Network system including actual result management system and repair portion estimation system and method for controlling the same

Abstract

To reduce a burden on an operator in input related to maintenance work, and store data related to the maintenance work in a format of data suitable for both an actual result management system and a repair portion estimation system.SOLUTION: An actual result management system 107 of a network system provides a replacement part actual result input screen 301 for inputting details of maintenance work performed on a device, and stores the input in a database. A repair portion estimation system 108 provides a feedback input screen 401 for sending feedback related to the details of the work according to the input through the replacement part actual result input screen 301, adds event information indicating an event that has caused the maintenance work to the details set on the feedback input screen 401, and stores resultant data in the database as feedback data.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] The present invention relates to data input in a network system including a performance management system and a repair location estimation system. [Background technology]

[0002] When an abnormality such as an error or breakdown occurs in an image forming device such as a multifunction printer, a maintenance person such as a serviceman is dispatched in response to a report of the abnormality. The maintenance person checks the manual and performs maintenance such as part replacement. After the maintenance work, the content of the maintenance work on the image forming device and the results of the parts replaced are entered into a results management system, and a report is created. Various systems have been proposed that support the creation of such maintenance work reports by servicemen and improve the work efficiency when creating the reports. For example, Patent Document 1 discloses a technology that automatically reflects some information of the multifunction printer in a file when creating a work report (a report describing the contents of the maintenance measures) on the UI of the multifunction printer.

[0003] A performance management system to which a serviceman submits a maintenance work report is capable of collecting a large amount of information on the work performed by the serviceman and the parts replaced. Therefore, a system is operated that uses collected data and estimates replacement parts using AI (Artificial Intelligence). One of the core technologies that realizes AI is machine learning. In machine learning, a learning model that extracts data features (characteristics, patterns, trends, etc.) by analyzing a large amount of data (big data) with a learning algorithm can be created. In general, in machine learning, a learning model is trained using learning data, and the learning model that has completed training is operated in production as a trained model. Since the learning data for training the model is essential for creating a trained model, a system that collects data for learning is required. In order to train a learning model of a system that estimates replacement parts (repair location estimation system 108), a large amount of learning data linked to errors such as failures and appropriate response records to the errors is required. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2009-15812 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, if a serviceman who performed maintenance work on an error were to input feedback including the response record into the repair location estimation system in order to collect learning data, this would require two inputs, one for the replacement part record system and one for the replacement part record system. This would increase the serviceman's workload, as data would have to be input from two separate screens, one for the replacement location estimation system and one for the replacement part record system. In addition, because learning data requires an appropriate data format, it is difficult to reuse existing input data for replacement part record as learning data.

[0006] The present invention aims to provide a network system that reduces the burden on workers of inputting data regarding maintenance work and can store data regarding maintenance work in a data format suitable for each of the performance management system and the repair location estimation system. [Means for solving the problem]

[0007] In order to solve the above problems, the network system of the present invention includes a performance management system for managing the performance of maintenance work on a network device, and a repair location estimation system for estimating a repair location of the network device, the performance management system having a first screen providing means for providing a first screen for inputting the work content of the maintenance work performed on the network device, and a first saving means for saving the input from the first screen in a first database. The repair location estimation system has a second screen providing means for providing a second screen for providing feedback regarding the work content of the maintenance work actually performed in response to the input via the first screen provided by the performance management system, to the estimation of the repair location of the network device, and a management means for adding event information indicating an event that caused the maintenance work to the content set on the second screen, and saving the feedback data in a second database. Effect of the Invention

[0008] According to the present invention, it is possible to provide a network system that reduces the burden on workers of inputting information regarding maintenance work and can store data regarding maintenance work in a data format suitable for each of the performance management system and the repair location estimation system. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating a configuration of a network system including a performance management system and a repair location estimation system. [Diagram 2] FIG. 2 is a diagram illustrating a hardware configuration of an image forming apparatus and an information processing apparatus. [Diagram 3] FIG. 13 is a diagram showing an example of an input screen for a replacement part record. [Figure 4] FIG. 13 is a diagram showing an example of an input screen for feedback information. [Diagram 5] FIG. 2 is a diagram illustrating a software configuration of a repair location notification server in the first embodiment. [Figure 6] 2 is a diagram illustrating the software configuration of a replacement part information collection server and an information input terminal. FIG. [Figure 7] 13 is a flowchart showing a process for acquiring a maintenance record. [Figure 8] 13 is a flowchart showing a process for acquiring a maintenance record. [Figure 9] 10 is a flowchart showing a process of acquiring feedback information according to the first embodiment. [Figure 10] 1 is a flowchart showing a process for creating a machine learning model. [Figure 11] FIG. 11 is a diagram illustrating a software configuration of a repair location notification server in the second embodiment. [Figure 12] 13 is a flowchart showing a process of acquiring feedback information according to the second embodiment. [Figure 13] 13 is a flowchart showing a process of acquiring feedback information according to the third embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Example 1 FIG. 1 is a diagram for explaining the configuration of a network system including a performance management system and a repair location estimation system. The network system of this embodiment includes a performance management system 107 that manages the performance of maintenance for network devices, and a repair location estimation system 108 that estimates the fault location of the network device. The performance management system 107 is a system provided by the device information collecting server 102 and the replacement part information collecting server 104. The repair location estimation system 108 is a system provided by the repair location notification server 105. Therefore, the network system is a system including the device information collecting server 102, the replacement part information collecting server 104, and the repair location notification server 105. Note that the network system may also include an information input terminal 103 that displays a screen provided by the performance management system 107 and the repair location estimation system 108 and through which input is made to the screen.

[0011] The network system is connected to a plurality of image forming devices 106 via a network 101. The plurality of image forming devices 106 are an example of network devices that are targets of repair location estimation by a repair location estimation system 108. The image forming devices 106 are, for example, multifunction peripherals, facsimile machines, printers, scanners, 3D printers, etc. The image forming devices 106 are connected to a repair location notification server 105 via the network 101. Note that, in this embodiment, a case where the network device is an image forming device will be described as an example, but this is not limited to this. For example, the network device may be any device capable of communication, such as an information processing device such as a PC, an image processing device such as a camera, or a smart home appliance.

[0012] The information input terminal 103 is an information processing device for displaying a screen provided by the performance management system 107 or the repair location estimation system 108 and inputting information to the performance management system 107 or the repair location estimation system 108. The information input terminal 103 is a device held by a maintenance person who performs maintenance on the image forming apparatus 106. The maintenance person inputs the details of the measures taken on the image forming apparatus 106 on the screen provided by the information input terminal 103. The information input terminal 103 transmits the input information, etc. to the replacement part information collection server 104 or the repair location notification server 105 via the network 101.

[0013] The device information collecting server 102 is an information processing device constituting an online service system that provides an information collecting system from the image forming device 106. The device information collecting server 102 collects and accumulates error history information from a plurality of image forming devices 106 via the network 101. The network 101 may be configured to be capable of transmitting and receiving data, and any communication method may be used. For example, the communication line 3000 may be configured as any one of a LAN, a WAN, a cellular network such as LTE or 5G, a wireless network, a telephone line, a dedicated digital line, and the like, or a combination of these.

[0014] The replacement part information collection server 104 is an information processing device constituting an online service system that provides an information collection system from the information input terminal 103. The replacement part information collection server 104 receives replacement part information transmitted from the information input terminal 103 via the network 101. The replacement part information collection server 104 collects and stores the information received from the information input terminal 103.

[0015] Repair part notification server 105 is an information processing device that estimates the repair part based on the operation information of image forming device 106. For example, repair part notification server 105 estimates the part to be repaired in image forming device 106 where an abnormality such as an error has occurred, or the part to be replaced if replacement of a part is required, based on the operation information collected by device information collection server 102 from image forming device 106.

[0016] In this embodiment, a replacement part estimation system that provides a service of estimating a part replacement work for eliminating a failure of an image forming apparatus 106, among the services provided by the repair part notification server 105, will be described as an example. The repair part notification server 105 uses collected data using AI (Artificial Intelligence) to estimate replacement parts. The AI ​​of the repair part notification server 105 operates a trained model by machine learning to estimate replacement parts. That is, the repair part notification server 105 operates a model used in the repair part estimation system 108 as a trained model, which is used to estimate a failure part of a network device by inputting operation information of the network device. In machine learning, a learning model is created by extracting features (characteristics, patterns, trends, etc.) of data by analyzing a large amount of data (big data) with a learning algorithm, the learning model is trained using learning data, and the trained learning model is used in production as a trained model. Repair location notification server 105 requires feedback data to be used for a model used by repair location estimation system 108, which uses operation information of the network device as input to estimate the fault location of the network device. Therefore, repair location notification server 105 requires information on errors such as failures and a large amount of data linked to past records of appropriate responses to errors as feedback data that serves as learning data for training the learning model of the system that estimates replacement parts.

[0017] The repair location notification server 105 acquires various information serving as learning data for training the learning model from the device information collecting server 102, the information input terminal 103, and the replacement part information collecting server 104. Specifically, the repair location notification server 105 acquires error history information collected by the device information collecting server 102 from the image forming device 106 from the device information collecting server 102 via the network 101. The repair location notification server 105 acquires feedback information relating to the work content of the maintenance work inputted at the information input terminal 103 from the information input terminal 103 via the network 101. The repair location notification server 105 acquires replacement part information collected by the replacement part information collecting server 104 from the replacement part information collecting server 104 via the network 101. The repair location notification server 105 creates and accumulates feedback data serving as learning data for learning and re-learning a model for estimating replacement parts based on the acquired various information.

[0018] In this embodiment, the performance management system 107 and the repair location estimation system 108 are configured by various servers, but the present invention is not limited to this. The performance management system 107 and the repair location estimation system 108 may be realized by one or more information processing devices, a virtual machine (cloud service) using resources provided by a data center including information processing devices, or a combination of these. The network system can also be implemented as a Web-based application, and can also be used via a Web browser on the information input terminal 103.

[0019] 2 is a diagram for explaining the hardware configuration of an image forming apparatus and an information processing apparatus. First, the hardware configuration of the image forming apparatus 106 will be explained. FIG. 2(A) is a diagram showing an example of the hardware configuration of the image forming apparatus 106. The image forming apparatus 106 has a CPU 201, a ROM 203, a RAM 204, a NIC 205, an external memory 206, an operation unit 207, a storage device 208, a device I / F 209, a printer 210, and a scanner 202. Each of these components is connected to a system bus 200.

[0020] The CPU (Central Processing Unit) 201 controls the entire image forming apparatus 106. The ROM 203 is a memory dedicated to reading data, and stores various data such as programs such as the basic I / O program of the image forming apparatus 106, font data used in document processing, and template data. The RAM 204 is a memory from which data can be read and written, and functions as the main memory, work area, and the like of the CPU 201. Note that the memory capacity of the image forming apparatus 106 can be expanded by an optional RAM connected to an expansion port (not shown). The external memory 206 is a storage device connected to the image forming apparatus 106 via a disk controller or the like. The external memory 206 stores control programs, resource data (resource information), and the like. The storage device 208 is a large-capacity memory such as a hard disk drive (HDD) or a solid state drive (SSD). The HDD and SSD store various programs, data, parameters, and the like. The CPU 201 performs overall control of each component connected to the system bus 200 by executing a program that controls the image forming apparatus 106 based on programs stored in memory (ROM 203, storage device 208, external memory 206), etc.

[0021] The NIC (Network Interface Card) 205 is a communication controller. The image forming apparatus 106 is connected to the network 101 via the NIC 205, and performs data communication with external apparatuses on the network 101, such as the apparatus information collecting server 102. The operation unit 207 displays a screen and accepts user operation instructions via the screen. The operation unit 207 includes a display unit such as a liquid crystal panel that displays the operating status and setting screen of the image forming apparatus, and buttons for setting the operating mode of the image forming apparatus, copy settings, and the like. The display unit and buttons may be realized as a touch panel that can be touched using an electrostatic method, a pressure-sensitive method, or the like. By associating input coordinates and display coordinates on the touch panel, a GUI can be configured as if the user could directly operate the screen displayed on the touch panel.

[0022] The device I / F (interface) 209 is an interface for connecting to an external device. The printer 210 outputs image data returned from print data (for example, PDL language, PDF language, etc.) onto a paper medium, etc. Examples of printing methods executed by the printer 210 include an electrophotographic method (laser beam method), an inkjet method, and a dye-sublimation method (thermal transfer method). The printer 210 forms an image according to a received print job and outputs it onto paper, or optically reads an image of an original document set on the scanner 202 and outputs it onto paper. The scanner 202 optically reads an original document set on a platen or an ADF (Auto Document Feeder) (not shown) and converts it into electronic data.

[0023] Next, a description will be given of the hardware configurations of the device information collecting server 102, the information input terminal 103, the replacement part information collecting server 104, and the repair location notifying server 105. In this embodiment, a hardware configuration of an information processing device will be described as the hardware configurations of the device information collecting server 102, the information input terminal 103, the replacement part information collecting server 104, and the repair location notifying server 105. Fig. 2(B) is a diagram showing the hardware configuration of the information processing device.

[0024] The information processing device includes a CPU 221, a GPU 222, a ROM 223, a RAM 224, a NIC 225, an external memory 226, an input / output unit 227, a storage device 228, and a device I / F 229. These components are connected to a system bus 220. The CPU 221 controls the information processing device. The GPU (Graphics Processing Unit) 222 is a calculation device specialized for vector calculations such as image processing and machine learning. The ROM 223 is a memory dedicated to reading data, and stores, for example, programs such as basic I / O programs of the information processing device, and various data. The RAM 224 is a memory from which data can be read / written, and functions as a main memory, a work area, and the like for the CPU 221 and the GPU 222. The memory capacity of the information processing device can be expanded by an optional RAM connected to an expansion port (not shown).

[0025] The external memory 226 is a storage device connected to the information processing device via a disk controller or the like. The external memory 226 stores control programs, resource data (resource information), and the like. The storage device 228 is a large-capacity memory such as a hard disk drive (HDD) or a solid state drive (SSD). The HDD and SSD store various programs, data, parameters, and the like. The CPU 221 performs overall control of each component connected to the system bus 220 by executing a program that controls the information processing device based on the programs and the like stored in the memory (ROM 223, storage device 228, external memory 226).

[0026] The NIC 225 is a communication controller. The information processing device connects to the network 101 via the NIC 225 and performs data communication with an external device on the network 101. The input / output unit 227 is an input / output interface that displays a screen and receives a user's operation instruction via the screen. For example, a liquid crystal panel, a display, a keyboard, a mouse, a smartphone, a tablet, etc. are connected to the input / output unit 227. In addition, the input / output unit 227 outputs information to an external device on the network 101 via the NIC 225, and the input / output unit 227 acquires information from an external device on the network 101 via the NIC 225. The device I / F 229 is a connection interface with an external device.

[0027] For a network device such as the image forming apparatus 106 where an error has occurred, a maintenance worker performs maintenance work. The worker who performed the maintenance work reports the work contents to both the performance management system 107 and the repair location estimation system 108. The report is performed by the worker inputting the work contents into an input screen provided by each system. The performance management system 107 provides a maintenance performance input screen as an input screen for the work contents of the maintenance work. The repair location estimation system 108 provides a feedback information input screen as an input screen for the work contents of the maintenance work. In this embodiment, an example will be described in which parts are replaced as maintenance work in response to a breakdown of the image forming apparatus 106, but the present invention is not limited to this. For example, the maintenance work may be maintenance work that does not involve part replacement, such as cleaning or clearing a paper jam.

[0028] 3 is a diagram showing an example of a maintenance record input screen. The replacement part record input screen 301 (first screen) is a screen for inputting the work content of the part replacement performed as the maintenance work for the device where an error has occurred, and reporting it to the record management system 107. In this embodiment, an example will be described in which a worker who has replaced a part of the broken image forming apparatus 106 inputs information on the replaced part as the work content into the replacement part record input screen 301. Note that the input format by the worker into the replacement part record input screen 301 may be a selection format such as a check box, or a free input format using characters.

[0029] The replacement part result input screen 301 is provided by the result management system 107, and is displayed on the display of the information input terminal 103. The input / output unit 227 of the replacement part information collection server 104 of the result management system 107 provides the replacement part result input screen 301 as a Web page on a Web browser operating on the information input terminal 103. In addition, the input / output unit 227 of the replacement part information collection server 104 accepts user operations on the screen displayed on the Web browser.

[0030] The replacement part performance input screen 301 includes a machine number information search section 311, a machine number information search result display section 312, an error detail information display section 313, a recommended repair content display section 314, a replacement part performance input section 315, and a replacement part performance send button 316. The machine number information search section 311 receives input of information about the image forming device 106 in which an error (failure) that was the subject of the maintenance work occurred, i.e., the image forming device 106 in which the maintenance work (part replacement) was performed. The machine number information search section 311 includes, for example, a product name and a machine number. The product type of the image forming device is input as the product name. A number (unique ID) that identifies the image forming device is input as the machine number. When information is input to the machine number information search section 311, a machine number information search result display section 312 is displayed based on the input information.

[0031] The machine number information search result display section 312 displays the machine number information search result based on the information input to the machine number information search section 311. The machine number information search result display section 312 includes, for example, the installation location and machine number of the image forming device 106. The information input to the machine number information search section 311 is transmitted to the device information collecting server 102 of the performance management system 107. The device information collecting server 102 returns the installation location and machine number of the image forming device that matches the conditions based on the information (product and machine number) acquired from the information input terminal 103 to the information input terminal 103 as the machine number information search result. The information input terminal 103 that has acquired the machine number information search result from the device information collecting server 102 displays the machine number information search result in the machine number information search result display section 312. When all digits of the machine number are entered in machine number information search section 311, the image forming device can be uniquely identified, but when all digits of the machine number are not entered, the installation locations and machine numbers of multiple image forming devices that match the entered information are displayed in machine number information search result display section 312. The installation locations are the installation locations of image forming devices that match the conditions entered in machine number information search section 311 and are received from device information collection server 102 via network 101. The machine number is a unique ID assigned to each image forming device, in other words, information that uniquely identifies the image forming device.

[0032] The error detail information display unit 313 includes information for identifying the device in which the error occurred and information indicating the error that occurred as the error detail information. For example, the error detail information display unit 313 includes a product name and a machine number as information for identifying the device in which the error occurred, and information indicating the error that occurred, that is, an error code as event information that caused the maintenance work. The error code is information for identifying the type of error, and is, for example, a unique character string code assigned to each type of error. The product name, machine number, and error code may all be input by the worker, or the product name and machine number may be automatically obtained from the machine number information search unit 311 and the machine number information search result display unit 312, and only the error code may be input by the worker. For example, the performance management system 107 displays the product name input in the machine number information search unit 311 as the product name in the error detail information display unit 313. The performance management system 107 displays, in the error detail information display section 313, the aircraft number uniquely identified in the aircraft number information search result display section 312, or the aircraft number selected from the multiple aircraft numbers limited to the multiple aircraft numbers in the aircraft number information search result display section 312.

[0033] The recommended repair content display unit 314 displays the contents of the recommended maintenance work that is estimated by the repair location notification server 105 to have a high possibility of solving the error as a recommended maintenance process. The performance management system 107 displays the recommended maintenance process acquired from the repair location estimation system 108 in the recommended repair content display unit 314. The recommended repair content display unit 314 includes the maintenance process recommended to solve the error, and may also include the likelihood (e.g., probability) that the error will be solved by the maintenance process. Types of recommended maintenance processes include, for example, replacement of a specific part, cleaning, repair, restart, etc. In the example shown in FIG. 3, the likelihood that the error will be solved by replacing part A is 80%, 15% for replacing part B, and 5% for replacing part C.

[0034] The replacement part performance input section 315 inputs the maintenance process that was actually performed to eliminate the error of the device. The replacement part performance input section 315 includes, for example, information that identifies the device to be maintained and information that indicates the maintenance process that was actually performed. The performance management system 107 displays, in the information that identifies the device to be maintained in the replacement part performance input section 315, the same information as the information that identifies the device in which the error occurred and is displayed in the error detail information display section 313. The information that identifies the device to be maintained includes, for example, the product name and the machine number. The maintenance process that the worker performed on the device in which the error occurred to eliminate the error is input in the information that indicates the maintenance process. If the maintenance process is a part replacement, the part replaced in the maintenance work is input in the information that indicates the maintenance process. The replacement part performance transmission button 316 is a button for transmitting the replacement part performance inputted in the replacement part performance input section 315 to the replacement part information collection server 104. When a transmission instruction is received from the Web UI, such as by the worker pressing the replacement part performance transmission button 316, the information input terminal 103 transmits the replacement part performance inputted into the replacement part performance input section 315 to the replacement part information collection server 104 of the performance management system 107.

[0035] 4 is a diagram showing an example of a feedback information input screen. The feedback input screen 401 (second screen) is a screen for inputting the work content of part replacement performed as maintenance work for a device in which an error has occurred, and feeding it back to the repair part estimation system 108. In this embodiment, an example will be described in which a worker who has replaced a part of a broken image forming apparatus 106 inputs information on the replaced part as the work content into the feedback input screen 401. Note that the input format by the worker into the feedback input screen 401 may be a selection format such as a check box, or a free input format using characters.

[0036] The feedback input screen 401 is provided by the repair location estimation system 108, and is displayed on the display of the information input terminal 103. The input / output unit 227 of the repair location notification server 105 of the repair location estimation system 108 provides the feedback input screen 401 as a Web page on a Web browser operating on the information input terminal 103. In addition, the input / output unit 227 of the repair location notification server 105 accepts user operations on the screen displayed on the Web browser.

[0037] The feedback input screen 401 includes a feedback information input section 421 and a feedback information transmission button 422. The feedback information input section 421 is a screen for inputting feedback information to be provided to the repair location estimation system 108. The worker (maintenance staff) inputs the contents of the maintenance work actually performed in the feedback information input section 421. The input format to the feedback information input section 421 may be a selection format such as a check box or a pull-down, or a free input format using characters. In addition, the feedback information input section 421 may display, for example, a repair location estimation result by the repair location estimation system 108, and the worker may select a repair location estimation result that matches the maintenance work actually performed. In the example shown in FIG. 4, the repair location estimation system 108 displays a plurality of candidates for parts to be replaced in the maintenance work as the repair location estimation result in the feedback information input section 421. The worker selects the part replaced in the actual maintenance work from the candidates for replacement parts displayed in the feedback information input section 421. In addition to the replacement part candidates, feedback information input section 421 may be provided with a column for selecting or entering a part that is not included in the candidates.

[0038] The feedback information transmission button 422 is a button for transmitting the replacement part record inputted in the feedback information input section 421 to the repair location estimation system 108. When a transmission instruction is received from the WebUI by, for example, pressing the feedback information transmission button 422 by the worker, the information input terminal 103 transmits information relating to the work content set in the feedback information input section 421 to the repair location estimation system 108. The repair location notification server 105 of the repair location estimation system 108 that has received information relating to the work content of the maintenance work from the information input terminal 103 forms learning data (feedback data) based on the information and stores it. Specifically, the repair location notification server 105 adds event information (information indicating an error that occurred) that caused the maintenance work to the information relating to the work content of the maintenance work, and forms the feedback data. The feedback data may also include information identifying the device on which the maintenance work was performed.

[0039] 5 is a diagram for explaining the software configuration of the repair location estimation system 108 in the first embodiment. The software configuration of the repair location estimation system 108 is realized by the CPU 221 and GPU 222 of the repair location notification server 105 executing a program stored in a memory. The repair location estimation system 108 has a device information storage unit 501, a part replacement information storage unit 502, an estimation result storage unit 503, a feedback information management unit 504, a screen providing unit 509, and a database 510. Furthermore, the repair location estimation system 108 has a learning / input data management unit 505, a learning execution unit 506, a machine learning model management unit 507, and an estimation execution unit 508.

[0040] The device information storage unit 501 manages error information and device information of the image forming device 106 received from the device information collection server 102 via the network 101. The part replacement information storage unit 502 manages information on the replacement part performance received from the replacement part information collection server 104 via the network 101. The screen providing unit 509 provides a screen to be displayed by the repair location estimation system 108 to an external device via a Web browser. The screen providing unit 509 of this embodiment provides the feedback input screen 401 to the information input terminal 103. The feedback information management unit 504 manages feedback information received from the information input terminal 103 via the network 101. The feedback information includes information input in the feedback information input unit 421 of the feedback input screen 401. In addition, the feedback information management unit 504 molds the received feedback information into feedback data used as learning data for learning a model of repair location estimation, and stores the data in the database 510. The database 510 stores the feedback data molded by the feedback information management unit 504.

[0041] The learning / input data management unit 505 creates and stores learning data and input data based on each element information stored in the repair location notification server 105. Each element information includes the following. Image forming device information stored in the device information storage unit 501 Replacement part information stored in the replacement part information storage unit 502 Feedback data managed by the feedback information management unit 504 Furthermore, the learning / input data management unit 505 creates and stores learning data during learning of the machine learning model, and creates and stores input data during estimation using the machine learning model.

[0042] The learning execution unit 506 acquires learning data from the learning and input data management unit 505, executes learning based on a pre-specified machine learning algorithm, and generates a machine learning model. The machine learning model is stored in the machine learning model management unit 507. Note that, in accordance with changes in the time series and the learning data stored in the learning and input data management unit 505, learning may be executed repeatedly to recreate the machine learning model. The machine learning model management unit 507 stores the machine learning model created by the learning execution unit 506. Note that, the machine learning model used for estimation may be replaced by triggering reception of a machine learning model from the learning execution unit 506, conditional judgment in the machine learning model management unit 507 (for example, the accuracy rate of a new machine learning model exceeds a certain level), or the like.

[0043] The estimation execution unit 508 executes estimation by acquiring input data from the learning / input data management unit 505 and inputting the data to the machine learning model stored in the machine learning model management unit 507. The machine learning model is a model for estimating a repair location using operation information of the image forming apparatus 106 as an input. The estimation result storage unit 503 estimates a repair location of the image forming apparatus 106 based on operation information of the image forming apparatus 106 acquired from the apparatus information collection server 102. In addition, the estimation result storage unit 503 may calculate a probability that a failure of the image forming apparatus 106 will be resolved when the repair location is repaired, together with estimating the repair location. In this embodiment, a case where the estimation execution unit 508 of the repair location estimation system 108 estimates a repair location will be described as an example, but the present invention is not limited to this, and the estimation target may be a failure location or the content of a required maintenance work.

[0044] The estimation result storage unit 503 stores the result of the estimation executed by the estimation execution unit 508. The estimation result storage unit 503 also transmits the estimation result to the information input terminal 103 or the information input terminal 103 via the network 101. For example, the estimation execution unit 508 receives a repair location estimation request from the information input terminal 103 via the network 101, performs estimation using a machine learning model, and returns the estimation result. The information input terminal 103 displays the estimation result received from the estimation execution unit 508 in the recommended repair content display unit 314 of the replacement part performance input screen 301.

[0045] Fig. 6 is a diagram explaining the software configuration of the result management system and the information input terminal. Fig. 6(B) is a diagram explaining the software configuration of the result management system 107. The software configuration of the result management system 107 is realized by the CPU 221 and GPU 222 of the replacement part information collection server 104 and the CPU 221 and GPU 222 of the equipment information collection server 102 executing programs stored in memory.

[0046] The performance management system 107 includes a screen providing unit 601, a device information management unit 602, an error information management unit 603, a performance management unit 604, and a performance management database 605. The screen providing unit 601 provides a screen displayed by the performance management system 107 to an external device via a Web browser. The screen providing unit 601 of this embodiment provides a replacement part performance input screen 301 to the information input terminal 103. The device information management unit 602 manages device information of devices managed by the equipment information collection server 102. The device information management unit 602 also acquires device information input on the replacement part performance input screen 301. The device information management unit 602 searches for managed device information based on the device information input on the replacement part performance input screen 301, and provides the search result to the information input terminal 103. The error information management unit 603 manages error information of devices managed by the equipment information collection server 102. Furthermore, the error information management unit 603 identifies error information corresponding to the device selected on the replacement part record input screen 301 , and provides it to the information input terminal 103 .

[0047] The record management unit 604 manages the work contents of the maintenance work input on the replacement part record input screen 301. The record management unit 604 also molds the work contents of the maintenance work acquired from the information input terminal 103 into data to be used by the record management system 107, and stores the data in the record management database 605. The record management unit 604 of this embodiment manages the part replacement records as the work contents of the maintenance work. The record management database 605 stores the work contents of the maintenance work molded by the record management unit 604.

[0048] 6(B) is a diagram for explaining the software configuration of the information input terminal 103. The software configuration of the information input terminal 103 is implemented by being read from the RAM 224, the storage device 228, a secondary storage device connected via the device I / F 229, and the like, and executed by the CPU 221 and the GPU 222. The information input terminal 103 has a device information storage unit 511, a part replacement information storage unit 512, an estimation result storage unit 513, a screen operation unit 514, and a data operation unit 515.

[0049] The apparatus information storage unit 511 stores error information and device information of the image forming apparatus 106 received from the apparatus information collecting server 102 via the network 101. The part replacement information storage unit 512 stores replacement part information received from the replacement part information collecting server 104 via the network 101 and replacement part results input from the replacement part results input screen 301. The estimation result storage unit 513 stores the repair part estimation result received from the repair part notification server 105 via the network 101. The screen operation unit 514 controls the display of the screen of the information input terminal 103. For example, the screen operation unit 514 displays the replacement part results input screen 301 provided from the results management system 107 on the WebUI. In addition, the screen operation unit 514 displays the feedback input screen 401 provided from the repair part estimation system 108 on the WebUI. The data operation unit 515 performs data shaping. For example, the data operation unit 515 performs data shaping of the replacement part results input from the replacement part results input screen 301. Furthermore, the data operation unit 515 performs data shaping of the feedback information inputted from the feedback input screen 401 .

[0050] Next, a series of processes in which the result management system 107 and the repair part estimation system 108 acquire the work contents of the maintenance work will be described with reference to Figs. 7 to 9. First, a process in which the result management system 107 acquires and stores the maintenance results will be described. Figs. 7 and 8 are flowcharts showing the process of acquiring the maintenance results. In the process of acquiring the maintenance results (replacement part results), the result management system 107 provides a screen for inputting the work results of the maintenance work, acquires the information inputted on the screen, and performs a series of processes of storing it in a database. The worker inputs the replacement part results from the WebUI of the result management system 107. In this embodiment, the process of acquiring the maintenance results is executed by the device information collecting server 102 and the replacement part information collecting server 104 constituting the result management system 107 via the information input terminal 103. More specifically, the process of acquiring the maintenance results is realized by the CPU 221 and the GPU 222 of the device information collecting server 102 and the CPU 221 and the GPU 222 of the replacement part information collecting server 104 executing a program stored in the memory.

[0051] In S701, the screen providing unit 601 of the performance management system 107 provides the replacement part performance input screen 301 (FIG. 3) to the information input terminal 103 and displays it. The screen operation unit 514 of the information input terminal 103 displays the replacement part performance input screen 301 on the WebUI. Then, the worker inputs information for identifying the target device of the maintenance work to the machine number information search unit 311 of the displayed replacement part performance input screen 301. In S702, the device information management unit 602 of the performance management system 107 acquires the information for identifying the target device of the maintenance work inputted to the machine number information search unit 311. The information for identifying the target device of the maintenance work is, for example, the product name and the machine number. The product name is a name representing the product type of the device. The machine number is a unique ID assigned to each device. Note that the product name and the machine number inputted to the machine number information search unit 311 may each be a part of the value indicating the product name or the machine number.

[0052] In S703, the device information management unit 602 of the performance management system 107 searches for the machine number information based on the information acquired in S702, and the screen providing unit 601 displays the search result in the machine number information search result display unit 312 of the replacement part performance input screen 301. The screen operation unit 514 of the information input terminal 103 displays the machine number information search result in the machine number information search result display unit 312 of the replacement part performance input screen 301 on the WebUI. The machine number information search result includes the installation location and the machine number of the device. The installation location is the installation location of the device that matches the condition of the input machine number information search unit 311 received from the device information collection server 102 via the network 101. The machine number is a unique ID assigned to each device. The worker selects the device on which the maintenance work was performed from the machine number information search result displayed in the machine number information search result display unit 312. In S704, the device information management unit 602 of the performance management system 107 accepts the selection of the device in the machine number information search result display unit 312.

[0053] In S705, the error information management unit 603 of the result management system 107 acquires the error details of the device selected in S704, and the screen providing unit 601 displays the acquired error details on the error details display unit 313 of the replacement part result input screen 301. The screen operation unit 514 of the information input terminal 103 displays the error details on the error details display unit 313 of the replacement part result input screen 301 on the WebUI. The error information management unit 603 acquires error information corresponding to the device selected in S704 from the device information collecting server 102 that collects and manages error information from the device. The screen providing unit 601 displays the error details including the acquired error information on the error details display unit 313. The error details include the product name, the machine number, and the occurred error code. The occurred error code is a unique character string code for recognizing the type of the error. The occurred error code may display multiple errors for which the maintenance results have not been reported. The worker selects the occurred error code corresponding to the error that was resolved by performing the maintenance work in the error detail information display section 313 of the displayed replacement part result input screen 301. In S706, the error information management section 603 of the result management system 107 accepts the selection of the occurred error code in the error detail information display section 313.

[0054] In S707, the error information management unit 603 of the result management system 107 requests the repair location notification server 105 to estimate the recommended repair content to eliminate the error (fault) corresponding to the occurred error code selected in S706. Specifically, the error information management unit 603 transmits the device information and the occurred error code to the repair location notification server 105 to request the repair location notification. The repair location notification server 105 estimates the recommended repair content based on the device information and the occurred error code acquired from the result management system 107, and returns the estimation result to the result management system 107. Note that, if the estimation of the recommended repair content has already been performed and the estimation result has been stored in the estimation result storage unit 503, the estimation result is acquired from the estimation result storage unit 503 based on the information acquired from the result management system 107, and returned to the result management system 107. The repair location notification server 105 transmits, for example, information on a recommended replacement part to the result management system 107 as the recommended repair content. In S708, the error information management unit 603 of the result management system 107 acquires the recommended repair contents from the repair location notification server 105 as a response to the repair location notification request.

[0055] In S709, the screen providing unit 601 of the result management system 107 displays the recommended repair content acquired from the repair location notification server 105 in the recommended repair content display unit 314 of the replacement part result input screen 301. The screen operation unit 514 of the information input terminal 103 displays the recommended repair content in the recommended repair content display unit 314 of the replacement part result input screen 301 on the WebUI. As the recommended repair content, for example, a recommended replacement part and a replacement probability are displayed. Note that the processes of S701 to S709 may be executed before the maintenance work is performed, in which case information on the device for which the maintenance work is scheduled to be performed and information on the error are input.

[0056] In S710, the screen providing unit 601 of the result management system 107 displays the replacement part result input section 315 and the replacement part result send button 316 on the replacement part result input screen 301. The screen operation unit 514 of the information input terminal 103 displays the replacement part result input section 315 and the replacement part result send button 316 on the replacement part result input screen 301 on the WebUI. The replacement part result input section 315 displays the product name and the machine number, and accepts input of the parts replaced in the maintenance work. The worker inputs the replacement part as the result information of the maintenance work in the replacement part result input section 315, and presses the replacement part result send button 316. In S711, the result management unit 604 of the result management system 107 acquires the replacement part result inputted in the replacement part result input section 315 of the displayed replacement part result input screen 301. The replacement part record sent from the information input terminal 103 to the record management system 107 includes, for example, the product name, the machine number, and the replacement part, which is the work content of the maintenance work.

[0057] In S712, the result management unit 604 of the result management system 107 molds the replacement part result acquired from the information input terminal 103 via the replacement part result input screen 301 into data to be used in the result management system 107. Here, an example of the data-molded replacement part result will be described. Table 1 shows an example of the data-molded replacement part result. The data-molded replacement part result includes, for example, the product name and machine number, which are information for identifying the target device, the part replacement date, and the replacement part indicating the work content of the maintenance work. On the other hand, information such as the generated error code indicating the event information that caused the maintenance work and the recommended replacement part estimated by the repair point notification server 105 may not be included in the data-molded replacement part result. In other words, the result management system 107 may mold data using only the information (for example, product name, machine number, replacement part) input on the replacement part result input screen 301, and store it in the result management database 605. [Table 1] The product name is the name that indicates the product type of the device. The serial number is a unique ID assigned to each device. The part replacement date is the date when the worker (maintenance technician) replaced the part. The replaced part is the name of the part that the worker actually replaced. For example, the first line in Table 1 means that "The device with the product name MODEL1 and serial number DEV00000 had part A replaced on 2022 / 11 / 02."

[0058] In S713, the result management unit 604 of the result management system 107 stores the data-shaped replacement part result in the result management database 605 of the replacement part information collection server 104 in the result management system 107. Note that in this embodiment, an example in which data shaping is performed in the result management system 107 has been described, but the present invention is not limited to this, and data shaping may be performed in the information input terminal 103. For example, the result management unit 604 may mold data based on the replacement part result in the information input terminal 103 via the data operation unit 515 of the information input terminal 103, acquire the molded data, and store it in the result management database 605. Through the above processing, the result management system 107 can store and manage the maintenance result (replacement part result) in the result management database 605.

[0059] When the result management system 107 completes the process of acquiring and storing the maintenance result, the repair location estimation system 108 then acquires and stores the feedback information. Here, the switching from the replacement part result input screen 301 to the feedback input screen 401 will be described. The replacement part result input screen 301 may be automatically switched to the feedback input screen 401 so that the worker can easily input. For example, when the replacement part result transmission button 316 is pressed, the feedback input screen 401 is provided and displayed on the information input terminal 103 in parallel with the replacement part result being transmitted and stored in the result management system 107. In addition, after the replacement part result is stored in the result management database 605 of the result management system 107, the screen providing unit 601 of the result management system 107 may perform a pop-up display of a screen for transitioning to the feedback input screen 401. When the user selects the transition of the screen in the pop-up, the feedback input screen 401 is provided from the repair location estimation system 108. Instead of displaying a pop-up, a screen for transitioning to the feedback input screen 401 may be displayed using an inline frame in a part of the screen. Information required as feedback information may be passed to the feedback input screen 401 via the replacement part performance input screen 301 (WebUI). The information required for feedback is the product name, the machine number, the error code that occurred, and the like. For example, POST transmission of JavaScript is used to transmit the information required for feedback. Data can be transmitted to the transition destination screen and passed from the performance management system 107 to the repair location estimation system 108 via the screen. This allows the contents input on the replacement part performance input screen 301 to be handed over to the feedback input screen 401 provided by the repair location estimation system 108, and input of device information on the feedback input screen 401, and the like, can be omitted. This makes it possible to reduce the burden of input on the worker.

[0060] Next, a process in which the repair location estimation system 108 acquires and stores feedback information will be described. FIG. 9 is a flowchart showing the process of acquiring feedback information in the first embodiment. In the process of acquiring feedback information, the repair location estimation system 108 provides a screen for inputting feedback information for the estimation of the fault location, acquires the information inputted on the screen, and performs a series of processes of storing it in a database. The worker inputs the feedback information from a WebUI of the repair location estimation system 108. In this embodiment, the process of acquiring feedback information is executed by the repair location notification server 105 constituting the repair location estimation system 108 via the information input terminal 103. More specifically, the process of acquiring the maintenance record is realized by the CPU 221 and GPU 222 of the repair location notification server 105 executing a program stored in the memory.

[0061] In S901, the screen providing unit 509 of the repair location estimating system 108 provides the feedback input screen 401 (FIG. 4) to the information input terminal 103 and displays it. The screen operating unit 514 of the information input terminal 103 displays the feedback input screen 401 on the WebUI. The repair location estimating system 108 acquires information required as feedback information via the replacement part performance input screen 301 (WebUI), and provides the feedback input screen 401 in response to input via the replacement part performance input screen 301. The feedback input screen 401 displays the contents of the maintenance work (e.g., parts to be replaced) that the repair location estimating system 108 estimates as being recommended as a response to the failure. Then, the worker selects information on the parts replaced in the maintenance work from among the candidates for replacement parts displayed in the feedback information input unit 421 of the displayed feedback input screen 401, and presses the feedback information send button 422. In S902, the feedback information management unit 504 acquires, as feedback information, information on the replacement part set in the feedback information input section 421 of the feedback input screen 401 as a part replaced in the maintenance work.

[0062] In S903, the feedback information management unit 504 molds the feedback information acquired from the information input terminal 103 via the feedback input screen 401 into data to be used by the repair location estimation system 108. An example of feedback data, which is the data-molded feedback information, will now be described. Table 2 shows an example of the feedback data. The feedback data includes, for example, the product name and machine number, which are information for identifying the target device, the part replacement date, the replacement part indicating the work content of the maintenance work, and the occurred error code, which indicates event information that caused the maintenance work. [Table 2] The product name is a name that indicates the product type of the device. The machine number is a unique ID assigned to each device. The part replacement date is the date on which the worker (maintenance staff) replaced the part. The replaced part is the name of the part that the worker actually replaced. The replaced part is the name of the part that the worker actually replaced. The error code is a unique character string code for identifying the type of error that caused the replaced part. For example, the first row of Table 2 means that "a device with a product name of MODEL1 and a machine number of DEV00000 replaced part A on 2022 / 11 / 02 for the error code Exxx-yyyy." The feedback information management unit 504 adds information such as the error code stored in the repair location estimation system 108 to the feedback information acquired from the information input terminal 103, and forms the data as feedback data.

[0063] In S904, the feedback information management unit 504 of the repair location estimation system 108 stores the feedback data (interaction feedback information subjected to data shaping) in the database 510 of the repair location notification server 105 in the repair location estimation system 108. In this embodiment, an example in which data shaping is performed in the repair location estimation system 108 has been described, but the present invention is not limited to this, and data shaping may be performed in the information input terminal 103. For example, the feedback information management unit 504 of the repair location estimation system 108 may perform data shaping based on feedback information in the information input terminal 103 via the data operation unit 515 of the information input terminal 103, and acquire the feedback data. The acquired feedback data is stored in the database 510 by the feedback information management unit 504. Through the above processing, the repair location estimation system 108 can store and manage the feedback data in the database 510.

[0064] Next, a description will be given of the creation of a machine learning model in the repair location estimation system 108. Fig. 10 is a flowchart showing the creation process of a machine learning model. Each process shown in Fig. 10 is realized by the CPU 221 and GPU 222 of the repair location notification server 105 executing a program stored in the memory.

[0065] In S1001, the learning / input data management unit 505 acquires the feedback data stored in the database 510 and the image forming device information stored in the device information storage unit 501, and integrates them to obtain collected data. The collected data is data that collects and summarizes information related to a specific error. The collected data summarizes, for each type of error, device information, the data acquisition date, the operating status on that day, whether an error occurred, and the details of maintenance for the error (for example, information on replacement parts). Table 3 shows an example of the collected data. The collected data includes, for example, information to identify the device, the data acquisition date, operating information, whether the relevant error occurred, and information on replacement parts. [Table 3]

[0066] The product name is information indicating the product type of the image forming device. The machine number is a unique ID assigned to each image forming device. The data acquisition date is the date on which the data was acquired. The operation information is information indicating the usage status of the image forming device on the data acquisition date. For example, operation information 1 indicates the number of sheets of paper printed on the data acquisition date. Operation information 2 indicates the number of sheets scanned on the data acquisition date. Note that the operation information is not limited to the number of sheets printed and scanned as long as it is information that indicates the usage status of the image forming device. Parts A to C are the names of parts that may be replaced in the case of the error, and whether or not each part has been replaced is indicated. If the part has been replaced, it is indicated as "1", and if the part has not been replaced, it is indicated as "0". For example, the first line of Table 3 indicates that "In an image forming device with a product name of MODEL 1, the parts that can be replaced when error Exxx-yyyy occurs are part A, part B, and part C. Furthermore, in an image forming device with a product name of MODEL 1 and model number DEV00000, parts A, B, and C were replaced in response to error code Exxx-yyyy that occurred on 2022 / 11 / 01. The value of operation information 1 on 2022 / 11 / 01 is 1, and the value of operation information 2 is 7."

[0067] Returning to the explanation of FIG. 10, in S1002, the learning / input data management unit 505 classifies the collected data prepared in S1002 by device. The classification by device is performed based on the machine number. In the example shown in Table 3, the collected data is classified into DEV00000 and DEV00001. The processing from S1003 onwards is performed on all the collected data classified by machine number in S1002.

[0068] In S1003, the learning / input data management unit 505 divides the collected data prepared in S1003 into input data and correct answer data. The input data is data that is expected to be input when the repair location notification server 105 estimates a maintenance work recommended for an error that has occurred in a device. The input data includes information indicating an error and operation information of the device in which the error has occurred. For example, the input data includes an error code, operation information 1, and operation information 2. Note that the input data can also include values ​​such as time information (such as the time when copying was performed), user attributes (such as department, position, age), and image forming device attributes (such as model, installation location, copy speed). The correct answer data corresponds to data that can be output as an estimation result of a maintenance work recommended for an error that has occurred in a device by the repair location notification server 105. The correct answer data includes information on a maintenance work to eliminate an error. For example, the correct answer data includes a replacement part.

[0069] In this embodiment, the correct answer data generated in S1003 is processed one setting item at a time to process all the setting items. In S1004, the learning execution unit 506 determines whether the processing of all the setting items of the correct answer data has been completed. If it is determined that the processing of all the setting items has been completed, this processing is terminated. On the other hand, if it is determined that the processing of all the setting items has not been completed, the learning execution unit 506 selects a setting item to be processed and performs the processing of S1005. That is, the learning execution unit 506 selects one setting item to be processed from the unprocessed setting items in order to process the setting items (part A, part B, part C) of the correct answer data one setting item at a time. Note that in this embodiment, an example in which the correct answer data is processed one setting item at a time will be described, but multiple setting items may be learned together. When learning is performed using multiple setting items of the correct answer data, a large amount of data is required to perform highly accurate estimation. For example, it is difficult to collect a large amount of learning data for each machine number, and the amount of learning data is small, so the estimation accuracy of the model may be low.

[0070] In S1006, the learning execution unit 506 learns the model using the input data generated in S1003 and one setting item of the correct answer data set in S1004. The learning here also includes re-learning of the model. The learning is performed, for example, using a Support Vector Machine (SVM). The SVM is a known machine learning algorithm, and in this embodiment, a nonlinear soft margin SVM using a Radial Basis function Kernel (RBF) is used. In the learning, the learning result is evaluated by cross-validation, which randomly divides the learning data into analysis data and validation data. In addition, the hyper parameters of the SVM using RBF include a cost parameter (C) and a gamma (γ), which affect the estimation performance, and therefore a grid search is performed to comprehensively try multiple values ​​for each, and the one with the highest estimation performance is determined as the learning result.

[0071] The machine learning algorithm used in the learning of S1005 is not limited to SVM, and other machine learning algorithms may be used. Machine learning algorithms include perceptron, logistic regression, neural network, k-nearest neighbor method, naive Bayes, convolutional neural network, decision tree, random forest, linear regression, polynomial regression, Lasso regression, Ridge regression, and the like. SVM also includes types such as hard margin SVM and polynomial kernel SVM. Hyperparameters of machine learning algorithms also differ depending on the machine learning algorithm. In addition, methods for evaluating the learning results include alternative estimation methods and test sample methods in addition to cross-validation. Furthermore, methods for optimizing hyperparameters of machine learning algorithms include random search, Latin hypercube sampling, Bayesian optimization, and the like in addition to grid search. In this embodiment, the machine learning algorithm, the method for evaluating the learning results, and the method for optimizing hyperparameters of machine learning algorithms may be changed.

[0072] In S1006, the machine learning model management unit 507 saves the trained model trained in S1005. The machine learning model management unit 507 saves the trained model in a file. The file in which the trained model is saved includes, in addition to the trained model, the type of learning algorithm (nonlinear soft margin SVM using RBF) and the values ​​of hyperparameters of the learning algorithm (cost parameter (C) and gamma (γ)). Through the above process, the repair location estimation system 108 creates a machine learning model using the feedback data. In this manner, since the collected data acquired for use in learning in this process is collected and integrated for each generated error code, the feedback data needs to include information on the generated error code in addition to device information and information on the replacement part.

[0073] As described above, according to this embodiment, it is possible to reduce the burden on the worker of inputting the replacement part history and feedback. Furthermore, in the repair location estimation system, by converting the feedback information input by feedback into data with an error code added, it is possible to store data suitable for re-learning a model that estimates the repair location. This makes it possible to store data related to maintenance work in a data format suitable for each of the history management system and the repair location estimation system.

[0074] Example 2 In the first embodiment, an example was described in which a maintenance worker (maintenance staff) inputs both replacement part records and feedback information via a WebUI in response to an error such as a breakdown. If both replacement part records and feedback information are always required to be input, it is conceivable that the time the worker spends inputting information will increase. In particular, when the repair location estimation system 108 has undergone sufficient learning and is capable of outputting highly accurate estimation results, inputting feedback information can be an additional learning cost. Therefore, in this embodiment, feedback information is not required for models that are capable of outputting highly accurate estimation results, and the feedback information input screen is not displayed.

[0075] In this embodiment, whether feedback information is necessary, i.e., whether there is a highly accurate estimation result, is determined based on the probability of each maintenance work recommended for the error. Specifically, if the highest probability of each maintenance work recommended for the error is equal to or greater than a threshold, it is determined that there is a highly accurate estimation result, feedback information is not necessary, and the feedback information input screen is not displayed. On the other hand, if the highest probability of each maintenance work recommended for the error is less than the threshold, it is determined that there is no highly accurate estimation result, feedback information is necessary, and the feedback information input screen is displayed.

[0076] For example, if the estimated maintenance work is a part replacement, the estimation result includes replacement parts that are replacement candidates and the probability that the error will be resolved by replacing the part with that part (replacement probability). Table 4 is a table showing an example of the estimation result by the repair location estimation system 108. [Table 4] In Table 4, the probability that replacing part A will resolve the error is 80%, 15% for replacing part B, and 5% for replacing part C. If the threshold is set to 70% for the estimation results in Table 4, then 80% of part A, which has the highest replacement probability, is above the threshold, and so the estimation results shown in Table 4 are judged to be highly accurate.

[0077] Only the differences from the first embodiment will be described below. Fig. 11 is a diagram for explaining the software configuration of the repair location notification server 105 in the second embodiment. The repair location notification server 105 in the second embodiment has a threshold management unit 1101. The threshold management unit 1101 stores a threshold value set in the repair location notification server 105 for determining whether or not a feedback information input screen is displayed, that is, whether or not the estimation result is highly accurate. For example, a threshold value of 70% is stored in the threshold management unit 1101.

[0078] 12 is a flowchart showing a process for acquiring feedback information in Example 2. In this example, the process for acquiring feedback information is executed by the repair location notifying server 105 constituting the repair location estimation system 108 via the information input terminal 103. More specifically, the process for acquiring maintenance results is realized by the CPU 221 and GPU 222 of the repair location notifying server 105 executing a program stored in the memory.

[0079] In this embodiment, it is assumed that input has already been made to the replacement part record input screen 301, and that necessary information has been passed as feedback information to the feedback input screen 401 via the replacement part record input screen 301 (WebUI). Information necessary for feedback includes the product name, the machine number, and the error code that has occurred. The information necessary for feedback may also include information in the recommended repair content display section 314, which is the estimated result of maintenance for the error in the repair location estimation system 108. For example, JavaScript POST transmission is used to transmit the information necessary for feedback.

[0080] In S1201, the estimation result storage unit 503 of the repair location notification server 105 judges whether the maximum value of the replacement probability is equal to or greater than a threshold value. The maximum value of the replacement probability is specified based on information required for feedback acquired from the replacement part performance input screen 301 of the performance management system 107. The threshold value is a threshold value for judging whether the estimation result stored in the threshold management unit 1101 is highly accurate. If the maximum value of the replacement probability is not equal to or greater than the threshold value, the repair location notification server 105 proceeds to S901 and displays the feedback input screen 401. On the other hand, if the maximum value of the replacement probability is equal to or greater than the threshold value, this process is terminated. That is, in this embodiment, if the repair location notification server 105 has an estimation result with an accuracy equal to or greater than the threshold value, the feedback input screen 401 is not displayed.

[0081] According to this embodiment, it is possible to switch whether to display the feedback input screen 401 or not after comparing the probability that the network device failure will be resolved by performing maintenance work on the repair location included in the estimation result with a threshold value. If the probability that the network device failure will be resolved by performing maintenance work on the estimated repair location is equal to or greater than the threshold value, the feedback input screen 401 is not displayed. This makes it possible to reduce the effort required of the worker to input feedback information for highly accurate estimation results. Furthermore, it is possible to reduce the cost of learning the estimation results in the repair location estimation system 108.

[0082] Example 3 In the first embodiment, an example has been described in which a maintenance worker (maintenance staff) inputs both replacement part records and feedback information via the WebUI in response to an error such as a breakdown. On the other hand, there is a mechanism for automatically transmitting feedback information from a device without input by a worker. When feedback information has already been automatically transmitted, if a worker inputs feedback information via the WebUI (feedback input screen 401), it is considered that the feedback information may be duplicated in the repair location estimation system 108. When feedback information is duplicated, data used for learning the model may also be duplicated, and the accuracy of estimation by the repair location estimation system 108 may decrease. Therefore, in this embodiment, when feedback information has already been transmitted by the device, that is, when the repair location notification server 105 has already received feedback information from the device, the feedback input screen 401 is not displayed.

[0083] Whether or not feedback information has been transmitted by the device is determined based on feedback data generated based on the replacement part record and the feedback information transmitted from the image forming apparatus 106. The replacement part record is information input on the replacement part record input screen 301. In this embodiment, it is assumed that input has already been made to the replacement part record input screen 301, and the replacement part record input on the replacement part record input screen 301 has been passed to the feedback input screen 401 via the replacement part record input screen 301 (WebUI). For example, JavaScript POST transmission is used to transmit the replacement part record. Table 5 shows an example of the replacement part record. [Table 5] The replacement part record includes, for example, the product name, the machine number, the part replacement date, and the replaced part.

[0084] Table 6 shows an example of feedback data generated from feedback information transmitted from the image forming apparatus 106 to the repair location estimating system 108. The feedback information transmitted to the repair location estimating system 108 is data-generated in the feedback information management unit 504 and stored in the database 510 as feedback data. [Table 6] The feedback data generated based on the feedback information transmitted from the image forming apparatus 106 to the repair part estimation system 108 includes the product name, the machine number, the part replacement date, the replaced part, and the error code that occurred.

[0085] The replacement part record of the maintenance work for the same image forming apparatus and the feedback data based on the feedback information transmitted from the image forming apparatus 106 to the repair location estimation system 108 match with predetermined information. The predetermined information is, for example, the product name, the machine number, the part replacement date, and the replacement part. Therefore, the replacement part record is compared with the feedback data, and if the product name, the machine number, the part replacement date, and the replacement part match, it is determined that the maintenance work is for the same image forming apparatus. In the examples shown in Tables 5 and 6, the product name, the machine number, the part replacement date, and the replacement part match, so it is understood that the maintenance work is for the same image forming apparatus. In this embodiment, the repair location notification server 105 determines that the feedback information has been received from the image forming apparatus 106 when the replacement part record and the predetermined information of the feedback data based on the feedback information transmitted from the image forming apparatus 106 match.

[0086] Only the differences from the first embodiment will be described below. Fig. 13 is a flowchart showing the process of acquiring feedback information in the third embodiment. In this embodiment, the process of acquiring feedback information is executed by the repair location notifying server 105 constituting the repair location estimation system 108 via the information input terminal 103. More specifically, the process of acquiring the maintenance record is realized by the CPU 221 and GPU 222 of the repair location notifying server 105 executing a program stored in the memory.

[0087] In S1301, the feedback information management unit 504 judges whether feedback information has been received from the image forming apparatus 106. The feedback information management unit 504 judges whether feedback information has been sent from the image forming apparatus 106 based on whether there is feedback data whose predetermined information matches the replacement part record acquired from the record management system 107. If the repair location notification server 105 judges that the predetermined information does not match, that is, if feedback information has not been sent from the image forming apparatus, it performs the process of S901 and displays the feedback input screen 401. On the other hand, if the repair location notification server 105 judges that the predetermined information matches, that is, if feedback information has been sent from the image forming apparatus, it ends this process. Therefore, if the repair location notification server 105 judges that the predetermined information matches, that is, if feedback information has been sent from the image forming apparatus, it does not display the feedback input screen 401.

[0088] As described above, according to this embodiment, when feedback information has already been transmitted from the device to the repair location estimating system 108, the input screen for prompting the worker to input the feedback information is not displayed. This makes it possible to avoid duplication of feedback information and suppress deterioration in the accuracy of estimation by the repair location estimating system 108.

[0089] The disclosure of this embodiment includes the following network system configuration. (Configuration 1) A network system including a performance management system for managing performance of maintenance work on a network device, and a repair location estimation system for estimating a repair location of the network device, The performance management system includes: a first screen providing means for providing a first screen for allowing a user to input details of maintenance work performed on a network device; a first storage means for storing the input from the first screen in a first database; The repair location estimation system includes: a second screen providing means for providing a second screen for providing feedback on the content of the maintenance work that has actually been performed with respect to the estimated repair location of the network device in response to an input via the first screen provided by the performance management system; and a management means for adding event information indicating the event that caused the maintenance work to the content set on the second screen and storing the added information as feedback data in a second database. (Configuration 2) 2. The network system according to configuration 1, wherein the maintenance work includes a part replacement work for solving a failure of a network device. (Configuration 3) 3. The network system according to configuration 1 or 2, wherein the event information is an error code corresponding to a failure of a network device. (Configuration 4) The network system according to any one of configurations 1 to 3, wherein the feedback data is a model used in the repair location estimation system, and is used for re-learning a model for estimating a repair location of a network device by inputting operation information of the network device. (Configuration 5) 5. The network system according to claim 1, wherein the repair location estimation system acquires an input via the first screen provided by the performance management system by POST transmission. (Configuration 6) the performance management system acquires from the repair location estimation system an estimation result in response to a request for estimating a repair location based on event information indicating an event that caused the maintenance work input on the first screen, and displays the estimation result on the first screen; 6. The network system according to claim 1, wherein the repair location estimating system displays the estimation result on the second screen. (Configuration 7) The network system described in any one of configurations 1 to 6, characterized in that the repair location estimation system does not provide the second screen when a probability that the network device failure will be resolved by performing maintenance work on the estimated repair location is equal to or greater than a threshold. (Configuration 8) The network system described in any one of configurations 1 to 7, characterized in that the repair location estimation system does not provide the second screen when it receives feedback regarding actual work content for the estimated maintenance work from the network device on which the maintenance work was performed.

[0090] (Other embodiments) The present invention can also be realized by a process in which a program for implementing one or more of the functions of the above-described embodiments is supplied to a system or device via a network or a storage medium, and one or more processors in a computer of the system or device read and execute the program. The present invention can also be realized by a circuit (e.g., ASIC) that implements one or more of the functions.

[0091] Although the preferred embodiments of the present invention have been described above, the present invention is not limited to these embodiments, and various modifications and changes are possible within the scope of the gist of the present invention.

Claims

1. A network system including a performance management system for managing performance of maintenance work on a network device, and a repair location estimation system for estimating a repair location of the network device, The performance management system includes: a first screen providing means for providing a first screen for inputting the contents of maintenance work performed on the network device; a first storage means for storing the input from the first screen in a first database; The repair location estimation system includes: a second screen providing means for providing a second screen for providing feedback on the content of the maintenance work that has actually been performed with respect to the estimated repair location of the network device in response to an input via the first screen provided by the performance management system; and a management means for adding event information indicating the event that caused the maintenance work to the content set on the second screen and storing the added event information as feedback data in a second database.

2. 2. The network system according to claim 1, wherein the maintenance work includes a part replacement work for eliminating a failure of a network device.

3. 2. The network system according to claim 1, wherein the event information is an error code corresponding to a failure of a network device.

4. The network system according to claim 1, characterized in that the feedback data is used for re-learning a model used in the repair location estimation system, the model inputting operation information of a network device and estimating a repair location of the network device.

5. 2. The network system according to claim 1, wherein the repair location estimation system acquires an input via the first screen provided by the performance management system by POST transmission.

6. the performance management system acquires from the repair location estimation system an estimation result in response to a request for estimating a repair location based on event information indicating an event that caused the maintenance work input on the first screen, and displays the estimation result on the first screen; 2. The network system according to claim 1, wherein said repair location estimating system displays said estimation result on said second screen.

7. The network system according to claim 1, characterized in that the repair location estimation system does not provide the second screen when a probability that the network device failure will be resolved by performing maintenance work on the estimated repair location is equal to or greater than a threshold.

8. The network system according to claim 1, characterized in that the repair location estimation system does not provide the second screen when it receives feedback regarding actual work content for the estimated maintenance work from the network device on which the maintenance work was performed.

9. A method for controlling a network system including a performance management system that manages performance of maintenance work for a network device, and a repair location estimation system that estimates the maintenance work for the network device, comprising: providing a first screen for allowing the performance management system to input the details of the maintenance work performed on the network device; a step of the performance management system storing the input from the first screen in a first database; a step in which the repair location estimation system provides a second screen for providing feedback regarding the content of actual maintenance work with respect to the estimated maintenance work in response to an input via the first screen provided by the performance management system; and a step in which the repair location estimation system adds event information indicating the event that caused the maintenance work to the content set on the second screen, and stores the added event information as feedback data in a second database.

Images