained model is a trained model generated through machine learning using training data including an image of a bundle of recording media that is in a state in which gas is being blown from a lateral side, and information regarding a floating state of the bundle of recording media shown in the image and a folded state of a recording medium constituting the bundle of recording media shown in the image, and the processor is configured to: use the trained model to generate the information regarding the floating state of the bundle of recording media shown in the acquired medium image and information regarding a folded state of a recording medium constituting the bundle of recording media shown in the medium image. ### Claim 15 (depends on 1) The information processing system according to claim 1, wherein at least a first trained model and a second trained model are prepared as the trained model, the first trained model is a trained model generated through machine learning using training data including an image of a bundle of recording media in which the number of recording media constituting the bundle of recording media is less than a predetermined threshold value, the bundle of recording media being in a state in which gas is being blown from a lateral side, and information regarding a floating state of the bundle of recording media shown in the image, the second trained model is a trained model generated through machine learning using training data including an image of a bundle of recording media in which the number of recording media constituting the bundle of recording media is greater than the predetermined threshold value, the bundle of recording media being in a state in which gas is being blown from a lateral side, and information regarding a floating state of the bundle of recording media shown in the image, and the processor is configured to: acquire sheet count information that is information regarding the number of recording media constituting the bundle of recording media shown in the medium image; in a case where the number specified by the sheet count information is less than the predetermined threshold value, use the first trained model to generate the information regarding the floating state of the bundle of recording media shown in the acquired medium image; and in a case where the number specified by the sheet count information is greater than the predetermined threshold value, use the second trained model to generate the information regarding the floating state of the bundle of recording media shown in the acquired medium image. ### Claim 16 (depends on 1) A recording medium accommodating device comprising: an accommodating section that accommodates a plurality of recording media; a blowing device that blows gas onto the recording media accommodated in the accommodating section; and an information processing system that processes information regarding the recording media accommodated in the accommodating section, wherein the information processing system has a configuration of the information processing system according to claim 1. ### Claim 17 (depends on 1) An image forming apparatus comprising: an accommodating section that accommodates a plurality of recording media; a blowing device that blows gas onto the recording media accommodated in the accommodating section; an image forming section that forms an image on a recording medium fed out from the accommodating section; and an information processing system that processes information regarding the recording media accommodated in the accommodating section, wherein the information processing system has a configuration of the information processing system according to claim 1. ### Claim 18 A non-transitory computer readable medium storing a program for causing a computer to implement: an acquisition function of acquiring a medium image that is an image of a bundle of recording media consisting of a plurality of recording media, the bundle of recording media being in a state in which gas is being blown from a lateral side of the recording media; and a generation function of generating information regarding a floating state of the bundle of recording media shown in the acquired medium image by using a trained model generated through machine learning using training data including an image of a bundle of recording media that is in a state in which gas is being blown from a lateral side and information regarding a floating state of the bundle of recording media shown in the image. ### Claim 19 An information processing method comprising: acquiring a medium image that is an image of a bundle of recording media consisting of a plurality of recording media, the bundle of recording media being in a state in which gas is being blown from a lateral side of the recording media; and generating information regarding a floating state of the bundle of recording media shown in the acquired medium image by using a trained model generated through machine learning using training data including an image of a bundle of recording media that is in a state in which gas is being blown from a lateral side and information regarding a floating state of the bundle of recording media shown in the image.