Image processing device, image processing device control method, and program

The image processing device leverages generative AI to automatically determine storage locations for image data by analyzing character strings, enhancing efficiency in folder path settings.

JP2025115055APending Publication Date: 2025-08-06CANON KK
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2024009370
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2024-01-25
Publication Date
2025-08-06

AI Technical Summary

Technical Problem

Existing image processing devices lack the ability to utilize generative AI services for allocating storage locations for image data based on character recognition, requiring manual input of prompts.

Method used

An image processing device that reads a document, generates image data, and uses a generative AI server to analyze the data for character extraction, determining the storage location based on the extracted character strings.

Benefits of technology

Allocates storage locations for image data using a generative AI service, reducing user effort and time in setting folder paths.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2025115055000001_ABST
    Figure 2025115055000001_ABST
Patent Text Reader

Abstract

To provide an image processing device capable of reducing time and labor of a user in setting a folder path by using a character string in an original.SOLUTION: An MFP 200 reads an image of an original and generates scan image data. The MFP 200 further receives a prompt for causing a generative AI server 400 to execute image analysis of extracting a predetermined character string from the scan image data and transmits the scan image data and the prompt to the generative AI server 400. The MFP 200 performs control of acquiring an analysis result of the image analysis by the generative AI server 400 and storing the scan image data in a folder indicated by the folder path including the character string of the acquired analysis result.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical Field]

[0001] The present invention relates to an image processing apparatus, a control method for an image processing apparatus, and a program. [Background technology]

[0002] Image processing devices that read an image of a document and generate image data are known. Patent Document 1 proposes a technique for saving such image data. In Patent Document 1, the generated image data is saved in a folder named after characters obtained by performing character recognition processing on the generated image data. This allows the image data to be allocated to an appropriate saving location for each character contained in the generated image data.

[0003] On the other hand, generative AI services are being used that use generative AI to perform image analysis processing, but generative AI services require the user to input arbitrary prompts. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2020-86717 Summary of the Invention [Problem to be solved by the invention]

[0005] In the technology of Patent Document 1 described above, character recognition processing is executed by an image processing device, and therefore character recognition processing using a generation AI service is not envisioned.

[0006] The present invention aims to provide an image processing device, a control method for an image processing device, and a program that can allocate storage locations for image data using a generation AI service. [Means for solving the problem]

[0007] In order to achieve the above-mentioned object, the image processing device of the present invention is characterized by comprising: a means for reading an image of a document and generating image data; a means for receiving a prompt to cause a generation AI to perform image analysis to extract a specified character string from the image data; a means for transmitting the image data and the prompt to the generation AI; a means for acquiring the character string extracted by the image analysis by the generation AI; and a means for controlling the saving of the image data in a folder indicated by a folder path containing the acquired character string. [Effects of the Invention]

[0008] According to the present invention, the storage location of image data can be allocated using a generation AI service. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a block diagram showing an example of the configuration of a system including an MFP as an image processing apparatus according to the present embodiment. [Figure 2] FIG. 2 is a block diagram schematically illustrating the hardware configuration of the MFP in FIG. [Figure 3] 2 is a block diagram schematically illustrating a hardware configuration of the user terminal of FIG. 1. [Figure 4] FIG. 2 is a block diagram showing an outline of the hardware configuration of the generation AI server of FIG. 1. [Figure 5] FIG. 2 is a block diagram schematically illustrating a hardware configuration of the storage server of FIG. [Figure 6] This is a sequence diagram showing the steps of the process in which the MFP in Figure 1 stores the scanned image data generated by scanning a document in a storage location determined based on the analysis results of image analysis by the generation AI server. [Figure 7] FIG. 3 is a screen transition diagram of the operation unit of FIG. 2. [Figure 8] 4 is a flowchart showing the procedure of a scan control process executed by the MFP of FIG. [Figure 9]FIG. 8 is a diagram showing an example of a job execution button setting screen for registering a job execution button displayed on the home screen of FIG. 7. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Note that the following embodiments do not limit the invention according to the claims, and not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention. In this embodiment, an image processing device will be described as an example of a multifunction peripheral (MFP) having multiple functions such as a print function, a scan function, and a fax function.

[0011] Fig. 1 is a block diagram showing an example of the configuration of a system including an MFP 200 as an image processing device according to this embodiment. In this system, as shown in Fig. 1, the MFP 200 and a user terminal 300 are communicably connected to a generation AI server 400 and a storage server 500 via a network 100. The network 100 may be the Internet or a LAN (Local Area Network). The network 100 may be either wired or wireless.

[0012] The MFP 200 has a function of scanning and digitizing paper documents. The MFP 200 transmits the scanned image data generated by scanning the paper documents to the storage server 500. The user terminal 300 is, for example, an electronic device owned by a user, such as a personal computer, smartphone, or tablet PC. The user terminal 300 communicates with the MFP 200 via the network 100, and functions of the MFP 200 can be configured from a browser or the like running on the user terminal 300.

[0013] The generation AI server 400 communicates with the MFP 200 via the network 100 and receives scanned image data generated by the MFP 200 and a prompt that instructs the MFP 200 to perform image analysis to extract a predetermined character string from the scanned image data. The generation AI server 400 interprets the received prompt and returns a response to the prompt to the MFP 200.

[0014] The storage server 500 is a NAS (Network Attached Storage) etc. The storage server 500 is a server that manages files using a file sharing protocol such as CIFS (Common Internet File System) or NFS (Network File System).

[0015] Fig. 2 is a block diagram showing a schematic hardware configuration of the MFP 200 shown in Fig. 1. In Fig. 2, the MFP 200 includes a CPU 201, a ROM 202, a RAM 203, a storage 204, an operation unit 205, a printing unit 206, a reading unit 207, and a communication unit 208. These are connected to one another via a bus 209.

[0016] The CPU 201 controls the overall operation of the MFP 200. The CPU 201 loads a control program stored in the ROM 202 or the storage 204 into the RAM 203 and executes the control program loaded into the RAM 203 to perform various types of control, such as scanning control and printing control. The ROM 202 stores control programs executable by the CPU 201. The RAM 203 is a main memory and is used as a work area and a temporary storage area for expanding the various control programs stored in the ROM 202 and the storage 204. The storage 204 stores image data, print data, various programs, and various setting information. Note that, in this embodiment, a flash memory is assumed as the storage 204, but a storage device such as an SSD (Solid State Drive) or an HDD (Hard Disc Drive) may also be used. An eMMC (Embedded Multi Media Card) may also be used as the storage 204. Note that, in the MFP 200 of this embodiment, one CPU 201 uses one RAM 203 to execute each process shown in the sequence described below, but this is not limited to this. For example, each process shown in the sequence described below can be executed by using multiple CPUs, RAMs, ROMs, and storages in cooperation with each other. Also, some processes can be executed using hardware circuits such as ASICs and FPGAs.

[0017] The operation unit 205 is, for example, a display unit such as a touch panel or hard keys. The operation unit 205 displays information to the user and detects input from the user. The printing unit 206 prints image data (print data) stored in the RAM 203 onto recording paper fed from a paper feed cassette. The reading unit 207 reads an image of an original, and the CPU 201 converts the image into scanned image data such as binary data. The scanned image data generated based on the image read by the reading unit 207 is sent to an external device or printed on recording paper by the printing unit 206.

[0018] The communication unit 208 is connected to the network 100. The communication unit 208 transmits image data to external devices on the network 100 and receives print data from the user terminal 300. Methods for transmitting and receiving data via the network 100 include transmission and reception using e-mail and file transmission using other protocols (e.g., FTP, SMB, WEBDAV, etc.). Furthermore, various setting data can be transmitted and received via the network 100 by accessing from the user terminal 300 via HTTP communication.

[0019] Fig. 3 is a block diagram showing a schematic hardware configuration of the user terminal 300 of Fig. 1. In Fig. 3, the user terminal 300 includes a CPU 301, a ROM 302, a RAM 303, a storage 304, a display unit 305, and a communication unit 306. These are connected to each other via a bus 307.

[0020] The CPU 301 controls the overall operation of the user terminal 300. The CPU 301 reads control programs stored in the ROM 302 or storage 304 into the RAM 303 and executes the control programs read into the RAM 303 to perform various processes for controlling the operation of the user terminal 300. The ROM 302 stores control programs executable by the CPU 301. The RAM 303 is a main memory and is used as a work area and a temporary storage area for expanding the various control programs stored in the ROM 302 and storage 304. The storage 304 stores application data, various programs, and various setting information. The display unit 305 is a display device such as an LCD panel, and displays, for example, image data processed by the CPU 301. The communication unit 306 transmits and receives data to and from the generation AI server 400, storage server 500, and MFP 200 via the network 100.

[0021] Fig. 4 is a block diagram showing a schematic hardware configuration of the generation AI server 400 in Fig. 1. In Fig. 4, the generation AI server 400 includes a CPU 401, a ROM 402, a RAM 403, a communication unit 404, and an HDD 405. These are connected to each other via a bus 406.

[0022] The CPU 401 executes processing to control the operation of generating an appropriate response using a control program stored in the ROM 402 and a learning model as a generative AI stored in the HDD 405. The learning model has an image analysis function and generates text and images in response to an input prompt. For example, when a natural language question such as "What is in the image?" is input as a prompt, the learning model performs image analysis according to the question and generates an answer to the question. This answer includes, for example, the name of the object shown in the image.

[0023] The ROM 402 stores a control program. The RAM 403 is used as a temporary storage area such as the main memory and work area of the CPU 401. The HDD 405 stores various data such as learning models and generated AI applications. The communication unit 404 exchanges data with various devices such as the user terminal 300 and the MFP 200. The communication unit 404 may perform wired communication using Ethernet (registered trademark) or wireless communication such as Wi-Fi.

[0024] Fig. 5 is a block diagram showing a schematic hardware configuration of the storage server 500 of Fig. 1. In Fig. 5, the storage server 500 includes a CPU 501, a ROM 502, a RAM 503, an HDD 504, and a communication unit 505. These are connected to each other via a bus 506.

[0025] The CPU 501 reads out a control program stored in the ROM 502 into the RAM 503 and executes the control program read out into the RAM 503, thereby performing various processes for controlling the operation of the storage server 500. The ROM 502 stores the control program. The RAM 503 is used as a temporary storage area such as the main memory and work area of the CPU 501. The HDD 504 stores files. The communication unit 505 receives files from the MFP 200 or the user terminal 300 via the Internet 100 and stores the received files in the HDD 504. The communication unit 505 also transmits files stored in the HDD 504 to the MFP 200 or the user terminal 300. The communication unit 505 may perform wired communication using Ethernet or wireless communication such as Wi-Fi.

[0026] 6 is a sequence diagram showing the steps of a process in which the MFP 200 in FIG. 1 scans a document and generates scanned image data, which is then stored in a storage location determined based on the results of image analysis by the generation AI server 400. It is assumed that the home screen 701 in FIG. 7 is displayed on the operation unit 205 of the MFP 200. The home screen 701 includes buttons corresponding to functions provided by the MFP 200, such as a copy button and a fax button, as well as job execution buttons such as an "AI allocation send" button 702.

[0027] In FIG. 6, first, when the user presses the “AI allocation SEND” button 702 on the home screen 701 (S601), the screen of the operation unit 205 of the MFP 200 switches from the home screen 701 to an AI allocation SEND setting screen 703.

[0028] Next, the user sets scan settings on the AI allocation SEND setting screen 703 (S602). Specifically, the user sets scan size 704, double-sided original 705, file format 706, split by page 707, save destination 708, and file name 709 as scan settings. Scan size 704 is a setting related to the size of the original to be scanned. Double-sided original 705 is a setting related to whether both sides of the original to be scanned are read. File format 706 is a setting related to the file format of the scanned image data generated by scanning. Split by page 707 is set to either ON or OFF. If Split by page 707 is set to OFF, when a multi-page original is scanned, one scanned image data set containing data for all pages is generated. On the other hand, if Split by page 707 is set to ON, when a multi-page original is scanned, multiple scanned image data sets are generated by splitting the original into the specified number of pages. Save destination 708 is a setting related to the save location of the scanned image data generated by scanning. File name 709 is a setting related to the file name of the scanned image data generated by scanning. When the user selects the reset button 710, the information set on the AI allocation SEND setting screen 703 is cleared.

[0029] For example, when a user selects a save destination 708, the screen of the operation unit 205 of the MFP 200 switches from the AI allocation send setting screen 703 to a save destination prompt selection screen 713. The save destination prompt selection screen 713 displays a list of prompts registered on a job execution button setting screen 901 (described later in FIG. 9 ). This prompt is a prompt for causing the generation AI server 400 to perform image analysis to extract a predetermined character string used to determine a save location from scanned image data generated by scanning. FIG. 7 displays, as examples, prompts such as "Tell me your company name," "Tell me the name written in the name field," and "Read the character string in the QR code." When a user selects a prompt from the list displayed on the save destination prompt selection screen 713, the screen of the operation unit 205 of the MFP 200 switches from the save destination prompt selection screen 713 to the AI allocation send setting screen 703. The prompt selected by the user on the save destination prompt selection screen 713 is set as the save destination 708 on the AI allocation send setting screen 703. In this way, the destination 708 is set not with the folder path itself indicating the location where the scanned image data is saved, but with a prompt that causes the generation AI server 400 to perform image analysis to extract a specified string of characters used to determine the save location.

[0030] Furthermore, when the user selects a file name 709, the screen of the operation unit 205 of the MFP 200 switches from the AI allocation SEND setting screen 703 to a file name prompt selection screen (not shown). This file name prompt selection screen displays a list of prompts registered on a job execution button setting screen 901 (described later in FIG. 9 ). This prompt is a prompt for causing the generation AI server 400 to perform image analysis to extract a predetermined character string used to determine a file name from scanned image data generated by scanning. When the user selects a prompt from the list displayed on this file name prompt selection screen, the screen of the operation unit 205 of the MFP 200 switches from this file name prompt selection screen to the AI allocation SEND setting screen 703. The prompt selected by the user on this file name prompt selection screen is set as the file name 709 on the AI allocation SEND setting screen 703. In this way, the file name 709 is set to a prompt for causing the generation AI server 400 to perform image analysis to extract a predetermined character string used to determine a file name, rather than the file name itself of the scanned image data.

[0031] Next, the user issues an instruction to start scanning the document (S603). In this embodiment, the user can issue an instruction to start scanning the document by selecting the monochrome start button 711 or the color start button 712 on the AI allocation SEND setting screen 703.

[0032] Upon receiving the instruction to start scanning the document, the CPU 201 of the MFP 200 controls the reading unit 207 to scan the set document (S604). In S604, the document is scanned based on the setting information of the reading size 704, double-sided document 705, file format 706, and split by page 707 on the AI allocation SEND setting screen 703. Scanned image data is generated by this scanning.

[0033] Next, the CPU 201 of the MFP 200 controls the communication unit 208 to send the scanned image data generated in S604 to the generation AI server 400 (S605). The CPU 201 also controls the communication unit 208 to send the prompt set on the AI allocation SEND setting screen 703 to the generation AI server 400 (S606).

[0034] The CPU 401 of the generation AI server 400, which has received the scanned image data and the prompt, performs image analysis using the learning model stored in the HDD 405 to extract a predetermined character string corresponding to the prompt from the scanned image data (S607). For example, if the received prompt is "Please tell me the name of your company," the image analysis using the learning model extracts a predetermined character string indicating the company name from the scanned image data.

[0035] The CPU 401 of the generation AI server 400 controls the communication unit 404 to transmit the predetermined character string extracted from the scanned image data to the MFP 200 as the analysis result (S608).

[0036] Next, the CPU 201 of the MFP 200 determines the storage location of the scanned image data by using the analysis result received from the generation AI server 400 as part of the folder path (S609).

[0037] Next, the CPU 201 of the MFP 200 controls the communication unit 208 to transmit the scanned image data generated in S604 to the storage server 500 (S610). At this time, the storage location determined in S609 is specified as the storage location for the scanned image data. As a result, the storage server 500 stores the scanned image data generated in S604 in the storage location determined in S609. Thereafter, this process ends.

[0038] Fig. 8 is a flowchart showing the procedure of scan control processing executed by MFP 200 of Fig. 1. This scan control processing is realized by CPU 201 of MFP 200 reading a program stored in ROM 202 into RAM 203 and executing the program read into RAM 203. This scan control processing is started when MFP 200 is powered on and home screen 701 is displayed on operation unit 205.

[0039] 8, first, the CPU 201 determines whether or not the "AI allocation SEND" button 702 has been selected (S801). If it is determined in S801 that the "AI allocation SEND" button 702 has not been selected, the process returns to S801. On the other hand, if it is determined in S801 that the "AI allocation SEND" button 702 has been selected, the process proceeds to S802.

[0040] In S802, the CPU 201 determines whether or not a prompt that can be selected has been registered for the save destination 708 and the file name 709. If it is determined in S802 that a prompt that can be selected for the save destination 708 or the file name 709 has not been registered, the process proceeds to S803.

[0041] In S803, the CPU 201 causes the operation unit 205 to display the AI allocation SEND setting screen 703 including an unregistered error notification indicating that no prompts that are selection candidates have been registered in the save destination 708 or file name 709. Next, the CPU 201 determines whether or not the "Back" button on the AI allocation SEND setting screen 703 has been selected (S804). If it is determined in S804 that the "Back" button has not been selected, the process returns to S804. On the other hand, if it is determined in S804 that the "Back" button has been selected, the process returns to S801.

[0042] If it is determined in S802 that prompts that are selection candidates in the save destination 708 and file name 709 have already been registered, the process proceeds to S805.

[0043] In S805, the CPU 201 displays the AI allocation SEND setting screen 703 on the operation unit 205. Furthermore, when the save destination 708 or file name 709 on the AI allocation SEND setting screen 703 is selected, the CPU 201 displays a prompt selection screen corresponding to the selected item on the operation unit 205 (S806). In the following, as an example, it is assumed that the save destination 708 is selected by the user and the save destination prompt selection screen 713 is displayed on the operation unit 205.

[0044] Next, the CPU 201 determines whether or not a prompt has been selected on the destination prompt selection screen 713 displayed on the operation unit 205 (S807). If it is determined in S807 that a prompt has not been selected on the destination prompt selection screen 713, the process returns to S806. On the other hand, if it is determined in S807 that a prompt has been selected on the destination prompt selection screen 713, the process proceeds to S808.

[0045] In S808, the CPU 201 determines whether an instruction to start scanning a document has been received. In S808, if the user has not selected either the monochrome start button 711 or the color start button 712 on the AI allocation send setting screen 703, it is determined that an instruction to start scanning a document has not been received, and the process returns to S808. On the other hand, if the user has selected the monochrome start button 711 or the color start button 712 on the AI allocation send setting screen 703, it is determined that an instruction to start scanning a document has been received, and the process proceeds to S809. Note that in this embodiment, if it is determined that an instruction to start scanning a document has been received but a prompt has not been set for at least one of the save destination 708 and the file name 709, the process may return to S806. In S806, a prompt selection screen corresponding to an item for which a prompt has not been set is displayed on the operation unit 205.

[0046] In S809, the CPU 201 controls the reading unit 207 based on the information set on the AI allocation send setting screen 703 to scan the set document. As a result, scanned image data is generated. Note that when a document with multiple pages is scanned, one scanned image data including data for all pages, or multiple scanned image data divided by the specified number of pages, is generated in accordance with the setting of the split by page 707 on the AI allocation send setting screen 703.

[0047] Next, the CPU 201 converts the scanned image data generated in step S809 into the file format set in the file format 706 on the AI allocation SEND setting screen 703 (step S810).

[0048] Next, the CPU 201 controls the communication unit 208 to send the scanned image data whose file format was converted in S810 to the generation AI server 400 (S811). The CPU 201 also controls the communication unit 208 to send the prompt selected in S807 to the generation AI server 400 (S812). Note that if multiple scanned image data are generated in S810, the processes of S811 and S812 are performed for each of the multiple scanned image data.

[0049] Next, the CPU 201 determines whether or not an analysis result has been received from the generation AI server 400 (S813). In S813, if the status code in the HTTP communication response is an error or if the body information of the response contains a parameter indicating that the information cannot be obtained, it is determined that the analysis result has not been received from the generation AI server 400. In this case, the process proceeds to S814.

[0050] In S814, the CPU 201 displays an acquisition error notice indicating that the analysis results could not be received on the AI allocation SEND setting screen 703. Next, the CPU 201 determines whether or not the "Back" button on the AI allocation SEND setting screen 703 has been selected (S815). If it is determined in S815 that the "Back" button on the AI allocation SEND setting screen 703 has not been selected, the process returns to S815. On the other hand, if it is determined in S815 that the "Back" button on the AI allocation SEND setting screen 703 has been selected, the process returns to S801.

[0051] If it is determined in step S813 that the analysis results have been received from the generation AI server 400, the CPU 201 generates a folder path indicating the location where the scanned image data will be saved based on the received analysis results (step S816). In step S816, the folder path is generated according to a folder path rule that is preset as a job setting in the folder path rule setting field 910 of the job execution button setting screen 901 (see FIG. 9 , which will be described later). Note that in step S816, the folder path may be generated according to other folder path generation rules. For example, a folder path rule using a keyword (in this embodiment, "{AI analysis result}") that is replaced with the character string obtained as the analysis result may be set to allocate the save location according to the analysis result. For example, if the folder path rule is "\\folder.net\folderA\{AI analysis result}" and "0123" is received from the generation AI server 400 as the analysis result, a folder path such as "\\folder.net\folderA\0123" is generated in step S816. As a keyword, other keywords such as "{yyyymmdd}" which is replaced with the date of execution of the scan may also be prepared in advance.

[0052] Next, the CPU 201 displays the folder path generated in S814 on the AI allocation SEND setting screen 703. The CPU 201 also displays a button on the AI allocation SEND setting screen 703 for selecting whether to use (confirm) or not (cancel) the folder indicated by this folder path as a storage location (S817). Note that a keyboard may be displayed on the operation unit 205 so that the user can edit the folder path generated in S814.

[0053] Next, CPU 201 determines whether the folder indicated by this folder path has been confirmed as the storage location (S818). If it is determined in S818 that the folder indicated by this folder path has been canceled as the storage location, this processing returns to S801. On the other hand, if it is determined in S818 that the folder indicated by this folder path has been confirmed as the storage location, this processing proceeds to S819.

[0054] In S819, the CPU 201 transmits the scanned image data, the file format of which has been converted in S810, to the storage server 500. At this time, the folder path confirmed in S818 is specified as the storage location for this scanned image data. As a result, in the storage server 500, the scanned image data transmitted from the MFP 200 is saved in the folder indicated by the folder path confirmed in S818. Thereafter, this process ends.

[0055] 9 is a diagram showing an example of a job execution button setting screen 901 for registering a job execution button displayed on the home screen 701 of FIG. 7. The job execution button setting screen 901 is displayed by accessing a button setting page provided by an HTTP server (not shown) of the MFP 200 from a browser on a PC operated by a user. In FIG. 9, information related to the "AI allocation SEND" button 702 is set as an example. Note that, in the present embodiment, a configuration in which the job execution button setting screen 901 is displayed on the display unit of the PC operated by the user will be described, but the present invention is not limited to this configuration. For example, a screen equivalent to the job execution button setting screen 901 may be displayed on the operation unit 205 of the MFP 200.

[0056] The login user field 902 displays the name of the user who is logged in to the MFP 200 to set the job execution button from the browser. When setting the "AI allocation SEND" button 702, a user with administrator privileges for the MFP 200 or a general user with the authority to make this setting logs in to the MFP 200. When the logout button 903 is selected, the user is logged out of the MFP 200, and a screen indicating that the user has been logged out of the MFP 200 is displayed on the browser.

[0057] When the user selects the OK button 904, the MFP 200 stores the job settings set in 906 to 917 in the storage 204, and displays a job execution button that executes a job according to the job settings on the home screen 701. When the user selects the cancel button 905, the MFP 200 clears the information set in 906 to 917 and ends the button settings.

[0058] A button name field 906 is set with the name of the job execution button displayed on the home screen 701. The values set in the read size selection field 907, the split by page selection field 908, and the file format selection field 909 are used as the initial values of the read size 704, the file format 706, and the split by page 707 on the AI allocation SEND setting screen 703, respectively.

[0059] The folder path rule setting field 910 sets a rule for generating a folder path that indicates where scanned image data is saved. The AI analysis content setting fields 911 to 913 set prompts that cause the generation AI server 400 to perform image analysis to extract from the scanned image data a character string to be used in the folder path. The prompts set in the AI analysis content setting fields 911 to 913 are displayed as options on the save destination prompt selection screen 713. Note that while FIG. 9 shows an example in which three prompts can be registered, the number of prompts that can be registered is not limited to three.

[0060] The file name rule setting field 914 sets a rule for generating a file name for the scanned image data. The AI analysis content setting fields 915 to 917 set prompts for causing the generation AI server 400 to perform image analysis to extract, from the scanned image data, a character string to be used in the file name of the scanned image data. The prompts set in the AI analysis content setting fields 915 to 917 are displayed as options on the file name prompt selection screen that is displayed on the operation unit 205 when the file name 709 is selected.

[0061] According to the above-described embodiment, an image of a document is read to generate scanned image data, and a prompt is received to cause the generation AI server 400 to perform image analysis to extract a predetermined character string from the scanned image data. The scanned image data and the prompt are sent to the generation AI server 400, which then obtains the results of the image analysis and controls the storage of the scanned image data in a folder indicated by a folder path that includes the character string from the obtained analysis result. This allows the generation AI service to be used to allocate the storage location of the image data.

[0062] Furthermore, in the above-described embodiment, the "AI allocation SEND" button 702, which is a job execution button, is registered in association with a prompt to be sent to the generation AI server 400. This allows the user to instruct the generation AI server 400 to perform image analysis simply by pressing the "AI allocation SEND" button 702, without having to input a prompt.

[0063] In the above-described embodiment, the folder path is displayed on the operation unit 205, and the user is prompted to select whether or not to save the scanned image data in the folder indicated by the folder path. This prevents the scanned image data from being saved in an unintended folder.

[0064] In the above-described embodiment, a keyboard that allows the user to edit the folder path is displayed on the operation unit 205. This allows the user to change the storage location of the scanned image data with minimal effort, based on the folder path generated based on the results of image analysis by the generation AI server 400.

[0065] In the above-described embodiment, the configuration in which the scanned image data is sent directly to the generation AI server 400 in S811 has been described, but the present invention is not limited to this configuration. For example, the configuration may be such that, after the scanned image data is saved in the storage server 500, the file path specifying this scanned image data is notified to the generation AI server 400 in S811.

[0066] In addition, in the above-described embodiment, as an example, a configuration was described in which the analysis results by the generation AI server 400 are used to determine the storage location of the scanned image data, but the analysis results by the generation AI server 400 may also be used to determine the file name of the scanned image data.

[0067] Furthermore, in this embodiment, if it is determined in S818 that the folder path displayed on the AI allocation SEND setting screen 703 has been canceled as the save location, a prompt editing screen may be displayed on the operation unit 205. On this screen, the prompt transmitted to the generation AI server 400 in S812 can be edited. For example, if the prompt transmitted to the generation AI server 400 in S812 was "What is the name of your company?", the user edits this prompt to "What is the name of your company that starts with "Inc." In other words, a prompt is generated in which the prompt "What is the name of your company?" is supplemented with supplemental information such as "Starts with "Inc." After that, the process returns to S811, and in S812, the prompt edited by the user is transmitted to the generation AI server 400. By controlling in this manner, if the image analysis by the generation AI server 400 does not produce the results intended by the user, the conditions can be changed and the generation AI server 400 can be caused to perform image analysis again. As a result, the scanned image data can be controlled to be saved in the intended save location.

[0068] Furthermore, in the present embodiment, a configuration has been described in which the generation AI server 400 executes image analysis to extract a predetermined character string from scanned image data. However, the present invention is not limited to this configuration, and the MFP 200 may also be configured to include the generation AI. For example, in S605 and S811, the CPU 201 of the MFP 200 inputs scanned image data to a learning model serving as a generation AI stored in the storage 204 or the like. In addition, in S606 and S812, the CPU 201 inputs a prompt to this learning model. This learning model performs the image analysis using this data as input. This configuration can also achieve the same effects as the above-described embodiment.

[0069] The present invention can also be realized by supplying a program that realizes one or more functions of the above-described embodiments to a system or device via a network or a storage medium, and having one or more processors in the 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 realizes one or more functions.

[0070] The disclosure of this embodiment includes the following configurations and methods. (Configuration 1) An image processing device characterized by comprising: a means for reading an image of a document and generating image data; a means for receiving a prompt to cause a generation AI to perform image analysis to extract a predetermined character string from the image data; a means for transmitting the image data and the prompt to the generation AI; a means for acquiring the character string extracted by the image analysis by the generation AI; and a means for controlling the saving of the image data in a folder indicated by a folder path containing the acquired character string. (Configuration 2) An image processing device according to configuration 1, characterized in that a job execution button is registered for executing a job to read an image of a document, generate image data, and save the image data in a folder indicated by the folder path, and the prompt is registered in association with the job execution button. (Configuration 3) The image processing device according to configuration 1 or 2, further comprising a means for displaying the folder path and a means for allowing a user to select whether or not to save the image data in the folder indicated by the folder path. (Configuration 4) The image processing device according to Configuration 3, further comprising means for allowing a user to edit the folder path. (Configuration 5) An image processing device as described in configuration 3 or 4, characterized in that if the user chooses not to save the image data in the folder indicated by the folder path, the sending means sends the image data and another prompt to the generation AI, with supplementary information added to the prompt. [Explanation of symbols]

[0071] 200 MFP 201 CPU 205 Operation section 207 Reading unit 208 Communications Department 702 "AI allocation SEND" button 703 AI allocation SEND setting screen

Claims

1. means for reading an image of an original and generating image data; A means for receiving a prompt to cause the generation AI to perform image analysis to extract a predetermined character string from the image data; means for transmitting the image data and the prompt to the generating AI; A means for acquiring a character string extracted by the image analysis by the generation AI; An image processing device comprising: a control unit for controlling saving of the image data in a folder indicated by a folder path including the acquired character string.

2. a job execution button for executing a job of reading an image of a document, generating image data, and saving the image data in a folder indicated by the folder path is registered; 2. The image processing apparatus according to claim 1, wherein the prompt is registered in association with the job execution button.

3. means for displaying the folder path; 2. The image processing apparatus according to claim 1, further comprising means for prompting a user to select whether or not to save the image data in the folder indicated by the folder path.

4. 4. The image processing apparatus according to claim 3, further comprising means for allowing a user to edit the folder path.

5. The image processing device described in claim 3, characterized in that if the user chooses not to save the image data in the folder indicated by the folder path, the sending means sends the image data and another prompt to the generation AI with supplementary information added to the prompt.

6. A control method for an image processing device, comprising: A step of reading an image of a document and generating image data; receiving a prompt to cause the generation AI to perform image analysis to extract a predetermined character string from the image data; sending the image data and the prompt to the generating AI; acquiring a character string extracted by the image analysis by the generation AI; A control method for an image processing apparatus, comprising the step of controlling the image data to be saved in a folder indicated by a folder path including the acquired character string.

7. A program for causing a computer to execute a control method for an image processing device, The control method for the image processing device includes: A step of reading an image of a document and generating image data; receiving a prompt to cause the generation AI to perform image analysis to extract a predetermined character string from the image data; sending the image data and the prompt to the generating AI; acquiring a character string extracted by the image analysis by the generation AI; A program comprising a step of controlling the saving of the image data in a folder indicated by a folder path including the acquired character string.

Citation Information

Patent Citations

  • Image processing device and control method thereof, and program

    JP2020086717A